Nils Homer nh13

Split a SAM tag value and store in multiple SAM tags

This is motiviated by fulcrumgenomics/fgsv#25 whereby the be tag stores a semi-colon delimited list of break end values, and we want each value to be in their own tag. Supports where the case where the be tag may contain multiple such delimited values, each seperated by a different delimiter (in this case a comma).

python split_sam_tag.py \
  --in-bam fgsv.bam \
  --out-bam split.bam \
 --in-tag be \

Snapshot repository: https://oss.sonatype.org/content/repositories/snapshots/com/fulcrumgenomics/dagr-tasks_2.12/1.1.0-2d84ae1-SNAPSHOT/

Added repositories for in my build.sc:

  def repositories = super.repositories ++ Seq(
    coursier.LocalRepositories.Dangerous.maven2Local,
    MavenRepository("https://oss.sonatype.org/content/repositories/public"),
    MavenRepository("https://oss.sonatype.org/content/repositories/snapshots"),
 MavenRepository("https://jcenter.bintray.com/")

	from collections import defaultdict
	from pathlib import Path
	from typing import Any
	from typing import Callable
	from typing import Dict
	from typing import List
	from typing import Optional

	import snakemake

	# Delimited-data files: no empty columns please
	function columnit { column -t $1 \| less -S; }
	function tabit { column -t -s $'\t' $1 \| less -S; }

	# Delimited-data files: empty columns values are nasty
	function columnit-empty { cat $1 \| sed -E 's_'$'\t'$'\t''_'$'\t''NA'$'\t''_g' \| column -t \| less -S; }
	function tabit-empty { cat $1 \| sed -E 's_'$'\t'$'\t''_'$'\t''NA'$'\t''_g' \| column -t -s $'\t' \| less -S; }

	# Show me the money grep, now
	function grep-nobuff { gstdbuf -o0 grep $@; }

	@HD VN:1.6
	@SQ SN:chr1 LN:249250621 am:1 ga:CM000663.1 sn:1 ra:NC_000001.10 un:chr1 AN:1,CM000663.1,NC_000001.10 sr:assembled-molecule
	@SQ SN:chr2 LN:243199373 am:2 ga:CM000664.1 sn:2 ra:NC_000002.11 un:chr2 AN:2,CM000664.1,NC_000002.11 sr:assembled-molecule
	@SQ SN:chr3 LN:198022430 am:3 ga:CM000665.1 sn:3 ra:NC_000003.11 un:chr3 AN:3,CM000665.1,NC_000003.11 sr:assembled-molecule
	@SQ SN:chr4 LN:191154276 am:4 ga:CM000666.1 sn:4 ra:NC_000004.11 un:chr4 AN:4,CM000666.1,NC_000004.11 sr:assembled-molecule
	@SQ SN:chr5 LN:180915260 am:5 ga:CM000667.1 sn:5 ra:NC_000005.9 un:chr5 AN:5,CM000667.1,NC_000005.9 sr:assembled-molecule
	@SQ SN:chr6 LN:171115067 am:6 ga:CM000668.1 sn:6 ra:NC_000006.11 un:chr6 AN:6,CM000668.1,NC_000006.11 sr:assembled-molecule
	@SQ SN:chr7 LN:159138663 am:7 ga:CM000669.1 sn:7 ra:NC_000007.13 un:chr7 AN:7,CM000669.1,NC_000007.13 sr:assembled-molecule
	@SQ SN:chr8 LN:146364022 am:8 ga:CM000670.1 sn:8 ra:NC_000008.10 un:chr8 AN:8,CM000670.1,NC_000008.10 sr:assembled-molecule
	@SQ SN:chr9 LN:14121343

	@HD VN:1.6 GO:query SO:unsorted SS:unsorted:template-coordinate
	@SQ SN:chr1 LN:248956422 M5:6aef897c3d6ff0c78aff06ac189178dd AS:hg38 UR:ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/405/GCF_000001405.39_GRCh38.p13/GCF_000001405.39_GRCh38.p13_genomic.fna.gz SP:Homo sapiens AN:NC_000001.11,CM000663.2
	@SQ SN:chr2 LN:242193529 M5:f98db672eb0993dcfdabafe2a882905c AS:hg38 UR:ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/405/GCF_000001405.39_GRCh38.p13/GCF_000001405.39_GRCh38.p13_genomic.fna.gz SP:Homo sapiens AN:NC_000002.12,CM000664.2
	@SQ SN:chr3 LN:198295559 M5:76635a41ea913a405ded820447d067b0 AS:hg38 UR:ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/405/GCF_000001405.39_GRCh38.p13/GCF_000001405.39_GRCh38.p13_genomic.fna.gz SP:Homo sapiens AN:NC_000003.12,CM000665.2
	@SQ SN:chr4 LN:190214555 M5:3210fecf1eb92d5489da4346b3fddc6e AS:hg38 UR:ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/405/GCF_000001405.39_GRCh38.p13/GCF_000001405.39_GRCh38.p13_genomic.fna.gz SP:Homo sapiens AN:NC_000004.12,CM00066

	import $ivy.`com.fulcrumgenomics::fgbio:1.1.0`
	import com.fulcrumgenomics.FgBioDef._
	import java.nio.file.{Path, Paths}
	import com.fulcrumgenomics.commons.util.{LazyLogging, Logger}
	import com.fulcrumgenomics.util.ProgressLogger
	import com.fulcrumgenomics.bam.api._
	import htsjdk.samtools.SAMReadGroupRecord


	// So that a [[Path]] can be built from a [[String]] on the command line

	pigz -d -c in.fastq.gz \|
	\| awk 'BEGIN {LN=0; } { if (LN == 1 \|\| LN == 3) { print substr($0, 0, 26) } else { print $0 } ; if (LN == 3) { LN = 0 } else { LN++ } }' \
	\| pigz -c - > out.fastq.gz

	import enum
	from typing import List
	from pathlib import Path


	class Alignment(enum.Enum):
	BWA = 1
	Bowtie = 2

	class VariantCalling(enum.Enum):


	function aws_switch {
	last_profile=$(cat ~/.aws/.last_profile \| xargs)
	last_profile_i=1;
	i=1
	profiles=()
	for profile in $(grep "^\[.*\]$" ~/.aws/credentials \| sed -e 's_^\[__' -e 's_\]$__' \| sort)
	do
	echo "[$i] $profile";
	profiles+=( "$profile" );