In [2]:

    

import pandas as pd
import os
import re


    

In [3]:

    

# Where is the shortstack directory
os.chdir("/Users/mgalland/SURFdrive/trichome_team/06.results_from_xp/sRNA-Seq/20170117_srnadesc/shortstack/")


    

In [4]:

    

# Get all ShortStack directories (sample list)
pattern = re.compile("[A-Z+][0-9]+")

# Store them in a list
files = [os.getcwd() + "/" + f + "/Results.txt" for f in os.listdir("./") if pattern.search(f)]

# print first elements
files[0:2]


    

    
Out[4]:





['/Users/mgalland/SURFdrive/trichome_team/06.results_from_xp/sRNA-Seq/20170117_srnadesc/shortstack/C32/Results.txt',
 '/Users/mgalland/SURFdrive/trichome_team/06.results_from_xp/sRNA-Seq/20170117_srnadesc/shortstack/LA0407/Results.txt']

In [5]:

    

# Store all ShortStack results dataframes in a list
shortstack_res = [pd.read_table(f) for f in files]

# This is how it looks
shortstack_res[0].head()


    

    
Out[5]:






  

    

      

      
#Locus
      
Name
      
Length
      
Reads
      
MeanReads
      
StdevReads
      
UniqueReads
      
FracTop
      
Strand
      
MajorRNA
      
...
      
MIRNA
      
PhaseSize
      
PhaseScore
      
Short
      
Long
      
20
      
21
      
22
      
23
      
24
    
  
  

    

      
0
      
SL2.40ch00:3099527-3099768
      
Cluster_1
      
242
      
77
      
68.7
      
1.6
      
2
      
0.649
      
.
      
UUACAUACUCCUGCUAAUAUGU
      
...
      
N6
      
20
      
2.9
      
0
      
1
      
1
      
5
      
57
      
3
      
10
    
    

      
1
      
SL2.40ch00:4197032-4197202
      
Cluster_2
      
171
      
86
      
55.9
      
4.8
      
4
      
0.965
      
+
      
CCCUUGAAAAUCCGGAGG
      
...
      
N2
      
NP2
      
NaN
      
40
      
2
      
8
      
15
      
3
      
5
      
13
    
    

      
2
      
SL2.40ch00:5204257-5204456
      
Cluster_3
      
200
      
20
      
14.5
      
2.0
      
4
      
0.550
      
.
      
UGUAAGUGCCCGAACAACAUCA
      
...
      
N6
      
21
      
1.1
      
1
      
0
      
0
      
1
      
11
      
6
      
1
    
    

      
3
      
SL2.40ch00:5774256-5774769
      
Cluster_4
      
514
      
87
      
85.4
      
1.1
      
41
      
0.425
      
.
      
UGAAAGCUCUCUAAAAAACCUCUC
      
...
      
N6
      
20
      
1.8
      
2
      
2
      
0
      
1
      
7
      
8
      
67
    
    

      
4
      
SL2.40ch00:6571367-6571564
      
Cluster_5
      
198
      
48
      
40.0
      
1.8
      
16
      
0.458
      
.
      
AUUUCGGGCAUAGAUUGAAGGGGU
      
...
      
N6
      
23
      
1.4
      
1
      
0
      
2
      
1
      
0
      
8
      
36
    
  

5 rows × 23 columns

In [6]:

    

# Select only the MajorRNA and merge
shortstack_res = [f[["MajorRNA"]] for f in shortstack_res]
shortstack_res[0].head()


    

    
Out[6]:






  

    

      

      
MajorRNA
    
  
  

    

      
0
      
UUACAUACUCCUGCUAAUAUGU
    
    

      
1
      
CCCUUGAAAAUCCGGAGG
    
    

      
2
      
UGUAAGUGCCCGAACAACAUCA
    
    

      
3
      
UGAAAGCUCUCUAAAAAACCUCUC
    
    

      
4
      
AUUUCGGGCAUAGAUUGAAGGGGU
    
  

In [11]:

    

# initialize the first dataframe and merge
df = pd.merge(shortstack_res[0],shortstack_res[1],on="MajorRNA",how="outer")
print("\n")
print("#############################")
print("First merge")
print(df.head())
rows, columns = df.shape
print("It contains {0} number of lines".format(str(rows)))
print("##############################")


    

    





#############################
First merge
                 MajorRNA
0  UUACAUACUCCUGCUAAUAUGU
1      CCCUUGAAAAUCCGGAGG
2      CCCUUGAAAAUCCGGAGG
3      CCCUUGAAAAUCCGGAGG
4  UGUAAGUGCCCGAACAACAUCA
It contains 44450 number of lines
##############################

In [21]:

    

l = list(set(df["MajorRNA"].tolist()))
l = l[1:10]


    

In [20]:

    




    

    




---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-20-1d81b7fbec86> in <module>()
----> 1 l = dict(l)
      2 l

ValueError: dictionary update sequence element #0 has length 24; 2 is required

In [ ]: