search_patterns.yaml

# MultiQC search patterns.
# Default configurations for how modules can find their log files.
# Loaded by the config module so that these patterns can be overwritten in user config files.

adapterRemoval:
  fn: "*.settings"
  contents: "AdapterRemoval"
  num_lines: 1
afterqc:
  fn: "*.json"
  contents: "allow_mismatch_in_poly"
  num_lines: 10000
anglerfish:
  fn: "*.json"
  contents: "anglerfish_version"
bamtools/stats:
  contents: "Stats for BAM file(s):"
  shared: true
  num_lines: 10
bbduk:
  contents: "Executing jgi.BBDuk"
  num_lines: 2
bbmap/stats:
  contents: "#Name	Reads	ReadsPct"
  num_lines: 4
bbmap/aqhist:
  contents: "#Quality	count1	fraction1	count2	fraction2"
  num_lines: 1
bbmap/bhist:
  contents: "#Pos	A	C	G	T	N"
  num_lines: 1
bbmap/bincov:
  # 3rd line (1st is #Mean)
  contents: "#RefName	Cov	Pos	RunningPos"
  num_lines: 3
bbmap/bqhist:
  contents: "#BaseNum	count_1	min_1	max_1	mean_1	Q1_1	med_1	Q3_1	LW_1	RW_1	count_2	min_2	max_2	mean_2	Q1_2	med_2	Q3_2	LW_2	RW_2"
  num_lines: 1
bbmap/covhist:
  contents: "#Coverage	numBases"
  num_lines: 1
bbmap/covstats:
  contents: "#ID	Avg_fold"
  num_lines: 1
bbmap/ehist:
  contents: "#Errors	Count"
  num_lines: 1
bbmap/gchist:
  # 5th line (1st is #Mean)
  contents: "#GC	Count"
  num_lines: 5
bbmap/idhist:
  contents: "#Mean_reads"
  num_lines: 1
bbmap/ihist:
  # 6th line (first is #Mean)
  contents: "#InsertSize	Count"
  num_lines: 6
bbmap/indelhist:
  contents: "#Length	Deletions	Insertions"
  num_lines: 1
bbmap/lhist:
  contents: "#Length	Count"
  num_lines: 1
bbmap/mhist:
  contents: "#BaseNum	Match1	Sub1	Del1	Ins1	N1	Other1	Match2	Sub2	Del2	Ins2	N2	Other2"
  num_lines: 1
bbmap/qahist:
  contents: "#Deviation"
  num_lines: 1
bbmap/qchist:
  contents_re: '#Quality	count1	fraction1\n'
  num_lines: 1
bbmap/qhist:
  contents: "#BaseNum	Read1_linear	Read1_log	Read1_measured	Read2_linear	Read2_log	Read2_measured"
  num_lines: 1
bbmap/rpkm:
  contents: "#File	"
  num_lines: 1
bbmap/statsfile_machine:
  contents: "Reads Used="
  num_lines: 1
bbmap/statsfile:
  contents: "Reads Used:"
  num_lines: 1
bcftools/stats:
  contents: "This file was produced by bcftools stats"
  shared: true
bcl2fastq:
  fn: "Stats.json"
  contents: "DemuxResults"
  num_lines: 300
bclconvert/runinfo:
  fn: "RunInfo.xml"
bclconvert/demux:
  fn: "Demultiplex_Stats.csv"
bclconvert/quality_metrics:
  fn: "Quality_Metrics.csv"
bclconvert/adaptermetrics:
  fn: "Adapter_Metrics.csv"
bclconvert/unknown_barcodes:
  fn: "Top_Unknown_Barcodes.csv"
biobambam2/bamsormadup:
  contents: "# bamsormadup"
  num_lines: 2
biobloomtools:
  contents: "filter_id	hits	misses	shared	rate_hit	rate_miss	rate_shared"
  num_lines: 2
biscuit/align_mapq:
  fn: "*_mapq_table.txt"
  contents: "BISCUITqc Mapping Quality Table"
  num_lines: 3
biscuit/align_strand:
  fn: "*_strand_table.txt"
  contents: "BISCUITqc Strand Table"
  num_lines: 3
biscuit/align_isize:
  fn: "*_isize_table.txt"
  contents: "BISCUITqc Insert Size Table"
  num_lines: 3
biscuit/dup_report:
  fn: "*_dup_report.txt"
  contents: "BISCUITqc Read Duplication Table"
  num_lines: 3
biscuit/qc_cv:
  fn: "*_cv_table.txt"
  contents: "BISCUITqc Uniformity Table"
  num_lines: 3
biscuit/covdist_all_base_botgc:
  fn: "*_covdist_all_base_botgc_table.txt"
biscuit/covdist_all_base:
  fn: "*_covdist_all_base_table.txt"
biscuit/covdist_all_base_topgc:
  fn: "*_covdist_all_base_topgc_table.txt"
biscuit/covdist_q40_base_botgc:
  fn: "*_covdist_q40_base_botgc_table.txt"
biscuit/covdist_q40_base:
  fn: "*_covdist_q40_base_table.txt"
biscuit/covdist_q40_base_topgc:
  fn: "*_covdist_q40_base_topgc_table.txt"
biscuit/covdist_all_cpg_botgc:
  fn: "*_covdist_all_cpg_botgc_table.txt"
biscuit/covdist_all_cpg:
  fn: "*_covdist_all_cpg_table.txt"
biscuit/covdist_all_cpg_topgc:
  fn: "*_covdist_all_cpg_topgc_table.txt"
biscuit/covdist_q40_cpg_botgc:
  fn: "*_covdist_q40_cpg_botgc_table.txt"
biscuit/covdist_q40_cpg:
  fn: "*_covdist_q40_cpg_table.txt"
biscuit/covdist_q40_cpg_topgc:
  fn: "*_covdist_q40_cpg_topgc_table.txt"
biscuit/cpg_retention_readpos:
  fn: "*_CpGRetentionByReadPos.txt"
biscuit/cph_retention_readpos:
  fn: "*_CpHRetentionByReadPos.txt"
biscuit/base_avg_retention_rate:
  fn: "*_totalBaseConversionRate.txt"
biscuit/read_avg_retention_rate:
  fn: "*_totalReadConversionRate.txt"
bismark/align:
  fn: "*_[SP]E_report.txt"
bismark/dedup:
  fn: "*.deduplication_report.txt"
bismark/meth_extract:
  fn: "*_splitting_report.txt"
bismark/m_bias:
  fn: "*M-bias.txt"
bismark/bam2nuc:
  fn: "*.nucleotide_stats.txt"
bowtie1:
  contents: "# reads processed:"
  exclude_fn:
    # Tophat log files
    - "bowtie.left_kept_reads.log"
    - "bowtie.left_kept_reads.m2g_um.log"
    - "bowtie.left_kept_reads.m2g_um_seg1.log"
    - "bowtie.left_kept_reads.m2g_um_seg2.log"
    - "bowtie.right_kept_reads.log"
    - "bowtie.right_kept_reads.m2g_um.log"
    - "bowtie.right_kept_reads.m2g_um_seg1.log"
    - "bowtie.right_kept_reads.m2g_um_seg2.log"
  shared: true
bowtie2:
  contents: "reads; of these:"
  exclude_contents:
    - "bisulfite"
    - "HiC-Pro"
  shared: true
busco:
  fn: "short_summary*"
  contents: "BUSCO version is:"
  num_lines: 1
bustools:
  fn: "*inspect.json"
ccs/v4:
  contents: "ZMWs generating CCS"
  num_lines: 2
  max_filesize: 1024
ccs/v5:
  contents: '"id": "ccs_processing"'
  fn: "*.json"
cellranger/count_html:
  - fn: "*.html"
    contents: '"command":"Cell Ranger","subcommand":"count"'
    num_lines: 13
  - fn: "*.html"
    contents: '"command": "Cell Ranger", "subcommand": "count"'
    num_lines: 13
cellranger/vdj_html:
  - fn: "*.html"
    contents: '"command":"Cell Ranger","subcommand":"vdj"'
    num_lines: 13
  - fn: "*.html"
    contents: '"command": "Cell Ranger", "subcommand": "vdj"'
    num_lines: 13
checkqc:
  contents: "instrument_and_reagent_type"
  fn: "*.json"
custom_content:
  fn_re: '.+_mqc\.(yaml|yml|json|txt|csv|tsv|log|out|png|jpg|jpeg|html)'
clipandmerge:
  contents: "ClipAndMerge ("
  num_lines: 5
clusterflow/logs:
  fn: "*_clusterFlow.txt"
  shared: true
clusterflow/runfiles:
  fn: "*.run"
  contents: "Cluster Flow Run File"
  num_lines: 2
conpair/concordance:
  contents: "markers (coverage per marker threshold : "
  num_lines: 3
conpair/contamination:
  contents: "Tumor sample contamination level: "
  num_lines: 3
cutadapt:
  contents: "This is cutadapt"
  # contents: 'cutadapt version' # Use this instead if using very old versions of cutadapt (eg. v1.2)
  shared: true
damageprofiler:
  fn: "*dmgprof.json"
dedup:
  fn: "*dedup.json"
deeptools/bamPEFragmentSizeTable:
  contents: "	Frag. Sampled	Frag. Len. Min.	Frag. Len. 1st. Qu.	Frag. Len. Mean	Frag. Len. Median	Frag. Len. 3rd Qu."
  num_lines: 1
deeptools/bamPEFragmentSizeDistribution:
  contents: "#bamPEFragmentSize"
  num_lines: 1
deeptools/estimateReadFiltering:
  contents: "Sample	Total Reads	Mapped Reads	Alignments in blacklisted regions	Estimated mapped reads"
  num_lines: 1
deeptools/plotCorrelationData:
  contents: "#plotCorrelation --outFileCorMatrix"
  num_lines: 1
deeptools/plotCoverageStdout:
  contents: "sample	mean	std	min	25%	50%	75%	max"
  num_lines: 1
deeptools/plotCoverageOutRawCounts:
  contents: "#plotCoverage --outRawCounts"
  num_lines: 1
deeptools/plotEnrichment:
  contents: "file	featureType	percent	featureReadCount	totalReadCount"
  num_lines: 1
deeptools/plotFingerprintOutRawCounts:
  contents: "#plotFingerprint --outRawCounts"
  num_lines: 1
deeptools/plotFingerprintOutQualityMetrics:
  contents: "Sample	AUC	Synthetic AUC	X-intercept	Synthetic X-intercept	Elbow Point	Synthetic Elbow Point"
  num_lines: 1
deeptools/plotPCAData:
  contents: "#plotPCA --outFileNameData"
  num_lines: 1
deeptools/plotProfile:
  contents: "bin labels"
  num_lines: 1
diamond:
  fn: "diamond.log"
dragen/vc_metrics:
  fn: "*.vc_metrics.csv"
dragen/ploidy_estimation_metrics:
  fn: "*.ploidy_estimation_metrics.csv"
dragen/wgs_contig_mean_cov:
  fn_re: '.*\.wgs_contig_mean_cov_?(tumor|normal)?\.csv'
dragen/overall_mean_cov_metrics:
  fn_re: '.*_overall_mean_cov.*\.csv'
dragen/coverage_metrics:
  fn_re: '.*_coverage_metrics.*\.csv'
dragen/wgs_fine_hist:
  fn_re: '.*\.wgs_fine_hist_?(tumor|normal)?\.csv'
dragen/fragment_length_hist:
  fn: "*.fragment_length_hist.csv"
dragen/mapping_metrics:
  fn: "*.mapping_metrics.csv"
  contents: "Number of unique reads (excl. duplicate marked reads)"
  num_lines: 50
dragen/gc_metrics:
  fn: "*.gc_metrics.csv"
dragen/trimmer_metrics:
  fn: "*.trimmer_metrics.csv"
dragen/time_metrics:
