Mercurial > repos > jay > pdaug_sequence_based_peptide_generation

changeset 4:00027b06d85b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/jaidevjoshi83/pdaug commit 45ebf32dcaa1eed91670d3a2491f9cf3dfb535ef"
author jay
date Tue, 12 Jan 2021 19:30:36 +0000
parents eab83d8fb156
children 4a58c72769df
files PDAUG_Merge_Dataframes/PDAUG_Merge_Dataframes.py PDAUG_Merge_Dataframes/test-data/1.tsv PDAUG_Merge_Dataframes/test-data/2.tsv PDAUG_Merge_Dataframes/test-data/3.tsv PDAUG_Merge_Dataframes/test-data/4.tsv PDAUG_Merge_Dataframes/test-data/5.tsv PDAUG_Merge_Dataframes/test-data/6.tsv PDAUG_Merge_Dataframes/test-data/out.tsv PDAUG_Merge_Dataframes/test-data/out1.tsv PDAUG_TSVtoFASTA/PDAUG_TSVtoFASTA.py PDAUG_TSVtoFASTA/test-data/1.fasta PDAUG_TSVtoFASTA/test-data/2.fasta PDAUG_TSVtoFASTA/test-data/out.fasta PDAUG_TSVtoFASTA/test-data/test.tsv PDAUG_TSVtoFASTA/test-data/test1.tsv PDAUG_TSVtoFASTA/test-data/test2.tsv PDAUG_TSVtoFASTA/test-data/test2/Out.fasta
diffstat 17 files changed, 212 insertions(+), 203 deletions(-) [+]
line wrap: on
line diff
--- a/PDAUG_Merge_Dataframes/PDAUG_Merge_Dataframes.py	Wed Dec 30 03:15:08 2020 +0000
+++ b/PDAUG_Merge_Dataframes/PDAUG_Merge_Dataframes.py	Tue Jan 12 19:30:36 2021 +0000
@@ -2,27 +2,38 @@
 import pandas as pd 
 import sys
 
-files = sys.argv[1]
-out_file = sys.argv[2]
+
+def MergeData(infiles, add_class_label, class_label, OutPut):
+
+    data_frame = pd.DataFrame()
 
+    if add_class_label == 'True' or add_class_label == 'true':
+        for i, file in enumerate(infiles.split(',')): 
+            df1 = pd.read_csv(file,sep='\t')
+            df2 = pd.DataFrame(df1.shape[0]*[i], columns=[class_label])
+            df3 =  pd.concat([df1,df2], axis=1)
+            data_frame =  pd.concat([data_frame,df3])
+        final_DF = data_frame.fillna(0)
 
-data_frame = pd.read_csv(files.split(',')[0],sep='\t')
+    else:
+
+        for file in infiles.split(','): 
+            df1 = pd.read_csv(file,sep='\t')
+            data_frame =  pd.concat([data_frame,df1])
+        final_DF = data_frame.fillna(0)
+
+    final_DF.to_csv(OutPut, sep="\t", index=False)
 
 
-for file in files.split(',')[1:]: 
-
-    df1 = pd.read_csv(file,sep='\t')
-    data_frame =  pd.concat([data_frame,df1])
-
-final_DF = data_frame.fillna(0)
-
-final_DF.to_csv(out_file,sep="\t", index=False)
+if __name__=="__main__":
 
-
-
-
+    import argparse
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-I", "--infiles", required=True, default=None, help=".tsv")
+    parser.add_argument("-L", "--add_class_label", required=False, default=False, help="Path to target tsv file")
+    parser.add_argument("-C", "--class_label", required=False, default='class_label', help="Path to target tsv file")
+    parser.add_argument("-O", "--OutPut", required=False, default='Out.tsv', help="Path to target tsv file")
 
-
+    args = parser.parse_args()
 
-
-
+    MergeData(args.infiles, args.add_class_label, args.class_label, args.OutPut)
--- a/PDAUG_Merge_Dataframes/test-data/1.tsv	Wed Dec 30 03:15:08 2020 +0000
+++ b/PDAUG_Merge_Dataframes/test-data/1.tsv	Tue Jan 12 19:30:36 2021 +0000
@@ -1,2 +1,2 @@
-Algo	accuracy	presision	recall	f1	mean_auc
-SVMC	0.608	0.781	0.608	0.537	0.608
+NAME	COL1	COL2	COL3	COL4	COL5
+1	15	10	12	5	3
\ No newline at end of file
--- a/PDAUG_Merge_Dataframes/test-data/2.tsv	Wed Dec 30 03:15:08 2020 +0000
+++ b/PDAUG_Merge_Dataframes/test-data/2.tsv	Tue Jan 12 19:30:36 2021 +0000
@@ -1,2 +1,2 @@
-Algo	accuracy	presision	recall	f1	mean_auc
-SVMC	0.608	0.781	0.608	0.537	0.608
+NAME	COL1	COL2	COL3	COL4	COL5
+2	15	10	12	5	3
\ No newline at end of file
--- a/PDAUG_Merge_Dataframes/test-data/3.tsv	Wed Dec 30 03:15:08 2020 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,2 +0,0 @@
-Algo	accuracy	presision	recall	f1	mean_auc
-SVMC	0.608	0.781	0.608	0.537	0.608
--- a/PDAUG_Merge_Dataframes/test-data/4.tsv	Wed Dec 30 03:15:08 2020 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,2 +0,0 @@
-Algo	accuracy	presision	recall	f1	mean_auc
-SVMC	0.608	0.781	0.608	0.537	0.608
--- a/PDAUG_Merge_Dataframes/test-data/5.tsv	Wed Dec 30 03:15:08 2020 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,2 +0,0 @@
-Algo	accuracy	presision	recall	f1	mean_auc
-SVMC	0.608	0.781	0.608	0.537	0.608
--- a/PDAUG_Merge_Dataframes/test-data/6.tsv	Wed Dec 30 03:15:08 2020 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,2 +0,0 @@
-Algo	accuracy	presision	recall	f1	mean_auc
-SVMC	0.608	0.781	0.608	0.537	0.608
--- a/PDAUG_Merge_Dataframes/test-data/out.tsv	Wed Dec 30 03:15:08 2020 +0000
+++ b/PDAUG_Merge_Dataframes/test-data/out.tsv	Tue Jan 12 19:30:36 2021 +0000
@@ -1,7 +1,3 @@
-Algo	accuracy	presision	recall	f1	mean_auc
-SVMC	0.608	0.7809999999999999	0.608	0.537	0.608
-SVMC	0.608	0.7809999999999999	0.608	0.537	0.608
-SVMC	0.608	0.7809999999999999	0.608	0.537	0.608
-SVMC	0.608	0.7809999999999999	0.608	0.537	0.608
-SVMC	0.608	0.7809999999999999	0.608	0.537	0.608
-SVMC	0.608	0.7809999999999999	0.608	0.537	0.608
+NAME	COL1	COL2	COL3	COL4	COL5
+1	15	10	12	5	3
+2	15	10	12	5	3
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/PDAUG_Merge_Dataframes/test-data/out1.tsv	Tue Jan 12 19:30:36 2021 +0000
@@ -0,0 +1,3 @@
+NAME	COL1	COL2	COL3	COL4	COL5	class_label
+1	15	10	12	5	3	0
+2	15	10	12	5	3	1
--- a/PDAUG_TSVtoFASTA/PDAUG_TSVtoFASTA.py	Wed Dec 30 03:15:08 2020 +0000
+++ b/PDAUG_TSVtoFASTA/PDAUG_TSVtoFASTA.py	Tue Jan 12 19:30:36 2021 +0000
@@ -1,64 +1,72 @@
-import os
-import argparse
+
+import pandas as pd
+
+
+def TSVtoFASTA(infile, method, firstdatafile, seconddatafile, outfile, clmpepid, slcclasslabel, peps):
+
+
+    fn = [firstdatafile, seconddatafile]
 
