def search(
database,
sequences=None,
query_file=None,
query_ids=None,
blast_file=None,
**kwargs,
):
"""Launch a new BLAST search using either DIAMOND or command-line BLASTp (remote).
Arguments:
database (str): Path to DIAMOND database
sequences (dict): Query sequences
query_file (str): Path to FASTA file containing query sequences
query_ids (list): NCBI sequence accessions
blast_file (str): Path to the file blast results are written to
Raises:
ValueError: No value given for query_file or query_ids
Returns:
list: Parsed rows with hits from DIAMOND results table
"""
if query_file:
table = diamond(query_file, database, **kwargs)
else:
if not sequences:
sequences = helpers.get_sequences(query_ids=query_ids)
# delete=False since you cannot open tempfiles twice in Windows
# see: https://stackoverflow.com/questions/46497842/passing-namedtemporaryfile-to-a-subprocess-on-windows
fasta = NTF("w", delete=False)
text = helpers.sequences_to_fasta(sequences)
try:
with fasta:
fasta.write(text)
table = diamond(fasta.name, database, **kwargs)
finally:
os.unlink(fasta.name)
results = parse(table)
if blast_file:
LOG.info("Writing DIAMOND hit table to %s", blast_file)
blast_table = "".join(table)
with open(blast_file, "w") as f:
f.write(blast_table)
return results
def search(
database,
sequences=None,
query_file=None,
query_ids=None,
blast_file=None,
**kwargs,
):
"""Launch a new BLAST search using either DIAMOND or command-line BLASTp (remote).
Arguments:
database (str): Path to DIAMOND database
sequences (dict): Query sequences
query_file (str): Path to FASTA file containing query sequences
query_ids (list): NCBI sequence accessions
blast_file (TextIOWrapper): file blast results are written to
Raises:
ValueError: No value given for query_file or query_ids
Returns:
list: Parsed rows with hits from DIAMOND results table
"""
if query_file:
table = diamond(query_file, database, **kwargs)
else:
if not sequences:
sequences = helpers.get_sequences(query_ids=query_ids)
# delete=False since you cannot open tempfiles twice in Windows
fasta = NTF("w", delete=False)
text = helpers.sequences_to_fasta(sequences)
try:
with fasta:
fasta.write(text)
table = diamond(fasta.name, database, **kwargs)
finally:
os.unlink(fasta.name)
results = parse(table)
if blast_file:
LOG.info("Writing DIAMOND hit table to %s", blast_file.name)
blast = "\n".join(results)
blast_file.write(blast)
return results
def start(
sequences=None,
query_file=None,
query_ids=None,
database="nr",
program="blastp",
megablast=False,
filtering="F",
evalue=0.1,
nucl_reward=None,
nucl_penalty=None,
gap_costs="11 1",
matrix="BLOSUM62",
hitlist_size=500,
threshold=11,
word_size=6,
comp_based_stats=2,
entrez_query=None,
):
"""Launch a remote BLAST search using NCBI BLAST API.
Note that the HITLIST_SIZE, ALIGNMENTS and DESCRIPTIONS parameters must all be set
together in order to mimic max_target_seqs behaviour.
Usage guidelines:
1. Don't contact server more than once every 10 seconds
2. Don't poll for a single RID more than once a minute
3. Use URL parameter email/tool
4. Run scripts weekends or 9pm-5am Eastern time on weekdays if >50 searches
For a full description of the parameters, see:
1. `BLAST API documentation<https://ncbi.github.io/blast-cloud/dev/api.html>`
2. `BLAST documentation <https://blast.ncbi.nlm.nih.gov/Blast.cgi?CMD=Web&PAGE_TYPE=BlastDocs&DOC_TYPE=BlastHelp>`
Parameters:
sequences (dict): Query sequence dict generated by helpers.get_sequences()
query_file (str): Path to a query FASTA file
query_ids (list): Collection of NCBI sequence identifiers
database (str): Target NCBI BLAST database
program (str): BLAST variant to run
megablast (bool): Enable megaBLAST option (only with BLASTn)
filtering (str): Low complexity filtering
evalue (float): E-value cutoff
nucl_reward (int): Reward for matching bases (only with BLASTN/megaBLAST)
nucl_penalty (int): Penalty for mismatched bases (only with BLASTN/megaBLAST)
gap_costs (str): Gap existence and extension costs
matrix (str): Scoring matrix name
hitlist_size (int): Number of database sequences to keep
threshold (int): Neighbouring score for initial words
word_size (int): Size of word for initial matches
comp_based_stats (int): Composition based statistics algorithm
entrez_query (str): NCBI Entrez search term for pre-filtering the BLAST database
Returns:
rid (str): Request Identifier (RID) assigned to the search
rtoe (int): Request Time Of Execution (RTOE), estimated run time of the search
"""
if not sequences:
sequences = helpers.get_sequences(query_file=query_file,
query_ids=query_ids)
query = helpers.sequences_to_fasta(sequences)
parameters = {
"CMD": "PUT",
"DATABASE": database,
"PROGRAM": program,
"FILTER": filtering,
"EXPECT": evalue,
"GAPCOSTS": gap_costs,
"MATRIX": matrix,
"HITLIST_SIZE": hitlist_size,
"ALIGNMENTS": hitlist_size,
"DESCRIPTIONS": hitlist_size,
"WORD_SIZE": word_size,
"COMPOSITION_BASED_STATISTICS": comp_based_stats,
}
if entrez_query:
parameters["ENTREZ_QUERY"] = entrez_query
if program == "blastn":
if megablast:
parameters["MEGABLAST"] = "on"
if nucl_reward:
parameters["NUCL_REWARD"] = nucl_reward
if nucl_penalty:
parameters["NUCL_PENALTY"] = nucl_penalty
else:
# Does not apply to blastn
parameters["THRESHOLD"] = threshold
response = requests.post(BLAST_API_URL,
files={"QUERY": query},
params=parameters)
LOG.debug("Search parameters: %s", parameters)
LOG.debug("Search URL: %s", response.url)
rid, rtoe = re.findall(r"(?:RID|RTOE) = (.+?)[\n\s]", response.text)
return rid, int(rtoe)