Mercurial > repos > drosofff > msp_blastparser_and_hits

comparison BlastParser_and_hits.py @ 3:8f5d48294f70 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_blastparser_and_hits commit 3d9ddd0f6f3c3b97a3bebf52646731ad6771e178
author drosofff
date Mon, 19 Oct 2015 12:13:12 -0400
parents bb0d4cd765c5
children 60b6bd959929
comparison
equal deleted inserted replaced
2:bb0d4cd765c5 3:8f5d48294f70
13 the_parser.add_argument('--fastaOutput', action="store", type=str, help="fasta output file of blast hits") 13 the_parser.add_argument('--fastaOutput', action="store", type=str, help="fasta output file of blast hits")
14 the_parser.add_argument('--tabularOutput', action="store", type=str, help="tabular output file of blast analysis") 14 the_parser.add_argument('--tabularOutput', action="store", type=str, help="tabular output file of blast analysis")
15 the_parser.add_argument('--flanking', action="store", type=int, help="number of flanking nucleotides added to the hit sequences") 15 the_parser.add_argument('--flanking', action="store", type=int, help="number of flanking nucleotides added to the hit sequences")
16 the_parser.add_argument('--mode', action="store", choices=["verbose", "short"], type=str, help="reporting (verbose) or not reporting (short) oases contigs") 16 the_parser.add_argument('--mode', action="store", choices=["verbose", "short"], type=str, help="reporting (verbose) or not reporting (short) oases contigs")
17 the_parser.add_argument('--filter_relativeCov', action="store", type=float, default=0, help="filter out relative coverages below the specified ratio (float number)") 17 the_parser.add_argument('--filter_relativeCov', action="store", type=float, default=0, help="filter out relative coverages below the specified ratio (float number)")
18 the_parser.add_argument('--filter_maxScore', action="store", type=float, default=0, help="filter out maximum BitScore below the specified float number") 18 the_parser.add_argument('--filter_maxScore', action="store", type=float, default=0, help="filter out best BitScores below the specified float number")
19 the_parser.add_argument('--filter_meanScore', action="store", type=float, default=0, help="filter out maximum BitScore below the specified float number") 19 the_parser.add_argument('--filter_meanScore', action="store", type=float, default=0, help="filter out mean BitScores below the specified float number")
20 the_parser.add_argument('--al_sequences', action="store", type=str, help="sequences that have been blast aligned") 20 the_parser.add_argument('--al_sequences', action="store", type=str, help="sequences that have been blast aligned")
21 the_parser.add_argument('--un_sequences', action="store", type=str, help="sequences that have not been blast aligned") 21 the_parser.add_argument('--un_sequences', action="store", type=str, help="sequences that have not been blast aligned")
22 args = the_parser.parse_args() 22 args = the_parser.parse_args()
23 if not all ( (args.sequences, args.blast, args.fastaOutput, args.tabularOutput) ): 23 if not all ( (args.sequences, args.blast, args.fastaOutput, args.tabularOutput) ):
24 the_parser.error('argument(s) missing, call the -h option of the script') 24 the_parser.error('argument(s) missing, call the -h option of the script')
144 continue 144 continue
145 print >> F, "#\n# %s" % subject 145 print >> F, "#\n# %s" % subject
146 print >> F, "# Suject Length: %s" % (results[subject]["subjectLength"]) 146 print >> F, "# Suject Length: %s" % (results[subject]["subjectLength"])
147 print >> F, "# Total Subject Coverage: %s" % (results[subject]["TotalCoverage"]) 147 print >> F, "# Total Subject Coverage: %s" % (results[subject]["TotalCoverage"])
148 print >> F, "# Relative Subject Coverage: %s" % (results[subject]["RelativeSubjectCoverage"]) 148 print >> F, "# Relative Subject Coverage: %s" % (results[subject]["RelativeSubjectCoverage"])
149 print >> F, "# Maximum Bit Score: %s" % (results[subject]["maxBitScores"]) 149 print >> F, "# Best Bit Score: %s" % (results[subject]["maxBitScores"])
150 print >> F, "# Mean Bit Score: %s" % (results[subject]["meanBitScores"]) 150 print >> F, "# Mean Bit Score: %s" % (results[subject]["meanBitScores"])
151 for header in results[subject]["HitDic"]: 151 for header in results[subject]["HitDic"]:
152 print >> Fasta, ">%s\n%s" % (header, insert_newlines(results[subject]["HitDic"][header]) ) 152 print >> Fasta, ">%s\n%s" % (header, insert_newlines(results[subject]["HitDic"][header]) )
153 print >> Fasta, "" # final carriage return for the sequence 153 print >> Fasta, "" # final carriage return for the sequence
154 for transcript in Xblastdict[subject]: 154 for transcript in Xblastdict[subject]:
159 info = [transcript] + [percentIdentity, alignLenght, subjectStart, subjectEnd, queryCov, Eval, BitScore] 159 info = [transcript] + [percentIdentity, alignLenght, subjectStart, subjectEnd, queryCov, Eval, BitScore]
160 info = [str(i) for i in info] 160 info = [str(i) for i in info]
161 info = "\t".join(info) 161 info = "\t".join(info)
162 print >> F, info 162 print >> F, info
163 else: 163 else:
164 print >>F, "# subject\tsubject length\tTotal Subject Coverage\tRelative Subject Coverage\tMaximum Bit Score\tMean Bit Score" 164 print >>F, "# subject\tsubject length\tTotal Subject Coverage\tRelative Subject Coverage\tBest Bit Score\tMean Bit Score"
165 for subject in sorted (results, key=lambda x: results[x]["meanBitScores"], reverse=True): 165 for subject in sorted (results, key=lambda x: results[x]["meanBitScores"], reverse=True):
166 if results[subject]["RelativeSubjectCoverage"]<filter_relativeCov or results[subject]["maxBitScores"]<filter_maxScore or results[subject]["meanBitScores"]<filter_meanScore: 166 if results[subject]["RelativeSubjectCoverage"]<filter_relativeCov or results[subject]["maxBitScores"]<filter_maxScore or results[subject]["meanBitScores"]<filter_meanScore:
167 continue 167 continue
168 line = [] 168 line = []
169 line.append(subject) 169 line.append(subject)