 
-def TSVtoFASTA(InFile, Method, Positive, Negative, OutFile):
-
-    if Method == 'WithClassLabel':
-
-        f = open(InFile)
-        lines = f.readlines()
-
-        of1 = open(Positive,'w')
-        of2 = open(Negative,'w')
-
-        n = 0
-        m = 0
-        
-        l = []
-
-        for line in lines[1:]:
-            l.append(line.split('\t')[1].strip('\n').strip('\r'))
-        l = list(set(l))
-
-        print(l)
-
-        for line in lines:
+    df = pd.read_csv(infile, sep="\t")
+    if clmpepid == None:
+        pass
+    else:
+        names = df[clmpepid].tolist()
 
-            if l[1] in line.split('\t')[1].strip('\n').strip('\r'):
-                n= n+1
-                of1.write('>peptide_'+str(n)+'_'+str(l[1])+'\n')
-                of1.write(line.split('\t')[0]+'\n')
-
-            if l[0] in line.split('\t')[1].strip('\n').strip('\r'):
-                m= m+1
-                of2.write('>peptide_'+str(m)+'_'+str(l[0])+'\n')
-                of2.write(line.split('\t')[0]+'\n')
+    peps = df[peps].tolist()
+    
+    if method == "withoutlabel":
+        f = open(outfile,'w')
+        if clmpepid is not None:
+            for i,n in enumerate(peps):
+                f.write(">"+names[i]+'\n')
+                f.write(n+'\n')
+            f.close()
+        else:
+            for i,n in enumerate(peps):
+                f.write(">"+str(i)+'\n')
+                f.write(n+'\n')
+            f.close()
+                 
+    elif method == "withlabel":
+        labels = df[slcclasslabel].tolist()
 
-    elif Method == 'NoClassLabel':
-
-        f = open(InFile)
-        lines = f.readlines()
-        of1 = open(OutFile,'w')
-
-        for i, line in enumerate(lines[1:]):
-            of1.write('>peptide_'+str(i)+'\n')
-            of1.write(line.split('\t')[0]+'\n')
-
-    else:
-        pass
+        label = list(set(labels))
+        
+        if clmpepid is None:
+            for i, l in enumerate(label):
+                f = open(fn[i],'w')
+                print('ok1')
+                for i, L in enumerate(labels):
+                    if l == L:
+                        f.write(">"+str(i)+"_"+str(l)+'\n')
+                        f.write(peps[i]+'\n')
+            f.close()
+        else:
+            for i, l in enumerate(label):
+                f = open(fn[i],'w')          
+                for i, L in enumerate(labels):
+                    if l == L:
+                        f.write(">"+names[i]+"_"+l+'\n')
+                        f.write(peps[i]+'\n')        
+            f.close()
 
 if __name__=="__main__":
 
     import argparse
-
     parser = argparse.ArgumentParser()
-
     parser.add_argument("-I", "--InFile", required=True, default=None, help=".fasta or .tsv")
-    parser.add_argument("-P", "--Postvs", required=False, default='FirstDataFile.fasta', help="Path to target tsv file")
-    parser.add_argument("-N", "--Negtvs", required=False, default='SecondDataFile.fasta', help="Path to target tsv file")
+    parser.add_argument("-F", "--FirstDataFile", required=False, default='FirstDataFile.fasta', help="Path to target tsv file")
+    parser.add_argument("-S", "--SecondDataFile", required=False, default='SecondDataFile.fasta', help="Path to target tsv file")
     parser.add_argument("-O", "--OutFile", required=False, default='OutFile.fasta', help="Path to target tsv file")
     parser.add_argument("-M", "--Method", required=True, default=None, help="Path to target tsv file")
+    parser.add_argument("-C", "--ClmPepID", required=False, default=None, help="Peptide Column Name")
+    parser.add_argument("-L", "--SlcClassLabel", required=False, default="Class_label", help="Class Label Column Name")
+    parser.add_argument("-P", "--PeptideColumn", required=True, default=None, help="Class Label Column Name")
     args = parser.parse_args()
 
-    TSVtoFASTA(args.InFile, args.Method, args.Postvs, args.Negtvs, args.OutFile)
\ No newline at end of file
+    TSVtoFASTA(args.InFile, args.Method, args.FirstDataFile, args.SecondDataFile, args.OutFile, args.ClmPepID, args.SlcClassLabel, args.PeptideColumn)
+
+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/PDAUG_TSVtoFASTA/test-data/1.fasta	Tue Jan 12 19:30:36 2021 +0000
@@ -0,0 +1,22 @@
+>12_AMP
+GLFDIVKKVVGALG
+>13_AMP
+KLLKLLKKKLLK
+>14_AMP
+KLLLLKLLK
+>15_AMP
+GLFDIVKKVVGALG
+>16_AMP
+GLFDIVKKVVGALG
+>17_AMP
+KLLKLLKKKLLK
+>18_AMP
+KLLLLKLLK
+>19_AMP
+GLFDIVKKVVGALG
+>20_AMP
+KLLKLLKKKLLK
+>21_AMP
+KLLLLKLLK
+>22_AMP
+GLFDIVKKVVGALG
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/PDAUG_TSVtoFASTA/test-data/2.fasta	Tue Jan 12 19:30:36 2021 +0000
@@ -0,0 +1,24 @@
+>0_TM
+GLFDIVKKVVGALG
+>1_TM
+KLLKLLKKKLLK
+>2_TM
+KLLLLKLLK
+>3_TM
+GLFDIVKKVVGALG
+>4_TM
+GLFDIVKKVVGALG
+>5_TM
+KLLKLLKKKLLK
+>6_TM
+KLLLLKLLK
+>7_TM
+GLFDIVKKVVGALG
+>8_TM
+GLFDIVKKVVGALG
+>9_TM
+KLLKLLKKKLLK
+>10_TM
+KLLLLKLLK
+>11_TM
+GLFDIVKKVVGALG
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/PDAUG_TSVtoFASTA/test-data/out.fasta	Tue Jan 12 19:30:36 2021 +0000
@@ -0,0 +1,46 @@
+>0
+GLFDIVKKVVGALG
+>1
+KLLKLLKKKLLK
+>2
+KLLLLKLLK
+>3
+GLFDIVKKVVGALG
+>4
+GLFDIVKKVVGALG
+>5
+KLLKLLKKKLLK
+>6
+KLLLLKLLK
+>7
+GLFDIVKKVVGALG
+>8
+GLFDIVKKVVGALG
+>9
+KLLKLLKKKLLK
+>10
+KLLLLKLLK
+>11
+GLFDIVKKVVGALG
+>12
+GLFDIVKKVVGALG
+>13
+KLLKLLKKKLLK
+>14
+KLLLLKLLK
+>15
+GLFDIVKKVVGALG
+>16
+GLFDIVKKVVGALG
+>17
+KLLKLLKKKLLK
+>18
+KLLLLKLLK
+>19
+GLFDIVKKVVGALG
+>20
+KLLKLLKKKLLK
+>21
+KLLLLKLLK
+>22
+GLFDIVKKVVGALG
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/PDAUG_TSVtoFASTA/test-data/test.tsv	Tue Jan 12 19:30:36 2021 +0000
@@ -0,0 +1,24 @@
+Name	Peptides	Class_label
+Pep1	GLFDIVKKVVGALG	TM
+Pep2	KLLKLLKKKLLK	TM
+Pep3	KLLLLKLLK	TM
+Pep4	GLFDIVKKVVGALG	TM
+Pep5	GLFDIVKKVVGALG	TM
+Pep6	KLLKLLKKKLLK	TM
+Pep7	KLLLLKLLK	TM
+Pep8	GLFDIVKKVVGALG	TM
+Pep9	GLFDIVKKVVGALG	TM
+Pep10	KLLKLLKKKLLK	TM
+Pep11	KLLLLKLLK	TM
+Pep12	GLFDIVKKVVGALG	TM
+Pep13	GLFDIVKKVVGALG	AMP
+Pep14	KLLKLLKKKLLK	AMP