  fn: "*.time_metrics.csv"
dragen/rna_quant_metrics:
  fn: "*.quant[._]metrics.csv"
dragen/rna_transcript_cov:
  fn: "*.quant.transcript_coverage.txt"
dragen/sc_rna_metrics:
  fn: "*.scRNA[._]metrics.csv"
dragen/sc_atac_metrics:
  fn: "*.scATAC[._]metrics.csv"
dragen_fastqc:
  fn: "*.fastqc_metrics.csv"
eigenstratdatabasetools:
  fn: "*_eigenstrat_coverage.json"
fastp:
  fn: "*fastp.json"
fastq_screen:
  fn: "*_screen.txt"
fastqc/data:
  fn: "fastqc_data.txt"
fastqc/zip:
  fn: "*_fastqc.zip"
fastqc/theoretical_gc:
  fn: "*fastqc_theoretical_gc*"
featurecounts:
  fn: "*.summary"
  shared: true
fgbio/groupreadsbyumi:
  contents: "fraction_gt_or_eq_family_size"
  num_lines: 3
fgbio/errorratebyreadposition:
  contents: "read_number	position	bases_total	errors	error_rate	a_to_c_error_rate	a_to_g_error_rate	a_to_t_error_rate	c_to_a_error_rate	c_to_g_error_rate	c_to_t_error_rate"
  num_lines: 3
filtlong:
  contents: Scoring long reads
  contents_re: ".*Filtering long reads.*"
  num_lines: 5
flash/log:
  contents: "[FLASH]"
  shared: true
flash/hist:
  fn: "*flash*.hist"
flexbar:
  contents: "Flexbar - flexible barcode and adapter removal"
  shared: true
gatk/varianteval:
  contents: "#:GATKTable:TiTvVariantEvaluator"
  shared: true
gatk/base_recalibrator:
  contents: "#:GATKTable:Arguments:Recalibration"
  num_lines: 3
gffcompare:
  fn: "*.stats"
  contents: "# gffcompare"
  num_lines: 2
goleft_indexcov/roc:
  fn: "*-indexcov.roc"
goleft_indexcov/ped:
  fn: "*-indexcov.ped"
gopeaks:
  fn: "*_gopeaks.json"
happy:
  fn: "*.summary.csv"
  contents: "Type,Filter,TRUTH"
htseq:
  contents_re: '^(feature\tcount|\w+\t\d+)$'
  num_lines: 1
hicexplorer:
  contents: "Min rest. site distance"
  max_filesize: 4096
  num_lines: 26
hicup:
  fn: "HiCUP_summary_report*"
hicpro/mmapstat:
  fn: "*.mmapstat"
hicpro/mpairstat:
  fn: "*.mpairstat"
hicpro/mergestat:
  fn: "*.mergestat"
hicpro/mRSstat:
  fn: "*.mRSstat"
hicpro/assplit:
  fn: "*.assplit.stat"
hifiasm:
  contents: "[M::ha_analyze_count]"
  num_lines: 1
hisat2:
  contents: "HISAT2 summary stats:"
  shared: true
homer/findpeaks:
  contents: "# HOMER Peaks"
  num_lines: 3
homer/GCcontent:
  fn: "tagGCcontent.txt"
homer/genomeGCcontent:
  fn: "genomeGCcontent.txt"
homer/RestrictionDistribution:
  fn: "petagRestrictionDistribution.*.txt"
homer/LengthDistribution:
  fn: "tagLengthDistribution.txt"
homer/tagInfo:
  fn: "tagInfo.txt"
homer/FreqDistribution:
  fn: "petag.FreqDistribution_1000.txt"
hops:
  fn: "heatmap_overview_Wevid.json"
humid:
  fn: "stats.dat"
  contents: "total: "
  num_lines: 1
interop/summary:
  contents: "Level,Yield,Projected Yield,Aligned,Error Rate,Intensity C1,%>=Q30"
interop/index-summary:
  contents: "Total Reads,PF Reads,% Read Identified (PF),CV,Min,Max"
ivar/trim:
  contents: "Number of references"
  num_lines: 8
jcvi:
  contents: "     o    % GC    % of genome    Average size (bp)    Median size (bp)    Number    Total length (Mb)"
jellyfish:
  fn: "*_jf.hist"
kaiju:
  contents_re: 'file\tpercent\treads\ttaxon_id\ttaxon_name'
  num_lines: 1
kallisto:
  contents: "[quant] finding pseudoalignments for the reads"
  shared: true
nanostat:
  max_filesize: 4096
  contents_re: "General summary:\\s*"
  num_lines: 1
kat:
  fn: "*.dist_analysis.json"
kraken:
  contents_re: '^\s{0,2}(\d{1,3}\.\d{1,2})\t(\d+)\t(\d+)\t([\dUDKRPCOFGS-]{1,3})\t(\d+)\s+(.+)'
  num_lines: 2
librarian:
  fn: "librarian_heatmap.txt"
leehom:
  contents: "Adapter dimers/chimeras"
  shared: true
lima/summary:
  contents: "ZMWs above all thresholds"
  num_lines: 2
  max_filesize: 1024
lima/counts:
  contents: "IdxFirst	IdxCombined	IdxFirstNamed	IdxCombinedNamed	Counts	MeanScore"
  num_lines: 1
longranger/summary:
  fn: "*summary.csv"
  contents: "longranger_version,instrument_ids,gems_detected,mean_dna_per_gem,bc_on_whitelist,bc_mean_qscore,n50_linked_reads_per_molecule"
  num_lines: 2
longranger/invocation:
  fn: "_invocation"
  contents: "call PHASER_SVCALLER_CS("
  max_filesize: 2048
macs2:
  fn: "*_peaks.xls"
malt:
  contents: "MaltRun - Aligns sequences using MALT (MEGAN alignment tool)"
  num_lines: 2
methylQA:
  fn: "*.report"
  shared: true
minionqc:
  fn: "summary.yaml"
  contents: "total.gigabases"
mirtop:
  fn: "*_mirtop_stats.log"
mirtrace/summary:
  fn: "mirtrace-results.json"
mirtrace/length:
  fn: "mirtrace-stats-length.tsv"
mirtrace/contaminationbasic:
  fn: "mirtrace-stats-contamination_basic.tsv"
mirtrace/mirnacomplexity:
  fn: "mirtrace-stats-mirna-complexity.tsv"
mtnucratio:
  fn: "*mtnuc.json"
mosdepth/summary:
  fn: "*.mosdepth.summary.txt"
mosdepth/global_dist:
  fn: "*.mosdepth.global.dist.txt"
mosdepth/region_dist:
  fn: "*.mosdepth.region.dist.txt"
motus:
  contents: "Reads are aligned (by BWA) to marker gene sequences in the reference database"
  num_lines: 2
multivcfanalyzer:
  fn: "MultiVCFAnalyzer.json"
disambiguate:
  contents: "unique species A pairs"
  num_lines: 2
nextclade:
  contents: "seqName;clade;"
  num_lines: 1
ngsderive/strandedness:
  contents: "File	TotalReads	ForwardPct	ReversePct	Predicted"
  num_lines: 1
ngsderive/instrument:
  contents: "File	Instrument	Confidence	Basis"
  num_lines: 1
ngsderive/readlen:
  contents: "File	Evidence	MajorityPctDetected	ConsensusReadLength"
  num_lines: 1
ngsderive/encoding:
  contents: "File	Evidence	ProbableEncoding"
  num_lines: 1
ngsderive/junction_annotation:
  contents: "File	total_junctions	total_splice_events	known_junctions	partial_novel_junctions	complete_novel_junctions	known_spliced_reads	partial_novel_spliced_reads	complete_novel_spliced_reads"
  num_lines: 1
optitype:
  contents: "	A1	A2	B1	B2	C1	C2	Reads	Objective"
  num_lines: 1
pangolin:
  contents: "pangolin_version"
  num_lines: 1
odgi:
  - fn: "*.og.stats.yaml"
  - fn: "*.og.stats.yml"
  - fn: "*.odgi.stats.yaml"
  - fn: "*.odgi.stats.yml"
peddy/summary_table:
  fn: "*.peddy.ped"
peddy/het_check:
  fn: "*.het_check.csv"
peddy/ped_check:
  fn: "*.ped_check.csv"
peddy/sex_check:
  fn: "*.sex_check.csv"
peddy/background_pca:
  fn: "*.background_pca.json"
somalier/somalier-ancestry:
  fn: "*.somalier-ancestry.tsv"
somalier/samples:
  fn: "*.samples.tsv"
  contents: "#family_id"
  num_lines: 5
somalier/pairs:
  fn: "*.pairs.tsv"
  contents: "hom_concordance"
  num_lines: 5
pbmarkdup:
  contents_re: "LIBRARY +READS +UNIQUE MOLECULES +DUPLICATE READS"
  num_lines: 5
phantompeakqualtools/out:
  fn: "*.spp.out"
picard/alignment_metrics:
  contents: "AlignmentSummaryMetrics"
  shared: true
picard/basedistributionbycycle:
  contents: "BaseDistributionByCycleMetrics"
  shared: true
picard/crosscheckfingerprints:
  contents: "CrosscheckFingerprints"
  shared: true
picard/gcbias:
  contents: "GcBias"
  shared: true
picard/hsmetrics:
  contents: "HsMetrics"
  shared: true
picard/insertsize:
  contents: "InsertSizeMetrics"
  shared: true
picard/markdups:
  contents: "DuplicationMetrics"
  shared: true
picard/oxogmetrics:
  contents: "OxoGMetrics"
  shared: true
picard/pcr_metrics:
  contents: "TargetedPcrMetrics"
  shared: true
picard/quality_by_cycle:
  contents_re: "[Qq]uality[Bb]y[Cc]ycle"
  contents: "MEAN_QUALITY"
  shared: true
picard/quality_score_distribution:
  contents_re: "[Qq]uality[Ss]core[Dd]istribution"
  contents: "COUNT_OF_Q"
  shared: true
picard/quality_yield_metrics:
  contents: "QualityYieldMetrics"
  shared: true
picard/rnaseqmetrics:
  contents_re: "[Rr]na[Ss]eq[Mm]etrics"
  contents: "## METRICS CLASS"
  shared: true
picard/rrbs_metrics:
  contents: "RrbsSummaryMetrics"
  shared: true
picard/sam_file_validation:
  fn: "*[Vv]alidate[Ss]am[Ff]ile*"
picard/variant_calling_metrics:
  # This looks wrong but I think it's intentional - tests fail if I "fix" it
  fn: "*.variant_calling_detail_metrics"
  contents: "CollectVariantCallingMetrics"
  shared: true
picard/wgs_metrics:
  contents: "CollectWgsMetrics"
  shared: true
picard/collectilluminabasecallingmetrics:
  contents: "CollectIlluminaBasecallingMetrics"
  shared: true
picard/collectilluminalanemetrics:
  contents: "CollectIlluminaLaneMetrics"
  shared: true
picard/extractilluminabarcodes:
  contents: "ExtractIlluminaBarcodes"
  shared: true
picard/markilluminaadapters:
  contents: "MarkIlluminaAdapters"
  shared: true
porechop:
  contents: "Looking for known adapter sets"
  num_lines: 10
preseq:
  - contents: "EXPECTED_DISTINCT"
    num_lines: 2
  - contents: "distinct_reads"
    num_lines: 2
preseq/real_counts:
  fn: "*preseq_real_counts*"
prinseqplusplus:
  - contents: "reads removed by -"
    num_lines: 2
prokka:
  contents: "contigs:"
  num_lines: 2
purple/qc:
  fn: "*.purple.qc"
purple/purity:
  fn: "*.purple.purity.tsv"
pycoqc:
  contents: '"pycoqc":'
  num_lines: 2
pychopper:
  contents: "Classification	Rescue"
  num_lines: 6
qc3C:
  fn: "*.qc3C.json"
qorts:
  contents: "BENCHMARK_MinutesOnSamIteration"
  num_lines: 100
qualimap/bamqc/genome_results:
  fn: "genome_results.txt"
qualimap/bamqc/coverage:
  fn: "coverage_histogram.txt"
qualimap/bamqc/insert_size:
  fn: "insert_size_histogram.txt"
qualimap/bamqc/genome_fraction:
  fn: "genome_fraction_coverage.txt"
qualimap/bamqc/gc_dist:
  fn: "mapped_reads_gc-content_distribution.txt"
qualimap/rnaseq/rnaseq_results:
  fn: "rnaseq_qc_results.txt"
qualimap/rnaseq/coverage:
  fn: "coverage_profile_along_genes_(total).txt"
quast:
  fn: "report.tsv"
  shared: true
rna_seqc/metrics_v1:
  fn: "*metrics.tsv"
  contents: "Sample	Note	"
  shared: true
rna_seqc/metrics_v2:
  fn: "*metrics.tsv"
  contents: "High Quality Ambiguous Alignment Rate"
  shared: true
rna_seqc/coverage:
  fn_re: 'meanCoverageNorm_(high|medium|low)\.txt'
rna_seqc/correlation:
  fn_re: 'corrMatrix(Pearson|Spearman)\.txt'
rockhopper:
  fn: "summary.txt"
  contents: "Number of gene-pairs predicted to be part of the same operon"
  max_filesize: 500000
rsem:
  fn: "*.cnt"
rseqc/bam_stat:
  contents: "Proper-paired reads map to different chrom:"
  max_filesize: 500000
rseqc/gene_body_coverage:
  fn: "*.geneBodyCoverage.txt"
rseqc/inner_distance:
  fn: "*.inner_distance_freq.txt"
rseqc/junction_annotation:
  contents: "Partial Novel Splicing Junctions:"
  max_filesize: 500000
rseqc/junction_saturation:
  fn: "*.junctionSaturation_plot.r"
rseqc/read_gc:
  fn: "*.GC.xls"
rseqc/read_distribution:
  contents: "Group               Total_bases         Tag_count           Tags/Kb"
  max_filesize: 500000
rseqc/read_duplication_pos:
  fn: "*.pos.DupRate.xls"
rseqc/infer_experiment:
  - fn: "*infer_experiment.txt"
  - contents: "Fraction of reads explained by"
    max_filesize: 500000
rseqc/tin:
  fn: "*.summary.txt"
  contents: "TIN(median)"
  num_lines: 1
salmon/meta:
  fn: "meta_info.json"
  contents: "salmon_version"
salmon/fld:
  fn: "flenDist.txt"
sambamba/markdup:
  contents: "finding positions of the duplicate reads in the file"
  num_lines: 50
samblaster:
  contents: "samblaster: Version"
  shared: true
samtools/stats:
  contents: "This file was produced by samtools stats"
  shared: true
samtools/flagstat:
  contents: "in total (QC-passed reads + QC-failed reads)"
  shared: true
samtools/idxstats:
  fn: "*idxstat*"
samtools/rmdup:
  contents: "[bam_rmdup"
  shared: true
sargasso:
  fn: "overall_filtering_summary.txt"
sentieon/alignment_metrics:
  contents: "--algo AlignmentStat"
  shared: true
sentieon/insertsize:
  contents: "--algo InsertSizeMetricAlgo"
  shared: true
sentieon/gcbias:
