def variant_call(self,
alignment,
reference_file,
stand_emit_conf=40,
stand_call_conf=100,
GATK_dir="",
num_of_threads=5,
output_mode="EMIT_VARIANTS_ONLY",
discovery_mode="BOTH",
output_file="GATK_raw.vcf",
default_base_qualities=None):
# manual http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_gatk_tools_walkers_genotyper_UnifiedGenotyper.html
# output_mode values:
# EMIT_VARIANTS_ONLY
# EMIT_ALL_CONFIDENT_SITES
# EMIT_ALL_SITES
# discovery_mode values:
# SNP
# INDEL
# GENERALPLOIDYSNP
# GENERALPLOIDYINDEL
# BOTH
default_qualities = ""
if default_base_qualities:
default_qualities = "--defaultBaseQualities %i" % default_base_qualities
gatk_dir = check_path(GATK_dir)
os.system(
" java -jar %sGenomeAnalysisTK.jar -nt %i -l INFO -R %s -T UnifiedGenotyper -I %s -stand_call_conf %i -stand_emit_conf %i -o %s --output_mode %s -glm %s %s"
% (gatk_dir, num_of_threads, reference_file, alignment,
stand_call_conf, stand_emit_conf, output_file, output_mode,
discovery_mode, default_qualities))
def RepeatModeler_search(query_file, db_name, output_file="run.out",
num_of_threads=5, RepeatModeler_dir=""):
print("\nRepeatModeler search...\n")
repmod_dir = check_path(RepeatModeler_dir)
os.system(repmod_dir + "BuildDatabase -engine ncbi -name %s %s" % (db_name, query_file))
os.system(repmod_dir + "RepeatModeler -engine ncbi -pa %i -database %s > %s"
% (num_of_threads, db_name, output_file))
def TRF_search(query_file, match=2, mismatch=7, delta=7, PM=80,
PI=10, minscore=50, max_period=500, flanked=False, TRF_dir=""):
print("\nTRF search...\n")
#use: trf File Match Mismatch Delta PM PI Minscore MaxPeriod [options]
#Where: (all weights, penalties, and scores are positive)
# File = sequences input file
# Match = matching weight
# Mismatch = mismatching penalty
# Delta = indel penalty
# PM = match probability (whole number)
# PI = indel probability (whole number)
# Minscore = minimum alignment score to report
# MaxPeriod = maximum period size to report
# [options] = one or more of the following :
# -m masked sequence file
# -f flanking sequence
# -d data file
# -h suppress HTML output
#Recomended options: trf yoursequence.txt 2 7 7 80 10 50 500 -f -d -m
flanking = ""
if flanked:
flanking = "-f"
trf_path = check_path(TRF_dir)
os.system(trf_path + "trf %s %i %i %i %i %i %i %i %s -d -m"
% (query_file, match, mismatch, delta, PM, PI, minscore, max_period, flanking))
def add_header2bam(input_bam,
output_bam,
RGID,
RGLB,
RGPL,
RGSM,
RGPU,
PICARD_dir=""):
picard_dir = check_path(PICARD_dir)
os.system(
"java -XX:MaxDirectMemorySize=4G -jar %sAddOrReplaceReadGroups.jar I= %s O= %s SORT_ORDER=coordinate RGID=%s RGLB=%s RGPL=%s RGSM=%s RGPU=%s CREATE_INDEX=True"
% (picard_dir, input_bam, output_bam, RGID, RGLB, RGPL, RGSM, RGPU))
def RepeatMasker_search(query_file, species, custom_lib_path=None, RepeatMasker_dir="",
num_of_threads=5, search_type="-s"):
#species: see list of possible species in repeatmasker.help coming with RepeatMasker
#search type: "-s" (sensetive), "" (default), "-q" (fast), "-qq" (very fast)
repmask_dir = check_path(RepeatMasker_dir)
custom_lib = ""
if custom_lib_path:
cuatom_lib = "-lib %s" % custom_lib_path
#additional options:
#-xm creates an additional output file in cross_match format (for parsing)
