def run_blast(species_id_path):
blast_cmd = NcbiblastnCommandline(
cmd=
'/mnt/d/zhes_learning_space/software_in_ubuntu/ncbi-blast-2.10.1+/bin/blastn',
query=query_file,
db=species_db_dir / species_id_path.stem,
outfmt=11,
out=species_out_asn_dir / (species_id_path.stem + ".asn")
# perc_identity=95
)
blast_xml_cmd = NcbiblastformatterCommandline(
archive=species_out_asn_dir / (species_id_path.stem + ".asn"),
outfmt=5,
out=species_out_xml_dir / (species_id_path.stem + ".xml"),
cmd=
'/mnt/d/zhes_learning_space/software_in_ubuntu/ncbi-blast-2.10.1+/bin/blast_formatter'
)
blast_txt_cmd = NcbiblastformatterCommandline(
archive=species_out_asn_dir / (species_id_path.stem + ".asn"),
outfmt=7,
out=species_out_txt_dir / (species_id_path.stem + ".txt"),
cmd=
'/mnt/d/zhes_learning_space/software_in_ubuntu/ncbi-blast-2.10.1+/bin/blast_formatter'
)
db_file = species_db_dir / (species_id_path.stem + ".ndb")
if (species_out_xml_dir /
(species_id_path.stem + ".xml")).exists() is False:
if db_file.exists() is False:
blastdb(species_id_path)
blast_cmd()
blast_txt_cmd()
blast_xml_cmd()
def blast(db_file, query_file, blast_out_xml_file, blast_out_asn_file,
blast_out_txt_file):
blast_asn_cmd = NcbiblastnCommandline(
cmd=
'/mnt/d/zhes_learning_space/software_in_ubuntu/ncbi-blast-2.10.1+/bin/blastn',
query=query_file,
db=db_file,
outfmt=11,
out=blast_out_asn_file)
blast_asn_cmd()
blast_xml_cmd = NcbiblastformatterCommandline(
archive=blast_out_asn_file,
outfmt=5,
out=blast_out_xml_file,
cmd=
'/mnt/d/zhes_learning_space/software_in_ubuntu/ncbi-blast-2.10.1+/bin/blast_formatter'
)
blast_xml_cmd()
blast_txt_cmd = NcbiblastformatterCommandline(
archive=blast_out_asn_file,
outfmt=7,
out=blast_out_txt_file,
cmd=
'/mnt/d/zhes_learning_space/software_in_ubuntu/ncbi-blast-2.10.1+/bin/blast_formatter'
)
blast_txt_cmd()
def psiBlastScoring():
"""
JB's instructions on psi-blast
1. We find all similar interfaces.
2. Make a MSA of structurally aligned sequences (multiple sequence alignment)
3. Form a score from the probability of a particular mutation showing up in the
MSA
4. Evaluate the mutation with this score - This is where we need the mutation
Notes:
-> Should not require an HPC to run each blast computation
Some biopython options for blast:
---------------------------------------------------------
blastn -> nucleotide vs nucleotide
blastp -> protein vs protein
blastx -> translated nucleotide vs protein
tblastn -> protein vs translcated nucleotide
tblastx -> translated nucelotide vs translated nucleotide
---------------------------------------------------------
"""
try:
# imports from previous functions
from Bio.PDB.PDBIO import PDBIO
from Bio.PDB.PDBParser import PDBParser
from Bio.Data.IUPACData import protein_letters
from Bio.SeqUtils.ProtParam import ProteinAnalysis
from Bio.PDB.Polypeptide import PPBuilder
from Bio.PDB.Polypeptide import standard_aa_names # Standard amino acid names - https://biopython.org/DIST/docs/api/Bio.PDB.Polypeptide-module.html
from Bio.PDB.Polypeptide import aa1 # aa1 = 'ACDEFGHIKLMNPQRSTVWY'
from Bio.PDB.Polypeptide import aa3 # aa3 = ['ALA', 'CYS', 'ASP', 'GLU', 'PHE', 'GLY', 'HIS', 'ILE',... ]
# Basic Local Alignment Search Tool (BLAST) reader
from Bio.Blast.Applications import NcbiblastformatterCommandline as blastn
from Bio.Blast import NCBIXML # For reaidng the BLAST output
except ImportError:
print("Error - cannot imoort")
BLAST_EXE = '/home/oohnohnoh1/Desktop/ACADEMIA/Papermaking/OPTIMUS_BIND/ZIP/ncbi-blast-2.9.0+/bin/blastn' # The example given is /home/sb/opt/ncbi-blast-2.6.0+/bin/blastn
#f_in = 'seq3.txt'
b_db = 'db/samples/TAIR8cds'
blastn_cline = blastn(cmd=BLAST_EXE,
query=f_in,
db=b_db,
evalue=.0005,
outfmt=5)
rh, eh = blastn.cline()
rh.readline()
def blast(db_file, query_file, blast_out_xml_file, blast_out_asn_file,
blast_out_txt_file):
blast_asn_cmd = NcbiblastnCommandline(cmd='blastn',
query=query_file,
db=db_file,
outfmt=11,
out=blast_out_asn_file)
blast_asn_cmd()
blast_xml_cmd = NcbiblastformatterCommandline(archive=blast_out_asn_file,
outfmt=5,
out=blast_out_xml_file,
cmd='blast_formatter')
blast_xml_cmd()
blast_txt_cmd = NcbiblastformatterCommandline(archive=blast_out_asn_file,
outfmt=7,
out=blast_out_txt_file,
cmd='blast_formatter')
blast_txt_cmd()
def run_blast(query_file,species_id_path,species_out_path):
make_db_cmd=NcbimakeblastdbCommandline(
cmd='/mnt/d/zhes_learning_space/software_in_ubuntu/ncbi-blast-2.10.1+/bin/makeblastdb',
dbtype='nucl',
input_file=species_id_path,
out=str(species_out_path/"blastdb"/species_id_path.stem)
)
blast_cmd=NcbiblastnCommandline(
cmd='/mnt/d/zhes_learning_space/software_in_ubuntu/ncbi-blast-2.10.1+/bin/blastn',
query=query_file,
db=species_out_path/"blastdb"/species_id_path.stem,
outfmt=11,
out=species_out_path/"asn"/(species_id_path.stem+".asn")
# perc_identity=95
)
blast_xml_cmd=NcbiblastformatterCommandline(
archive=species_out_path/"asn"/(species_id_path.stem+".asn"),
outfmt=5,
out=species_out_path/"xml"/(species_id_path.stem+".xml"),
cmd='/mnt/d/zhes_learning_space/software_in_ubuntu/ncbi-blast-2.10.1+/bin/blast_formatter'
)
blast_txt_cmd=NcbiblastformatterCommandline(
archive=species_out_path/"asn"/(species_id_path.stem+".asn"),
outfmt=7,
out=species_out_path/"txt"/(species_id_path.stem+".txt"),
cmd='/mnt/d/zhes_learning_space/software_in_ubuntu/ncbi-blast-2.10.1+/bin/blast_formatter'
)
db_file=species_out_path/"blastdb"/(species_id_path.stem+".ndb")
if (species_out_path/"xml"/(species_id_path.stem+".xml")).exists() is False:
if db_file.exists() is False:
make_db_cmd()
try:
blast_cmd()
except ApplicationError:
print(blast_xml_cmd)
try:
blast_txt_cmd()
except ApplicationError:
print(blast_xml_cmd)
try:
blast_xml_cmd()
except ApplicationError:
print(blast_xml_cmd)
def conserved_domain_search(
nucleotide_seq_path: str,
cd_ans_path: str,
cd_xml_path: Optional[str],
cd_txt_path: Optional[str],
cd_csv_path: Optional[str],
) -> None:
"""conserved domain search for a given nucleotide sequence
:param nucleotide_seq_path: path to nucleotide sequence to be searched
for conserved domains
:type nucleotide_seq_path: str
:param cd_ans_path: path to the result in BLAST archive (ASN.1) format,
preferably ended with '.ans'
:type cd_ans_path: str
:param cd_xml_path: optional path to the result in BLAST XML format,
preferably ended with '.xml'
:type cd_xml_path: str
:param cd_txt_path: optional path to the result in post-rpsblast in text
format, preferably ended with '.txt'
:type cd_txt_path: str
:param cd_csv_path: optional path to the result in post-rpsblast in CSV
format, preferably ended with '.csv'
:type cd_csv_path: str
:return: None
"""
# return of the result BLAST archive (ASN.1) already exists
if not os.path.exists(cd_ans_path):
rpstblastn_cmd = NcbirpstblastnCommandline(
query=nucleotide_seq_path,
**RPSTBLASTN_KWARGS,
)
cd_ans, rpsblast_cmd_error_msg = rpstblastn_cmd()
# write to result ANS.1 file if given
if cd_ans_path:
with open(cd_ans_path, 'w+') as _fh:
_fh.write(cd_ans)
# translate ANS to XML format for easier Biopython parsing
if cd_xml_path and (not os.path.exists(cd_xml_path)):
formatter_cmd = NcbiblastformatterCommandline(
archive=cd_ans_path,
out=cd_xml_path,
outfmt=5,
)
_, formatter_cmd_error_msg = formatter_cmd()
# post-rpsblast processing with rpsbproc and store in text format
if cd_txt_path and (not os.path.exists(cd_txt_path)):
rpsbproc_cmd = Popen(
[
f'rpsbproc',
f'--infile', f'{cd_ans_path}',
f'--outfile', f'{cd_txt_path}',
f'--data-path', f'{CDD_DATA_DIR_PATH}',
f'--data-mode', 'full',
f'--evalue', f'{RPSTBLASTN_KWARGS["evalue"]}',
f'--show-families',
f'--quiet',
],
stdout=PIPE,
stderr=PIPE,
stdin=PIPE,
)
rpsbproc_cmd.communicate()
# parse the post-rpsblast processing results and store in CSV format
if cd_csv_path and (not os.path.exists(cd_csv_path)):
with open(cd_txt_path, 'r') as _fh:
rpsbproc_output = _fh.read()
rpsbproc_output_df = parse_rpsbproc_output(rpsbproc_output)
rpsbproc_output_df.to_csv(cd_csv_path, index=False)
def search_conserved_domains(
fasta_file_path: str,
cd_ans_path: str,
fasta_file_type: Optional[Union[FASTAType, str]] = None,
cd_xml_path: Optional[str] = None,
cd_txt_path: Optional[str] = None,
cd_csv_path: Optional[str] = None,
) -> None:
"""perform conserved domain search for a given FASTA sequence and parse
the results into multiple formats
:param fasta_file_path: path to the FASTA file for domain search
:type fasta_file_path: str
:param fasta_file_type: FASTA file type, could be string or FASTAType
defined in this file, or None, in which case the function will infer
the FASTA type from the file extension
:type fasta_file_type: Optional[Union[FASTAType, str]]
:param cd_ans_path: path to the result in BLAST archive (ASN.1) format,
preferably ended with '.ans'
:type cd_ans_path: str
:param cd_xml_path: optional path to the result in BLAST XML format,
preferably ended with '.xml'
:type cd_xml_path: Optional[str]
:param cd_txt_path: optional path to the result in post-rpsblast in text
format, preferably ended with '.txt'
:type cd_txt_path: Optional[str]
:param cd_csv_path: optional path to the result in post-rpsblast in CSV
format, preferably ended with '.csv'
:type cd_csv_path: Optional[str]
:return: None
"""
# refer the FASTA file type if not explicitly given or given as string
if not fasta_file_type:
fasta_file_type: str = os.path.splitext(fasta_file_path)[1]
if not isinstance(fasta_file_type, FASTAType):
try:
fasta_file_type = FASTAType(fasta_file_type)
except ValueError:
_error_msg = \
f'cannot parse the given FASTA file with extension ' \
f'\'{fasta_file_type}\', which must be one of ' \
f'{list(FASTAType.__members__.keys())}.'
raise ValueError(_error_msg)
# return of the result BLAST archive (ASN.1) already exists
if not os.path.exists(cd_ans_path):
if fasta_file_type == FASTAType.fna:
rpsblast_cmd = NcbirpstblastnCommandline(
query=fasta_file_path,
**RPSTBLASTN_KWARGS,
)
elif fasta_file_type == FASTAType.faa:
rpsblast_cmd = NcbirpsblastCommandline(
query=fasta_file_path,
**RPSTBLASTN_KWARGS,
)
else:
_error_msg = \
f'conserved domains search has not been implemented for ' \
f'FASTA file type with extension \'{fasta_file_type.value}\'.'
raise NotImplementedError(_error_msg)
try:
cd_ans, _ = rpsblast_cmd()
except ApplicationError as __error:
_warning_msg = f'error from rpsblast: {__error}; skipping ...'
_LOGGER.warning(_warning_msg)
return
# write to result ANS.1 file if given
if cd_ans_path:
with open(cd_ans_path, 'w+') as _fh:
_fh.write(cd_ans)
# translate ANS to XML format for easier Biopython parsing
if cd_xml_path and (not os.path.exists(cd_xml_path)):
formatter_cmd = NcbiblastformatterCommandline(
archive=cd_ans_path,
out=cd_xml_path,
outfmt=5,
)
_, formatter_cmd_error_msg = formatter_cmd()
# post-rpsblast processing with rpsbproc and store in text format
if cd_txt_path and (not os.path.exists(cd_txt_path)):
rpsbproc_cmd = Popen(
[
f'rpsbproc',
f'--infile',
f'{cd_ans_path}',
f'--outfile',
f'{cd_txt_path}',
f'--data-path',
f'{CDD_DATA_DIR_PATH}',
f'--data-mode',
'full',
f'--evalue',
f'{RPSTBLASTN_KWARGS["evalue"]}',
f'--show-families',
f'--quiet',
],
stdout=PIPE,
stderr=PIPE,
stdin=PIPE,
)
rpsbproc_cmd.wait()
rpsbproc_cmd.communicate()
# parse the post-rpsblast processing results and store in CSV format
if cd_csv_path and (not os.path.exists(cd_csv_path)):
with open(cd_txt_path, 'r') as _fh:
rpsbproc_output = _fh.read()
rpsbproc_output_df = __parse_rpsbproc_output(rpsbproc_output)
if rpsbproc_output_df is not None:
rpsbproc_output_df.to_csv(cd_csv_path, index=False)