Created
December 28, 2013 16:31
-
-
Save pfaucon/8161308 to your computer and use it in GitHub Desktop.
wrapper for deltablast
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
... | |
Wrappers for the new NCBI BLAST+ tools (written in C++): | |
- NcbiblastpCommandline - Protein-Protein BLAST | |
- NcbideltablastCommandline - Protein-Protein domain enhanced lookup time accelerated blast | |
... | |
class NcbideltablastCommandline(_NcbiblastMain2SeqCommandline): | |
"""Create a commandline for the NCBI BLAST+ program deltablast (for proteins). | |
This is a wrapper for the deltablast command line command included in the NCBI BLAST+ software (not present in the original BLAST) | |
>>> from Bio.Blast.Applications import NcbideltablastCommandline | |
>>> cline = NcbideltablastCommandline(query="rosemary.pro", db="nr", | |
... evalue=0.001, remote=True, ungapped=True) | |
>>> cline | |
NcbideltablastCommandline(cmd='deltablast', query='rosemary.pro', db='nr', evalue=0.001, remote=True, ungapped=True) | |
>>> print(cline) | |
deltablast -query rosemary.pro -db nr -evalue 0.001 -remote -ungapped | |
You would typically run the command line with cline() or via the Python | |
subprocess module, as described in the Biopython tutorial. | |
""" | |
def __init__(self, cmd="deltablast", **kwargs): | |
self.parameters = [ | |
#General search options: | |
_Option(["-task", "task"], | |
"Task to execute (string, or deltablast).", | |
checker_function=lambda value : value in ["deltablast"], | |
equate=False), | |
_Option(["-matrix", "matrix"], | |
"Scoring matrix name (default BLOSUM62)."), | |
_Option(["-threshold", "threshold"], | |
"Minimum word score such that the word is added to the " | |
"BLAST lookup table (float)", | |
equate=False), | |
_Option(["-comp_based_stats", "comp_based_stats"], | |
"""Use composition-based statistics (string, default 2, i.e. True). | |
0, F or f: no composition-based statistics | |
2, T or t, D or d : Composition-based score adjustment as in | |
Bioinformatics 21:902-911, 2005, conditioned on sequence properties | |
Note that tblastn also supports values of 1 and 3.""", | |
checker_function=lambda value : value in "0Ft2TtDd", | |
equate=False), | |
#Query filtering options: | |
_Option(["-seg", "seg"], | |
"""Filter query sequence with SEG (string). | |
Format: "yes", "window locut hicut", or "no" to disable. | |
Default is "12 2.2 2.5""", | |
equate=False), | |
#Extension options: | |
_Switch(["-ungapped", "ungapped"], | |
"Perform ungapped alignment only?"), | |
#Miscellaneous options: FIXME: these are probably not valid args | |
_Switch(["-use_sw_tback", "use_sw_tback"], | |
"Compute locally optimal Smith-Waterman alignments?"), | |
] | |
_NcbiblastMain2SeqCommandline.__init__(self, cmd, **kwargs) | |
... | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment