ENH update 10_Transmembrane_secreted

Author: cocodyq

General_Scripts/10_Transmembrane_secreted/01_Annotation/03_SignalP.sh

@@ -1,7 +1,14 @@
 #!/usr/bin/env bash
 
 # Concept: 
-# Run SisnalP 4.1 on 90AA smORF families
+# Run SisnalP 5.0 on 90AA smORF families
+for n in {0..2399}
+  do
+    signalp -fasta sub_${n}.faa -org gram+ -batch 100000
+    signalp -fasta sub_${n}.faa -org gram- -batch 100000
+  done
 
-signalp -t gram+ 90AA_GMSC.faa >90AA_signalp_gram_positive.tsv
-signalp -t gram- 90AA_GMSC.faa >90AA_signalp_gram_negative.tsv
+for n in {0..62}
+  do
+signalp -fasta sub_${n}.faa -org arch -batch 100000
+  done

General_Scripts/10_Transmembrane_secreted/01_Annotation/04_find_signal.py

@@ -9,7 +9,6 @@ def statistic(infile,outfile):
                 continue
             else:
                 linelist = line.strip().split(' ')
-                print(linelist)
                 if linelist[18] == 'Y':
                     out.write(line)
     out.close()

General_Scripts/10_Transmembrane_secreted/02_Compare between archaea and bacteria/01_map_taxonomy_trans.py

@@ -4,9 +4,8 @@
 '''
 
 def store_trans(infile1):
-    import gzip
     trans = set()
-    with gzip.open(infile1,'rt') as f:
+    with open(infile1,'rt') as f:
         for line in f:
             trans.add(line.strip())
     return trans
@@ -30,8 +29,8 @@ def count_trans(infile,outfile):
     trans_count = df.groupby(['domain','phylum'])['transmembrane'].value_counts()
     trans_count.to_csv(outfile)
 
-infile1 = '90AA_tm_signal.tsv.gz'
-infile2 = '90AA_ref_taxonomy_format.tsv.xz'
+infile1 = '90AA_tm_signal.tsv'
+infile2 = '90AA_tax.tsv.xz'
 outfile1 = 'trans_taxa.tsv'
 outfile2 = 'trans_phylum.csv'
 

General_Scripts/10_Transmembrane_secreted/02_Compare between archaea and bacteria/02_extract_cog.py

@@ -39,10 +39,11 @@ def cog(infile1,infile2,infile3,outfile):
 
     merged.to_csv(outfile,sep='\t',index=None)
 
-infile1 = '90AA_ref_taxonomy_format.tsv.xz'
+infile1 = '90AA_tax.tsv.xz'
 infile2 = '1_cdd_tcov_90AA.tsv.gz'
 infile3 = 'cddid_all.tbl'
 infile4 = 'cog-20.def.tab.tsv'
+
 outfile1 = 'bac_motif.txt'
 outfile2 = 'arc_motif.txt'
 outfile3 = '0_arc_motif_cog.tsv'

General_Scripts/10_Transmembrane_secreted/02_Compare between archaea and bacteria/03_count_cog_class.py

@@ -1,5 +1,5 @@
 '''
-Count cog class number an fraction of smORFs with annotation
+Count the number of each COG class of smORFs with annotation
 '''
 def merge_class(infile):
     seq_cogs = {}

General_Scripts/10_Transmembrane_secreted/02_Compare between archaea and bacteria/04_count_cog.py

@@ -1,5 +1,5 @@
 '''
-Count cog number an fraction of smORFs with annotation
+Count the number of each COG of smORFs with annotation
 '''
 import pandas as pd
 
@@ -22,7 +22,7 @@ def count_bg(infile,outfile):
 infile1 = '0_arc_motif_cog.tsv'
 outfile1 = '1_arc_motif_cog_count.tsv'
 infile2 = '0_bg_motif_cog.tsv'
-outfile2 = '1_bg_motif_cog_count.tsv_new'
+outfile2 = '1_bg_motif_cog_count.tsv'
 
 count_arc(infile1,outfile1)
 count_bg(infile2,outfile2)

General_Scripts/10_Transmembrane_secreted/02_Compare between archaea and bacteria/05_count_cog_class_trans.py

@@ -2,9 +2,8 @@
 Count cog class number an fraction of transmembrane or secreted smORFs with annotation
 '''
 def store(infile0):
-    import gzip
     trans = set()
-    with gzip.open(infile0,'rt') as f:
+    with open(infile0,'rt') as f:
         for line in f:
             trans.add(line.strip())
     return trans
@@ -55,7 +54,7 @@ def count_class(trans,seq_cogs,outfile):
                 out.write(f'{key}\t0\t{t}\t{cog_class_not[key]}\t{f}\n')
 
 
-infile = '90AA_tm_signal.tsv.gz'
+infile = '90AA_tm_signal.tsv'
 infile1 = '0_arc_motif_cog.tsv'
 outfile1 = '1_arc_motif_cog_class_count_trans.tsv'
 infile2 = '0_bac_motif_cog.tsv'

General_Scripts/10_Transmembrane_secreted/02_Compare between archaea and bacteria/06_count_cog_trans.py

