In [29]:
workDir = '/home/nick/notebook/SIPSim/dev/bac_genome1147/validation/multiWindow_HRSIP/'
genomeDir = '/var/seq_data/ncbi_db/genome/Jan2016/bac_complete_spec-rep1_rn/'
figureDir = '/home/nick/notebook/SIPSim/figures/bac_genome_n1147/'
In [30]:
import glob
import nestly
import os
%load_ext rpy2.ipython
%load_ext pushnote
The rpy2.ipython extension is already loaded. To reload it, use:
%reload_ext rpy2.ipython
The pushnote extension is already loaded. To reload it, use:
%reload_ext pushnote
In [31]:
%%R
library(ggplot2)
library(dplyr)
library(tidyr)
library(gridExtra)
In [32]:
if not os.path.isdir(workDir):
os.makedirs(workDir)
%cd $workDir
/home/nick/notebook/SIPSim/dev/bac_genome1147/validation/multiWindow_HRSIP
In [33]:
def HRSIP_multi_window(physeq, BD_shift, BDs, outname, padj=0.1, log2=0.25):
# HR-SIP for each window
occurs = ','.join([str(x/100.0) for x in range(0,55,5)])
outname2 = outname + '_DS2.txt'
!SIPSimR phyloseq_DESeq2 --occur_all $occurs -w $BDs $physeq > $outname2
# making confusion matrix
!SIPSimR DESeq2_confuseMtx --padj $padj --log2 $log2 $BD_shift -o $outname $outname2
In [6]:
BDs = '1.70-1.74,1.72-1.76'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW1')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1070
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 75 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.05
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1056
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 1056
post-filter: number of taxa: 1041
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 74 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.1
pre-filter: number of taxa: 1147
post-filter: number of taxa: 990
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 990
post-filter: number of taxa: 978
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 74 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.15
pre-filter: number of taxa: 1147
post-filter: number of taxa: 930
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 930
post-filter: number of taxa: 919
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 71 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.2
pre-filter: number of taxa: 1147
post-filter: number of taxa: 855
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 855
post-filter: number of taxa: 849
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 66 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.25
pre-filter: number of taxa: 1147
post-filter: number of taxa: 781
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 781
post-filter: number of taxa: 777
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 63 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.3
pre-filter: number of taxa: 1147
post-filter: number of taxa: 715
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 715
post-filter: number of taxa: 715
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 60 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.35
pre-filter: number of taxa: 1147
post-filter: number of taxa: 638
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 638
post-filter: number of taxa: 638
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 53 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.4
pre-filter: number of taxa: 1147
post-filter: number of taxa: 555
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 555
post-filter: number of taxa: 555
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 49 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.45
pre-filter: number of taxa: 1147
post-filter: number of taxa: 502
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 502
post-filter: number of taxa: 502
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 44 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.5
pre-filter: number of taxa: 1147
post-filter: number of taxa: 438
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 438
post-filter: number of taxa: 438
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 33 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.76
pre-filter: number of samples: 56
post-filter: number of samples: 19
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 973
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 4 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 100
# occurance cutoff: 0.05
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1056
# "heavy" BD window: 1.72-1.76
pre-filter: number of samples: 56
post-filter: number of samples: 19
# occurance cutoff: 0
pre-filter: number of taxa: 1056
post-filter: number of taxa: 964
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 5 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 100
# occurance cutoff: 0.1
pre-filter: number of taxa: 1147
post-filter: number of taxa: 990
# "heavy" BD window: 1.72-1.76
pre-filter: number of samples: 56
**OUTPUT MUTED**
In [7]:
BDs = '1.70-1.75,1.72-1.77'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW2')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1076
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 82 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 21
# occurance cutoff: 0.05
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1056
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 1056
post-filter: number of taxa: 1047
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 82 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 21
# occurance cutoff: 0.1
pre-filter: number of taxa: 1147
post-filter: number of taxa: 990
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 990
post-filter: number of taxa: 981
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 81 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 23
# occurance cutoff: 0.15
pre-filter: number of taxa: 1147
post-filter: number of taxa: 930
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 930
post-filter: number of taxa: 922
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 81 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 28
