In [1]:

    

!tree


    

    




.
├── 1_get_hits_from_tools.ipynb
├── 1_merged_viruses.tsv
├── 2_set_intersection_viz.R
├── README.md
├── find_viruses_in_families
│   ├── 0_virus_fasta
│   │   ├── blastdb
│   │   │   ├── viruses.fasta
│   │   │   ├── viruses.nhr
│   │   │   ├── viruses.nin
│   │   │   └── viruses.nsq
│   │   ├── crassphage.fasta
│   │   ├── enterobacteria_phage_phi92.fasta
│   │   └── parvovirus-nih_cqv.fasta
│   ├── 1_blastn
│   │   ├── asn
│   │   │   └── orfan_to_viruses.asn
│   │   ├── plots
│   │   └── tsv
│   │       ├── blast_tsv_columns.txt
│   │       ├── orfan_to_viruses.tsv
│   │       └── orfan_to_viruses_filt.tsv
│   ├── 1_orfans_to_viruses.sh
│   ├── blastn.mak
│   ├── plot_blastn_hits.py
│   └── plot_blastn_tsv_hits.py
├── kaiju
│   ├── kaiju_greedy
│   │   ├── 454_seqs_kaiju_greedy.family.report
│   │   ├── 454_seqs_kaiju_greedy.filt_species.tsv
│   │   ├── 454_seqs_kaiju_greedy.genus.report
│   │   ├── 454_seqs_kaiju_greedy.names.txt
│   │   ├── 454_seqs_kaiju_greedy.names.virus.txt
│   │   ├── 454_seqs_kaiju_greedy.species.report
│   │   ├── 454_seqs_kaiju_greedy.txt
│   │   ├── kaiju_greedy_summarize_virus_hits.ipynb
│   │   └── summarize_virus_hits.ipynb
│   ├── kaiju_mem
│   │   ├── 454_seqs_kaiju.genus.report
│   │   ├── 454_seqs_kaiju.names.txt
│   │   ├── 454_seqs_kaiju.names.virus.txt
│   │   ├── 454_seqs_kaiju.report
│   │   ├── 454_seqs_kaiju.species.report
│   │   ├── 454_seqs_kaiju.txt
│   │   └── kaiju_mem_summarize_virus_hits.ipynb
│   ├── poophage_in_kaiju.ipynb
│   ├── run_kaiju_greedy.sh
│   └── run_kaiju_mem.sh
├── kraken
│   ├── 454_seqs_kraken.out
│   ├── 454_seqs_kraken_filt.out
│   ├── 454_seqs_kraken_filt.report
│   ├── _filt.virus.report
│   ├── kraken.log
│   └── run_kraken.sh
└── metaphlan2
    ├── 454_reads_mpa2.bowtie2.bz2
    ├── 454_reads_mpa2.sam
    ├── 454_reads_mpa2.txt
    ├── get_marker_taxon_annot.ipynb
    ├── markers_to_taxons.csv
    └── run_mpa2.sh

12 directories, 50 files

In [2]:

    

import pandas as pd


    

In [3]:

    

kraken = pd.read_csv("kraken/_filt.virus.report",sep="\t",header=None,names=["pct_sum","reads_sum","reads_assigned","tax_level","taxid","taxname"])
kraken["taxname"] = kraken["taxname"].apply(lambda x: x.lstrip("\t ").rstrip("\t "))
kraken[kraken.reads_assigned >0]


    

    
Out[3]:






  

    

      

      
pct_sum
      
reads_sum
      
reads_assigned
      
tax_level
      
taxid
      
taxname
    
  
  

    

      
5
      
0.0
      
3
      
3
      
S
      
1341019
      
Parvovirus NIH-CQV
    
    

      
8
      
0.0
      
1
      
1
      
S
      
93678
      
TTV-like mini virus
    
    

      
11
      
0.0
      
2
      
2
      
S
      
1211417
      
uncultured phage crAssphage
    
    

      
16
      
0.0
      
1
      
1
      
S
      
948870
      
Enterobacteria phage phi92
    
    

      
18
      
0.0
      
1
      
1
      
-
      
196894
      
unclassified Siphoviridae
    
  

In [4]:

    

kaiju = pd.read_csv("kaiju/kaiju_greedy/454_seqs_kaiju_greedy.filt_species.tsv",sep="\t")
print(kaiju.shape)
kaiju


    

    




(16, 2)






    
Out[4]:






  

    

      

      
species
      
read_count
    
  
  

    

      
0
      
Enterobacteria phage phi92
      
52
    
    

      
1
      
uncultured crAssphage
      
34
    
    

      
2
      
Parabacteroides phage YZ-2015b;Parabacteroides...
      
24
    
    

      
3
      
Parvovirus NIH-CQV
      
18
    
    

      
4
      
Phytophthora parasitica virus
      
18
    
    

      
5
      
Gokushovirinae Fen672_31;Gokushovirinae Fen787...
      
10
    
    

      
6
      
Sewage-associated gemycircularvirus 11;Sewage-...
      
5
    
    

      
7
      
Chimpanzee faeces associated microphage 2;Chim...
      
4
    
    

      
8
      
Salmonella virus SP31
      
4
    
    

      
9
      
unclassified NA
      
4
    
    

      
10
      
Pseudomonas virus NP1
      
3
    
    

      
11
      
Rhizobium phage RHEph10;Rhizobium phage vB_Rgl...
      
