YuuMJ1997/EukPhylo
1
0
Fork 0
mirror of http://43.156.76.180:8026/YuuMJ/EukPhylo.git synced 2025-12-27 12:00:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add files via upload

Browse Source
This commit is contained in:
Auden Cote-L'Heureux 2023-06-13 14:00:56 -04:00 committed by GitHub
parent 165a95fa9d
commit 7da3de77e4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 24 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
PTL1/Genomes/Scripts/6_SummaryStats.py
View File

@ -54,18 +54,20 @@ def aa_comp_lengths(args, gcodes):
for rec in SeqIO.parse(args.input + '/ReadyToGo/ReadyToGo_AA/' + file, 'fasta'): for rec in SeqIO.parse(args.input + '/ReadyToGo/ReadyToGo_AA/' + file, 'fasta'):
r2g_lengths.update({ rec.id : len(str(rec.seq)) * 3 }) r2g_lengths.update({ rec.id : len(str(rec.seq)) * 3 })
fymink = 0; garp = 0; other = 0; total = 0 fymink = 0; garp = 0; other = 0; total = 0; x = 0
for char in str(rec.seq): for char in str(rec.seq):
if char in 'FYMINK': if char in 'FYMINKfymink':
fymink += 1 fymink += 1
elif char in 'GARP': elif char in 'GARPgarp':
garp += 1 garp += 1
elif char in 'Xx':
x += 1
else: else:
other += 1 other += 1
total += 1 total += 1
aa_comp.update({ rec.id : { 'FYMINK' : fymink/total, 'GARP' : garp/total, 'Other' : other/total } }) aa_comp.update({ rec.id : { 'FYMINK' : fymink/total, 'GARP' : garp/total, 'Other' : other/total, 'X' : x} })
recid_by_contig_n.update({ rec.id.split('Contig_')[-1].split('_')[0] : rec.id }) recid_by_contig_n.update({ rec.id.split('Contig_')[-1].split('_')[0] : rec.id })
@ -91,16 +93,14 @@ def get_nuc_comp(args, gcodes):
nuc_comp = { } nuc_comp = { }
for file in tqdm([f for f in os.listdir(args.input + '/ReadyToGo/ReadyToGo_NTD')]): for file in tqdm([f for f in os.listdir(args.input + '/ReadyToGo/ReadyToGo_NTD')]):
if file.endswith('.fasta') and file[:10] in gcodes: if file.endswith('.fasta') and file[:10] in gcodes:
cub_out = CUB.CalcRefFasta(args.input + '/ReadyToGo/ReadyToGo_NTD/' + file, gcodes[file[:10]])[0] cub_out = CUB.CalcRefFasta(args.input + '/ReadyToGo/ReadyToGo_NTD/' + file, gcodes[file[:10]].lower())[0]
for k in cub_out: for k in cub_out:
nuc_comp.update({ k : cub_out[k] }) nuc_comp.update({ k : cub_out[k] })
return nuc_comp return nuc_comp
def per_seq(args, nuc_comp, aa_comp, all_transcripts, r2g_lengths, transcript_id_corr): def per_seq(args, nuc_comp, aa_comp, all_transcripts, r2g_lengths, transcript_id_corr, og_mean_lens):
og_mean_lens = hook_lens(args)
if not os.path.isdir(args.input + '/PerSequenceStatSummaries'): if not os.path.isdir(args.input + '/PerSequenceStatSummaries'):
os.mkdir(args.input + '/PerSequenceStatSummaries') os.mkdir(args.input + '/PerSequenceStatSummaries')
@ -109,7 +109,7 @@ def per_seq(args, nuc_comp, aa_comp, all_transcripts, r2g_lengths, transcript_id
for taxon in taxa: for taxon in taxa:
