Python snippets for biology

Open common formats:

%ENDCODE%

.fa / .fasta / .fna %CODE{"python"}% import SeqIO fastaList = list(SeqIO.parse("path/file.fasta", "fasta")) %ENDCODE%

Write common formats:

.gbk / .gbf / .gb %CODE{"python"}% import SeqIO SeqIO.write(seqRecordObj_or_list,'/my/path/file.gbk', 'gb') %ENDCODE%

.fa / .fasta / .fna %CODE{"python"}% import SeqIO SeqIO.write(seqRecordObj_or_list,'/my/path/file.fasta', 'fasta') %ENDCODE%

local BLASTing from Python

Also requires NCBI BLAST command line software, a local BLAST database, and Pandas %CODE{"python"}% from Bio.Seq import Seq from Bio import SeqIO from Bio.SeqRecord import SeqRecord import subprocess from tempfile import NamedTemporaryFile import pandas as pd

query = NamedTemporaryFile() tmp = NamedTemporaryFile() SeqIO.write(SeqRecord(Seq(seq), id="temp"), query.name, "fasta")

flags = 'qstart qend sseqid sframe pident slen sseq length sstart send qlen' # 'flags' specifies the specific outputs for 'output format 6' in the BLAST CL software extras = "-max_target_seqs 20000 -culling_limit 10 -perc_identity 75" # 'extras' are further flags that can be called on the CL

subprocess.call( #the actual CL BLAST

with open(tmp.name, "r") as file_handle: #opens BLAST file align = file_handle.readlines()

tmp.close() query.close()

df = pd.DataFrame([ele.split() for ele in align], columns = flags.split()) df = df.apply(pd.to_numeric, errors='ignore') # puts the output of BLAST into a tidy Pandas dataframe

return df %ENDCODE%

Python snippets for biology

Open common formats:

%ENDCODE%

.fa / .fasta / .fna %CODE{"python"}% import SeqIO fastaList = list(SeqIO.parse("path/file.fasta", "fasta")) %ENDCODE%

Write common formats:

.gbk / .gbf / .gb %CODE{"python"}% import SeqIO SeqIO.write(seqRecordObj_or_list,'/my/path/file.gbk', 'gb') %ENDCODE%

.fa / .fasta / .fna %CODE{"python"}% import SeqIO SeqIO.write(seqRecordObj_or_list,'/my/path/file.fasta', 'fasta') %ENDCODE%

local BLASTing from Python

Also requires NCBI BLAST command line software, a local BLAST database, and Pandas %CODE{"python"}% from Bio.Seq import Seq from Bio import SeqIO from Bio.SeqRecord import SeqRecord import subprocess from tempfile import NamedTemporaryFile import pandas as pd

def BLAST(seq, db = 'nr_db', type = "p"): # 'seq' is a sequence (as a str) of a protein or nucleotide sequence # 'db' points to location of local BLAST database # 'type' specifies the type of BLAST (e.g. 'n', 'p', 'x', etc)

query = NamedTemporaryFile() tmp = NamedTemporaryFile() SeqIO.write(SeqRecord(Seq(seq), id="temp"), query.name, "fasta")

flags = 'qstart qend sseqid sframe pident slen sseq length sstart send qlen' # 'flags' specifies the specific outputs for 'output format 6' in the BLAST CL software extras = "-max_target_seqs 20000 -culling_limit 10 -perc_identity 75" # 'extras' are further flags that can be called on the CL

subprocess.call( #the actual CL BLAST (f'blast{type} -query {query.name} -out {tmp.name} ' f'-db {db} {extras} -word_size {str(wordsize)} -outfmt "6 {flags}"'), shell=True)

with open(tmp.name, "r") as file_handle: #opens BLAST file align = file_handle.readlines()

tmp.close() query.close()

df = pd.DataFrame([ele.split() for ele in align], columns = flags.split()) df = df.apply(pd.to_numeric, errors='ignore') # puts the output of BLAST into a tidy Pandas dataframe

return df %ENDCODE%

Python snippets for biology

Open common formats:

%ENDCODE%

.fa / .fasta / .fna %CODE{"python"}% import SeqIO fastaList = list(SeqIO.parse("path/file.fasta", "fasta")) %ENDCODE%

Write common formats:

.gbk / .gbf / .gb %CODE{"python"}% import SeqIO SeqIO.write(seqRecordObj_or_list,'/my/path/file.gbk', 'gb') %ENDCODE%

.fa / .fasta / .fna %CODE{"python"}% import SeqIO SeqIO.write(seqRecordObj_or_list,'/my/path/file.fasta', 'fasta') %ENDCODE%

local BLASTing from Python

Also requires NCBI BLAST command line software, a local BLAST database, and Pandas %CODE{"python"}% from Bio.Seq import Seq from Bio import SeqIO from Bio.SeqRecord import SeqRecord import subprocess from tempfile import NamedTemporaryFile import pandas as pd

def BLAST(seq, db = 'nr_db', type = "p"): # 'seq' is a sequence (as a str) of a protein or nucleotide sequence # 'db' points to location of local BLAST database # 'type' specifies the type of BLAST (e.g. 'n', 'p', 'x', etc)

query = NamedTemporaryFile() tmp = NamedTemporaryFile() SeqIO.write(SeqRecord(Seq(seq), id="temp"), query.name, "fasta")

flags = 'qstart qend sseqid sframe pident slen sseq length sstart send qlen' # 'flags' specifies the specific outputs for 'output format 6' in the BLAST CL software extras = "-max_target_seqs 20000 -culling_limit 10 -perc_identity 75" # 'extras' are further flags that can be called on the CL

subprocess.call( #the actual CL BLAST (f'blast{type} -query {query.name} -out {tmp.name} ' f'-db {db} {extras} -word_size {str(wordsize)} -outfmt "6 {flags}"'), shell=True)

with open(tmp.name, "r") as file_handle: #opens BLAST file align = file_handle.readlines()

tmp.close() query.close()

df = pd.DataFrame([ele.split() for ele in align], columns = flags.split()) df = df.apply(pd.to_numeric, errors='ignore') # puts the output of BLAST into a tidy Pandas dataframe

return df %ENDCODE%

-- Matt Mc Guffie - 2020-12-03

Comments

<--/commentPlugin-->