add salmon output into design

seqnado/config.py

@@ -86,7 +86,7 @@ def setup_configuration(assay, genome, template_data):
             "Path to fastqscreen config:",
             default="/ceph/project/milne_group/shared/seqnado_reference/fastqscreen_reference/fastq_screen.conf",
         )
-    
+
     # Blacklist
     template_data["remove_blacklist"] = get_user_input(
         "Do you want to remove blacklist regions? (yes/no)",
@@ -108,8 +108,8 @@ def setup_configuration(assay, genome, template_data):
         )
         # Library Complexity
         template_data["library_complexity"] = get_user_input(
-        "Calculate library complexity? (yes/no)", default="no", is_boolean=True
-    )
+            "Calculate library complexity? (yes/no)", default="no", is_boolean=True
+        )
     else:
         template_data["remove_pcr_duplicates_method"] = "False"
         template_data["library_complexity"] = "False"
@@ -169,6 +169,26 @@ def setup_configuration(assay, genome, template_data):
                 choices=["lanceotron", "macs", "homer"],
             )
 
+    # RNA options
+    template_data["rna_quantification"] = (
+        get_user_input(
+            "RNA quantification method:",
+            default="feature_counts",
+            choices=["feature_counts", "salmon"],
+        )
+        if assay == "rna"
+        else "False"
+    )
+
+    template_data["salmon_index"] = (
+        get_user_input(
+            "Path to salmon index:",
+            default="/ceph/project/milne_group/shared/salmon_ref/hg38/cDNA/Homo_sapiens.GRCh38.cdna.all.fa.gz",
+        )
+        if template_data["rna_quantification"] == "salmon"
+        else "False"
+    )
+
     # Run DESeq2
     template_data["run_deseq2"] = (
         get_user_input("Run DESeq2? (yes/no)", default="no", is_boolean=True)
@@ -256,6 +276,10 @@ def setup_configuration(assay, genome, template_data):
     threads: 16
     options: -s 0 -p --countReadPairs -t exon -g gene_id
 
+salmon:
+    threads: 16
+    options: --libType A
+    
 homer:
     maketagdirectory:
     makebigwig:

seqnado/design.py

@@ -958,10 +958,14 @@ class RNAOutput(Output):
     assay: Literal["RNA"]
     project_name: str
     run_deseq2: bool = False
+    rna_quantification: Optional[Literal["feature_counts", "salmon"]] = None
 
     @property
     def counts(self):
-        return ["seqnado_output/feature_counts/read_counts.tsv"]
+        if self.rna_quantification == "feature_counts":
+            return ["seqnado_output/quantification/feature_counts/read_counts.tsv"]
+        elif self.rna_quantification == "salmon":
+            return ["seqnado_output/quantification/salmon/quant.sf"]
 
     @property
     def deseq2(self):

seqnado/workflow/config/config.yaml.jinja

@@ -39,6 +39,9 @@ make_heatmaps: "{{make_heatmaps}}"
 call_peaks: "{{call_peaks}}"
 peak_calling_method: "{{peak_calling_method}}"
 
+rna_quantification: "{{rna_quantification}}"
+salmon_index: "{{salmon_index}}"
+
 run_deseq2: "{{run_deseq2}}"
 
 

seqnado/workflow/rules/alignment_counts.smk

@@ -1,22 +1,20 @@
 from seqnado.helpers import check_options
 
-
-
 rule feature_counts:
     input:
         bam=expand("seqnado_output/aligned/{sample}.bam", sample=SAMPLE_NAMES),
         bai=expand("seqnado_output/aligned/{sample}.bam.bai", sample=SAMPLE_NAMES),
         annotation=config["genome"]["gtf"],
     output:
-        counts="seqnado_output/feature_counts/read_counts.tsv",
+        counts="seqnado_output/quantification/feature_counts/read_counts.tsv",
     params:
         options=check_options(config["featurecounts"]["options"]),
     threads: config["featurecounts"]["threads"]
     resources:
         mem=lambda wildcards, attempt: f"{3 * 2 ** (attempt)}GB",
         runtime="2h",
     log:
-        "seqnado_output/logs/readcounts/featurecounts/featurecounts.log",
+        "seqnado_output/logs/quantification/featurecounts/featurecounts.log",
     shell:
         """
         featureCounts \
@@ -30,3 +28,44 @@ rule feature_counts:
         {input.bam} \
         > {log} 2>&1
         """
+
+rule salmon_counts_paired:
+    input:
+        fq1="seqnado_output/fastq/{sample}_1.fastq.gz", sample=SAMPLE_NAMES,
+        fq2="seqnado_output/fastq/{sample}_2.fastq.gz", sample=SAMPLE_NAMES,
+    output:
+        counts="seqnado_output/quantification/salmon/quant.sf",
+    params:
+        index=config["salmon"]["index"],
+        options=check_options(config["salmon"]["options"]),
+    threads: config["salmon"]["threads"]
+    resources:
+        mem=lambda wildcards, attempt: f"{3 * 2 ** (attempt)}GB",
+        runtime="2h",
+    log:
+        "seqnado_output/logs/readcounts/salmon/salmon.log",
+    shell:
+        """
+        salmon quant -p -t {params.index} {params.options} -1 {input.fq1} -2 {input.fq2} -p {threads} -o seqnado_output/quantification/salmon
+        """
+
+rule salmon_counts_single:
+    input:
+        fq="seqnado_output/fastq/{sample}.fastq.gz", sample=SAMPLE_NAMES,
+    output:
+        counts="seqnado_output/quantification/salmon/quant.sf",
+    params:
+        index=config["salmon"]["index"],
+        options=check_options(config["salmon"]["options"]),
+    threads: config["salmon"]["threads"]
+    resources:
+        mem=lambda wildcards, attempt: f"{3 * 2 ** (attempt)}GB",
+        runtime="2h",
+    log:
+        "seqnado_output/logs/readcounts/salmon/salmon.log",
+    shell:
+        """
+        salmon quant -t {params.index} {params.options} -r {input.fq} -p {threads} -o seqnado_output/quantification/salmon
+        """
+
+ruleorder: feature_counts > salmon_counts_paired > salmon_counts_single