@@ -1,7 +1,6 @@
 def store(infile):
-    import gzip
     trans = set()
-    with gzip.open(infile0,'rt') as f:
+    with open(infile,'rt') as f:
         for line in f:
             trans.add(line.strip())
     return trans
@@ -53,10 +52,11 @@ def count_bac(infile1,infile2,outfile1,outfile2):
     cog_count['bac_not_trans_all'] = len(result.drop_duplicates('smorf',keep='first'))
     cog_count.to_csv(outfile2,sep='\t',index=None)
 
-infile = '90AA_tm_signal.tsv.gz'
+infile = '90AA_tm_signal.tsv'
 
 infile1 = '0_arc_motif_cog.tsv'
 infile2 = '0_bac_motif_cog.tsv'
+
 outfile1 = '0_arc_motif_cog_trans.tsv'
 outfile2 = '0_arc_motif_cog_not_trans.tsv'
 outfile3 = '0_bac_motif_cog_trans.tsv'

General_Scripts/10_Transmembrane_secreted/Readme.md

@@ -12,9 +12,9 @@
 
 | **Code** | **Description** | **Input** | **Output** |
 | :---: | :---: | :---: | :---: |
-| 01_map_taxonomy_trans.py | Map transmembrane or secreted families to taxonomy and count transmembrane or secreted fraction of each phylum | 90AA_tm_signal.tsv 90AA_ref_taxonomy_format.tsv.xz | trans_taxa.tsv trans_phylum.csv |
-| 02_extract_cog.py | Extract bacterial and archaeal 90AA families with COG annotation | 90AA_ref_taxonomy_format.tsv.xz 1_cdd_tcov_90AA.tsv.gz cddid_all.tbl cog-20.def.tab.tsv | 0_arc_motif_cog.tsv 0_bac_motif_cog.tsv 0_bg_motif_cog.tsv |
-| 03_count_cog_class.py | Count cog class number an fraction of smORFs with annotation | 0_bac_motif_cog.tsv 0_arc_motif_cog.tsv 0_bg_motif_cog.tsv | 1_bac_motif_cog_class_count.tsv 1_arc_motif_cog_class_count.tsv 1_bg_motif_cog_class_count.tsv |
-| 04_count_cog.py | Count cog number an fraction of smORFs with annotation | 0_arc_motif_cog.tsv 0_bg_motif_cog.tsv | 1_arc_motif_cog_count.tsv 1_bg_motif_cog_count.tsv_new |
-| 05_count_cog_class_trans.py | Count cog class number an fraction of transmembrane or secreted smORFs with annotation | 90AA_tm_signal.tsv.gz 0_arc_motif_cog.tsv 0_bac_motif_cog.tsv | 1_arc_motif_cog_class_count_trans.tsv 1_bac_motif_cog_class_count_trans.tsv |
-| 06_count_cog_trans.py | Combine TMHMM and SignalP results | 90AA_tm_signal.tsv.gz 90AA_tm_signal.tsv.gz 0_arc_motif_cog.tsv 0_bac_motif_cog.tsv | 1_arc_motif_cog_count_trans.tsv 1_arc_motif_cog_count_not_trans.tsv 1_bac_motif_cog_count_trans.tsv 1_bac_motif_cog_count_not_trans.tsv |
+| 01_map_taxonomy_trans.py | Map transmembrane or secreted families to taxonomy and count transmembrane or secreted fraction of each phylum | 90AA_tm_signal.tsv 90AA_tax.tsv.xz | trans_taxa.tsv trans_phylum.csv |
+| 02_extract_cog.py | Extract bacterial and archaeal 90AA families with COG annotation | 90AA_tax.tsv.xz 1_cdd_tcov_90AA.tsv.gz cddid_all.tbl cog-20.def.tab.tsv | 0_arc_motif_cog.tsv 0_bac_motif_cog.tsv 0_bg_motif_cog.tsv |
+| 03_count_cog_class.py | Count the number of each COG class of smORFs | 0_bac_motif_cog.tsv 0_arc_motif_cog.tsv 0_bg_motif_cog.tsv | 1_bac_motif_cog_class_count.tsv 1_arc_motif_cog_class_count.tsv 1_bg_motif_cog_class_count.tsv |
+| 04_count_cog.py | Count the number of each COG of smORFs | 0_arc_motif_cog.tsv 0_bg_motif_cog.tsv | 1_arc_motif_cog_count.tsv 1_bg_motif_cog_count.tsv_new |
+| 05_count_cog_class_trans.py | Count number of each cog class number of transmembrane or secreted smORFs | 90AA_tm_signal.tsv 0_arc_motif_cog.tsv 0_bac_motif_cog.tsv | 1_arc_motif_cog_class_count_trans.tsv 1_bac_motif_cog_class_count_trans.tsv |
+| 06_count_cog_trans.py | Count number of each COG of transmembrane or secreted smORFs | 90AA_tm_signal.tsv.gz 90AA_tm_signal.tsv.gz 0_arc_motif_cog.tsv 0_bac_motif_cog.tsv | 1_arc_motif_cog_count_trans.tsv 1_arc_motif_cog_count_not_trans.tsv 1_bac_motif_cog_count_trans.tsv 1_bac_motif_cog_count_not_trans.tsv |