with open(args.input + '/PerSequenceStatSummaries/' + taxon + '.csv', 'w') as o: with open(args.input + '/PerSequenceStatSummaries/' + taxon + '.csv', 'w') as o:
o.write('Sequence,Taxon,OG,Transcript,TranscriptLength,CDSLength,AvgLengthOGinHook,AmbiguousCodons,GC-Overall,GC1,GC2,GC3,GC3-Degen,ExpWrightENc,ObsWrightENc_6Fold,ObsWrightENc_No6Fold,ObsWeightedENc_6Fold,ObsWeightedENc_No6Fold,FYMINK,GARP,OtherAA\n') o.write('Sequence,Taxon,OG,Transcript,TranscriptLength,CDSLength,AvgLengthOGinHook,AmbiguousCodons,GC-Overall,GC1,GC2,GC3,GC3-Degen,ExpWrightENc,ObsWrightENc_6Fold,ObsWrightENc_No6Fold,ObsWeightedENc_6Fold,ObsWeightedENc_No6Fold,FYMINK,GARP,OtherAA,N.Xs\n')
for rec in nuc_comp: for rec in nuc_comp:
if rec[:10] == taxon: if rec[:10] == taxon:
o.write(rec + ',' + rec[:10] + ',' + rec[-10:]) o.write(rec + ',' + rec[:10] + ',' + rec[-10:])
@ -126,15 +126,15 @@ def per_seq(args, nuc_comp, aa_comp, all_transcripts, r2g_lengths, transcript_id
ENc = [str(v.expENc), str(v.obsENc_6F), str(v.obsENc_No6F), str(v.SunENc_6F),str(v.SunENc_No6F)] ENc = [str(v.expENc), str(v.obsENc_6F), str(v.obsENc_No6F), str(v.SunENc_6F),str(v.SunENc_No6F)]
o.write(',' + ','.join([str(v.amb_cdn)] + gcs + ENc)) o.write(',' + ','.join([str(v.amb_cdn)] + gcs + ENc))
o.write(',' + str(aa_comp[rec]['FYMINK']) + ',' + str(aa_comp[rec]['GARP']) + ',' + str(aa_comp[rec]['Other']) + '\n') o.write(',' + str(aa_comp[rec]['FYMINK']) + ',' + str(aa_comp[rec]['GARP']) + ',' + str(aa_comp[rec]['Other']) + ',' + str(aa_comp[rec]['X']) + '\n')
def per_tax(args, nuc_comp, aa_comp, all_transcripts, r2g_lengths, gcodes): def per_tax(args, nuc_comp, aa_comp, all_transcripts, r2g_lengths, gcodes, og_mean_lens):
taxa = list(dict.fromkeys([seq[:10] for seq in nuc_comp])) taxa = list(dict.fromkeys([seq[:10] for seq in nuc_comp]))
with open(args.input + '/PerTaxonSummary.csv', 'w') as o: with open(args.input + '/PerTaxonSummary.csv', 'w') as o:
o.write('Taxon,TranscriptsInput,Median_GCTranscripts,IQR_GCTranscripts,Median_LenTranscripts,IRQ_LenTranscripts,SeqsR2G,OGsR2G,Median_GC3R2G,IQR_GC3R2G,Median_ENcR2G,IQR_ENcR2G,Median_LenR2G,IQR_LenR2G,GeneticCode\n') o.write('Taxon,TranscriptsInput,Median_GCTranscripts,5-95Perc_GCTranscripts,Median_LenTranscripts,IQR_LenTranscripts,SeqsR2G,OGsR2G,Median_GC3R2G,5Perc_GC3R2G,95Perc_GC3R2G,5-95Perc_GC3R2G,Median_ENcR2G,IQR_ENcR2G,Median_LenR2G,IQR_LenR2G,Prop.G1.5_OGAvg,Prop.L0.5_OGAvg,GeneticCode\n')
for taxon in taxa: for taxon in taxa:
try: try:
@ -149,7 +149,7 @@ def per_tax(args, nuc_comp, aa_comp, all_transcripts, r2g_lengths, gcodes):
transcript_gcs = sorted(transcript_gcs) transcript_gcs = sorted(transcript_gcs)
o.write(',' + str(transcript_gcs[floor(len(transcripts)*0.5)])) o.write(',' + str(transcript_gcs[floor(len(transcripts)*0.5)]))
