Mercurial > repos > jasmine_amir > snrqk2
annotate SNRQK2.py @ 8:1ab67c0c0054
"planemo upload commit 08e13026c6990a76f8e58fc52d0ea25e8a9e2880-dirty"
| author | jasmine_amir |
|---|---|
| date | Fri, 10 Jun 2022 14:08:43 -0400 |
| parents | 2547394443a0 |
| children | ed9e26fdfce9 |
| rev | line source |
|---|---|
| jasmine_amir@8 | 1 #!/dep/_conda/bin/python3 |
| jasmine_amir@0 | 2 # coding: utf-8 |
| jasmine_amir@0 | 3 ########################################################### |
| jasmine_amir@0 | 4 ########################################################### |
| jasmine_amir@0 | 5 ## Jasmine Amirzadegan |
| jasmine_amir@0 | 6 ## 2022 APRIL 14 |
| jasmine_amir@0 | 7 ########################################################### |
| jasmine_amir@0 | 8 ## SNRQC.py: |
| jasmine_amir@0 | 9 ## compute QC metrics specific to SSQuAWK v4 + workflows |
| jasmine_amir@0 | 10 ## usage: python SNRQC.py intermediateSSQuAWKfile.txt |
| jasmine_amir@0 | 11 ## python 3.7 |
| jasmine_amir@0 | 12 ########################################################### |
| jasmine_amir@0 | 13 import pandas as pd |
| jasmine_amir@0 | 14 import sys |
| jasmine_amir@0 | 15 |
| jasmine_amir@0 | 16 fn = sys.argv[1] |
| jasmine_amir@0 | 17 df = pd.read_csv(fn, sep = "\t", header = 0) |
| jasmine_amir@0 | 18 |
| jasmine_amir@0 | 19 |
| jasmine_amir@0 | 20 |
| jasmine_amir@0 | 21 if (df['Sample'].str.contains('negativeControl')).any(): |
| jasmine_amir@0 | 22 m = df.loc[ (df['Sample'].str.contains('negativeControl')) ] |
| jasmine_amir@0 | 23 noise = m['readsAlignPassFilt'] |
| jasmine_amir@0 | 24 SNR = [] |
| jasmine_amir@0 | 25 |
| jasmine_amir@0 | 26 for i in df['readsAlignPassFilt']: |
| jasmine_amir@0 | 27 SNR.append(i/noise.item()) |
| jasmine_amir@0 | 28 #[float(j) for j in SNR] |
| jasmine_amir@0 | 29 df['SNR'] = SNR |
| jasmine_amir@0 | 30 |
| jasmine_amir@0 | 31 else: |
| jasmine_amir@0 | 32 df['SNR'] = "NA" |
| jasmine_amir@0 | 33 |
| jasmine_amir@0 | 34 #print(df) |
| jasmine_amir@0 | 35 #fn1 = fn.split("/")[1] |
| jasmine_amir@0 | 36 #df.to_csv('test-data/snrqk_result' + fn1 + '.tsv', sep="\t") |
| jasmine_amir@0 | 37 df.to_csv('snrqk_result.tsv', sep='\t') |