initial work before i go home

dgidb · Dec 19, 2024 · 88eaacf · 88eaacf
1 parent 5737396
commit 88eaacf
Show file tree

Hide file tree

Showing 12 changed files with 608 additions and 29 deletions.
diff --git a/scripts/download_files.py b/scripts/download_files.py
diff --git a/server/lib/genome/importers/base.rb b/server/lib/genome/importers/base.rb
@@ -40,11 +40,15 @@ def default_filename
         'claims'
       end
 
+      def default_data_dir
+        "#{Dir.home}/.local/share/wags_tails"
+      end
+
       def handle_file_location(file_path)
         return file_path unless file_path.nil?
 
-        dir_name = self.class.name.split('::')[-2].underscore
-        "lib/data/#{dir_name}/#{default_filename}.#{default_filetype}"
+        src_name = self.class.name.split('::')[-2].underscore
+        "#{default_data_dir}/#{src_name}/#{src_name}_#{default_filename}.#{default_filetype}"
       end
 
       def remove_existing_source

diff --git a/server/lib/genome/importers/file_importers/chembl.rb b/server/lib/genome/importers/file_importers/chembl.rb
@@ -10,12 +10,11 @@ def initialize(file_path)
       @source_db_name = "ChEMBL"
     end
 
-    def default_filetype
-      'db'
-    end
+    def handle_file_location(file_path)
+      return file_path unless file_path.nil?
 
-    def default_filename
-      'chembl'
+      directory = "#{default_data_dir}/chembl/"
+      Dir.glob(File.join(directory, 'chembl_*.db')).max_by { |file| file.match(/chembl_(\d+)\.db/)[1].to_i rescue 0 }
     end
 
     def create_claims

diff --git a/server/lib/genome/importers/file_importers/clearity_foundation_biomarkers.rb b/server/lib/genome/importers/file_importers/clearity_foundation_biomarkers.rb
@@ -31,6 +31,12 @@ def create_new_source
       @source.save
     end
 
+    def handle_file_location(file_path)
+      return file_path unless file_path.nil?
+
+      "#{Dir.home}/.local/share/wags_tails/clearity_foundation/clearity_foundation_biomarkers_claims.tsv"
+    end
+
     def create_interaction_claims
       CSV.foreach(file_path, headers: true, col_sep: "\t") do |row|
         gene_claim = create_gene_claim(row['gene_name'].upcase)

diff --git a/server/lib/genome/importers/file_importers/clearity_foundation_clinical_trial.rb b/server/lib/genome/importers/file_importers/clearity_foundation_clinical_trial.rb
@@ -31,6 +31,12 @@ def create_new_source
       @source.save
     end
 
+    def handle_file_location(file_path)
+      return file_path unless file_path.nil?
+
+      "#{Dir.home}/.local/share/wags_tails/clearity_foundation/clearity_foundation_clinical_trial_claims.tsv"
+    end
+
     def create_interaction_claims
       CSV.foreach(file_path, headers: true, col_sep: "\t") do |row|
         next if row['Entrez Gene Name'] == 'N/A' || row['Pubchem name'] == 'N/A'

diff --git a/server/lib/genome/importers/file_importers/docm.rb b/server/lib/genome/importers/file_importers/docm.rb
@@ -7,7 +7,7 @@ class Importer < Genome::Importers::Base
 
           def initialize(tsv_root_path)
             @tsv_root = if tsv_root_path.nil?
-                          'lib/data/docm/'
+                          "#{default_data_dir}/docm/"
                         else
                           tsv_root_path
                         end
@@ -49,37 +49,37 @@ def create_new_source
 
 
           def create_drug_claims
-            CSV.foreach("#{@tsv_root}drug_claim.csv", headers: true, col_sep: ',') do |row|
+            CSV.foreach("#{@tsv_root}docm_drug_claims.csv", headers: true, col_sep: ',') do |row|
               dc = create_drug_claim(row[0])
               @drug_claims[row[0]] = dc
             end
           end
 
           def create_gene_claims
-            CSV.foreach("#{@tsv_root}gene_claim.csv", headers: true, col_sep: ',') do |row|
+            CSV.foreach("#{@tsv_root}docm_gene_claims.csv", headers: true, col_sep: ',') do |row|
               gc = create_gene_claim(row[0], GeneNomenclature::NCBI_NAME)
               @gene_claims[row[0]] = gc
             end
           end
 
           def create_interaction_claims
-            CSV.foreach("#{@tsv_root}interaction_claim.csv", headers: true, col_sep: ',') do |row|
+            CSV.foreach("#{@tsv_root}docm_interaction_claims.csv", headers: true, col_sep: ',') do |row|
               gc = @gene_claims[row[1]]
               dc = @drug_claims[row[0]]
               next if gc.nil? || dc.nil?
 
               ic = create_interaction_claim(gc, dc)
               @interaction_claims[[gc, dc]] = ic
             end
-            CSV.foreach("#{@tsv_root}interaction_claim_attributes.csv", headers: true, col_sep: ',') do |row|
+            CSV.foreach("#{@tsv_root}docm_interaction_claim_attributes.csv", headers: true, col_sep: ',') do |row|
               gc = @gene_claims[row[3]]
               dc = @drug_claims[row[2]]
               next if gc.nil? || dc.nil?
 
               ic = @interaction_claims[[gc, dc]]
               create_interaction_claim_attribute(ic, row[0], row[1])
             end
-            CSV.foreach("#{@tsv_root}interaction_claim_publications.csv", headers: true, col_sep: ',') do |row|
+            CSV.foreach("#{@tsv_root}docm_interaction_claim_publications.csv", headers: true, col_sep: ',') do |row|
               gc = @gene_claims[row[3]]
               dc = @drug_claims[row[2]]
               next if gc.nil? || dc.nil?

diff --git a/server/lib/genome/importers/file_importers/drugbank.rb b/server/lib/genome/importers/file_importers/drugbank.rb
@@ -11,8 +11,15 @@ def initialize(file_path)
       @source_db_name = 'DrugBank'
     end
 
-    def default_filetype
-      'xml'
+    def handle_file_location(file_path)
+      return file_path unless file_path.nil?
+
+      directory = "#{default_data_dir}/drugbank/"
+      Dir.glob(File.join(directory, 'drugbank_*.xml'))
+           .max_by do |file|
+             match = file.match(/drugbank_(\d+)\.(\d+)\.(\d+)\.xml/)
+             match ? [match[1].to_i, match[2].to_i, match[3].to_i] : [0, 0, 0]
+           end
     end
 
     def run_parser

diff --git a/server/lib/genome/importers/file_importers/guide_to_pharmacology.rb b/server/lib/genome/importers/file_importers/guide_to_pharmacology.rb
@@ -1,14 +1,14 @@
 include ActionView::Helpers::SanitizeHelper
 
 module Genome; module Importers; module FileImporters; module GuideToPharmacology;
-  # gene_file_path should point to `targets_and_families.csv`
-  # interaction_file_path should point to `interactions.csv`
+  # gene_file_path should point to `gtop_targets_and_families_*.tsv`
+  # interaction_file_path should point to `gtop_interactions_*.tsv`
   class Importer < Genome::Importers::Base
     attr_reader :interaction_file_path, :gene_file_path, :target_to_entrez
 
     def initialize(interaction_file_path, gene_file_path)
-      @interaction_file_path = interaction_file_path
-      @gene_file_path = gene_file_path
+      @interaction_file_path = handle_gtop_file_location(interaction_file_path, "interactions")
+      @gene_file_path = handle_gtop_file_location(gene_file_path, "targets_and_families")
       @target_to_entrez = {}
       @source_db_name = 'GuideToPharmacology'
     end
@@ -20,6 +20,16 @@ def create_claims
 
     private
 
+    def handle_gtop_file_location(file_path, datatype)
+      return file_path unless file_path.nil?
+
+      raise "Unrecognized GtoP datatype: #{datatype}" unless %w[targets_and_families interactions].include? datatype
+
+      directory = "#{default_data_dir}/guidetopharmacology/"
+      Dir.glob(File.join(directory, "gtop_#{datatype}_*.tsv"))
+         .max_by { |file| file.match(/gtop_#{datatype}_(\d+)\.db/)[1].to_i rescue 0 }
+    end
+
     def get_version
       version = ''
       File.open(@interaction_file_path, 'r') do |file|
@@ -57,7 +67,7 @@ def create_new_source
     def import_gene_claims
       refseq_id_pattern = /^((AC|AP|NC|NG|NM|NP|NR|NT|NW|XM|XP|XR|YP|ZP)_\d+|(NZ\_[A-Z]{4}\d+))(\.\d+)?$/
 