# occurance cutoff: 0.2
pre-filter: number of taxa: 1147
post-filter: number of taxa: 855
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 855
post-filter: number of taxa: 851
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 74 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 40
# occurance cutoff: 0.25
pre-filter: number of taxa: 1147
post-filter: number of taxa: 781
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 781
post-filter: number of taxa: 779
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 64 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 37
# occurance cutoff: 0.3
pre-filter: number of taxa: 1147
post-filter: number of taxa: 715
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 715
post-filter: number of taxa: 715
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 61 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 33
# occurance cutoff: 0.35
pre-filter: number of taxa: 1147
post-filter: number of taxa: 638
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 638
post-filter: number of taxa: 638
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 60 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 32
# occurance cutoff: 0.4
pre-filter: number of taxa: 1147
post-filter: number of taxa: 555
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 555
post-filter: number of taxa: 555
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 46 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 29
# occurance cutoff: 0.45
pre-filter: number of taxa: 1147
post-filter: number of taxa: 502
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 502
post-filter: number of taxa: 502
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 43 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 29
# occurance cutoff: 0.5
pre-filter: number of taxa: 1147
post-filter: number of taxa: 438
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 438
post-filter: number of taxa: 438
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 38 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 20
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 25
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1000
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 21 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 103
# occurance cutoff: 0.05
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1056
# "heavy" BD window: 1.72-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 25
# occurance cutoff: 0
pre-filter: number of taxa: 1056
post-filter: number of taxa: 991
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 21 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 103
# occurance cutoff: 0.1
pre-filter: number of taxa: 1147
post-filter: number of taxa: 990
# "heavy" BD window: 1.72-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 25
# occurance cutoff: 0
pre-filter: number of taxa: 990
post-filter: number of taxa: 947
# DESeq2 run
**OUTPUT MUTED**
In [8]:
BDs = '1.70-1.73,1.72-1.75,1.74-1.77'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW3')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1064
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 13 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.05
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1056
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 1056
post-filter: number of taxa: 1037
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 14 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.1
pre-filter: number of taxa: 1147
post-filter: number of taxa: 990
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 990
post-filter: number of taxa: 977
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 13 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.15
pre-filter: number of taxa: 1147
post-filter: number of taxa: 930
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 930
post-filter: number of taxa: 919
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 15 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.2
pre-filter: number of taxa: 1147
post-filter: number of taxa: 855
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 855
post-filter: number of taxa: 849
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 14 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.25
pre-filter: number of taxa: 1147
post-filter: number of taxa: 781
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 781
post-filter: number of taxa: 777
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 13 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.3
pre-filter: number of taxa: 1147
post-filter: number of taxa: 715
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 715
post-filter: number of taxa: 715
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 14 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.35
pre-filter: number of taxa: 1147
post-filter: number of taxa: 638
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 638
post-filter: number of taxa: 638
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 15 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.4
pre-filter: number of taxa: 1147
post-filter: number of taxa: 555
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 555
post-filter: number of taxa: 555
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 13 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.45
pre-filter: number of taxa: 1147
post-filter: number of taxa: 502
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 502
post-filter: number of taxa: 502
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 10 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.5
pre-filter: number of taxa: 1147
post-filter: number of taxa: 438
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 438
post-filter: number of taxa: 438
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 10 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 15