#-ace creates an additional output file in ACeDB format
#-gff creates an additional Gene Feature Finding format
#-excln The percentages displayed in the .tbl file are calculated using a
# total sequence length excluding runs of 25 Ns or more.
print("\nRepeatMasker search...\n")
os.system(repmask_dir + "RepeatMasker -excln -xm -ace -gff %s -pa %i -species %s %s %s"
% (custom_lib, num_of_threads, species, search_type, query_file))
for filename in dir_list:
if ("_R1" in filename) and (sample_name in filename):
left_reads = filename
if ("_R2" in filename) and (sample_name in filename):
right_reads = filename
return left_reads, right_reads
reference_name = "LAN210_v0.10m"
reference_dir = "/home/mahajrod/genetics/desaminases/data/LAN210_v0.10m/"
reference = "%s%s.fasta" % (reference_dir, reference_name)
reference_dict = "%s%s.dict" % (reference_dir, reference_name)
reference_index = "%s%s" % (reference_dir, reference_name)
workdir = "/media/mahajrod/d9e6e5ee-1bf7-4dba-934e-3f898d9611c8/Data/LAN2xx/all"
gatk_dir = check_path("/home/mahajrod/Repositories/genetic/NGS_tools/GenomeAnalysisTK-3.2-0/")
platform = "illumina"
read_subdir = "trimmed/spades/corrected/"
#samples_file = "/media/mahajrod/d9e6e5ee-1bf7-4dba-934e-3f898d9611c8/Data/LAN2xx/samples_nonwt.t"
#samples_file = "/media/mahajrod/d9e6e5ee-1bf7-4dba-934e-3f898d9611c8/Data/LAN2xx/samples_wt.t"
#samples_file = "/media/mahajrod/d9e6e5ee-1bf7-4dba-934e-3f898d9611c8/Data/LAN2xx/samples_nonHAP.t"
samples_file = "/media/mahajrod/d9e6e5ee-1bf7-4dba-934e-3f898d9611c8/Data/LAN2xx/samples_HAP.t"
alignment_dir = "alignment_LAN210_v0.10m"
os.chdir(reference_dir)
make_fasta_dict(reference, reference_dict, PICARD_dir="/home/mahajrod/Repositories/genetic/NGS_tools/picard-tools-1.115/picard-tools-1.115/")
get_chromosomes_bed(reference, reference_index, mitochondrial_region_name="mt",
chrom_out_file="chromosomes.bed", mito_out_file="mt.bed", reference_filetype="fasta")
os.system("samtools faidx %s" % reference)
def snp_call_GATK(alignment,
sample_name,
reference_file,
known_sites_vcf,
stand_emit_conf=40,
stand_call_conf=100,
QD=2.0,
FS=60.0,
MQ=40.0,
HaplotypeScore=13.0,
MappingQualityRankSum=-12.5,
ReadPosRankSum=-8.0,
GATK_dir="",
num_of_threads=5,
skip_base_recalibration=False):
#default filter expression
#"QD < 2.0 || FS > 60.0 || MQ < 40.0 || HaplotypeScore > 13.0 || MappingQualityRankSum < -12.5 || ReadPosRankSum < -8.0"
gatk_dir = check_path(GATK_dir)
intermediate_alignment = alignment
if not skip_base_recalibration:
intermediate_alignment = alignment + "_recal_reads.bam"
#Analyze patterns of covariation in the sequence dataset
os.system(
"java -jar %sGenomeAnalysisTK.jar -nct %i -T BaseRecalibrator -R %s -I %s -knownSites %s -o %s_recal_data.table"
% (gatk_dir, num_of_threads, reference_file, alignment,
known_sites_vcf, sample_name))
#Do a second pass to analyze covariation remaining after recalibration
os.system(