3
    
    

      
12
      
Croceibacter phage P2559Y
      
2
    
    

      
13
      
Pseudomonas phage PAJU2;Pseudomonas phage phiP...
      
2
    
    

      
14
      
TTV-like mini virus
      
2
    
    

      
15
      
unclassified Siphoviridae
      
2
    
  

In [5]:

    

mpa2 = pd.read_csv("metaphlan2/454_reads_mpa2.txt",sep="\t")
mpa2.columns = ["full_tax","rel_ab"]
mpa2["clade"] = mpa2["full_tax"].apply(lambda t: t.split("|")[-1])
mpa2_sp = mpa2[mpa2["clade"].apply(lambda c: c.startswith("s__"))].copy()
mpa2_sp


    

    
Out[5]:






  

    

      

      
full_tax
      
rel_ab
      
clade
    
  
  

    

      
6
      
k__Viruses|p__Viruses_noname|c__Viruses_noname...
      
100.0
      
s__Parvovirus_NIH_CQV
    
  

In [6]:

    

import functools
replacements = {("crassphage",):"uncultured crAssphage",
                ("parvovirus","nih","cqv"): "Parvovirus NIH-CQV"
               }

def replacement_fx(clade_name):
    new_name = clade_name
    for r in replacements:
        name_matches = functools.reduce(lambda x,y:x and y, [word in clade_name.lower() for word in r ])
        if name_matches:
            new_name = replacements[r]
            break
    return new_name


    

In [7]:

    

mpa2_sp["std_cladename"] = mpa2_sp["clade"].apply(replacement_fx)
mpa2_sp = mpa2_sp[["std_cladename","rel_ab"]].copy()
mpa2_sp.columns = ["clade","abundance"]
mpa2_sp["tool"] = "metaphlan2"


    

In [8]:

    

kraken["std_cladename"] = kraken["taxname"].apply(replacement_fx)
kraken = kraken[kraken.reads_assigned >0][["std_cladename","reads_assigned"]].copy()
kraken.columns = ["clade","abundance"]
kraken["tool"] = "kraken"


    

In [9]:

    

kaiju["std_cladename"] = kaiju["species"].apply(replacement_fx)
kaiju = kaiju[["std_cladename","read_count"]].copy()
kaiju.columns = ["clade","abundance"]
kaiju["tool"] = "kaiju"


    

In [10]:

    

orfan_hits = [["TTV-like mini virus",1],
              ["Phytophthora parasitica virus",1],
              ["uncultured POOphage",1]]

orfan_method = pd.DataFrame.from_records(orfan_hits,columns=["clade","abundance"])
orfan_method["tool"] = "ORFan"


    

In [11]:

    

merged_viruses = pd.concat([mpa2_sp,kraken,kaiju,orfan_method],ignore_index=True,axis=0)
merged_viruses.to_csv("1_merged_viruses.tsv",sep="\t",index=False)
merged_viruses


    

    
Out[11]:






  

    

      

      
clade
      
abundance
      
tool
    
  
  

    

      
0
      
Parvovirus NIH-CQV
      
100.0
      
metaphlan2
    
    

      
1
      
Parvovirus NIH-CQV
      
3.0
      
kraken
    
    

      
2
      
TTV-like mini virus
      
1.0
      
kraken
    
    

      
3
      
uncultured crAssphage
      
2.0
      
kraken
    
    

      
4
      
Enterobacteria phage phi92
      
1.0
      
kraken
    
    

      
5
      
unclassified Siphoviridae
      
1.0
      
kraken
    
    

      
6
      
Enterobacteria phage phi92
      
52.0
      
kaiju
    
    

      
7
      
uncultured crAssphage
      
34.0
      
kaiju
    
    

      
8
      
Parabacteroides phage YZ-2015b;Parabacteroides...
      
24.0
      
kaiju
    
    

      
9
      
Parvovirus NIH-CQV
      
18.0
      
kaiju
    
    

      
10
      
Phytophthora parasitica virus
      
18.0
      
kaiju
    
    

      
11
      
Gokushovirinae Fen672_31;Gokushovirinae Fen787...
      
10.0
      
kaiju
    
    

      
12
      
Sewage-associated gemycircularvirus 11;Sewage-...
      
5.0
      
kaiju
    
    

      
13
      
Chimpanzee faeces associated microphage 2;Chim...
      
4.0
      
kaiju
    
    

      
14
      
Salmonella virus SP31
      
4.0
      
kaiju
    
    

      
15
      
unclassified NA
      
4.0
      
kaiju
    
    

      
16
      
Pseudomonas virus NP1
      
3.0
      
kaiju
    
    

      
17
      
Rhizobium phage RHEph10;Rhizobium phage vB_Rgl...
      
3.0
      
kaiju
    
    

      
18
      
Croceibacter phage P2559Y
      
2.0
      
kaiju
    
    

      
19
      
Pseudomonas phage PAJU2;Pseudomonas phage phiP...
      
2.0
      
kaiju
    
    

      
20
      
TTV-like mini virus
      
2.0
      
kaiju
    
    

      
21
      
unclassified Siphoviridae
      
2.0
      
kaiju
    
    

      
22
      
TTV-like mini virus
      
1.0
      
ORFan
    
    

      
23
      
Phytophthora parasitica virus
      
1.0
      
ORFan
    
    

      
24
      
uncultured POOphage
      
1.0
      
ORFan
    
  

In [ ]: