integrate completed rules into workflow

- Rules now integrated include #7, #8, #9, #10, #11, #12, #13, #14, #15, #16, #17 - Applies both for single-end and paired-end subworkflows - DAG image updated - Test sample tables and outcomes updated - Unused preprocessing subworkflow removed Closes #48 Closes #6

integrate completed rules into workflow
ca9a2bb4 · BIOPZ-Iborra de Toledo Paula · Alex Kanitz · d5c96d88 · ca9a2bb4 · ca9a2bb4
Commit ca9a2bb4 authored 5 years ago by BIOPZ-Iborra de Toledo Paula Committed by Alex Kanitz 5 years ago
--- a/.gitignore
+++ b/.gitignore
@@ -326,7 +326,9 @@ pip-selfcheck.json
 # Custom additions
 .vscode
 .DS_Store
-snakemake/.*
 runs/.*
 !runs/PUT_YOUR_WORKFLOW_RUN_CONFIGS_HERE
+._.DS_Store
 .snakemake/
+logs/
+results/
--- a/images/workflow_dag.svg
+++ b/images/workflow_dag.svg
--- a/snakemake/Snakefile
+++ b/snakemake/Snakefile
@@ -27,18 +27,29 @@ include: 'single_end.snakefile.smk'

 rule finish:
 	input:
-		outdir1 = expand(os.path.join(config["output_dir"], "paired_end", "{sample}", "mate1_fastqc"), sample=samples_table.index.values),
-		outdir2 = expand(os.path.join(config["output_dir"], "paired_end", "{sample}", "mate2_fastqc"), sample=samples_table.index.values),
-		reads1 = expand(os.path.join(config["output_dir"], "paired_end", "{sample}", "{sample}.remove_polya_mate1.fastq.gz"), sample=samples_table.index.values)
-		
-
+		outdir1 = expand(os.path.join(config["output_dir"], "{seqmode}", "{sample}", "mate1_fastqc"),
+			zip,
+			sample= [i for i in list(samples_table.index.values)], 
+			seqmode= [samples_table.loc[i,"seqmode"] for i in list(samples_table.index.values)]),
+		bai_index_map = expand(os.path.join(config["output_dir"], "{seqmode}", "{sample}", "map_genome", "{sample}_Aligned.sortedByCoord.out.bam.bai"),
+			zip,
+			sample= [i for i in list(samples_table.index.values)], 
+			seqmode= [samples_table.loc[i,"seqmode"] for i in list(samples_table.index.values)]), 
+		salmon_gn_estimates = expand(os.path.join(config["output_dir"],"{seqmode}","{sample}","salmon_quant","quant.genes.sf"),
+			zip,
+			sample= [i for i in list(samples_table.index.values)], 
+			seqmode= [samples_table.loc[i,"seqmode"] for i in list(samples_table.index.values)]),
+		pseudoalignment = expand(os.path.join(config["output_dir"],"{seqmode}","{sample}","quant_kallisto", "{sample}.kallisto.pseudo.sam"),
+			zip,
+			sample= [i for i in list(samples_table.index.values)], 
+			seqmode= [samples_table.loc[i,"seqmode"] for i in list(samples_table.index.values)]),


 rule create_index_star:
 	''' Create index using STAR'''
 	input:
-		genome = lambda wildcards: samples_table.loc[wildcards.sample, 'genome'],
-		gtf = lambda wildcards: samples_table.loc[wildcards.sample, 'gtf']
+		genome =lambda wildcards: samples_table["genome"][samples_table["organism"]==wildcards.organism][0],
+		gtf =lambda wildcards: samples_table["gtf"][samples_table["organism"]==wildcards.organism][0]
 	output:
 		chromosome_info = os.path.join(
 			config["star_indexes"],
@@ -63,8 +74,7 @@ rule create_index_star:
 				"{organism}",
 				"{index_size}",
 				"STAR_index/STAR_"),
-		sjdbOverhang = lambda wildcards:
-			samples_table[wildcards.sample, "index_size"],
+		sjdbOverhang = "{index_size}"
 	singularity:
 		"docker://zavolab/star:2.6.0a"
 	threads: 12
@@ -86,46 +96,44 @@ rule create_index_star:
 rule create_index_salmon:
 	'''Create index for salmon quantification'''
 	input:
-		transcriptome = lambda wildcards:
-			samples_table.loc[wildcards.sample, 'tr_fasta_filtered']
+		transcriptome = lambda wildcards: samples_table['tr_fasta_filtered'][samples_table["organism"]==wildcards.organism][0]
 	output:
-		index = os.path.join(
+		index = directory(os.path.join(
 			config["salmon_indexes"],
 			"{organism}",
-			"salmon.idx")
+			"{kmer}",
+			"salmon.idx"))
+
 	params:
-		kmerLen = lambda wildcards:
-			samples_table.loc[wildcards.sample, 'kmer']
+		kmerLen = "{kmer}"
 	singularity:
 		"docker://zavolab/salmon:0.11.0"
 	log:
-		os.path.join(config["local_log"], "{organism}_create_index_salmon.log")
+		os.path.join(config["local_log"], "{organism}_{kmer}_create_index_salmon.log")
 	threads:	8
 	shell:
 		"(salmon index \
-		--t {input.transcriptome} \
-		--i {output.index} \
-		--k {params.kmerLen} \
+		--transcripts {input.transcriptome} \
+		--index {output.index} \
+		--kmerLen {params.kmerLen} \
 		--threads {threads}) &> {log}"


 rule create_index_kallisto:
 	'''Create index for running Kallisto'''
 	input:
-		transcriptome = lambda wildcards:
-			samples_table.loc[wildcards.sample, 'tr_fasta_filtered']
+		transcriptome = lambda wildcards: samples_table['tr_fasta_filtered'][samples_table["organism"]==wildcards.organism][0]
 	output:
 		index = os.path.join(
 				config["kallisto_indexes"],
 				"{organism}",
 				"kallisto.idx")
 	params:
-		output_dir = lambda wildcards:
-			os.path.join(
+		output_dir = os.path.join(
 				config["kallisto_indexes"],
-				samples_table[wildcards.sample, 'organism'])
+				"{organism}")
 	singularity:
-		"docker://zavolab/kallisto:0.9"
+		"docker://zavolab/kallisto:0.46.1"
 	log:
 		os.path.join(config["local_log"], "{organism}_create_index_kallisto.log")
 	shell:

--- a/snakemake/paired_end.snakefile.smk
+++ b/snakemake/paired_end.snakefile.smk
@@ -6,14 +6,14 @@ rule pe_fastqc:
 		reads1 = lambda wildcards: samples_table.loc[wildcards.sample, "fq1"],
 		reads2 = lambda wildcards: samples_table.loc[wildcards.sample, "fq2"]
 	output:
-		outdir1 = directory(os.path.join(config["output_dir"], "paired_end", "{sample}", "mate1_fastqc")),
-		outdir2 = directory(os.path.join(config["output_dir"], "paired_end", "{sample}", "mate2_fastqc"))
+		outdir1 = directory(os.path.join(config["output_dir"],"paired_end", "{sample}", "mate1_fastqc")),
+		outdir2 = directory(os.path.join(config["output_dir"],"paired_end", "{sample}", "mate2_fastqc"))
 	threads:
 		2
 	singularity:
 		"docker://zavolab/fastqc:0.11.8"
 	log:
-		os.path.join(config["local_log"], "paired_end", "{sample}", "fastqc.log")
+		os.path.join(config["local_log"],"paired_end", "{sample}", "fastqc.log")
 	shell:
 		"(mkdir -p {output.outdir1}; \
 		mkdir -p {output.outdir2}; \
@@ -127,8 +127,8 @@ rule pe_map_genome_star:
 		index = lambda wildcards:
 			os.path.join(
 				config["star_indexes"],
-				samples_table.loc[wildcards.sample, "organism"],
