Mercurial > repos > bornea > saint_preprocessing
comparison SAINT_preprocessing.py @ 10:1b0547d3c7bc draft
Uploaded
| author | bornea |
|---|---|
| date | Tue, 29 Mar 2016 14:46:04 -0400 |
| parents | 019e60bd3f7f |
| children | b688d0dae86b |
comparison
equal
deleted
inserted
replaced
| 9:d6a427973fe4 | 10:1b0547d3c7bc |
|---|---|
| 130 if ">sp" in data_line: | 130 if ">sp" in data_line: |
| 131 namer = data_line.split("|")[2] | 131 namer = data_line.split("|")[2] |
| 132 if uniprot_accession_in == data_line.split("|")[1]: | 132 if uniprot_accession_in == data_line.split("|")[1]: |
| 133 match = count + 1 | 133 match = count + 1 |
| 134 if 'GN=' in data_line: | 134 if 'GN=' in data_line: |
| 135 lst = data_linedata_line.split('GN=') | 135 lst = data_line.split('GN=') |
| 136 lst2 = lst[1].split(' ') | 136 lst2 = lst[1].split(' ') |
| 137 genename = lst2[0] | 137 genename = lst2[0] |
| 138 if 'GN=' not in data_line: | 138 if 'GN=' not in data_line: |
| 139 genename = 'NA' | 139 genename = 'NA' |
| 140 while ">sp" not in data_lines[match]: | 140 while ">sp" not in data_lines[match]: |
| 142 seqlength = seqlength + len(data_lines[match].strip()) | 142 seqlength = seqlength + len(data_lines[match].strip()) |
| 143 match = match + 1 | 143 match = match + 1 |
| 144 else: | 144 else: |
| 145 break | 145 break |
| 146 return ReturnValue1(seqlength, genename) | 146 return ReturnValue1(seqlength, genename) |
| 147 elif uniprot_accession_in == namer.split(" ")[0]: | 147 if uniprot_accession_in == namer.split(" ")[0]: |
| 148 match = count + 1 | 148 match = count + 1 |
| 149 # Ensures consistent spacing throughout. | 149 # Ensures consistent spacing throughout. |
| 150 if 'GN=' in data_line: | 150 if 'GN=' in data_line: |
| 151 lst = data_line.split('GN=') | 151 lst = data_line.split('GN=') |
| 152 lst2 = lst[1].split(' ') | 152 lst2 = lst[1].split(' ') |