pets 0.1.2

data/templates/cohort_report.erb

@@ -0,0 +1,93 @@
+<%
+	def add_tip(text, help_text)
+		return "<div class=\"tooltip\">#{text}<span class=\"tooltiptext\">#{help_text}</span></div>"
+	end
+%>
+
+<div style="width: 90%; background-color:#ecf0f1; margin: 0 auto;"> 
+	<h1 style="text-align: center; background-color:#d6eaf8">Summary stats</h1>
+	<p> General stats about the patient cohort</p>
+	<%= table(id: :summary_stats, header: true, border: 2, 
+		cell_align: %w(left center )) do |data|
+		data.unshift(['Stat', 'Value'])
+		end
+	%>
+</div>
+
+<div style="width: 90%; background-color:#ecf0f1; margin: 0 auto;"> 
+	<h1 style="text-align: center; background-color:#d6eaf8">HPO stats</h1>
+	<p> HPOs more frequent in the cohort </p>
+	<%= table(id: :hpo_stats, header: true, border: 2, 
+		cell_align: %w(left center )) do |data|
+			data.unshift(['HPO', ' Patient percentage'])
+		end
+	%>
+</div>
+
+<div style="width: 90%; background-color:#ecf0f1; margin: 0 auto;"> 
+	<h1 style="text-align: center; background-color:#d6eaf8">Cohort genome coverage analysis</h1>
+	<p> Distribution of the genome coverage of all mutations characterized in the cohort. Second figure shows the same results for SORs.</p>
+	<%= 
+		plot = File.join(@hash_vars[:temp_folder],'coverage_plot.pdf')
+		if File.exists?(plot)
+			embed_pdf(File.join(@hash_vars[:temp_folder],'coverage_plot.pdf'), 'width="800" height="800"') 
+		else
+			"<p> No genomic data was specified for this cohort </p>"
+		end
+	%>
+	<%= 
+		plot = File.join(@hash_vars[:temp_folder],'sor_coverage_plot.pdf')
+		if File.exists?(plot)
+			embed_pdf(File.join(@hash_vars[:temp_folder],'sor_coverage_plot.pdf'), 'width="800" height="800"') 
+		else
+			"<p> No genomic data was specified for this cohort </p>"
+		end
+	%>
+	<div style="overflow: hidden">
+	<h1 style="text-align: center; background-color:#d6eaf8">Distribution of mutations</h1>
+	<p> Distribution of all mutations along the genome (Length) and the number of patients that have at least one of them (Count). Second figure shows the same for SORs. </p>
+		<%=
+			if !@hash_vars[:all_cnvs_length].nil?
+				sccater2D(id: :all_cnvs_length, header: false, title: 'CNV', row_names: false, x_label: 'Length', y_label: 'Count', width: "800px", height: "800px", responsive: false)
+			else
+				"<p> No genomic data was specified for this cohort </p>"
+			end
+		%>
+		<%=
+			if !@hash_vars[:all_sor_length].nil?
+				sccater2D(id: :all_sor_length, header: false, title: 'SOR', row_names: false, x_label: 'Length', y_label: 'Count', width: "800px", height: "800px", responsive: false)
+			else
+				"<p> No genomic data was specified for this cohort </p>"
+			end
+		%>
+	</div>
+</div>
+
+
+<div style="width: 90%; background-color:#ecf0f1; margin: 0 auto;"> 
+	<h1 style="text-align: center; background-color:#d6eaf8">Clustering patients by HPO profile</h1>
+	<p> All patients are clustered using their HPO profiles. First figure shows the information coefficient distribution for the top clusters. Second figure shows which chromosomes are affected in the patients for each top cluster. </p>
+	<%= 
+		plot = File.join(@hash_vars[:temp_folder],'scatterplot.pdf')
+		if File.exists?(plot)
+			embed_pdf(plot, 'width="800" height="800"') 
+		else
+			"<p> Genomic data was not specified </p>"
+		end
+	%>
+	<%= embed_pdf(File.join(@hash_vars[:temp_folder],'boxplot.pdf'), 'width="800" height="800"') %>
+
+</div>
+
+<div style="width: 90%; background-color:#ecf0f1; margin: 0 auto;"> 
+	<h1 style="text-align: center; background-color:#d6eaf8">HPO frequency by cluster</h1>
+	<% @hash_vars[:new_cluster_phenotypes].times do |n| %>
+		<%= table(id: "clust_#{n}", header: true, border: 2, row_names: false, text: true, 
+			cell_align: %w( center )) do |data|
+				# data.unshift([add_tip("HPO information in cluster #{n}"), "Patients" "Phenotypes", "Frequency")])
+				# data.unshift(["HPO information in cluster #{n}\tPhenotypes\tFrequency"])
+				data.unshift(["Patients in Cluster #{n}","Phenotypes", "Frequency"])
+			end
+		%>
+	<%end%>
+</div>

data/templates/patient_report.erb

@@ -0,0 +1,209 @@
+<%
+	def get_hpo_link(hpo_code)
+		# STDERR.puts hpo_code.inspect
+		if hpo_code == '-'
+			link = '-'
+		else
+			link = "<a href=\"http://compbio.charite.de/hpoweb/showterm?id=#{hpo_code}\">#{hpo_code}</a>"
+		end
+		return link
+	end
+
+	def red_text(text)
+		return "<font color=\"red\">#{text}</font>"
+	end
+
+	def add_tip(text, help_text)
+		return "<div class=\"tooltip\">#{text}<span class=\"tooltiptext\">#{help_text}</span></div>"
+	end
+
+%>
+
+<div class="chunk">
+	<style type="text/css" scoped>	
+	.tooltip {
+    position: relative;
+    display: inline-block;
+    border-bottom: 1px dotted black;
+}
+
+.tooltip .tooltiptext {
+    visibility: hidden;
+    width: 120px;
+    background-color: #555;
+    color: #fff;
+    text-align: center;
+    border-radius: 6px;
+    padding: 5px 0;
+    position: absolute;
+    z-index: 1;
+    bottom: 125%;
+    left: 50%;
+    margin-left: -60px;
+    opacity: 0;
+    transition: opacity 1s;
+}
+
+.tooltip .tooltiptext::after {
+    content: "";
+    position: absolute;
+    top: 100%;
+    left: 50%;
+    margin-left: -5px;
+    border-width: 5px;
+    border-style: solid;
+    border-color: #555 transparent transparent transparent;
+}
+
+.tooltip:hover .tooltiptext {
+    visibility: visible;
+    opacity: 1;
+}
+	</style>
+</div>
+
+<div style="width: 90%; background-color:#ecf0f1; margin: 0 auto;"> 
+<h1 style="text-align: center; background-color:#d6eaf8">Input HPO quality control</h1>
+<p>HPO terms with IC values less than <b>1</b> are marked in red, and they do not give much information to our system. Please, if possible, select more specific HPO terms suggested in <b>Possible child HPO terms </b>column.</p>
+
+	<%= table(id: :characterised_hpos, header: true, border: 2, 
+		cell_align: %w(left center center center center left)) do |data|
+		data.each do |row|
+			row.each_with_index do |cell, i|
+				if i == 1
+					# STDERR.puts cell.inspect
+					row[i] = get_hpo_link(cell)
+				elsif i == 4
+					row[i] = cell.map{|h,n| [get_hpo_link(h), n].compact}.join(', ')	
+				elsif i == 5
+					row[i] = cell.map{|r| "#{get_hpo_link(r.first)} (#{r.last})"}.join(', ')
+				elsif i == 3
+					ci = cell.to_f
+					if ci <= 1
+						text = red_text(ci.round(2))
+					else
+						text = ci.round(2)
+					end
+					row[i] = text
+				elsif i == 2
+					if cell == 'no'
+						row[i] = red_text(cell)
+					end
+				end
+			end
+		end
+		data.unshift([add_tip("HPO name", "Name of the HPO"), "HPO code", "Exists in database?", "Information Coefficient (IC)", "Is child of", "Possible child HPO terms"])
+		end
+	%>
+
+<h1 style="text-align: center; background-color:#d6eaf8">Regions associated to HPO profile</h1>
+<h2 style="text-align: center; background-color:#d6eaf8">General representation</h2>
+<div style="overflow: hidden;">
+<%=
+	if !@hash_vars[:merged_regions].nil?