-				samples_table.loc[wildcards.sample, "index_size"],
+				str(samples_table.loc[wildcards.sample, "organism"]),
+				str(samples_table.loc[wildcards.sample, "index_size"]),
 				"STAR_index",
 				"chrNameLength.txt"),
 		reads1 = os.path.join(
@@ -159,7 +159,8 @@ rule pe_map_genome_star:
 		index = lambda wildcards:
 			os.path.join(
 				config["star_indexes"],
-				samples_table.loc[wildcards.sample, "index_size"],
+				str(samples_table.loc[wildcards.sample, "organism"]),
+				str(samples_table.loc[wildcards.sample, "index_size"]),
 				"STAR_index"),
 		outFileNamePrefix = os.path.join(
 			config["output_dir"],
@@ -168,7 +169,7 @@ rule pe_map_genome_star:
 			"map_genome",
 			"{sample}_"),
 		multimappers = lambda wildcards:
-			samples_table.loc[wildcards.sample, "mulitmappers"],
+			str(samples_table.loc[wildcards.sample, "multimappers"]),
 		soft_clip = lambda wildcards:
 			samples_table.loc[wildcards.sample, "soft_clip"],
 		pass_mode = lambda wildcards:
@@ -202,8 +203,8 @@ rule pe_map_genome_star:
 		--outFilterMatchNminOverLread 0.3 \
 		--outFilterType BySJout \
 		--outReadsUnmapped None \
-		--outSAMattrRGline ID:rnaseq_pipeline SM:{params.sample} \
-		--alignEndsType {params.soft_clip}} > {output.bam};) &> {log}"
+		--outSAMattrRGline ID:rnaseq_pipeline SM:{params.sample_id} \
+		--alignEndsType {params.soft_clip} > {output.bam};) &> {log}"


 rule pe_index_genomic_alignment_samtools:
@@ -249,7 +250,8 @@ rule pe_quantification_salmon:
 		index = lambda wildcards:
 			os.path.join(
 				config["salmon_indexes"],
-				samples_table.loc[wildcards.sample, 'organism'],
+				str(samples_table.loc[wildcards.sample, "organism"]),
+				str(samples_table.loc[wildcards.sample, "kmer"]),
 				"salmon.idx")
 	output:		
 		gn_estimates = os.path.join(
@@ -317,16 +319,15 @@ rule pe_genome_quantification_kallisto:
 			"quant_kallisto",
 			"{sample}.kallisto.pseudo.sam")
 	params:
-		output_dir = lambda wildcards:
-			os.path.join(
+		output_dir = os.path.join(
 				config["output_dir"],
 				"paired_end",
-				wildcards.sample,
+				"{sample}",
 				"quant_kallisto"),
 		directionality = lambda wildcards:
 			samples_table.loc[wildcards.sample, "kallisto_directionality"]
 	singularity:
-		"docker://zavolab/kallisto:0.9"
+		"docker://zavolab/kallisto:0.46.1"
 	threads:	8
 	log:
 		os.path.join(config["local_log"], "paired_end", "{sample}", "genome_quantification_kallisto.log")

--- a/snakemake/preprocessing.snakefile.smk
+++ b/snakemake/preprocessing.snakefile.smk
-
-
-rule index_genome_STAR:
-    '''
-    Create Star index
-    '''
-	input:
-		genome = os.path.join(config["output_dir"], "genome.fa"),
-		annotation = os.path.join(config["output_dir"], "annotation.gtf")
-	output:
-		output = os.path.join(config["database_path"], config['organism'], config['STAR_idx_folder], "STAR_index" + {sjdb})
-	params:
-		outputdir = os.path.join(config["output_dir"],"STAR_index"),
-		sjdb = lambda wildcards: samples.loc['sjdb']
-	threads:	8
-	singularity:
-		"docker://zavolab/star:2.6.0a"
-	log:
-		os.path.join(config["local_log"],"index_genome_STAR.log")
-	shell:
-		"mkdir -p {output.output}; \
-		chmod -R 777 {output.output}; \
-		(STAR --runMode genomeGenerate \
-		--sjdbOverhang {params.sjdbOverhang} \
-		--genomeDir {params.outputdir} \
-		--genomeFastaFiles {input.genome} \
-		--runThreadN {threads} \
-		--sjdbGTFfile {input.annotation}) &> {log}"
\ No newline at end of file
--- a/snakemake/single_end.snakefile.smk
+++ b/snakemake/single_end.snakefile.smk
@@ -4,7 +4,9 @@ rule fastqc:
 	input:
 		reads = lambda wildcards: samples_table.loc[wildcards.sample, "fq1"],
 	output:
-		outdir = directory(os.path.join(config["output_dir"], "single_end", "{sample}", "fastqc"))
+		outdir = directory(os.path.join(config["output_dir"], "single_end", "{sample}", "mate1_fastqc"))
+	params:
+		seqmode= lambda wildcards: samples_table.loc[wildcards.sample, "seqmode"]
 	singularity:
 		"docker://zavolab/fastqc:0.11.8"
 	log:
@@ -21,7 +23,7 @@ rule remove_adapters_cutadapt:
 	input:
 		reads = lambda wildcards: samples_table.loc[wildcards.sample, "fq1"]
 	output:
-		reads = os.path.join(config["output_dir"], "single_end", "{sample}", "{sample}.remove_adapters.fastq.gz")
+		reads = os.path.join(config["output_dir"], "single_end", "{sample}", "{sample}.remove_adapters_mate1.fastq.gz")
 	params:
 		adapters_3 = lambda wildcards: 
 			samples_table.loc[wildcards.sample, 'fq1_3p'],
@@ -34,7 +36,7 @@ rule remove_adapters_cutadapt:
 	log:
 		os.path.join(config["local_log"], "single_end", "{sample}", "remove_adapters_cutadapt.log")
 	shell:
-		"cutadapt \
+		"(cutadapt \
 		-e 0.1 \
 		-O 1 \
 		-j {threads} \
@@ -49,9 +51,9 @@ rule remove_adapters_cutadapt:
 rule remove_polya_cutadapt:
 	''' Remove ployA  tails'''
 	input:
-		reads = lambda wildcards: samples_table[wildcards.sample, "fq1"]
+		reads = os.path.join(config["output_dir"], "single_end", "{sample}", "{sample}.remove_adapters_mate1.fastq.gz")
 	output:
-		reads = os.path.join(config["output_dir"], "single_end", "{sample}", "{sample}.remove_polya.fastq.gz")
+		reads = os.path.join(config["output_dir"], "single_end", "{sample}", "{sample}.remove_polya_mate1.fastq.gz")
 	params:
 		polya_3 = lambda wildcards: 
 			samples_table.loc[wildcards.sample, "fq1_polya"]
@@ -80,10 +82,10 @@ rule map_genome_star:
 		index = lambda wildcards:
 			os.path.join(
 				config["star_indexes"],
-				samples_table.loc[wildcards.sample, "organism"],
-				samples_table.loc[wildcards.sample, "index_size"], 
+				str(samples_table.loc[wildcards.sample, "organism"]),
+				str(samples_table.loc[wildcards.sample, "index_size"]), 
 				"STAR_index","chrNameLength.txt"),
-		reads = os.path.join(config["output_dir"], "single_end", "{sample}", "{sample}.remove_polya.fastq.gz")
+		reads = os.path.join(config["output_dir"], "single_end", "{sample}", "{sample}.remove_polya_mate1.fastq.gz")
 	output:
 		bam = os.path.join(config["output_dir"], "single_end", 
 			"{sample}", 
@@ -96,16 +98,15 @@ rule map_genome_star:
 	params:
 		sample_id = "{sample}",
 		index = lambda wildcards:
-				os.path.join(
-					config["star_indexes"],
-					samples_table.loc["{sample}", "organism"],
-					samples_table.loc[wildcards.sample, "index_size"], 
-					"STAR_index"),
-		outFileNamePrefix = lambda wildcards:
-				os.path.join(
-					config["output_dir"], 
-					"single_end", 
-					"{sample}", "map_genome", "{sample}_"),
+			os.path.join(
+				config["star_indexes"],
+				str(samples_table.loc[wildcards.sample, "organism"]),
+				str(samples_table.loc[wildcards.sample, "index_size"]), 
+				"STAR_index"),
+		outFileNamePrefix = os.path.join(
+				config["output_dir"], 
+				"single_end", 
+				"{sample}", "map_genome", "{sample}_"),
 		multimappers = lambda wildcards:
 				samples_table.loc[wildcards.sample, "multimappers"],
 		soft_clip = lambda wildcards:
@@ -138,7 +139,7 @@ rule map_genome_star:
 		--outFilterType BySJout \
 		--outReadsUnmapped None \
 		--outSAMattrRGline ID:rcrunch SM:{params.sample_id} \
-		--alignEndsType {params.soft_clip}} > {output.bam};) &> {log}"
+		--alignEndsType {params.soft_clip} > {output.bam};) &> {log}"


 rule index_genomic_alignment_samtools:
@@ -171,11 +172,12 @@ rule quantification_salmon:
 			config["output_dir"], 
 			"single_end", 
 			"{sample}", 
-			"{sample}.remove_polya.fastq.gz"),
+			"{sample}.remove_polya_mate1.fastq.gz"),
 		index = lambda wildcards:
 			os.path.join(
 				config["salmon_indexes"],
-				samples_table[wildcards.sample, 'organism'],
+				str(samples_table.loc[wildcards.sample, "organism"]),
+				str(samples_table.loc[wildcards.sample, "kmer"]),
 				"salmon.idx"),
 	   	gtf = lambda wildcards: samples_table.loc[wildcards.sample, "gtf_filtered"]
 	output:
@@ -202,8 +204,8 @@ rule quantification_salmon:
 	log:
 		os.path.join(config["local_log"], "single_end", "{sample}", "quantification_salmon.log")
 	threads:    12
-	conda:
-		"envs/salmon.yaml"
+	singularity:
+		"docker://zavolab/salmon:0.11.0"
 	shell:
 		"(salmon quant \
 		--libType {params.libType} \
@@ -224,7 +226,7 @@ rule genome_quantification_kallisto:
 			config["output_dir"], 
 			"single_end", 
 			"{sample}", 
-			"{sample}.remove_polya.fastq.gz"),
+			"{sample}.remove_polya_mate1.fastq.gz"),
 		index = lambda wildcards:
 			os.path.join(
 				config["kallisto_indexes"],
@@ -235,10 +237,10 @@ rule genome_quantification_kallisto:
 			config["output_dir"], 
 			"single_end", 
 			"{sample}", 
+			"quant_kallisto",
 			"{sample}.kallisto.pseudo.sam")
 	params:
-		output_dir = lambda wildcards:
-			os.path.join(
+		output_dir = os.path.join(
 				config["output_dir"], 
 				"single_end", 
 				"{sample}", 
@@ -250,7 +252,7 @@ rule genome_quantification_kallisto:
 	log:
 		os.path.join(config["local_log"],"kallisto_align_{sample}.log")
 	singularity:
-		"docker://zavolab/kallisto:0.9"
+		"docker://zavolab/kallisto:0.46.1"
 	shell:
 		"(kallisto quant \
 		-i {input.index} \
@@ -262,4 +264,4 @@ rule genome_quantification_kallisto:
 		{params.directionality} \
 		{input.reads} > {output.pseudoalignment}) &> {log}"

-		
\ No newline at end of file
+		
--- a/tests/test_create_dag_chart/samples.tsv
+++ b/tests/test_create_dag_chart/samples.tsv
 sample	fq1	fq2	fq1_3p	fq1_5p	fq2_3p	fq2_5p	fq1_polya	fq2_polya	organism	index_size	multimappers	soft_clip	pass_mode	gtf_filtered	libtype	kallisto_directionality	mean	sd	genome	gtf	tr_fasta_filtered	kmer	seqmode
-HNRNPC_control_rep1	input_files/GSM1502498_1.fastq.gz	input_files/GSM1502498_2.fastq.gz	AGATCGGAAGAGCACA	XXXXXXXX	AGATCGGAAGAGCGT	XXXXXXXX	AAAAAAAAAAAAAAAAAAAA	TTTTTTTTTTTTTTTTTTT	homo_sapiens	100	10	Local	Basic	input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	A	kallisto_directionality	250	100	input_files/Homo_sapiens.GRCh38.dna_sm.primary_assembly.chrom_22.fa	input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	input_files/transcripts_chrom_22.fa	31	fr
-HNRNPC_KD_rep1	input_files/GSM1502500_1.fastq.gz	input_files/GSM1502500_2.fastq.gz	AGATCGGAAGAGCACA	XXXXXXXX	AGATCGGAAGAGCGT	XXXXXXXX	AAAAAAAAAAAAAAAAAAAA	TTTTTTTTTTTTTTTTTTT	homo_sapiens	100	10	Local	Basic	input_files/Homo_sapiens.GRCh38.99.chr.filterd.chrom_22.gtf	A	kallisto_directionality	250	100	input_files/Homo_sapiens.GRCh38.dna_sm.primary_assembly.chrom_22.fa	input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	input_files/transcripts_chrom_22.fa	31	fr
+HNRNPC_control_rep1	input_files/GSM1502498_1.fastq.gz	input_files/GSM1502498_2.fastq.gz	AGATCGGAAGAGCACA	XXXXXXXX	AGATCGGAAGAGCGT	XXXXXXXX	AAAAAAAAAAAAAAAAAAAA	TTTTTTTTTTTTTTTTTTT	homo_sapiens	100	10	Local	Basic	../test_integration_workflow/input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	A	kallisto_directionality	250	100	../test_integration_workflow/input_files/Homo_sapiens.GRCh38.dna_sm.primary_assembly.chrom_22.fa	../test_integration_workflow/input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	../test_integration_workflow/input_files/transcripts_chrom_22.fa	31	single_end
+HNRNPC_KD_rep1	input_files/GSM1502500_1.fastq.gz	input_files/GSM1502500_2.fastq.gz	AGATCGGAAGAGCACA	XXXXXXXX	AGATCGGAAGAGCGT	XXXXXXXX	AAAAAAAAAAAAAAAAAAAA	TTTTTTTTTTTTTTTTTTT	homo_sapiens	100	10	Local	Basic	../test_integration_workflow/input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	A	kallisto_directionality	250	100	../test_integration_workflow/input_files/Homo_sapiens.GRCh38.dna_sm.primary_assembly.chrom_22.fa	../test_integration_workflow/input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	../test_integration_workflow/input_files/transcripts_chrom_22.fa	31	paired_end
\ No newline at end of file
--- a/tests/test_integration_workflow/expected_output.md5
+++ b/tests/test_integration_workflow/expected_output.md5
-c45be0333e4d84285d530855342763e0  results/paired_end/HNRNPC_control_rep1/HNRNPC_control_rep1.remove_adapters_mate1.fastq
-e1e0d16add8db1a314c780d497e863c9  results/paired_end/HNRNPC_control_rep1/HNRNPC_control_rep1.remove_polya_mate2.fastq
-a46359f784d3eca4268c788a74789bf2  results/paired_end/HNRNPC_control_rep1/HNRNPC_control_rep1.remove_polya_mate1.fastq
-58ef63f61c82e050f05b871eea8d4b25  results/paired_end/HNRNPC_control_rep1/HNRNPC_control_rep1.remove_adapters_mate2.fastq
+7be61b24952edd765a151a82fa8ad8bb  results/single_end/HNRNPC_control_rep1/HNRNPC_control_rep1.remove_adapters_mate1.fastq
+d41d8cd98f00b204e9800998ecf8427e  results/single_end/HNRNPC_control_rep1/quant_kallisto/HNRNPC_control_rep1.kallisto.pseudo.sam
+efec14c44f708c23a99c5653fc020966  results/single_end/HNRNPC_control_rep1/quant_kallisto/pseudoalignments.bam