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 944
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 2 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 79
# occurance cutoff: 0.05
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1056
# "heavy" BD window: 1.72-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 15
# occurance cutoff: 0
pre-filter: number of taxa: 1056
post-filter: number of taxa: 935
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 2 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 80
# occurance cutoff: 0.1
pre-filter: number of taxa: 1147
post-filter: number of taxa: 990
# "heavy" BD window: 1.72-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 15
# occurance cutoff: 0
pre-filter: number of taxa: 990
**OUTPUT MUTED**
In [9]:
BDs = '1.70-1.72,1.71-1.73,1.72-1.74,1.73-1.75'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW4')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1040
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.05
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1056
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 1056
post-filter: number of taxa: 1020
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.1
pre-filter: number of taxa: 1147
post-filter: number of taxa: 990
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 990
post-filter: number of taxa: 967
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.15
pre-filter: number of taxa: 1147
post-filter: number of taxa: 930
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 930
post-filter: number of taxa: 913
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.2
pre-filter: number of taxa: 1147
post-filter: number of taxa: 855
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 855
post-filter: number of taxa: 845
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.25
pre-filter: number of taxa: 1147
post-filter: number of taxa: 781
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 781
post-filter: number of taxa: 774
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.3
pre-filter: number of taxa: 1147
post-filter: number of taxa: 715
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 715
post-filter: number of taxa: 714
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.35
pre-filter: number of taxa: 1147
post-filter: number of taxa: 638
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 638
post-filter: number of taxa: 637
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.4
pre-filter: number of taxa: 1147
post-filter: number of taxa: 555
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 555
post-filter: number of taxa: 555
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.45
pre-filter: number of taxa: 1147
post-filter: number of taxa: 502
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 502
post-filter: number of taxa: 502
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.5
pre-filter: number of taxa: 1147
post-filter: number of taxa: 438
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 438
post-filter: number of taxa: 438
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 979
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.05
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1056
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0
pre-filter: number of taxa: 1056
post-filter: number of taxa: 959
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.1
pre-filter: number of taxa: 1147
post-filter: number of taxa: 990
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0
pre-filter: number of taxa: 990
post-filter: number of taxa: 914
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.15
pre-filter: number of taxa: 1147
post-filter: number of taxa: 930
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0
pre-filter: number of taxa: 930
post-filter: number of taxa: 867
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.2
pre-filter: number of taxa: 1147
post-filter: number of taxa: 855
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0
pre-filter: number of taxa: 855
post-filter: number of taxa: 809
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.25
pre-filter: number of taxa: 1147
post-filter: number of taxa: 781
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0
pre-filter: number of taxa: 781
post-filter: number of taxa: 746
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0.3
pre-filter: number of taxa: 1147
post-filter: number of taxa: 715
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0
pre-filter: number of taxa: 715
post-filter: number of taxa: 694
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
**OUTPUT MUTED**
In [10]:
BDs = '1.71-1.75'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW5')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1025
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 17 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 59
# occurance cutoff: 0.05
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1056
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 1056
post-filter: number of taxa: 1003
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 17 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 59
# occurance cutoff: 0.1
pre-filter: number of taxa: 1147
post-filter: number of taxa: 990
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 990
post-filter: number of taxa: 949
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 17 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 63
# occurance cutoff: 0.15
pre-filter: number of taxa: 1147
post-filter: number of taxa: 930
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 930
post-filter: number of taxa: 897
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 15 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 62
# occurance cutoff: 0.2
pre-filter: number of taxa: 1147
post-filter: number of taxa: 855
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 855
post-filter: number of taxa: 832
