added rules for generating all-genes from ppi network

prepare_data/workflow/Snakefile

@@ -4,6 +4,7 @@ include: "rules/last_whole_genome_alignment.smk"
 include: "rules/prepare_annotation.smk"
 include: "rules/transcription_factor_binding_sites.smk"
 include: "rules/module_detection.smk"
+include: "rules/prepare_enrichment_analysis.smk"
 
 #rule download_ref_genomes:
     #wget and then make symbolic links

prepare_data/workflow/configfile.yaml

@@ -43,6 +43,12 @@ network_dir: "../../static/app_data/networks"
 mod_detect_dir: "../../static/raw_data/network_modules"
 network_mod_dir: "../../static/app_data/network_modules"
 
+ppi_dir: "../../static/raw_data/ppi"
+raw_enrich_dir: "../../static/raw_data/enrichment_analysis"
+
+gene_id_mapping_dir: "../../static/app_data/gene_id_mapping"
+gene_desc_dir: "../../static/app_data/gene_descriptions"
+
 networks:
     "STRING-Physical": "{network_dir}/STRING-Physical.txt"
 

prepare_data/workflow/rules/prepare_enrichment_analysis.smk

@@ -0,0 +1,55 @@
+# Resolve Network Dependency
+for key, path in config['networks'].items():
+    config["networks"][key] = path.format(network_dir=config["network_dir"])
+
+rule data_prep_for_enrichment_analysis:
+    input:
+        expand(
+            "{ppi_dir}/all_proteins/{network}/{file_format}/{name}.txt",
+            ppi_dir = config["ppi_dir"],
+            network = config["networks"].keys(),
+            file_format = "uniprot",
+            name = "all-proteins"
+        ),
+        expand(
+            "{gene_id_mapping_dir}/msu_mapping/{file_name}.pickle",
+            gene_id_mapping_dir = config["gene_id_mapping_dir"],
+            file_name = "uniprot_to_msu"
+        ),
+        expand(
+            "{raw_enrich_dir}/all_genes/{network}/{file_format}/all-genes.txt",
+            raw_enrich_dir = config["raw_enrich_dir"],
+            network = config["networks"].keys(),
+            file_format = "MSU"
+        )
+
+rule get_proteins_from_network:
+    input:
+        lambda wildcards: config['networks'][wildcards.network]
+    output:
+        "{ppi_dir}/all_proteins/{network}/{file_format}/{name}.txt"
+    shell:
+        "python scripts/network_util/get-nodes-from-network.py " \
+        "{input} {wildcards.ppi_dir}/all_proteins/{wildcards.network}/{wildcards.file_format} " \
+        "--name {wildcards.name}"
+
+rule convert_all_proteins_to_genes:
+    input:
+        proteins_file="{0}/all_proteins/{{network}}/uniprot/all-proteins.txt".format(config["ppi_dir"]),
+        protein_to_gene_mapping="{0}/msu_mapping/uniprot_to_msu.pickle".format(config["gene_id_mapping_dir"])
+    output:
+        "{raw_enrich_dir}/all_genes/{network}/{file_format}/all-genes.txt"
+    shell:
+        "python scripts/ppi_util/convert_all_prot_to_gene.py " \
+        "{input.proteins_file} {input.protein_to_gene_mapping} " \
+        "{wildcards.raw_enrich_dir}/all_genes/{wildcards.network}/{wildcards.file_format}"
+
+rule prepare_uniprot_to_gene:
+    input:
+        "{0}/Nb/Nb_gene_descriptions.csv".format(config["gene_desc_dir"])
+    output:
+        "{gene_id_mapping_dir}/msu_mapping/{file_name}.pickle"
+    shell:
+        "python scripts/ppi_util/prepare_uniprot_to_gene.py " \
+        "{input} {wildcards.gene_id_mapping_dir}/msu_mapping " \
+        "{wildcards.file_name}"