3.8.0

.test/makefile

@@ -21,7 +21,9 @@ snakefiles := \
 	"../workflow/rules/picard_dict.smk" \
 	"../workflow/rules/pyfaidx.smk" \
 	"../workflow/rules/pyroe.smk" \
+	"../workflow/rules/salmon_index.smk" \
 	"../workflow/rules/samtools_faidx.smk" \
+	"../workflow/rules/star_index.smk" \
 	"../workflow/rules/tabix.smk" \
 	"../workflow/rules/transcript_to_gene.smk" \
 	"../workflow/rules/ucsc.smk" \

CHANGELOG.md

@@ -1,3 +1,12 @@
+# 3.8.0
+
+## Features:
+
+* STAR indexes
+* Salmon index
+* Genepred file formats
+* Re-use of indexed files
+
 # 3.7.0
 
 ## Fix:

workflow/Snakefile

@@ -11,7 +11,9 @@ include: "rules/gffread.smk"
 include: "rules/picard_dict.smk"
 include: "rules/pyfaidx.smk"
 include: "rules/pyroe.smk"
+include: "rules/salmon_index.smk"
 include: "rules/samtools_faidx.smk"
+include: "rules/star_index.smk"
 include: "rules/tabix.smk"
 include: "rules/transcript_to_gene.smk"
 include: "rules/ucsc.smk"

workflow/rules/common.smk

@@ -288,6 +288,20 @@ def get_gff(
     return lookup_genomes(wildcards, key="gff3", default=default, genomes=genomes)
 
 
+def get_genepred(
+    wildcards: snakemake.io.Wildcards, genomes: pandas.DataFrame = genomes
+) -> str:
+    """
+    Return correct path to genepred file
+    """
+    default: str = (
+        f"reference/annotation/{wildcards.species}.{wildcards.build}.{wildcards.release}/{wildcards.species}.{wildcards.build}.{wildcards.release}.genePred".format(
+            wildcards
+        ),
+    )
+    return lookup_genomes(wildcards, key="genepred", default=default, genomes=genomes)
+
+
 def used_genomes(
     genomes: pandas.DataFrame = genomes, samples: pandas.DataFrame | None = None
 ) -> tuple[str]:
@@ -370,6 +384,10 @@ def get_fair_genome_indexer_target(
             "reference/annotation/{genomes_property}/{genomes_property}.genePred",
             genomes_property=genomes_properties,
         ),
+        "genepred_bed": expand(
+            "reference/annotation/{genomes_property}/{genomes_property}.genePred.bed",
+            genomes_property=genomes_properties,
+        ),
         "bowtie2_index": expand(
             "reference/bowtie2_index/{genomes_property}.{datatype}/{genomes_property}.{datatype}{bt2_ext}",
             genomes_property=genomes_properties,
@@ -383,6 +401,28 @@ def get_fair_genome_indexer_target(
                 ".rev.2.bt2",
             ),
         ),
+        "star_index": expand(
+            "reference/star_index/{genomes_property}.{datatype}",
+            genomes_property=genomes_properties,
+            datatype=("dna", "cdna", "transcripts"),
+        ),
+        "salmon_index": expand(
+            "reference/salmon_index/{genomes_property}/{genomes_property}/{salmon_ext}",
+            genomes_property=genomes_properties,
+            salmon_ext=(
+                "complete_ref_lens.bin",
+                "ctable.bin",
+                "ctg_offsets.bin",
+                "duplicate_clusters.tsv",
+                "info.json",
+                "mphf.bin",
+                "pos.bin",
+                "pre_indexing.log",
+                "rank.bin",
+                "refAccumLengths.bin",
+                "ref_indexing.log",
+            ),
+        ),
     }
 
     # Public blacklist are not available for all genomes

workflow/rules/picard_dict.smk

@@ -12,7 +12,7 @@ for grch38
 
 rule fair_genome_indexer_picard_create_dict:
     input:
-        "reference/sequences/{species}.{build}.{release}/{species}.{build}.{release}.{datatype}.fasta",
+        lambda wildcards: select_fasta(wildcards),
     output:
         "reference/sequences/{species}.{build}.{release}/{species}.{build}.{release}.{datatype}.dict",
     threads: 1

workflow/rules/salmon_index.smk

@@ -0,0 +1,60 @@
+rule fair_genome_indexer_salmon_decoy_sequences:
+    input:
+        transcriptome=lambda wildcards: get_transcripts_fasta(wildcards),
+        genome=lambda wildcards: get_dna_fasta(wildcards),
+    output:
+        gentrome=temp("reference/sequences/{species}.{build}.{release}.gentrome.fasta"),
+        decoys=temp("reference/sequences/{species}.{build}.{release}.decoys.txt"),
+    threads: 2
+    resources:
+        mem_mb=lambda wildcards, attempt: 512 * attempt,
+        runtime=lambda wildcards, attempt: 25 * attempt,
+        tmpdir=tmp,
+    log:
+        "logs/fair_genome_indexer_salmon_decoy_sequences/{species}.{build}.{release}.log",
+    benchmark:
+        "benchmark/fair_genome_indexer_salmon_decoy_sequences/{species}.{build}.{release}.tsv"
+    wrapper:
+        f"{snakemake_wrappers_prefix}/bio/salmon/decoys"
+
+
+rule fair_genome_indexer_salmon_index_gentrome:
+    input:
+        sequences="reference/sequences/{species}.{build}.{release}.gentrome.fasta",
+        decoys="reference/sequences/{species}.{build}.{release}.decoys.txt",
+    output:
+        temp(
+            multiext(
+                "reference/salmon_index/{species}.{build}.{release}/{species}.{build}.{release}/",
+                "complete_ref_lens.bin",
+                "ctable.bin",
+                "ctg_offsets.bin",
+                "duplicate_clusters.tsv",
+                "info.json",
+                "mphf.bin",
+                "pos.bin",
+                "pre_indexing.log",
+                "rank.bin",
+                "refAccumLengths.bin",
+                "ref_indexing.log",
+                "reflengths.bin",
+                "refseq.bin",
+                "seq.bin",
+                "versionInfo.json",
+            )
+        ),
+    threads: 20
+    resources:
+        mem_mb=lambda wildcards, attempt: 48 * 1024 * attempt,
+        runtime=lambda wildcards, attempt: 50 * attempt,
+        tmpdir=tmp,
+    log:
+        "logs/fair_genome_indexer_salmon_index_gentrome/{species}.{build}.{release}.log",
+    benchmark:
+        "benchmark/fair_genome_indexer_salmon_index_gentrome/{species}.{build}.{release}.tsv"
+    params:
+        extra=lookup_config(
+            dpath="params/fair_genome_indexer_salmon_index_gentromee", default=""
+        ),
+    wrapper:
+        f"{snakemake_wrappers_prefix}/bio/salmon/index"

workflow/rules/samtools_faidx.smk

@@ -12,7 +12,7 @@ for grch38
 
 rule fair_genome_indexer_samtools_index:
     input:
-        "reference/sequences/{species}.{build}.{release}/{species}.{build}.{release}.{datatype}.fasta",
+        lambda wildcards: select_fasta(wildcards),
     output:
         "reference/sequences/{species}.{build}.{release}/{species}.{build}.{release}.{datatype}.fasta.fai",
     threads: 1

workflow/rules/star_index.smk

@@ -0,0 +1,22 @@
+rule fair_genome_indexer_star_index:
+    input:
+        fasta=lambda wildcards: select_fasta(wildcards),
+        fai=lambda wildcards: select_fai(wildcards),
+    output:
+        directory("reference/star_index/{species}.{build}.{release}.{datatype}"),
+    threads: 20
+    resources:
+        mem_mb=lambda wildcards, attempt: attempt * 5_000 + 45_000,
+        runtime=lambda wildcards, attempt: attempt * 30 + 60,
+        tmpdir=tmp,
+    log:
+        "logs/fair_genome_indexer_star_index/{species}.{build}.{release}.{datatype}/index.log",
+    benchmark:
+        "benchmark/fair_genome_indexer_star_index/{species}.{build}.{release}.{datatype}/index.tsv"
+    params:
+        extra=lookup_config(
+            dpath="params/fair_genome_indexer_star_index",
+            default="",
+        ),
+    wrapper:
+        f"{snakemake_wrappers_prefix}/bio/star/index"

workflow/rules/ucsc.smk

@@ -31,3 +31,26 @@ rule fair_genome_indexer_ucsc_gtf_to_genepred:
         ),
     wrapper:
         f"{snakemake_wrappers_prefix}/bio/ucsc/gtfToGenePred"
+
+
+rule fair_genome_indexer_ucsc_genepred_to_bed:
+    input:
+        lambda wildcards: get_genepred(wildcards),
+    output:
+        "reference/annotation/{species}.{build}.{release}/{species}.{build}.{release}.genePred.bed",
+    threads: 1
+    resources:
+        mem_mb=lambda wildcards, attempt: 1_000 * (500 * attempt),
+        runtime=lambda wildcards, attempt: attempt * 10,
+        tmpdir=tmp,
+    log:
+        "logs/fair_genome_indexer_ucsc_genepred_to_bed/{species}.{build}.{release}.log",
+    benchmark:
+        "benchmark/fair_genome_indexer_ucsc_genepred_to_bed/{species}.{build}.{release}.tsv"
+    params:
+        extra=lookup_config(
+            dpath="params/fair_genome_indexer_ucsc_genepred_to_bed",
+            default="",
+        ),
+    wrapper:
+        f"{snakemake_wrappers_prefix}/bio/ucsc/genePredToBed"

workflow/schemas/config.schema.yaml

@@ -13,98 +13,110 @@ params:
   type: object
   description: Optional parameters
 
+  fair_genome_indexer_star_index:
+    type: string
+    description: Optional parameters for STAR index
+
+  fair_genome_indexer_bowtie2_index:
+    type: string
+    description: Optional parameters for bowtie2 build
+
+  fair_genome_indexer_ucsc_genepred_to_bed:
+    type: string
+    description: Optional parameters for ucsc genePredToBed
+
   fair_genome_indexer_ucsc_gtf_to_genepred:
-    type: str
+    type: string
     description: Optional parameters for ucsc gtfToGenePred
 
   fair_genome_indexer_agat_convert_sp_gff2tsv:
-    type: str
+    type: string
     description: Optional parameters for agat_convert_sp_gff2tsv.pl
 
   fair_genome_indexer_xsv_select_t2g_columns:
-    type: str
+    type: string
     description: Optional parameters for xsv select
 
   fair_genome_indexer_xsv_fmt_t2g:
-    type: str
+    type: string
     description: Optional parameters for xsv fmt
 
   fair_genome_indexer_tabix_index_dbsnp:
-    type: str
+    type: string
     description: Optional parameters for tabix index
 
   fair_genome_indexer_tabix_index_dbsnp_index_raw_dbsnp:
-    type: str
+    type: string
     description: Optional parameters for tabix index
 
   fair_genome_indexer_samtools_index:
-    type: str
+    type: string
     description: Optional parameters for samtools faidx
 
   fair_genome_indexer_pyroe_id_to_name:
-    type: str
+    type: string
     description: Optional parameters for pyroe idtoname
 
   fair_genome_indexer_rsync_make_fasta_available:
-    type: str
+    type: string
     description: Optional parameters for rsync
 
   fair_genome_indexer_pyfaidx_filter_out_noncanonical_chromosomes:
     type: object
     description: pyfaidx optional parameters for each subtype of sequences
 
     dna:
-      type: str
+      type: string
       description: pyfaidx optional parameters for DNA sequences
 
     cdna:
-      type: str
+      type: string
       description: pyfaidx optional parameters for cDNA sequences
 
     transcripts:
-      type: str
+      type: string
       description: pyfaidx optional parameters for transcripts DNA sequences
 
   fair_genome_indexer_picard_create_dict:
-    type: str
+    type: string
     description: Picard CreateSequenceDictionary optional parameters
 
   fair_genome_indexer_gffread_transcripts:
-    type: str
+    type: string
     description: GffRead optional parameters for transcripts extraction
 
   fair_genome_indexer_gffread_cdna:
-    type: str
+    type: string
     description: GffRead optional parameters for cDNA extraction
 
   fair_genome_indexer_wget:
-    type: str
+    type: string
     description: Optional parameters for wget
 
   fair_genome_indexer_bedtools_merge_blacklist:
-    type: str
+    type: string
     description: Optional parameters for bedtools merge
 
   fair_genome_indexer_bcftools_filter_non_canonical_chrom:
-    type: str
+    type: string
     description: Optional parameters for bcftools filter
 
   fair_genome_indexer_pyfaidx_fasta_dict_to_bed:
-    type: str
+    type: string
     description: Optional parameters for pyfaidx 
 
   fair_genome_indexer_agat_sq_filter_feature_from_fasta:
-    type: str
+    type: string
     description: Optional parameters for agat_sq_filter_feature_from_fasta.pl
 
   fair_genome_indexer_agat_sp_filter_feature_by_attribute_value:
-    type: str
+    type: string
     description: Optional parameters for agat_sp_filter_feature_by_attribute_value.pl
 
   fair_genome_indexer_agat_convert_sp_gff2gtf:
-    type: str
+    type: string
     escription: Optional parameters for agat_convert_sp_gff2gtf.pl
 
   fair_genome_indexer_agat_config:
     type: object
-    description: Mapping of all agat parameters
+    description: Mapping of all agat parameters

workflow/schemas/genomes.schema.yaml

@@ -64,6 +64,38 @@ genepred:
   type: string
   description: Gene model in genepred format (bed6-like)
 
+genepred_bed:
+  type: string
+  description: Gene model in bed format (bed6-like)
+
+bowtie2_dna_index:
+  type: string
+  description: Bowtie2 index for DNA sequences
+
+bowtie2_cdna_index:
+  type: string
+  description: Bowtie2 index for cDNA sequences
+
+bowtie2_transcripts_index:
+  type: string
+  description: Bowtie2 index for cDNA sequences including non-coding
+
+star_dna_index:
+  type: string
+  description: STAR index for DNA sequences
+
+star_cdna_index:
+  type: string
+  description: STAR index for cDNA sequences
+
+star_transcript_index:
+  type: string
+  description: STAR index for cDNA sequences including non-coding
+
+salmon_index:
+  type: string
+  description: Decoy aware gentrome index
+
 required:
   - species
   - build