"java -jar %sGenomeAnalysisTK.jar -nct %i -T BaseRecalibrator -R %s -I %s -knownSites %s -BQSR %s_recal_data.table -o %s_post_recal_data.table"
% (gatk_dir, num_of_threads, reference_file, alignment,
known_sites_vcf, sample_name, sample_name))
#Generate before/after plots
#os.system("java -jar %sGenomeAnalysisTK.jar -T AnalyzeCovariates -R %s -before %s_recal_data.table -after %s_post_recal_data.table -plots %s_recalibration_plots.pdf"
# % (gatk_dir, reference_file, sample_name, sample_name, sample_name))
#Apply the recalibration to your sequence data
os.system(
"java -jar %sGenomeAnalysisTK.jar -nct %i -T PrintReads -R %s -I %s -BQSR %s_recal_data.table -o %s"
% (gatk_dir, num_of_threads, reference_file, alignment,
sample_name, intermediate_alignment))
print("\nSNP call...\n")
#SNP call
os.system(
" java -jar %sGenomeAnalysisTK.jar -nt %i -l INFO -R %s -T UnifiedGenotyper -I %s -stand_call_conf %i -stand_emit_conf %i -o %s_GATK_raw.vcf --output_mode EMIT_VARIANTS_ONLY"
% (gatk_dir, num_of_threads, reference_file, intermediate_alignment,
stand_call_conf, stand_emit_conf, sample_name))
#extract SNP
os.system(
"java -jar %sGenomeAnalysisTK.jar -T SelectVariants -R %s -V %s_GATK_raw.vcf -selectType SNP -o %s_GATK_raw_no_indel.vcf"
% (gatk_dir, reference_file, sample_name, sample_name))
#extract indels
os.system(
"java -jar %sGenomeAnalysisTK.jar -T SelectVariants -R %s -V %s_GATK_raw.vcf -selectType INDEL -o %s_GATK_raw_only_indel.vcf"
% (gatk_dir, reference_file, sample_name, sample_name))
#filtering
print("\nFiltering SNP...\n")
os.system(
"java -jar %sGenomeAnalysisTK.jar -T VariantFiltration -R %s -V %s_GATK_raw_no_indel.vcf --filterExpression 'QD < %f || FS > %f || MQ < %f || HaplotypeScore > %f || MappingQualityRankSum < %f || ReadPosRankSum < %f' --filterName 'ambigious_snp' -o %s_GATK_filtered_snps.vcf "
% (gatk_dir, reference_file, sample_name, QD, FS, MQ, HaplotypeScore,
MappingQualityRankSum, ReadPosRankSum, sample_name))
#os.system("vcftools --vcf %s_GATK_filtered_snps.vcf --remove-filtered-all --out %s_GATK_best_snps.vcf --recode --recode-INFO-all"
# % (sample_name, sample_name ))
"""
def windowmasker_search(windowmasker_dir):
winmask_dir = check_path(windowmasker_dir)
#TODO: write this function
pass
def rmout2gff3(rmoutfile, outfile, RepeatMaskerUtils_dir=""):
repmaskutils_dir = check_path(RepeatMaskerUtils_dir)
os.system(repmaskutils_dir + "rmOutToGFF3.pl %s > %s" % (rmoutfile, outfile))
def extract_repbase(species, output_file="RepBase.fasta", RepeatMaskerUtils_dir=""):
print("\nExtracting RepBase for %s\n" % species)
repmaskutils_dir = check_path(RepeatMaskerUtils_dir)
os.system(repmaskutils_dir + "queryRepeatDatabase.pl -species %s > %s" % (species, output_file))
def make_fasta_dict(fasta_file, dict_name, PICARD_dir=""):
picard_dir = check_path(PICARD_dir)
os.system("java -jar %sCreateSequenceDictionary.jar R= %s O= %s" %
(picard_dir, fasta_file, dict_name))