diff --git a/tool-data/blastdb.loc.sample b/tool-data/blastdb.loc.sample index c27c605011a..ee3ce8af2a1 100644 --- a/tool-data/blastdb.loc.sample +++ b/tool-data/blastdb.loc.sample @@ -4,6 +4,6 @@ # #TODO: fill in this format # -nt /depot/data2/galaxy/blastdb/nt/nt.chunk.00 /depot/data2/galaxy/blastdb/nt/nt.chunk.01 /depot/data2/galaxy/blastdb/nt/nt.chunk.02 /depot/data2/galaxy/blastdb/nt/nt.chunk.03 /depot/data2/galaxy/blastdb/nt/nt.chunk.04 /depot/data2/galaxy/blastdb/nt/nt.chunk.05 /depot/data2/galaxy/blastdb/nt/nt.chunk.06 /depot/data2/galaxy/blastdb/nt/nt.chunk.07 /depot/data2/galaxy/blastdb/nt/nt.chunk.08 /depot/data2/galaxy/blastdb/nt/nt.chunk.09 /depot/data2/galaxy/blastdb/nt/nt.chunk.10 /depot/data2/galaxy/blastdb/nt/nt.chunk.11 /depot/data2/galaxy/blastdb/nt/nt.chunk.12 /depot/data2/galaxy/blastdb/nt/nt.chunk.13 /depot/data2/galaxy/blastdb/nt/nt.chunk.14 /depot/data2/galaxy/blastdb/nt/nt.chunk.15 /depot/data2/galaxy/blastdb/nt/nt.chunk.16 /depot/data2/galaxy/blastdb/nt/nt.chunk.17 /depot/data2/galaxy/blastdb/nt/nt.chunk.18 /depot/data2/galaxy/blastdb/nt/nt.chunk.19 /depot/data2/galaxy/blastdb/nt/nt.chunk.20 /depot/data2/galaxy/blastdb/nt/nt.chunk.21 /depot/data2/galaxy/blastdb/nt/nt.chunk.22 /depot/data2/galaxy/blastdb/nt/nt.chunk.23 +nt /depot/data2/galaxy/blastdb/nt/nt.chunk nr /depot/data2/galaxy/blastdb/nr/nr.chunk.0 /depot/data2/galaxy/blastdb/nr/nr.chunk.1 /depot/data2/galaxy/blastdb/nr/nr.chunk.2 test /depot/data2/galaxy/blastdb/test/test.fa diff --git a/tools/metag_tools/blat_wrapper.py b/tools/metag_tools/blat_wrapper.py index cc62a7e4a8a..7cd3929c849 100644 --- a/tools/metag_tools/blat_wrapper.py +++ b/tools/metag_tools/blat_wrapper.py @@ -62,6 +62,7 @@ def __main__(): try: test = int(sys.argv[7]) one_off = sys.argv[7] + assert test >= 0 and test <= int(tile_size) except: stop_err('Invalid value for mismatch numbers in the word') diff --git a/tools/metag_tools/blat_wrapper.xml b/tools/metag_tools/blat_wrapper.xml index 07db56e7cc3..27baa7c7777 100644 --- a/tools/metag_tools/blat_wrapper.xml +++ b/tools/metag_tools/blat_wrapper.xml @@ -22,7 +22,7 @@ - + @@ -42,13 +42,17 @@ .. class:: warningmark -Use smaller word size (*Minimal Size of Exact Match*) will increase the computational time. +Use a smaller word size (*Minimal Size of Exact Match*) will increase the computational time. + +.. class:: warningmark + +Use a larger mismatch number (*Number of Mismatch in the Word*) will increase the computational time. ----- **What it does** - This tool runs alignment program **BLAT**. Your short reads file is searched against a genome build (select from table) or another uploaded file. + This tool runs alignment program **BLAT**. Your short reads file is searched against a genome build or another uploaded file. ----- @@ -59,16 +63,29 @@ Use smaller word size (*Minimal Size of Exact Match*) will increase the computat >seq1 TGGTAATGGTGGTTTTTTTTTTTTTTTTTTATTTTT -- Search against ce2 (C. elegans March 2004):: +- Use default settings. + +- Search against ce2 (C. elegans March 2004), partial result:: 25 1 0 0 0 0 0 0 + seq1 36 10 36 chrI 15080483 9704438 9704464 1 26, 10, 9704438, ggttttttttttttttttttattttt, ggtttttttttttttttttttttttt, 27 0 0 0 0 0 1 32 + seq1 36 9 36 chrI 15080483 1302536 1302595 2 21,6, 9,30, 1302536,1302589, tggtttttttttttttttttt,attttt, tggtttttttttttttttttt,attttt, ----- +**Parameters** + +- *Minimal Identity (-minIdentity)* : In percent, the minimum sequence identity between the query and target alignment. Default is 90. + +- *Minimal Size of Exact Match (-tileSize)* : The size of a match that will trigger an alignment. Default is 11. Usually between 8 and 12. Must be between 6 and 18. + +- *Number of Mismatch in the Word (-oneOff)* : The number of mismatches allowed in the word (tile size) and still triggers an alignment. Default is 0. + +----- + **Reference** - BLAT: Kent, W James, BLAT--the BLAST-like alignment tool. (2002) Genome Research:12(4) 656-664. - + **BLAT**: Kent, W James, BLAT--the BLAST-like alignment tool. (2002) Genome Research:12(4) 656-664. + + diff --git a/tools/metag_tools/megablast_wrapper.py b/tools/metag_tools/megablast_wrapper.py index aae06cdf73a..4113c65eac1 100644 --- a/tools/metag_tools/megablast_wrapper.py +++ b/tools/metag_tools/megablast_wrapper.py @@ -49,9 +49,9 @@ def __main__(): # prepare the database db = {} - db_file = open(DB_LOC, "r") - for i, line in enumerate(db_file): + for i, line in enumerate(file(DB_LOC)): line = line.rstrip('\r\n') + if line.startswith('#'): continue fields = line.split() db[(fields[0])] = [] for j in xrange(1, len(fields)): @@ -61,6 +61,11 @@ def __main__(): retcode = subprocess.call('which megablast 2>&1', shell='True') if retcode < 0: stop_err("Cannot locate megablast.") + + try: + assert db.has_key(db_build) is True + except: + stop_err('Cannot locate the target database. Please check your location file.') for chunk in db[(db_build)]: megablast_arguments = ["megablast", "-d", chunk, "-i", query_filename] diff --git a/tools/metag_tools/megablast_wrapper.xml b/tools/metag_tools/megablast_wrapper.xml index ba1ff0ec6b9..3908226abf8 100644 --- a/tools/metag_tools/megablast_wrapper.xml +++ b/tools/metag_tools/megablast_wrapper.xml @@ -5,9 +5,9 @@ - + - + @@ -55,11 +55,7 @@ Other databases and megablast parameters will be available shortly. ----- -**Reference** - - **megablast**: Zhang et al. A Greedy Algorithm for Aligning DNA Sequences. 2000. JCB: 203-214. - - Corresponding command line options: +**Parameters** - **-W**: Word size - **-p**: Identity percentage cut-off @@ -67,5 +63,11 @@ Other databases and megablast parameters will be available shortly. - **-N**: Type of a discontiguous word template - **-F**: Filter query sequence +----- + +**Reference** + + **megablast**: Zhang et al. A Greedy Algorithm for Aligning DNA Sequences. 2000. JCB: 203-214. +