+Pep15	KLLLLKLLK	AMP
+Pep16	GLFDIVKKVVGALG	AMP
+Pep17	GLFDIVKKVVGALG	AMP
+Pep18	KLLKLLKKKLLK	AMP
+Pep19	KLLLLKLLK	AMP
+Pep20	GLFDIVKKVVGALG	AMP
+Pep21	KLLKLLKKKLLK	AMP
+Pep22	KLLLLKLLK	AMP
+Pep23	GLFDIVKKVVGALG	AMP
\ No newline at end of file
--- a/PDAUG_TSVtoFASTA/test-data/test1.tsv	Wed Dec 30 03:15:08 2020 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,24 +0,0 @@
-Peptides	Class_label
-GLFDIVKKVVGALG	0
-KLLKLLKKKLLK	0
-KLLLLKLLK	0
-GLFDIVKKVVGALG	0
-GLFDIVKKVVGALG	0
-KLLKLLKKKLLK	0
-KLLLLKLLK	0
-GLFDIVKKVVGALG	0
-GLFDIVKKVVGALG	0
-KLLKLLKKKLLK	0
-KLLLLKLLK	0
-GLFDIVKKVVGALG	0
-GLFDIVKKVVGALG	1
-KLLKLLKKKLLK	1
-KLLLLKLLK	1
-GLFDIVKKVVGALG	1
-GLFDIVKKVVGALG	1
-KLLKLLKKKLLK	1
-KLLLLKLLK	1
-GLFDIVKKVVGALG	1
-KLLKLLKKKLLK	1
-KLLLLKLLK	1
-GLFDIVKKVVGALG	1
\ No newline at end of file
--- a/PDAUG_TSVtoFASTA/test-data/test2.tsv	Wed Dec 30 03:15:08 2020 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,24 +0,0 @@
-Peptides
-GLFDIVKKVVGALG
-KLLKLLKKKLLK
-KLLLLKLLK
-GLFDIVKKVVGALG
-GLFDIVKKVVGALG
-KLLKLLKKKLLK
-KLLLLKLLK
-GLFDIVKKVVGALG
-GLFDIVKKVVGALG
-KLLKLLKKKLLK
-KLLLLKLLK
-GLFDIVKKVVGALG
-GLFDIVKKVVGALG
-KLLKLLKKKLLK
-KLLLLKLLK
-GLFDIVKKVVGALG
-GLFDIVKKVVGALG
-KLLKLLKKKLLK
-KLLLLKLLK
-GLFDIVKKVVGALG
-KLLKLLKKKLLK
-KLLLLKLLK
-GLFDIVKKVVGALG
\ No newline at end of file
--- a/PDAUG_TSVtoFASTA/test-data/test2/Out.fasta	Wed Dec 30 03:15:08 2020 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,69 +0,0 @@
->peptide_0
-GLFDIVKKVVGALG
-
->peptide_1
-KLLKLLKKKLLK
-
->peptide_2
-KLLLLKLLK
-
->peptide_3
-GLFDIVKKVVGALG
-
->peptide_4
-GLFDIVKKVVGALG
-
->peptide_5
-KLLKLLKKKLLK
-
->peptide_6
-KLLLLKLLK
-
->peptide_7
-GLFDIVKKVVGALG
-
->peptide_8
-GLFDIVKKVVGALG
-
->peptide_9
-KLLKLLKKKLLK
-
->peptide_10
-KLLLLKLLK
-
->peptide_11
-GLFDIVKKVVGALG
-
->peptide_12
-GLFDIVKKVVGALG
-
->peptide_13
-KLLKLLKKKLLK
-
->peptide_14
-KLLLLKLLK
-
->peptide_15
-GLFDIVKKVVGALG
-
->peptide_16
-GLFDIVKKVVGALG
-
->peptide_17
-KLLKLLKKKLLK
-
->peptide_18
-KLLLLKLLK
-
->peptide_19
-GLFDIVKKVVGALG
-
->peptide_20
-KLLKLLKKKLLK
-
->peptide_21
-KLLLLKLLK
-
->peptide_22
-GLFDIVKKVVGALG
-