IMPROVE: add conda pragma into all rules and docler path for use with --singularity option

Snakefile

 configfile: "config.yaml"
 
+container: "docker://continuumio/miniconda3:4.4.10"
+
 rule all: 
 	input:
 		config['finalPrefix']+'_HC.gff3',

rules/bedtoolsClosest.smk

 rule selectMappedISBP:
 	message: " Select only mapped ISBPS on new refseq"
+	conda: "envs/environment.yml"
 	input: mapped=config['results']+'/1.filteredISBPs/{chrom}/sorted.bed',
 		 original=config['isbpBed']
 	output: config['results']+'/2.mappedISBPs/{chrom}/coordsOnQuery.bed'
@@ -12,6 +13,7 @@ rule selectMappedISBP:
 
 rule keepMappedOnSameChrom:
 	message: " Select Mapped ISBPs on same chromosome (or on unknown chromosome)"
+	conda: "envs/environment.yml"
 	input: isbpOnQuery=config['results']+'/2.mappedISBPs/{chrom}/coordsOnQuery.bed', 
 		isbpOnTarget=config['results']+'/1.filteredISBPs/{chrom}/sorted.bed',
 	output: config['results']+'/2.mappedISBPs/{chrom}/OnSameChrom.bed'
@@ -23,6 +25,7 @@ rule keepMappedOnSameChrom:
 
 rule upstreamClosest:
 	message: " Collect closest marker upstream of genes"
+	conda: "envs/environment.yml"
 	input: annot=config['results']+"/1.features/{chrom}.bed", 
 		markers=config['results']+'/2.mappedISBPs/{chrom}/OnSameChrom.bed'
 	output: config['results']+'/2.closestbed/{chrom}/upstream.txt'
@@ -34,6 +37,7 @@ rule upstreamClosest:
 
 rule downstreamClosest:
 	message: " Collect Downstream marker downstream of genes"
+	conda: "envs/environment.yml"
 	input: annot=config['results']+"/1.features/{chrom}.bed", 
 			markers=config['results']+'/2.mappedISBPs/{chrom}/OnSameChrom.bed'
 	output: config['results']+'/2.closestbed/{chrom}/downstream.txt'
@@ -45,6 +49,7 @@ rule downstreamClosest:
 
 # rule splitPerChrom:
 # 	message: "Split data per chromosome"
+	conda: "envs/environment.yml"
 # 	input: 
 # 		upstream=config['results']+'/2.closestbed/{chrom}/upstream.txt',
 # 		downstream=config['results']+'/2.closestbed/{chrom}/downstream.txt'

rules/checkCds.smk

 rule validateCdsHC:
 	message: " check CDS integrity for HC genes"
+	conda: "envs/environment.yml"
 	input: config['finalPrefix']+'_HC.cds.fasta'
 	output: fasta=config['finalPrefix']+'_HC.cds.valid.fasta',
 		csv=config['finalPrefix']+'_HC.cds.valid.explained.txt'
@@ -10,6 +11,7 @@ rule validateCdsHC:
 
 rule validateCdsLC:
 	message: " check CDS integrity for LC genes"
+	conda: "envs/environment.yml"
 	input: config['finalPrefix']+'_LC.cds.fasta'
 	output: fasta=config['finalPrefix']+'_LC.cds.valid.fasta',
 		csv=config['finalPrefix']+'_LC.cds.valid.explained.txt'

rules/geneAnchoring.smk

 rule mapHomologousRegions:
 	message: " mapping homologous regions of both references using ISBPs markers as anchors for chromosome {wildcards.chrom}"
+	conda: "envs/environment.yml"
 	input:
 		#closestMarkers=config['results']+'/2.mergedClosestMarkers.txt',
 		marker5prime=config['results']+'/2.closestbed/{chrom}/upstream.txt',
@@ -22,6 +23,7 @@ rule mapHomologousRegions:
 
 rule recalcBlatMapped:
 	message: " Recalc the coordinates of genes mapped with the Blat pipeline for chromosome {wildcards.chrom}"
+	conda: "envs/environment.yml"
 	input:
 		allBlat=config['results']+'/3.mapping/{chrom}/allBlat.csv',
 		summary=config['results']+'/3.mapping/{chrom}/mappingSummary.csv',
@@ -41,6 +43,7 @@ rule recalcBlatMapped:
 
 rule gtCleanBlatGff:
 	message: " Clean the gff file recalculated based on Blat fine mapping for chromosome {wildcards.chrom}"
+	conda: "envs/environment.yml"
 	input: gff=config['results']+'/4.recalcBlat/{chrom}/RecalcAnnotOnTarget.gff3',
 		mapping=config['results']+'/3.mapping/{chrom}/temp'
 	output: config['results']+'/4.recalcBlat/{chrom}/RecalcAnnotOnTarget-clean.gff3'
@@ -52,6 +55,7 @@ rule gtCleanBlatGff:
 
 rule gmapRescue:
 	message: " Rescue anchoring of failed genes with gmap for chrom {wildcards.chrom}"
+	conda: "envs/environment.yml"
 	input: blat=config['results']+'/3.mapping/{chrom}/allBlat.csv',
 		wholeGenomeFasta=config['targetFasta'],
 		mapping=config['results']+'/3.mapping/{chrom}/temp'
@@ -71,6 +75,7 @@ rule gmapRescue:
 
 rule recalcGmapRescue:
 	message: "Recalc the coordinates of the GMAP on target GFF3 files for chromosome {wildcards.chrom}"
+	conda: "envs/environment.yml"
 	input: gff=config['results']+'/4.gmapRescue/{chrom}.target.gff3',
 		mapping=config['results']+'/3.mapping/{chrom}/temp'
 	output: config['results']+'/4.recalcGmap/{chrom}/recalc.gff3'
@@ -84,6 +89,7 @@ rule recalcGmapRescue:
 
 rule saveGmapWG:
 	message: "Save the GMAP results of genes mapped on Whole Genome"
+	conda: "envs/environment.yml"
 	input: gff=config['results']+'/4.gmapRescue/{chrom}.wholeGenome.gff3',
 		map=config['chromMapID'],
 		mapping=config['results']+'/3.mapping/{chrom}/temp'
@@ -99,6 +105,7 @@ rule saveGmapWG:
 
 rule mergeFinalGff3:
 	message: " Merge Final GFF3 files: blat.gff3, rescue.gff3 and wholeGenome.gff3"
+	conda: "envs/environment.yml"
 	input: blat=config['results']+'/4.recalcBlat/{chrom}/RecalcAnnotOnTarget-clean.gff3',
 		rescue=config['results']+'/4.recalcGmap/{chrom}/recalc.gff3',
 		wg=config['results']+'/4.gmapWholeGenome/{chrom}.wholeGenome.gff3',
@@ -110,7 +117,8 @@ rule mergeFinalGff3:
 		gt gff3 -sort -fixregionboundaries -tidy -retainids {input.blat} {input.rescue} {input.wg} 1> {output.annot} 2> {log.annot}
 		"""
 rule checkMissing:
-	message: ""
+	message: " Check missing transfered genes"
+	conda: "envs/environment.yml"
 	input: gff=config['results']+'/5.FINAL/{chrom}/annotation.gff3',
 		ref=config['results']+"/1.features/{chrom}.bed"
 	output: config['results']+'/5.FINAL/{chrom}/missing.txt'
@@ -122,6 +130,7 @@ rule checkMissing:
 
 rule concatAllChromResults:
 	message: " concat all per chromosome results"
+	conda: "envs/environment.yml"
 	input: annot=expand(config['results']+'/5.FINAL/{chrom}/annotation.gff3',chrom=config['chromosomes']),
 		differentChrom=expand(config['results']+'/4.gmapWholeGenome/{chrom}.wholeGenome_differentChrom.txt',chrom=config['chromosomes']),
 		missing=expand(config['results']+'/5.FINAL/{chrom}/missing.txt', chrom=config['chromosomes']),
@@ -139,6 +148,7 @@ rule concatAllChromResults:
 
 rule renameGeneIds:
 	message: " set final gene IDs for the new annotation"
+	conda: "envs/environment.yml"
 	input: gff=config['finalPrefix']+'tmp.gff3',
 		map=config['chromMapID']
 	output: gffhc=config['finalPrefix']+'_HC.gff3',
@@ -154,6 +164,7 @@ rule renameGeneIds:
 
 rule generateFastaSequencesHC:
 	message: "generate fasta sequences using gffread for HC genes"
+	conda: "envs/environment.yml"
 	input: gff=config['finalPrefix']+'_HC.gff3',
 		fastaref=config['targetFasta']
 	output: mrna=config['finalPrefix']+'_HC.transcripts.fasta',
@@ -166,6 +177,7 @@ rule generateFastaSequencesHC:
 		"""
 rule generateFastaSequencesLC:
 	message: "generate fasta sequences using gffread for LC genes"
+	conda: "envs/environment.yml"
 	input:
 		gff=config['finalPrefix']+'_LC.gff3',
 		fastaref=config['targetFasta']
@@ -180,6 +192,7 @@ rule generateFastaSequencesLC:
 
 rule concatblatSummary:
 	message: " Concat all Blat summary"
+	conda: "envs/environment.yml"
 	input:blat=expand(config['results']+'/3.mapping/{chrom}/allBlat.csv', chrom=config['chromosomes']),
 		mapping=expand(config['results']+'/3.mapping/{chrom}/temp', chrom=config['chromosomes'])
 	output: config['finalPrefix']+'_blatSummary.csv'
@@ -190,6 +203,7 @@ rule concatblatSummary:
 
 rule concatAnchoringSummary:
 	message: " Concat all Anchoring summary"
+	conda: "envs/environment.yml"
 	input:anchoring=expand(config['results']+'/3.mapping/{chrom}/mappingSummary.csv', chrom=config['chromosomes']),
 		mapping=expand(config['results']+'/3.mapping/{chrom}/temp', chrom=config['chromosomes'])
 	output: config['finalPrefix']+'_anchoringSummary.csv'

rules/preprocessGenomes.smk

 rule grepGffFeature:
-        message: " Collect selected features from GFF file"
-        input: config['annotationQuery']
-        params: config['featureType']
-        output: temp(config['results']+"/1.features.bed")
-        log: config['results']+"/1.grepGffFeature.log"
-        shell: "bin/gff2bed.sh {params} {input} 1> {output} 2> {log}"
+    message: " Collect selected features from GFF file"
+	conda: "envs/environment.yml"
+    input: config['annotationQuery']
+    params: config['featureType']
+    output: temp(config['results']+"/1.features.bed")
+    log: config['results']+"/1.grepGffFeature.log"
+    shell: "bin/gff2bed.sh {params} {input} 1> {output} 2> {log}"
 
 rule splitGffPerChrom:
-        message: "Split Gff Features per chromosome: current is {wildcards.chrom}"
-        input: config['results']+"/1.features.bed"
-        output: temp(config['results']+"/1.features/{chrom}.bed")
-        log: config['results']+"/1.features/{chrom}.fgrep.log"
-        params: "chr{chrom}"
-        shell:  "fgrep -i {params} {input} 1> {output} 2> {log}"
+    message: "Split Gff Features per chromosome: current is {wildcards.chrom}"
+	conda: "envs/environment.yml"
+    input: config['results']+"/1.features.bed"
+    output: temp(config['results']+"/1.features/{chrom}.bed")
+    log: config['results']+"/1.features/{chrom}.fgrep.log"
+    params: "chr{chrom}"
+    shell:  "fgrep -i {params} {input} 1> {output} 2> {log}"
 
 rule indexQuery:
 	message: " Indexing Query fasta file using samtools faidx"
+	conda: "envs/environment.yml"
 	input: config['queryFasta']
 	output: config['queryFasta']+'.fai'
 	shell: "samtools faidx {input}"
 
 rule indexTarget:
 	message: " Indexing Target fasta file using samtools faidx"
+	conda: "envs/environment.yml"
 	input: config['targetFasta']
 	output: config['targetFasta']+'.fai'
 	shell: "samtools faidx {input}"
 
 rule gmapIndexTarget:
 	message: " Create Gmap Index for rescue"
+	conda: "envs/environment.yml"
 	input: config['targetFasta']
 	output: directory(config['results']+"/target_gmapindex")
 	params: indexname="target_gmapindex", indexPath=config['results']

rules/preprocessISBP.smk

 rule filterBam:
 	message: "Filtering BAM file of ISBPs"
+	conda: "envs/environment.yml"
 	input: config['isbpBam']
 	output: config['results']+'/1.filteredISBPs.bam'
 	params: mapq=config['mapq'], mismatches=config['mismatches']
@@ -8,6 +9,7 @@ rule filterBam:
 
 rule bam2bed:
 	message: "Convert Filtered BAM file into BED"
+	conda: "envs/environment.yml"
 	input: config['results']+"/1.filteredISBPs.bam"
 	output: config['results']+"/1.filteredISBPs/{chrom}/sorted.bed"
 	log: config['results']+"/1.filteredISBPs/{chrom}/sorted.log"
@@ -17,12 +19,14 @@ rule bam2bed:
 
 #rule dumpISBPsID:
 #	message: "Dump ISBPs IDs"
+	conda: "envs/environment.yml"
 #	input: config['results']+"/1.filteredISBPs.bed"
 #	output: config['results']+"/1.filteredISBPs.ids"
 #	shell: " cut -f 4 {input} > {output}"
 
 #rule splitISBP:
 #	message: "Split isbps per chromosome"
+	conda: "envs/environment.yml"
 #	input: config['results']+"/1.filteredISBPs.bed"
 #	output: config['results']+"/1.filteredISBPs/{chrom}/sorted.bed"
 #	log: config['results']+"/1.filteredISBPs/{chrom}/sorted.log"