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 11 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 63
# occurance cutoff: 0.25
pre-filter: number of taxa: 1147
post-filter: number of taxa: 781
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 781
post-filter: number of taxa: 767
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 10 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 54
# occurance cutoff: 0.3
pre-filter: number of taxa: 1147
post-filter: number of taxa: 715
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 715
post-filter: number of taxa: 709
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 8 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 51
# occurance cutoff: 0.35
pre-filter: number of taxa: 1147
post-filter: number of taxa: 638
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 638
post-filter: number of taxa: 637
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 9 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 47
# occurance cutoff: 0.4
pre-filter: number of taxa: 1147
post-filter: number of taxa: 555
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 555
post-filter: number of taxa: 555
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 8 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 38
# occurance cutoff: 0.45
pre-filter: number of taxa: 1147
post-filter: number of taxa: 502
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 502
post-filter: number of taxa: 502
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 8 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 34
# occurance cutoff: 0.5
pre-filter: number of taxa: 1147
post-filter: number of taxa: 438
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 438
post-filter: number of taxa: 438
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 6 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 27
# A file of all DESeq2 run results was written to: DESeq2_all_runs.txt
#- Greatest number of rejected hypotheses for each BD window -#
heavy_BD_min heavy_BD_max max_n_rej_hypo occur_all occur_heavy
1.71 1.75 63 0.1 0
# Global adjustment of p-values for all BW windows with "best" occurance cutoff
#- Greatest number of rejected hypotheses for each BD window -#
heavy_BD_min heavy_BD_max max_n_rej_hypo occur_all occur_heavy
1.71 1.75 63 0.1 0
Log2Fold cutoff: -Inf
padj cutoff: 0.1
File written: OTU_n2_abs1e9_PCR_subNorm_MW5
File written: OTU_n2_abs1e9_PCR_subNorm_MW5_data.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW5_table.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW5_overall.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW5_byClass.txt
In [11]:
BDs = '1.71-1.8'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW6')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1053
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 69 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 88
# occurance cutoff: 0.05
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1056
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 1056
post-filter: number of taxa: 1031
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 68 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 88
# occurance cutoff: 0.1
pre-filter: number of taxa: 1147
post-filter: number of taxa: 990
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 990
post-filter: number of taxa: 974
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 65 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 91
# occurance cutoff: 0.15
pre-filter: number of taxa: 1147
post-filter: number of taxa: 930
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 930
post-filter: number of taxa: 920
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 66 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 89
# occurance cutoff: 0.2
pre-filter: number of taxa: 1147
post-filter: number of taxa: 855
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 855
post-filter: number of taxa: 851
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 64 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 85
# occurance cutoff: 0.25
pre-filter: number of taxa: 1147
post-filter: number of taxa: 781
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 781
post-filter: number of taxa: 778
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 63 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 72
# occurance cutoff: 0.3
pre-filter: number of taxa: 1147
post-filter: number of taxa: 715
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 715
post-filter: number of taxa: 714
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 62 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 67
# occurance cutoff: 0.35
pre-filter: number of taxa: 1147
post-filter: number of taxa: 638
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 638
post-filter: number of taxa: 638
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 62 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 62
# occurance cutoff: 0.4
pre-filter: number of taxa: 1147
post-filter: number of taxa: 555
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 555
post-filter: number of taxa: 555
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 59 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 52
# occurance cutoff: 0.45
pre-filter: number of taxa: 1147
post-filter: number of taxa: 502
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 502
post-filter: number of taxa: 502
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 54 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 47
# occurance cutoff: 0.5
pre-filter: number of taxa: 1147
post-filter: number of taxa: 438
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 438
post-filter: number of taxa: 438
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 47 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 38
# A file of all DESeq2 run results was written to: DESeq2_all_runs.txt
#- Greatest number of rejected hypotheses for each BD window -#