o.write(',' + str(transcript_gcs[floor(len(transcripts)*0.75)] - transcript_gcs[floor(len(transcripts)*0.25)])) o.write(',' + str(transcript_gcs[floor(len(transcripts)*0.95)] - transcript_gcs[floor(len(transcripts)*0.05)]))
transcript_lens = sorted([len(transcript) for transcript in transcripts]) transcript_lens = sorted([len(transcript) for transcript in transcripts])
o.write(',' + str(transcript_lens[floor(len(transcripts)*0.5)])) o.write(',' + str(transcript_lens[floor(len(transcripts)*0.5)]))
@ -162,7 +162,9 @@ def per_tax(args, nuc_comp, aa_comp, all_transcripts, r2g_lengths, gcodes):
r2g_gc3s = sorted([seq.gc4F for seq in r2g_ntds]) r2g_gc3s = sorted([seq.gc4F for seq in r2g_ntds])
o.write(',' + str(r2g_gc3s[floor(len(r2g_ntds)*0.5)])) o.write(',' + str(r2g_gc3s[floor(len(r2g_ntds)*0.5)]))
o.write(',' + str(r2g_gc3s[floor(len(r2g_gc3s)*0.75)] - r2g_gc3s[floor(len(r2g_gc3s)*0.25)])) o.write(',' + str(r2g_gc3s[floor(len(r2g_gc3s)*0.05)]))
o.write(',' + str(r2g_gc3s[floor(len(r2g_gc3s)*0.95)]))
o.write(',' + str(r2g_gc3s[floor(len(r2g_gc3s)*0.95)] - r2g_gc3s[floor(len(r2g_gc3s)*0.05)]))
r2g_encs = sorted([seq.obsENc_6F for seq in r2g_ntds]) r2g_encs = sorted([seq.obsENc_6F for seq in r2g_ntds])
o.write(',' + str(r2g_encs[floor(len(r2g_encs)*0.5)])) o.write(',' + str(r2g_encs[floor(len(r2g_encs)*0.5)]))
@ -172,6 +174,11 @@ def per_tax(args, nuc_comp, aa_comp, all_transcripts, r2g_lengths, gcodes):
o.write(',' + str(tax_r2g_lens[floor(len(tax_r2g_lens)*0.5)])) o.write(',' + str(tax_r2g_lens[floor(len(tax_r2g_lens)*0.5)]))
o.write(',' + str(tax_r2g_lens[floor(len(tax_r2g_lens)*0.75)] - tax_r2g_lens[floor(len(tax_r2g_lens)*0.25)])) o.write(',' + str(tax_r2g_lens[floor(len(tax_r2g_lens)*0.75)] - tax_r2g_lens[floor(len(tax_r2g_lens)*0.25)]))
prop_len_g = len([seq for seq in r2g_lengths if seq[:10] == taxon and r2g_lengths[seq] > 4.5 * og_mean_lens[seq[-10:]]])/len(tax_r2g_lens)
prop_len_l = len([seq for seq in r2g_lengths if seq[:10] == taxon and r2g_lengths[seq] < 1.5 * og_mean_lens[seq[-10:]]])/len(tax_r2g_lens)
o.write(',' + str(prop_len_g) + ',' + str(prop_len_l))
o.write(',' + gcodes[taxon] + '\n') o.write(',' + gcodes[taxon] + '\n')
except: except:
pass pass
@ -243,9 +250,10 @@ if __name__ == "__main__":
aa_comp, transcripts, r2g_lengths, transcript_id_corr = aa_comp_lengths(args, gcodes) aa_comp, transcripts, r2g_lengths, transcript_id_corr = aa_comp_lengths(args, gcodes)
nuc_comp = get_nuc_comp(args, gcodes) nuc_comp = get_nuc_comp(args, gcodes)
og_mean_lens = hook_lens(args)
per_tax(args, nuc_comp, aa_comp, transcripts, r2g_lengths, gcodes) per_tax(args, nuc_comp, aa_comp, transcripts, r2g_lengths, gcodes, og_mean_lens)
per_seq(args, nuc_comp, aa_comp, transcripts, r2g_lengths, transcript_id_corr) per_seq(args, nuc_comp, aa_comp, transcripts, r2g_lengths, transcript_id_corr, og_mean_lens)
if args.r2g_jf: if args.r2g_jf:
r2g_jf(args, nuc_comp, gcodes) r2g_jf(args, nuc_comp, gcodes)