+adf0922672c7088138f564d418e2c055  results/single_end/HNRNPC_control_rep1/HNRNPC_control_rep1.remove_polya_mate1.fastq
+6a62e57dc1765f8881bd114a64c69563  results/single_end/HNRNPC_control_rep1/map_genome/HNRNPC_control_rep1_Aligned.sortedByCoord.out.bam
 d3898e6e03d98db65b61172f8275f319  results/paired_end/HNRNPC_KD_rep1/HNRNPC_KD_rep1.remove_adapters_mate2.fastq
+d41d8cd98f00b204e9800998ecf8427e  results/paired_end/HNRNPC_KD_rep1/quant_kallisto/HNRNPC_KD_rep1.kallisto.pseudo.sam
+67fd10e98d6b1b9041c0171b1cea4eb0  results/paired_end/HNRNPC_KD_rep1/quant_kallisto/pseudoalignments.bam
 489e5a5bd92fafe9a79e164fb334e036  results/paired_end/HNRNPC_KD_rep1/HNRNPC_KD_rep1.remove_polya_mate2.fastq
 8a01f7aa476992c2bc32d3457f703865  results/paired_end/HNRNPC_KD_rep1/HNRNPC_KD_rep1.remove_adapters_mate1.fastq
+5c415fd62934c389dfd76abb7e9875c2  results/paired_end/HNRNPC_KD_rep1/map_genome/HNRNPC_KD_rep1_Aligned.sortedByCoord.out.bam
 f048f50b6695c80e2c9d4ecf10c0d0a9  results/paired_end/HNRNPC_KD_rep1/HNRNPC_KD_rep1.remove_polya_mate1.fastq
--- a/tests/test_integration_workflow/samples.tsv
+++ b/tests/test_integration_workflow/samples.tsv
 sample	fq1	fq2	fq1_3p	fq1_5p	fq2_3p	fq2_5p	fq1_polya	fq2_polya	organism	index_size	multimappers	soft_clip	pass_mode	gtf_filtered	libtype	kallisto_directionality	mean	sd	genome	gtf	tr_fasta_filtered	kmer	seqmode
-HNRNPC_control_rep1	input_files/GSM1502498_1.fastq.gz	input_files/GSM1502498_2.fastq.gz	AGATCGGAAGAGCACA	XXXXXXXX	AGATCGGAAGAGCGT	XXXXXXXX	AAAAAAAAAAAAAAAAAAAA	TTTTTTTTTTTTTTTTTTT	homo_sapiens	100	10	Local	Basic	input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	A	kallisto_directionality	250	100	input_files/Homo_sapiens.GRCh38.dna_sm.primary_assembly.chrom_22.fa	input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	input_files/transcripts_chrom_22.fa	31	fr
-HNRNPC_KD_rep1	input_files/GSM1502500_1.fastq.gz	input_files/GSM1502500_2.fastq.gz	AGATCGGAAGAGCACA	XXXXXXXX	AGATCGGAAGAGCGT	XXXXXXXX	AAAAAAAAAAAAAAAAAAAA	TTTTTTTTTTTTTTTTTTT	homo_sapiens	100	10	Local	Basic	input_files/Homo_sapiens.GRCh38.99.chr.filterd.chrom_22.gtf	A	kallisto_directionality	250	100	input_files/Homo_sapiens.GRCh38.dna_sm.primary_assembly.chrom_22.fa	input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	input_files/transcripts_chrom_22.fa	31	fr
+HNRNPC_control_rep1	input_files/GSM1502498_1.fastq.gz	input_files/GSM1502498_2.fastq.gz	AGATCGGAAGAGCACA	XXXXXXXX	AGATCGGAAGAGCGT	XXXXXXXX	AAAAAAAAAAAAAAAAAAAA	TTTTTTTTTTTTTTTTTTT	homo_sapiens	100	10	Local	Basic	input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	A	--fr	250	100	input_files/Homo_sapiens.GRCh38.dna_sm.primary_assembly.chrom_22.fa	input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	input_files/transcripts_chrom_22.fa	31	single_end
+HNRNPC_KD_rep1	input_files/GSM1502500_1.fastq.gz	input_files/GSM1502500_2.fastq.gz	AGATCGGAAGAGCACA	XXXXXXXX	AGATCGGAAGAGCGT	XXXXXXXX	AAAAAAAAAAAAAAAAAAAA	TTTTTTTTTTTTTTTTTTT	homo_sapiens	100	10	Local	Basic	input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	A	--fr	250	100	input_files/Homo_sapiens.GRCh38.dna_sm.primary_assembly.chrom_22.fa	input_files/Homo_sapiens.GRCh38.99.chr.chrom_22.gtf	input_files/transcripts_chrom_22.fa	31	paired_end