heavy_BD_min heavy_BD_max max_n_rej_hypo occur_all occur_heavy
1.71 1.8 91 0.1 0
# Global adjustment of p-values for all BW windows with "best" occurance cutoff
#- Greatest number of rejected hypotheses for each BD window -#
heavy_BD_min heavy_BD_max max_n_rej_hypo occur_all occur_heavy
1.71 1.8 91 0.1 0
Log2Fold cutoff: -Inf
padj cutoff: 0.1
File written: OTU_n2_abs1e9_PCR_subNorm_MW6
File written: OTU_n2_abs1e9_PCR_subNorm_MW6_data.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW6_table.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW6_overall.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW6_byClass.txt
In [12]:
files = ['OTU_n2_abs1e9_PCR_subNorm_MW{}_byClass.txt'.format(i) for i in xrange(1,7)]
files
Out[12]:
['OTU_n2_abs1e9_PCR_subNorm_MW1_byClass.txt',
'OTU_n2_abs1e9_PCR_subNorm_MW2_byClass.txt',
'OTU_n2_abs1e9_PCR_subNorm_MW3_byClass.txt',
'OTU_n2_abs1e9_PCR_subNorm_MW4_byClass.txt',
'OTU_n2_abs1e9_PCR_subNorm_MW5_byClass.txt',
'OTU_n2_abs1e9_PCR_subNorm_MW6_byClass.txt']
In [13]:
%%R -i files
renames = data.frame(file = c('MW1', 'MW2', 'MW3', 'MW4', 'MW5', 'MW6'),
BD_window = c('1.70-1.74,\n1.72-1.76',
'1.70-1.75,\n1.72-1.77',
'1.70-1.73,\n1.72-1.75,\n1.74-1.77',
'1.70-1.72,\n1.71-1.73,\n1.72-1.74,\n1.73-1.75',
'1.71-1.75', '1.71-1.8'))
df = list()
for(F in files){
tmp = read.delim(F, sep='\t')
df[[F]] = tmp
}
df = do.call(rbind, df)
df$file = gsub('.+(MW[0-9]+).+', '\\1', rownames(df))
df = inner_join(df, renames, c('file' = 'file'))
df %>% head(n=3)
library variables values file BD_window
1 2 Sensitivity 0.8990826 MW1 1.70-1.74,\n1.72-1.76
2 2 Specificity 1.0000000 MW1 1.70-1.74,\n1.72-1.76
3 2 Pos Pred Value 1.0000000 MW1 1.70-1.74,\n1.72-1.76
In [14]:
%%R -h 550
ggplot(df, aes(variables, values)) +
geom_bar(stat='identity') +
labs(y='Value') +
facet_grid(BD_window ~ .) +
theme_bw() +
theme(
text = element_text(size=16),
axis.title.x = element_blank(),
axis.text.x = element_text(angle=45, hjust=1)
)
In [15]:
%%R -h 250 -w 550
df.f = df %>%
filter(variables %in% c('Sensitivity', 'Specificity', 'Balanced Accuracy')) %>%
mutate(variables = gsub(' ', '\n', variables))
ggplot(df.f, aes(BD_window, values, color=variables)) +
geom_point(size=3, alpha=0.7) +
theme_bw() +
theme(
text = element_text(size=16),
axis.title.x = element_blank(),
axis.text.x = element_text(angle=60, hjust=1)
)
In [16]:
%pushnote validation MW-HR-SIP complete
In [17]:
def HRSIP_multi_window_post(physeq, BD_shift, BDs, outname, padj=0.1, log2=0.25):
# HR-SIP for each window
occurs = ','.join([str(x/100.0) for x in range(0,55,5)])
outname2 = outname + '_DS2.txt'
!SIPSimR phyloseq_DESeq2 --occur_heavy $occurs -w $BDs $physeq > $outname2
# making confusion matrix
!SIPSimR DESeq2_confuseMtx --padj $padj --log2 $log2 $BD_shift -o $outname $outname2
In [18]:
BDs = '1.70-1.74,1.72-1.76'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window_post(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW1p')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1070
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 75 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.76
pre-filter: number of samples: 56
post-filter: number of samples: 19
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 973
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 4 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 100
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1070
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 75 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.76
pre-filter: number of samples: 56
post-filter: number of samples: 19
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 973
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 4 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 100
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1023
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 74 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.76
pre-filter: number of samples: 56
post-filter: number of samples: 19
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 870
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 5 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 101
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 972
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 70 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.76
pre-filter: number of samples: 56
post-filter: number of samples: 19
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 803
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 5 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 103
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0.2
pre-filter: number of taxa: 1090
post-filter: number of taxa: 917
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 66 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.76
pre-filter: number of samples: 56
post-filter: number of samples: 19
# occurance cutoff: 0.2
pre-filter: number of taxa: 1090
post-filter: number of taxa: 737
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 5 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 100
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0.25
pre-filter: number of taxa: 1090
post-filter: number of taxa: 863
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 57 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.76
pre-filter: number of samples: 56
post-filter: number of samples: 19
# occurance cutoff: 0.25
pre-filter: number of taxa: 1090
post-filter: number of taxa: 677
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 5 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 94
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 18
# occurance cutoff: 0.3
pre-filter: number of taxa: 1090
post-filter: number of taxa: 809
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 44 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.76
pre-filter: number of samples: 56
post-filter: number of samples: 19
# occurance cutoff: 0.3
pre-filter: number of taxa: 1090