  contents: "--algo GCBias"
  shared: true
seqyclean:
  fn: "*_SummaryStatistics.tsv"
sexdeterrmine:
  fn: "sexdeterrmine.json"
sickle:
  contents_re: 'FastQ \w*\s?records kept: .*'
  num_lines: 2
skewer:
  contents: "maximum error ratio allowed (-r):"
  shared: true
slamdunk/summary:
  contents: "# slamdunk summary"
  num_lines: 1
slamdunk/PCA:
  contents: "# slamdunk PCA"
  num_lines: 1
slamdunk/rates:
  contents: "# slamdunk rates"
  num_lines: 1
slamdunk/utrrates:
  contents: "# slamdunk utrrates"
  num_lines: 1
slamdunk/tcperreadpos:
  contents: "# slamdunk tcperreadpos"
  num_lines: 1
slamdunk/tcperutrpos:
  contents: "# slamdunk tcperutr"
  num_lines: 1
snippy/snippy:
  contents: "snippy"
  num_lines: 20
snippy/snippy-core:
  contents_re: 'ID\tLENGTH\tALIGNED\tUNALIGNED\tVARIANT\tHET\tMASKED\tLOWCOV'
  num_lines: 1
snpeff:
  contents: "SnpEff_version"
  max_filesize: 5000000
snpsplit/old:
  contents: "Writing allele-flagged output file to:"
  num_lines: 2
snpsplit/new:
  fn: "*SNPsplit_report.yaml"
sortmerna:
  contents: "Minimal SW score based on E-value"
  shared: true
stacks/gstacks:
  fn: "gstacks.log.distribs"
  contents: "BEGIN effective_coverages_per_sample"
stacks/populations:
  fn: "populations.log.distribs"
  contents: "BEGIN missing_samples_per_loc_prefilters"
stacks/sumstats:
  fn: "*.sumstats_summary.tsv"
  contents: "# Pop ID	Private	Num_Indv	Var	StdErr	P	Var"
  max_filesize: 1000000
star:
  fn: "*Log.final.out"
star/genecounts:
  fn: "*ReadsPerGene.out.tab"
supernova/report:
  fn: "*report*.txt"
  num_lines: 100
  contents: "- assembly checksum ="
supernova/summary:
  fn: "summary.json"
  num_lines: 120
  contents: '"lw_mean_mol_len":'
supernova/molecules:
  fn: "histogram_molecules.json"
  num_lines: 10
  contents: '"description": "molecules",'
supernova/kmers:
  fn: "histogram_kmer_count.json"
  num_lines: 10
  contents: '"description": "kmer_count",'
theta2:
  fn: "*.BEST.results"
tophat:
  fn: "*align_summary.txt"
  shared: true
trimmomatic:
  contents: "Trimmomatic"
  shared: true
umitools:
  contents: "# UMI-tools version:"
  num_lines: 3
varscan2/mpileup2snp:
  contents: "Only SNPs will be reported"
  num_lines: 3
varscan2/mpileup2indel:
  contents: "Only indels will be reported"
  num_lines: 3
varscan2/mpileup2cns:
  contents: "Only variants will be reported"
  num_lines: 3
vcftools/relatedness2:
  fn: "*.relatedness2"
vcftools/tstv_by_count:
  fn: "*.TsTv.count"
vcftools/tstv_by_qual:
  fn: "*.TsTv.qual"
vcftools/tstv_summary:
  fn: "*.TsTv.summary"
vep/vep_html:
  fn: "*.html"
  contents: "VEP summary"
  num_lines: 10
  max_filesize: 1000000
vep/vep_txt:
  contents: "[VEP run statistics]"
  num_lines: 1
  max_filesize: 100000
verifybamid/selfsm:
  fn: "*.selfSM"
whatshap/stats:
  contents: "#sample	chromosome	file_name	variants	phased	unphased	singletons"
  num_lines: 1