-      CSV.foreach(gene_file_path, headers: true, skip_lines: /GtoPdb Version/) do |line|
+      CSV.foreach(gene_file_path, headers: true, skip_lines: /GtoPdb Version/, col_sep: "\t") do |line|
         gene_lui = line['Human Entrez Gene']
         next if blank?(gene_lui) || gene_lui.include?('|')
 
@@ -111,7 +121,7 @@ def import_gene_claims
     end
 
     def import_interaction_claims
-      CSV.foreach(interaction_file_path, headers: true, skip_lines: /GtoPdb Version/) do |line|
+      CSV.foreach(interaction_file_path, headers: true, skip_lines: /GtoPdb Version/, col_sep: "\t") do |line|
         next unless valid_interaction_line?(line)
 
         gene_claim = create_gene_claim("NCBIGENE:#{line['Target ID']}", GeneNomenclature::NCBI_ID)

diff --git a/server/lib/genome/importers/file_importers/my_cancer_genome_clinical_trial.rb b/server/lib/genome/importers/file_importers/my_cancer_genome_clinical_trial.rb
@@ -12,6 +12,17 @@ def create_claims
     end
 
     private
+    def default_filename
+      'clinical_trial_claims'
+    end
+
+    def handle_file_location(file_path)
+      return file_path unless file_path.nil?
+
+      src_name = "my_cancer_genome"
+      "#{default_data_dir}/#{src_name}/#{src_name}_#{default_filename}.#{default_filetype}"
+    end
+
     def create_new_source
       @source ||= Source.create(
         {

diff --git a/server/lib/genome/importers/file_importers/oncokb.rb b/server/lib/genome/importers/file_importers/oncokb.rb
@@ -1,11 +1,11 @@
 module Genome; module Importers; module FileImporters; module Oncokb;
   class Importer < Genome::Importers::Base
     def initialize(tsv_root_path)
-      if tsv_root_path.nil?
-        @tsv_root = 'lib/data/oncokb/'
-      else
-        @tsv_root = tsv_root_path
-      end
+      @tsv_root = if tsv_root_path.nil?
+                    "#{default_data_dir}/oncokb/"
+                  else
+                    tsv_root_path
+                  end
       @source_db_name = 'OncoKB'
       @drug_claims = {}
       @gene_claims = {}

diff --git a/server/lib/genome/importers/file_importers/pharmgkb.rb b/server/lib/genome/importers/file_importers/pharmgkb.rb
@@ -13,6 +13,20 @@ def create_claims
 
     private
 
+    def handle_file_location(file_path)
+      return file_path unless file_path.nil?
+
+      directory = "#{default_data_dir}/pharmgkb/"
+      Dir.glob(File.join(directory, 'pharmgkb_*.tsv')).max_by { |file| file.match(/chembl_(\d+)\.db/)[1].to_i rescue 0 }
+    end
+
+
+    def get_version
+      match = @file_path.match(/(\d{8})/)
+      match ? match[1] : nil
+    end
+
+
     def create_new_source
       @source ||= Source.create(
         {
@@ -23,7 +37,7 @@ def create_new_source
           pmid: '34216021',
           pmcid: 'PMC8457105',
           doi: '10.1002/cpt.2350',
-          source_db_version: '2024-04-05',  # using static file, see issue #420
+          source_db_version: get_version,
           source_db_name: source_db_name,
           full_name: 'PharmGKB - The Pharmacogenomics Knowledgebase',
           license: License::CC_BY_SA_4_0,

diff --git a/server/lib/tasks/importers.rake b/server/lib/tasks/importers.rake
@@ -72,8 +72,8 @@ namespace :dgidb do
     # Guide to Pharmacology is a special case because it needs two input files
     def run_gtop_import(args)
       args.with_defaults(
-        interaction_file_path: 'lib/data/guide_to_pharmacology/interactions.csv',
-        gene_file_path: 'lib/data/guide_to_pharmacology/targets_and_families.csv',
+        interaction_file_path: nil,
+        gene_file_path: nil,
         gene_group: false,
         drug_group: false
       )