post-filter: number of taxa: 611
# DESeq2 run
**OUTPUT MUTED**
In [19]:
BDs = '1.70-1.75,1.72-1.77'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window_post(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW2p')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1076
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 82 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 21
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 25
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1000
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 21 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 103
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1035
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 82 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 20
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 25
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 923
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 22 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 103
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 997
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 83 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 23
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 25
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 850
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 22 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 103
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 947
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 81 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 20
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 25
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 791
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 22 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 103
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0.2
pre-filter: number of taxa: 1090
post-filter: number of taxa: 906
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 79 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 28
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 25
# occurance cutoff: 0.2
pre-filter: number of taxa: 1090
post-filter: number of taxa: 709
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 22 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 98
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0.25
pre-filter: number of taxa: 1090
post-filter: number of taxa: 815
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 72 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 33
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 25
# occurance cutoff: 0.25
pre-filter: number of taxa: 1090
post-filter: number of taxa: 665
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 20 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 94
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 24
# occurance cutoff: 0.3
pre-filter: number of taxa: 1090
post-filter: number of taxa: 765
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 68 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 35
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 25
# occurance cutoff: 0.3
pre-filter: number of taxa: 1090
**OUTPUT MUTED**
In [20]:
BDs = '1.70-1.73,1.72-1.75,1.74-1.77'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window_post(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW3p')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1064
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 13 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 15
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 944
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 2 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 79
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.74-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 16
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 945
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 39 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 92
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1064
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 13 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 15
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 944
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 2 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 79
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.74-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 16
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 945
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 39 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 92
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1008
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 13 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 15
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 835
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 2 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 80
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.74-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 16
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 832
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 40 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 93
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 948
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 12 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 15
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 747
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 2 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 83
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.74-1.77
pre-filter: number of samples: 56
post-filter: number of samples: 16
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 722
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 38 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 93
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 14
