-
Notifications
You must be signed in to change notification settings - Fork 0
/
ParseCMscan1.0.py
150 lines (129 loc) · 7.14 KB
/
ParseCMscan1.0.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
# -*- coding: utf-8 -*-
"""
Created on Wed Feb 26 07:57:27 2020
@author: mcveigh
"""
import pandas as pd
import Bio
import os
import sys
inputfile = sys.argv[1]
outputfile = sys.argv[2]
CMscan_output = (r'cmscan_final.tblout')
CMscan_df = pd.read_csv(CMscan_output,
sep='\t',
index_col=None,
low_memory=False,
usecols=[0,2,3,5,6,7,8,9,10,11,12,13,14,15,16,17],
header=None,
names=["gene", "accession","model", "mdl_from",
"mdl_to", "seq_from", "seq_to", "strand",
"trunc", "pass", "gc", "bias", "score",
"E-value", "Inc", "Length"])
#CMscan_df = CMscan_df[1:]
#print(CMscan_df.head(10))
#Remove 5S model rows
CMscan_df2 = CMscan_df[CMscan_df['gene'] != "5S_rRNA"]
#print(CMscan_df2.head(20))
#Find sequences on the minus strand
minus_strand = CMscan_df2[CMscan_df2['strand'] != "+"]
print("I found sequences on the minus strand\n ", minus_strand)
#NEEDS add a step to flip any sequences found on the minus strain
#Find sequences that have truncated models
truncated = CMscan_df2[CMscan_df2['trunc'] == "5'&3'"]
print("I found truncated models suggesting the presence of an intron\n ", truncated)
#print(truncated['accession'])
#Possible action needed here
#Find sequences that do not pass CMscan tests
fail_test = CMscan_df2[CMscan_df2['Inc'] == "?"]
print("Sequences that have a ? are\n ", fail_test)
#show rows containing SSU or LSU
SSU_RNA_df = CMscan_df2[CMscan_df2['gene'] == "SSU_rRNA_eukarya"]
#print("these sequences have SSU\n ", SSU_RNA_df)
Five_RNA_df = CMscan_df2[CMscan_df2['gene'] == "5_8S_rRNA"]
FiveComplete = Five_RNA_df[Five_RNA_df['trunc'] == "no"]
FiveFivePartial = Five_RNA_df[Five_RNA_df['trunc'] == "5'"]
FiveThreePartial = Five_RNA_df[Five_RNA_df['trunc'] == "3'"]
#FiveBothPartial = Five_RNA_df[Five_RNA_df['trunc'] == "5'&3'"] & Five_RNA_df[Five_RNA_df['seq_from'] > 2]
FiveBothPartial = Five_RNA_df[Five_RNA_df['trunc'] == "5'&3'"]
print("These 5.8S rRNA are 5' partial\n", FiveFivePartial)
print("These 5.8S rRNA are 3' partial\n", FiveThreePartial)
print("These 5.8S rRNA are 5'&3'\n", FiveBothPartial)
#Sequences with extra sequence on the 5' the extends beyond position 1 of the SSU model
SSU_not5_end = SSU_RNA_df[SSU_RNA_df['seq_from'] != 1]
SSUextra = SSU_not5_end[SSU_not5_end['mdl_from'] == 1]
print("sequences with extra data on the 5' end \n", SSUextra)
#Sequnces with extra data on the 3' end beyond the end of LSU
LSU_RNA_df = CMscan_df2[CMscan_df2['gene'] == "LSU_rRNA_eukarya"]
LSUextra=LSU_RNA_df.loc[(LSU_RNA_df['seq_to'] != LSU_RNA_df['Length']) & (LSU_RNA_df['mdl_to'] == 3401) & (LSU_RNA_df['mdl_from'] == 1)]
print("sequences with extra data on the 3' end \n", LSUextra)
#SSU_LSUexact=LSU_RNA_df.loc[(LSU_RNA_df['seq_to'] == LSU_RNA_df['Length']) & (LSU_RNA_df['mdl_to'] == 3401) & (SSU_RNA_df['mdl_from'] == 1) & (SSU_RNA_df['seq_from'] == 1)]
#SSU_LSUpartial=LSU_RNA_df.loc[(LSU_RNA_df['seq_to'] == LSU_RNA_df['Length']) & (LSU_RNA_df['mdl_to'] < 3401) & (SSU_RNA_df['mdl_from'] > 1)]
#Trim the sequences with extra sequence flanking the SSU and LSU then rewrite the editted fasta to a new file
from Bio import SeqIO
sequences = []
for seq_record in SeqIO.parse("ribo-out/ribo-out.ribodbmaker.final.fa", "fasta"):
s = seq_record
if seq_record.id not in Five_RNA_df['accession'].tolist():
#sequences.remove(seq_record)
print("No 5.8S rRNA was found in ", seq_record.id)
#missingRNA.append(seq_record)
else:
if seq_record.id in LSUextra['accession'].tolist():
#start_df = CMscan_df2[(CMscan_df2['accession'] == seq_record.id) & (CMscan_df2['gene'] == 'SSU_rRNA_eukarya')]
#start = start_df['seq_from'].iloc[0]
to_df = CMscan_df2[(CMscan_df2['accession'] == seq_record.id) & (CMscan_df2['gene'] == 'LSU_rRNA_eukarya')]
to = to_df['seq_to'].iloc[0]
s.seq = s.seq[0:to]
#seq_record.description = seq_record.description + " small subunit ribosomal RNA, internal transcribed spacer 1, 5.8S ribosomal RNA, internal transcribed spacer 2 and large subunit ribosomal RNA, complete sequence"
#seq_record.description = seq_record.description + " COMPLETE LSU"
#print(seq_record.id,seq_record.description)
if seq_record.id in SSUextra['accession'].tolist():
if seq_record.id in LSUextra['accession'].tolist():
start_df = CMscan_df2[(CMscan_df2['accession'] == seq_record.id) & (CMscan_df2['gene'] == 'SSU_rRNA_eukarya')]
start = start_df['seq_from'].iloc[0]
s.seq = s.seq[start-1:to]
else:
start_df = CMscan_df2[(CMscan_df2['accession'] == seq_record.id) & (CMscan_df2['gene'] == 'SSU_rRNA_eukarya')]
start = start_df['seq_from'].iloc[0]
to = start_df['Length'].iloc[0]
s.seq = s.seq[start-1:to]
#seq_record.description = seq_record.description + " COMPLETE SSU"
#else:
if seq_record.id in minus_strand['accession'].tolist():
print("I reverse complemented ", seq_record.id)
s.seq = s.seq.reverse_complement()
if seq_record.id in SSU_RNA_df['accession'].tolist():
seq_record.description = seq_record.description + " SSU"
if seq_record.id in FiveFivePartial['accession'].tolist():
seq_record.description = seq_record.description + " <5.8S ITS2"
elif seq_record.id in FiveThreePartial['accession'].tolist():
seq_record.description = seq_record.description + " ITS1 5.8S>"
elif seq_record.id in FiveComplete['accession'].tolist():
seq_record.description = seq_record.description + " ITS1 5.8S ITS2"
elif seq_record.id in FiveBothPartial['accession'].tolist():
seq_record.description = seq_record.description + " 5.8S truncated"
if seq_record.id in LSU_RNA_df['accession'].tolist():
seq_record.description = seq_record.description + " LSU"
#else:
#seq_record.description = seq_record.description + " ITS region"
sequences.append(s)
SeqIO.write(sequences, outputfile, "fasta")
#SeqIO.write(missingRNA, "missing5_8.fsa", "fasta")
#Print seq_record.id and sequence length from output file
from Bio import SeqIO
for record in SeqIO.parse(outputfile, "fasta"):
tmp = LSUextra[LSUextra['accession'] == record.id]
if not tmp.empty:
length = len(record)
print("Sequences that were trimmed are: ", record.id, length)
#Add the new definition lines to the outputfile by appending text to seq_record.description
#Count the number of sequences in the final output file
fh = open(outputfile)
n = 0
for line in fh:
if line.startswith(">"):
n += 1
fh.close()
print("The number of sequences in the final output file is: ", n)
print ("processITS script is done and output is saved in:", outputfile)