diff options
author | Peter Amstutz | 2020-06-22 16:32:54 +0000 |
---|---|---|
committer | Peter Amstutz | 2020-06-22 16:32:54 +0000 |
commit | 4001368ab29c988e94dddd29767c4b64a5bd2a5b (patch) | |
tree | 5642bf6a5cd02bc76b0aa98ae086b010f5131cf0 /bh20sequploader | |
parent | 7daa9ff2cdba742a811db00c924ccde25fa2c9b6 (diff) | |
download | bh20-seq-resource-4001368ab29c988e94dddd29767c4b64a5bd2a5b.tar.gz bh20-seq-resource-4001368ab29c988e94dddd29767c4b64a5bd2a5b.tar.lz bh20-seq-resource-4001368ab29c988e94dddd29767c4b64a5bd2a5b.zip |
Better invalid sequence QC handling
Diffstat (limited to 'bh20sequploader')
-rw-r--r-- | bh20sequploader/qc_fasta.py | 11 |
1 files changed, 8 insertions, 3 deletions
diff --git a/bh20sequploader/qc_fasta.py b/bh20sequploader/qc_fasta.py index 607c8c0..e198430 100644 --- a/bh20sequploader/qc_fasta.py +++ b/bh20sequploader/qc_fasta.py @@ -58,6 +58,9 @@ def qc_fasta(arg_sequence): tmp1.write(submitlabel.encode("utf8")) tmp1.write(("".join(submitseq)).encode("utf8")) tmp1.flush() + subbp = 0 + refbp = 0 + similarity = 0 try: cmd = ["clustalw", "-infile="+tmp1.name, "-quicktree", "-iteration=none", "-type=DNA"] @@ -78,12 +81,14 @@ def qc_fasta(arg_sequence): except Exception as e: logging.warn("Error trying to QC against reference sequence using 'clustalw': %s", e) - if (subbp/refbp) < .7: + if refbp and (subbp/refbp) < .7: raise ValueError("QC fail: submit sequence length is shorter than 70% reference") - if (subbp/refbp) > 1.3: + if refbp and (subbp/refbp) > 1.3: raise ValueError("QC fail: submit sequence length is greater than 130% reference") - if similarity < 70.0: + if similarity and similarity < 70.0: raise ValueError("QC fail: submit similarity is less than 70%") + if refbp == 0 or similarity == 0: + raise ValueError("QC fail") return ("sequence.fasta"+gz, seqlabel) elif seq_type == "text/fastq": |