# occurance cutoff: 0.2
pre-filter: number of taxa: 1090
post-filter: number of taxa: 948
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 12 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 15
# occurance cutoff: 0.2
pre-filter: number of taxa: 1090
post-filter: number of taxa: 674
# DESeq2 run
converting counts to integer mode
**OUTPUT MUTED**
In [21]:
BDs = '1.70-1.72,1.71-1.73,1.72-1.74,1.73-1.75'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window_post(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW4p')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1040
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 979
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 816
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 29
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.73-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 896
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 92
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1040
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 979
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 816
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 29
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.73-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 896
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 92
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1040
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 880
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 816
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 29
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.73-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 759
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 92
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 971
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 880
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.72-1.74
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 659
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 33
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.73-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 759
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 92
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.7-1.72
pre-filter: number of samples: 56
post-filter: number of samples: 9
# occurance cutoff: 0.2
pre-filter: number of taxa: 1090
post-filter: number of taxa: 971
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# Number of rejected hypotheses: 0
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.73
pre-filter: number of samples: 56
post-filter: number of samples: 10
# occurance cutoff: 0.2
pre-filter: number of taxa: 1090
post-filter: number of taxa: 771
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
**OUTPUT MUTED**
In [22]:
BDs = '1.71-1.75'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window_post(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW5p')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1025
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 17 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 59
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 963
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 17 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 59
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 908
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 18 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 63
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 851
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 17 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 63
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0.2
pre-filter: number of taxa: 1090
post-filter: number of taxa: 794
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 17 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 62
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0.25
pre-filter: number of taxa: 1090
post-filter: number of taxa: 728
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 11 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 63
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0.3
pre-filter: number of taxa: 1090
post-filter: number of taxa: 670
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 11 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 56
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0.35
pre-filter: number of taxa: 1090
post-filter: number of taxa: 611
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 9 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 49
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0.4
pre-filter: number of taxa: 1090
post-filter: number of taxa: 550
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 9 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 41
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0.45
pre-filter: number of taxa: 1090
post-filter: number of taxa: 499
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 7 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 32
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.75
pre-filter: number of samples: 56
post-filter: number of samples: 20
# occurance cutoff: 0.5
pre-filter: number of taxa: 1090
post-filter: number of taxa: 444
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 6 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 25
# A file of all DESeq2 run results was written to: DESeq2_all_runs.txt
#- Greatest number of rejected hypotheses for each BD window -#
heavy_BD_min heavy_BD_max max_n_rej_hypo occur_all occur_heavy
1.71 1.75 63 0 0.1
# Global adjustment of p-values for all BW windows with "best" occurance cutoff
#- Greatest number of rejected hypotheses for each BD window -#
heavy_BD_min heavy_BD_max max_n_rej_hypo occur_all occur_heavy
1.71 1.75 63 0 0.1
Log2Fold cutoff: -Inf
padj cutoff: 0.1
File written: OTU_n2_abs1e9_PCR_subNorm_MW5p
