Skip to content
Snippets Groups Projects
Commit ba3bf94b authored by Valentina Galata's avatar Valentina Galata
Browse files

mv scripts in rules/ to scripts/ (issue #15)

parent f2d5c20f
No related branches found
No related tags found
1 merge request!1Spring clean
Hide whitespace changes
Inline Side-by-side
rules/AMR/filter.pl deleted 100755 → 0
+ 0
− 19
View file @ f2d5c20f
#!/usr/bin/env perl
use strict;
use warnings;
my $minlen = shift or die "Error: `minlen` parameter not provided\n";
{
local $/=">";
while(<>) {
chomp;
next unless /\w/;
s/>$//gs;
my @chunk = split /\n/;
my $header = shift @chunk;
my $seqlen = length join "", @chunk;
print ">$_" if($seqlen >= $minlen);
}
local $/="\n";
}
rules/Virulence/virulence_prediction.py deleted 100755 → 0
+ 0
− 87
View file @ f2d5c20f
#!/usr/bin/env python
import Bio
from Bio import SeqIO
import re
import pandas as pd
#import argparse
import numpy as np
from sklearn import model_selection
from sklearn.ensemble import RandomForestClassifier
import pickle
#from PyBioMed.PyProtein import AAComposition
AALetter = ["A", "R", "N", "D", "C", "E", "Q", "G", "H", "I", "L", "K", "M", "F", "P", "S", "T", "W", "Y", "V"]
def CalculateAAComposition(ProteinSequence):
LengthSequence = len(ProteinSequence)
Result={}
for i in AALetter:
Result[i] = round(float(ProteinSequence.seq.count(i))/ LengthSequence * 100, 2)
return Result
def CalculateDipeptideComposition(ProteinSequence):
LengthSequence = len(ProteinSequence)
Result = {}
for i in AALetter:
for j in AALetter:
Dipeptide = i + j
Result[Dipeptide] = round(float(ProteinSequence.seq.count(Dipeptide)) / (LengthSequence -1) * 100, 2)
return Result
def CalculateKmerComposition(ProteinSequence):
LengthSequence = len(ProteinSequence)
Result = {}
for i in AALetter:
for j in AALetter:
for k in AALetter:
Kmer = i + j + k
Result[Kmer] = round(float(ProteinSequence.seq.count(Kmer)) / (LengthSequence -2) * 100, 2)
return Result
def CalculateAADipeptideComposition(ProteinSequence):
Result = {}
Result.update(CalculateAAComposition(ProteinSequence))
Result.update(CalculateDipeptideComposition(ProteinSequence))
Result.update(CalculateKmerComposition(ProteinSequence))
return Result
#if __name__ == "__main__":
# parser = argparse.ArgumentParser(description='Process fasta input with random forest virulence prediction model')
# parser.add_argument('infile', metavar='infile', type=str,
# help='The input file (FASTA format)')
# parser.add_argument('outfile', metavar='outfile', type=str,
# help='The outpufile (TSV format)')
# args = parser.parse_args()
df = pd.DataFrame([])
for Sequence in SeqIO.parse(snakemake.input[0], "fasta"):
ProteinSequence = Sequence
DIP = CalculateAADipeptideComposition(ProteinSequence)
data = DIP
data = pd.DataFrame(data.items())
data = data.transpose()
data.columns=data.iloc[0]
data = data.drop(data.index[[0]])
data['Sequence'] = Sequence.id
df =df.append(data)
rfc = pickle.load(open("finalized_model_3f.sav", 'rb'))
X_predict = df.drop('Sequence', axis = 1)
rfc_predict = rfc.predict(X_predict)
rfc_probs = rfc.predict_proba(X_predict)[:,1]
Prediction = pd.DataFrame([])
dfToList = df['Sequence'].tolist()
Prediction['Sequence'] = dfToList
Prediction['Prediction'] = rfc_predict
Prediction['Probability'] = rfc_probs
Prediction.to_csv(snakemake.output[0], sep='\t')
rules/AMR/AMR_MGE.R → scripts/AMR_MGE.R
+ 0
− 0
View file @ ba3bf94b
File moved
rules/Universal/PathoFact.R → scripts/PathoFact.R
+ 0
− 0
View file @ ba3bf94b
File moved
rules/Virulence/hmm.R → scripts/hmm.R
+ 0
− 0
View file @ ba3bf94b
File moved
rules/Toxin/ownHMM_library.R → scripts/ownHMM_library.R