+		circular_data = []
+		@hash_vars[:merged_regions].sort{|reg1, reg2| [reg1[0].to_i, reg1[1].to_i] <=> [reg2[0].to_i, reg2[1].to_i]}.each do |row|
+			#TODO if chr were x or y, change them to 23 and 24 and, when print, use x and y again
+			circular_data_row = []
+			circular_data_row << "#{row[1]}-#{row[2]}"
+			circular_data_row << row[5]
+			circular_data_row << row[0]
+			circular_data << circular_data_row
+		end
+		circular_data.unshift(%w[Coords CombScore Chr])
+		@hash_vars[:circular_data] = circular_data
+		circular(
+			id: :circular_data, 
+			header: true,
+			row_names: true,
+			responsive: false,
+			sample_attributes: {'Chr' => 2},
+			config:{
+		#		'smpLabelOrientation' => 'circular',
+				'smpOverlays' => ['Chr'],
+				'colorSpectrum' => ["#d73027", "#fc8d59", "#fee090", "#ffffbf", "#e0f3f8", "#91bfdb", "#4575b4"],
+		#		'segregateSamplesBy' => ['Chr']
+				}
+			) do |data|
+				data.pop #Discard chromosome data
+			end
+	end
+%>
+</div>
+<h2 style="text-align: center; background-color:#d6eaf8">Ranked genomic regions associated to the HPO profile</h2>
+<p>The following table shows all the predicted genomic regions, the HPO terms found for it, their original association values and the calculated combined score. Results are ranked from the highest to the lowest combined score.</p>
+	<%= 
+	if !@hash_vars[:merged_regions].nil?
+		gene_var = @hash_vars[:genes_with_kegg_data]
+		table(id: :merged_regions, header: true, border: 2, 
+		cell_align: %w(center center center left center center)) do |data|
+		hpo_metadata = @hash_vars[:hpo_metadata]
+		data.each_with_index do |row, row_number|
+			row.each_with_index do |cell, i|
+				if i == 3
+					row[i] = cell.map{|h| "#{get_hpo_link(h)}: #{hpo_metadata[h][1]}"}.join("\n<br>")
+				elsif i == 4
+					row[i] = cell.map{|a| 
+						if a.abs > 0.01
+							a.to_f.round(2)
+						else
+							"%e" %a
+						end
+						}.join("\n<br>")
+				end
+			end
+			if !gene_var.nil?
+				gene_data = gene_var[row_number]
+				if !gene_data.empty?
+					table = '<table border= "2">'
+					table << "<tr><th>#{["GeneID", "Gene Names", "Description", "KEGG pathways"].join('</th><th>')}</th></tr>"
+					geneIDs = gene_data.map{|gd| gd.first}
+					gene_data.each do |geneID, attributes|
+						table << '<tr>'
+						table << "<td><a href=https://www.ncbi.nlm.nih.gov/gene/?term=#{geneID}>#{geneID}</a></td>"
+						if !attributes.nil?
+							table << "<td>#{attributes[0][0..1].join(', ')}</td>"
+							table << "<td>#{attributes[1]}</td>"
+							table << "<td>#{attributes[2].map{|pws| "<a href=\"https://www.kegg.jp/pathway/#{pws.first}+#{geneIDs.join('+')}\">#{pws.last}</a>"}.join('<br>')}</td>"
+						else
+							table << '<td></td>' * 3
+						end
+						table << '</tr>'
+					end
+					table << '</table>'
+					row << table
+				else
+					row << ('-')
+				end
+			else
+				row << ('-')
+			end
+		end
+		data.unshift(["Chromosome", "Start", "Stop", "Associated HPOs", "Association values<br>(For each HPO)", "Combined score", "Gene data" ])
+		end
+	end
+	%>
+
+<% if !@hash_vars[:pathway_stats].empty? %>
+	<h2 style="text-align: center; background-color:#d6eaf8">KEGG pathways significance in the genes located into the predicted regions </h2>
+	<p></p>
+		<%= table(id: :pathway_stats, header: true, border: 2 ) do |data|
+			data.each do |row|
+				row.each_with_index do |field, i|
+					new_field = field
+					if i == 0
+						new_field = "<a href=\"https://www.kegg.jp/pathway/#{field.first}+#{row[i+1].join('+')}\">#{field.last}</a>"
+					elsif i == 1
+						new_field = field.map{|geneID| "<a href=https://www.ncbi.nlm.nih.gov/gene/?term=#{geneID}>#{geneID}</a>" }.join(', ')
+					elsif i == 2
+						new_field = field.join(", ")
+					end
+					row[i] = new_field
+				end
+			end
+			data.unshift(["KEGG pathway", "Genes in pathway", "Contigency table: PN, NP, PP, NN", "Fisher p-value" ])
+		end
+		%>
+<% end %>
+
+</div>

metadata

@@ -0,0 +1,183 @@
+--- !ruby/object:Gem::Specification
+name: pets
+version: !ruby/object:Gem::Version
+  version: 0.1.2
+platform: ruby
+authors:
+- Elena Rojano, Pedro Seoane
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2019-10-24 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: statistics2
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: terminal-table
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: report_html
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: PETS suite includes three different tools. CohortAnalyzer performs the
+  calculation of several statistics that gives an overview of a cohort of patients
+  to analyse. Reg2Phen uses associations between pathological phenotypes and regions
+  of the genome (these associations can be calculated from the cohort of patients
+  if they include genotypic & phenotypic information using NetAnalyzer, another Ruby
+  gem) to find, for a given genomic region, which pathological phenotypes have been
+  associated with that region. The third tool, Phen2Reg, is a predictor that using
+  the same associations as Reg2Phen, predicts which genomic regions can be the cause
+  of a list of pathological phenotypes observed in a patient.
+email:
+- elenarojano@uma.es, seoanezonjic@uma.es
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/area_under_curve_pr.rb
+- bin/association_metrics_average.rb
+- bin/coPatReporter.rb
+- bin/console
+- bin/fmeasure_index.rb
+- bin/get_PR_values.rb
+- bin/get_clusters.R
+- bin/get_network_nodes.rb
+- bin/lines.R
+- bin/merge_by_cluster.rb
+- bin/merge_pairs.rb
+- bin/paco_translator.rb
+- bin/phen2reg.rb
+- bin/phen2reg_predictor_check.rb
+- bin/plot_area.R
+- bin/plot_boxplot.R
+- bin/plot_density.R
+- bin/plot_scatterplot.R
+- bin/reg2phen.rb
+- bin/region_to_patients_generator.rb
+- bin/relate_CI_to_association_value.rb
+- bin/setup
+- bin/standardize_scores.R
+- bin/xyplot_graph.R
+- external_data/biosystems_gene.gz
+- external_data/bsid2info.gz
+- external_data/chromosome_sizes_hg19.txt
+- external_data/gene_data.gz
+- external_data/gene_data_with_pathways.gz
+- external_data/gene_location.gz
+- external_data/hp.obo
+- external_data/remove
+- lib/pets.rb
+- lib/pets/coPatReporterMethods.rb
+- lib/pets/generalMethods.rb
+- lib/pets/phen2reg_methods.rb
+- lib/pets/version.rb
+- pets.gemspec
+- templates/cohort_report.erb
+- templates/patient_report.erb
+homepage: https://bitbucket.org/elenarojano/reg2phen/src/master/bin/reg2phen.rb
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.14
+signing_key: 
+specification_version: 4
+summary: Suite with predictive tools.
+test_files: []