File written: OTU_n2_abs1e9_PCR_subNorm_MW5p_data.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW5p_table.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW5p_overall.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW5p_byClass.txt
In [23]:
BDs = '1.71-1.8'
physeq = '../OTU_n2_abs1e9_PCR_subNorm.physeq'
BD_shift = '../ampFrags_BD-shift.txt'
HRSIP_multi_window_post(physeq, BD_shift, BDs, 'OTU_n2_abs1e9_PCR_subNorm_MW6p')
Warning message:
replacing previous import ‘S4Vectors::Position’ by ‘ggplot2::Position’ when loading ‘DESeq2’
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0
pre-filter: number of taxa: 1090
post-filter: number of taxa: 1053
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 69 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 88
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0.05
pre-filter: number of taxa: 1090
post-filter: number of taxa: 992
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 68 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 89
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0.1
pre-filter: number of taxa: 1090
post-filter: number of taxa: 915
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 67 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 92
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0.15
pre-filter: number of taxa: 1090
post-filter: number of taxa: 874
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 66 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 91
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0.2
pre-filter: number of taxa: 1090
post-filter: number of taxa: 790
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 64 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 90
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0.25
pre-filter: number of taxa: 1090
post-filter: number of taxa: 722
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 60 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 85
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0.3
pre-filter: number of taxa: 1090
post-filter: number of taxa: 688
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 57 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 81
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0.35
pre-filter: number of taxa: 1090
post-filter: number of taxa: 624
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 59 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 76
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0.4
pre-filter: number of taxa: 1090
post-filter: number of taxa: 580
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 57 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 67
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0.45
pre-filter: number of taxa: 1090
post-filter: number of taxa: 509
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 57 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 62
# occurance cutoff: 0
pre-filter: number of taxa: 1147
post-filter: number of taxa: 1090
# "heavy" BD window: 1.71-1.8
pre-filter: number of samples: 56
post-filter: number of samples: 32
# occurance cutoff: 0.5
pre-filter: number of taxa: 1090
post-filter: number of taxa: 435
# DESeq2 run
converting counts to integer mode
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 55 genes
-- DESeq argument 'minReplicatesForReplace' = 7
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing
# Number of rejected hypotheses: 54
# A file of all DESeq2 run results was written to: DESeq2_all_runs.txt
#- Greatest number of rejected hypotheses for each BD window -#
heavy_BD_min heavy_BD_max max_n_rej_hypo occur_all occur_heavy
1.71 1.8 92 0 0.1
# Global adjustment of p-values for all BW windows with "best" occurance cutoff
#- Greatest number of rejected hypotheses for each BD window -#
heavy_BD_min heavy_BD_max max_n_rej_hypo occur_all occur_heavy
1.71 1.8 92 0 0.1
Log2Fold cutoff: -Inf
padj cutoff: 0.1
File written: OTU_n2_abs1e9_PCR_subNorm_MW6p
File written: OTU_n2_abs1e9_PCR_subNorm_MW6p_data.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW6p_table.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW6p_overall.txt
File written: OTU_n2_abs1e9_PCR_subNorm_MW6p_byClass.txt
In [24]:
files = ['OTU_n2_abs1e9_PCR_subNorm_MW{}p_byClass.txt'.format(i) for i in xrange(1,7)]
files
Out[24]:
['OTU_n2_abs1e9_PCR_subNorm_MW1p_byClass.txt',
'OTU_n2_abs1e9_PCR_subNorm_MW2p_byClass.txt',
'OTU_n2_abs1e9_PCR_subNorm_MW3p_byClass.txt',
'OTU_n2_abs1e9_PCR_subNorm_MW4p_byClass.txt',
'OTU_n2_abs1e9_PCR_subNorm_MW5p_byClass.txt',
'OTU_n2_abs1e9_PCR_subNorm_MW6p_byClass.txt']
In [25]:
%%R -i files
renames = data.frame(file = c('MW1', 'MW2', 'MW3', 'MW4', 'MW5', 'MW6'),
BD_window = c('1.70-1.74,\n1.72-1.76',
'1.70-1.75,\n1.72-1.77',
'1.70-1.73,\n1.72-1.75,\n1.74-1.77',
'1.70-1.72,\n1.71-1.73,\n1.72-1.74,\n1.73-1.75',
'1.71-1.75', '1.71-1.8'))
df = list()
for(F in files){
tmp = read.delim(F, sep='\t')
df[[F]] = tmp
}
df = do.call(rbind, df)
df$file = gsub('.+(MW[0-9]+).+', '\\1', rownames(df))
df = inner_join(df, renames, c('file' = 'file'))
df %>% head(n=3)
library variables values file BD_window
1 2 Sensitivity 0.9082569 MW1 1.70-1.74,\n1.72-1.76
2 2 Specificity 1.0000000 MW1 1.70-1.74,\n1.72-1.76
3 2 Pos Pred Value 1.0000000 MW1 1.70-1.74,\n1.72-1.76
In [26]:
%%R -h 550
ggplot(df, aes(variables, values)) +
geom_bar(stat='identity') +
labs(y='Value') +
facet_grid(BD_window ~ .) +
theme_bw() +
theme(
text = element_text(size=16),
axis.title.x = element_blank(),
axis.text.x = element_text(angle=45, hjust=1)
)
In [27]:
%%R -h 250 -w 550
df.f = df %>%
filter(variables %in% c('Sensitivity', 'Specificity', 'Balanced Accuracy')) %>%
mutate(variables = gsub(' ', '\n', variables))
ggplot(df.f, aes(BD_window, values, color=variables)) +
geom_point(size=3, alpha=0.7) +
theme_bw() +
theme(
text = element_text(size=16),
axis.title.x = element_blank(),
axis.text.x = element_text(angle=60, hjust=1)
)
In [28]:
%pushnote validation MW-HR-SIP complete
In [ ]:
Content source: nick-youngblut/SIPSim
Similar notebooks: