def diamondAlignORF(infile, outfile):
#set memory and threads
job_memory = str(PARAMS["Diamond_memory"]) + "G"
job_threads = int(PARAMS["Diamond_threads"])
#generate call to diamond
statement = PipelineAnnotate.runDiamond(infile, outfile, PARAMS)
P.run(statement)
def detectOrfs(infile, outfile):
statementlist = []
#set job memory and threads
job_memory = str(PARAMS["Prodigal_memory"]) + "G"
job_threads = int(PARAMS["Prodigal_threads"])
#command to generate index files
seqdat = PipelineAssembly.SequencingData(infile)
#generate outfile without gz
outfile = outfile.replace(".gz", "")
#ensure input is FASTA
if seqdat.paired == True:
print("Cannot detect ORFs from paired-end reads.")
else:
if seqdat.fileformat == "fastq":
statementlist.append("reformat.sh in={} out={}".format(
infile, "orfs.dir/" + seqdat.cleanname + ".fa"))
infile = "orfs.dir/" + seqdat.cleanname + ".fa"
#generate the call to prodigal
statementlist.append(
PipelineAnnotate.runProdigal(infile, outfile, PARAMS))
#remove the temp FASTA if created
if seqdat.fileformat == "fastq":
statementlist.append("rm {}".format("orfs.dir/" +
seqdat.cleanname + ".fa"))
#compress the outputs
statementlist.append("gzip {}".format(outfile))
statementlist.append("gzip {}".format(
outfile.replace("peptides", "positions")))
statement = " && ".join(statementlist)
P.run(statement)
def detectOrfs(infile, outfile):
statementlist = []
#set job memory and threads
job_memory = str(PARAMS["Prodigal_memory"]) + "G"
job_threads = int(PARAMS["Prodigal_threads"])
#command to generate index files
seqdat = PipelineAssembly.SequencingData(infile)
#ensure input is FASTA
if seqdat.paired == True:
print(
"Prodigal requires single/merged (i.e. not paired-end) reads for ORF detection."
)
else:
if seqdat.fileformat == "fastq":
statementlist.append("reformat.sh in={} out={}".format(
infile, "orfs.dir/" + seqdat.cleanname + ".fa"))
infile = "orfs.dir/" + seqdat.cleanname + ".fa"
#generate the call to prodigal
statementlist.append(
PipelineAnnotate.runProdigal(infile, outfile, PARAMS))
#remove the temp FASTA if created
if seqdat.fileformat == "fastq":
statementlist.append("rm {}".format("orfs.dir/" +
seqdat.cleanname + ".fa"))
statement = " && ".join(statementlist)
P.run(statement)
def functionalAnnotSeed(infile, outfile):
job_memory = str(PARAMS["Eggnogmapper_memory"]) + "G"
job_threads = int(PARAMS["Eggnogmapper_threads"])
#generate call to eggnog-mapper
#requires older version of diamond to use the eggnog mapper databases
statement = "module load bio/diamond/0.8.22 && "
statement += PipelineAnnotate.runEggmapSeed(infile, infile, PARAMS)
P.run(statement)
def krakenAlignContig(infile, outfile):
#set memory and threads
job_memory = str(PARAMS["Kraken_memory"]) + "G"
job_threads = int(PARAMS["Kraken_threads"])
#generate call to diamond
statement = PipelineAnnotate.runKraken(
infile, outfile, PARAMS, "{}scripts/translateKraken2.py".format(
os.path.dirname(__file__).rstrip("pipelines")))
P.run(statement)
def functionalAnnotSeed(infile, outfile):
job_memory = str(PARAMS["Eggnogmapper_memory"]) + "G"
job_threads = int(PARAMS["Eggnogmapper_threads"])
#generate call to eggnog-mapper
#option to add commands to load specific versions of diamond and python2 etc. if needed
if PARAMS["Eggnogmapper_preload"] not in ["", "false"]:
statement = "{} &&".format(PARAMS["Eggnogmapper_preload"])
else:
statement = ""
statement += PipelineAnnotate.runEggmapSeed(infile.replace(".log", ""),
infile.replace(".log", ""),
PARAMS)
statement += ' && echo "Made file {}." > {}'.format(
outfile.replace(".log", ""), outfile)
P.run(statement)
def krakenAlignContig(infile, outfile):
#set memory and threads
job_memory = str(PARAMS["Kraken_memory"]) + "G"
job_threads = int(PARAMS["Kraken_threads"])
#generate call to diamond
statementlist = [
PipelineAnnotate.runKraken(
infile, outfile.replace(".gz", ""), PARAMS,
"{}scripts/translateKraken2.py".format(
os.path.dirname(__file__).rstrip("pipelines")))
]
#compress outputs
statementlist.append("gzip {}".format(
outfile.replace("translated.gz", "out")))
statementlist.append("gzip {}".format(outfile.replace(".gz", "")))
statement = " && ".join(statementlist)
P.run(statement)
def functionalAnnotChunks(infile, outfile):
job_memory = str(PARAMS["Eggnogmapper_memory_annot"]) + "G"
job_threads = int(str(PARAMS["Eggnogmapper_threads_annot"]))
statement = []
if PARAMS["Eggnogmapper_scratch"] == "true":
#copy the db into fast local SSD
statement.append("cp {}eggnog.db $SCRATCH_DIR/eggnog.db".format(
PARAMS["Eggnogmapper_eggdata"]))
datadir = "$SCRATCH_DIR"
else:
datadir = PARAMS["Eggnogmapper_eggdata"]
#get annotation from seeds
statement.append(
PipelineAnnotate.runEggmapAnnot(
infile, outfile.replace(".emapper.annotations", ""), PARAMS,
datadir))
statement = " && ".join(statement)
#run the annotation step
P.run(statement)
def functionalAnnotChunks(infile, outfile):
job_memory = str(PARAMS["Eggnogmapper_memory_annot"]) + "G"
job_threads = int(str(PARAMS["Eggnogmapper_threads_annot"]))
statement = []
#option to add commands to load specific versions of diamond and python2 etc. if needed
if PARAMS["Eggnogmapper_preload"] not in ["", "false"]:
statement.append("{}".format(PARAMS["Eggnogmapper_preload"]))
if PARAMS["Eggnogmapper_scratch"] == "true":
#copy the db into fast local SSD
statement.append("cp {}eggnog.db $SCRATCH_DIR/eggnog.db".format(
PARAMS["Eggnogmapper_eggdata"]))
datadir = "$SCRATCH_DIR"
else:
datadir = PARAMS["Eggnogmapper_eggdata"]
#get annotation from seeds
statement.append(
PipelineAnnotate.runEggmapAnnot(
infile.replace(".log", ""),
outfile.replace(".emapper.annotations.log", ""), PARAMS, datadir))
statement.append('echo "Made file {}." > {}'.format(
outfile.replace(".log", ""), outfile))
statement = " && ".join(statement)
#run the annotation step
P.run(statement)
def meganAnnot(infile, outfile):
job_memory = str(PARAMS["Blast2lca_memory"]) + "G"
job_threads = int(PARAMS["Blast2lca_threads"])
#generate call to blast2lca
statement = PipelineAnnotate.runBlast2Lca(infile, outfile, PARAMS)
P.run(statement)