+ 0
− 0
View file @ ba3bf94b
File moved
scripts/virulence_prediction.py
+ 72
− 19
View file @ ba3bf94b
#!/usr/bin/env python #!/usr/bin/env python
import Bio
from Bio import SeqIO
import re import re
import pandas as pd import pandas as pd
import argparse #import argparse
import numpy as np import numpy as np
from sklearn import model_selection
from sklearn.ensemble import RandomForestClassifier from sklearn.ensemble import RandomForestClassifier
import pickle import pickle
#from PyBioMed.PyProtein import AAComposition
if __name__ == "__main__": AALetter = ["A", "R", "N", "D", "C", "E", "Q", "G", "H", "I", "L", "K", "M", "F", "P", "S", "T", "W", "Y", "V"]
parser = argparse.ArgumentParser(description='Process fasta input with random forest virulence prediction model')
parser.add_argument('infile', metavar='infile', type=str,
help='The input file (FASTA format)')
parser.add_argument('outfile', metavar='outfile', type=str,
help='The outpufile (TSV format)')
args = parser.parse_args()
df = pd.read_csv(args.infile, sep='\t') def CalculateAAComposition(ProteinSequence):
X = df.drop('#', axis=1) LengthSequence = len(ProteinSequence)
Result={}
for i in AALetter:
Result[i] = round(float(ProteinSequence.seq.count(i))/ LengthSequence * 100, 2)
return Result
def CalculateDipeptideComposition(ProteinSequence):
LengthSequence = len(ProteinSequence)
Result = {}
for i in AALetter:
for j in AALetter:
Dipeptide = i + j
Result[Dipeptide] = round(float(ProteinSequence.seq.count(Dipeptide)) / (LengthSequence -1) * 100, 2)
return Result
def CalculateKmerComposition(ProteinSequence):
LengthSequence = len(ProteinSequence)
Result = {}
for i in AALetter:
for j in AALetter:
for k in AALetter:
Kmer = i + j + k
Result[Kmer] = round(float(ProteinSequence.seq.count(Kmer)) / (LengthSequence -2) * 100, 2)
return Result
def CalculateAADipeptideComposition(ProteinSequence):
Result = {}
Result.update(CalculateAAComposition(ProteinSequence))
Result.update(CalculateDipeptideComposition(ProteinSequence))
Result.update(CalculateKmerComposition(ProteinSequence))
return Result
#if __name__ == "__main__":
# parser = argparse.ArgumentParser(description='Process fasta input with random forest virulence prediction model')
# parser.add_argument('infile', metavar='infile', type=str,
# help='The input file (FASTA format)')
# parser.add_argument('outfile', metavar='outfile', type=str,
# help='The outpufile (TSV format)')
# args = parser.parse_args()
df = pd.DataFrame([])
rfc = pickle.load(open("scripts/Virulence_factor_model.sav", 'rb')) for Sequence in SeqIO.parse(snakemake.input[0], "fasta"):
rfc_predict = rfc.predict(X) ProteinSequence = Sequence
rfc_probs = rfc.predict_proba(X)[:,1] DIP = CalculateAADipeptideComposition(ProteinSequence)
data = DIP
data = pd.DataFrame(data.items())
data = data.transpose()
data.columns=data.iloc[0]
data = data.drop(data.index[[0]])
data['Sequence'] = Sequence.id
df =df.append(data)
rfc = pickle.load(open("finalized_model_3f.sav", 'rb'))
X_predict = df.drop('Sequence', axis = 1)
rfc_predict = rfc.predict(X_predict)
rfc_probs = rfc.predict_proba(X_predict)[:,1]
Prediction = pd.DataFrame([]) Prediction = pd.DataFrame([])
dfToList = df['#'].tolist() dfToList = df['Sequence'].tolist()
Prediction['Sequence'] = dfToList Prediction['Sequence'] = dfToList
Prediction['Prediction'] = rfc_predict Prediction['Prediction'] = rfc_predict
Prediction['Probability'] = rfc_probs Prediction['Probability'] = rfc_probs
Prediction.to_csv(args.outfile, sep='\t', header=False) Prediction.to_csv(snakemake.output[0], sep='\t')
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment