diff --git a/rescript/extract_seq_segments.py b/rescript/extract_seq_segments.py index 0a4ed96..315b027 100644 --- a/rescript/extract_seq_segments.py +++ b/rescript/extract_seq_segments.py @@ -15,8 +15,8 @@ def extract_seq_segments(input_sequences: DNAFASTAFormat, reference_segment_sequences: DNAFASTAFormat, perc_identity: float = 0.7, target_coverage: float = 0.9, - min_seq_len: int = None, - max_seq_len: int = None, + min_seq_len: int = 32, + max_seq_len: int = 50000, threads: int = 1 ) -> (DNAFASTAFormat, DNAFASTAFormat): # Note: the `--db` is actually comprised of the short amplicon @@ -44,13 +44,15 @@ def extract_seq_segments(input_sequences: DNAFASTAFormat, '--id', str(perc_identity), '--target_cov', str(target_coverage), '--strand', 'plus', + '--minseqlength', str(min_seq_len), + '--maxseqlength', str(max_seq_len), '--threads', str(threads), '--qmask', 'none', '--qsegout', extr_f.name, '--notmatched', no_match_f.name] - if min_seq_len: - cmd += ['--minseqlength', '%i' % min_seq_len] - if max_seq_len: - cmd += ['--maxseqlength', '%i' % max_seq_len] + # if min_seq_len: + # cmd += ['--minseqlength', '%i' % min_seq_len] + # if max_seq_len: + # cmd += ['--maxseqlength', '%i' % max_seq_len] run_command(cmd) return (extr_seq_segs, no_matches) diff --git a/rescript/plugin_setup.py b/rescript/plugin_setup.py index 88a2828..1da9ec2 100644 --- a/rescript/plugin_setup.py +++ b/rescript/plugin_setup.py @@ -1154,12 +1154,10 @@ 'from \'input-sequences\'.', 'min_seq_len': 'Minimum length of reference sequence segment ' 'allowed for searching. Any sequence less than ' - 'this will be discarded. If not set, default ' - 'program settings will be used.', + 'this will be discarded.', 'max_seq_len': 'Maximum length of reference sequence segment ' 'allowed for searching. Any sequence greater ' - 'than this will be discarded. If not set, ' - 'default program settings will be used.'}, + 'than this will be discarded.'}, output_descriptions={ 'extracted_sequence_segments': 'Extracted sequence segments ' 'from \'input-sequences\' '