data push

samhimes92 · Sep 18, 2023 · b3d2c77 · b3d2c77
1 parent 2b2aca3
commit b3d2c77
Show file tree

Hide file tree

Showing 35 changed files with 12,785 additions and 6,373 deletions.
diff --git a/data/.DS_Store b/data/.DS_Store
diff --git a/data/19919_alphas.json → data/current_runs.csv b/data/19919_alphas.json → data/current_runs.csv
diff --git a/data/current_runs_old.csv b/data/current_runs_old.csv
diff --git a/.../emp_res/full-test__empirical_results.csv → .../emp_res/full-test__empirical_results.csv b/.../emp_res/full-test__empirical_results.csv → .../emp_res/full-test__empirical_results.csv
diff --git a/new_data/emp_res/run1__empirical_results.csv → data/emp_res/run1__empirical_results.csv b/new_data/emp_res/run1__empirical_results.csv → data/emp_res/run1__empirical_results.csv
diff --git a/...asone-run1__Serum_Free-run1__FBS-run1.csv → ...asone-run1__Serum_Free-run1__FBS-run1.csv b/...asone-run1__Serum_Free-run1__FBS-run1.csv → ...asone-run1__Serum_Free-run1__FBS-run1.csv
diff --git a/...run1__FBS-run1__missing_architectures.csv → ...run1__FBS-run1__missing_architectures.csv b/...run1__FBS-run1__missing_architectures.csv → ...run1__FBS-run1__missing_architectures.csv
diff --git a/..._Free-19664__FBS-19664__Marin_1-20250.csv → ..._Free-19664__FBS-19664__Marin_1-20250.csv b/..._Free-19664__FBS-19664__Marin_1-20250.csv → ..._Free-19664__FBS-19664__Marin_1-20250.csv
diff --git a/..._Marin_1-20250__missing_architectures.csv → ..._Marin_1-20250__missing_architectures.csv b/..._Marin_1-20250__missing_architectures.csv → ..._Marin_1-20250__missing_architectures.csv
diff --git a/new_data/pairwise_res/.DS_Store → data/pairwise_res/.DS_Store b/new_data/pairwise_res/.DS_Store → data/pairwise_res/.DS_Store
diff --git a/...rum_Free__full-test_vs_ATP__full-test.csv → ...rum_Free__full-test_vs_ATP__full-test.csv b/...rum_Free__full-test_vs_ATP__full-test.csv → ...rum_Free__full-test_vs_ATP__full-test.csv
diff --git a/...ATP__full-test__missing_architectures.csv → ...ATP__full-test__missing_architectures.csv b/...ATP__full-test__missing_architectures.csv → ...ATP__full-test__missing_architectures.csv
diff --git a/...full-test_vs_Dexamethasone__full-test.csv → ...full-test_vs_Dexamethasone__full-test.csv b/...full-test_vs_Dexamethasone__full-test.csv → ...full-test_vs_Dexamethasone__full-test.csv
diff --git a/...one__full-test__missing_architectures.csv → ...one__full-test__missing_architectures.csv b/...one__full-test__missing_architectures.csv → ...one__full-test__missing_architectures.csv
diff --git a/...rum_Free__full-test_vs_FBS__full-test.csv → ...rum_Free__full-test_vs_FBS__full-test.csv b/...rum_Free__full-test_vs_FBS__full-test.csv → ...rum_Free__full-test_vs_FBS__full-test.csv
diff --git a/...FBS__full-test__missing_architectures.csv → ...FBS__full-test__missing_architectures.csv b/...FBS__full-test__missing_architectures.csv → ...FBS__full-test__missing_architectures.csv
diff --git a/...m_Free__full-test_vs_Forsk__full-test.csv → ...m_Free__full-test_vs_Forsk__full-test.csv b/...m_Free__full-test_vs_Forsk__full-test.csv → ...m_Free__full-test_vs_Forsk__full-test.csv
diff --git a/...rsk__full-test__missing_architectures.csv → ...rsk__full-test__missing_architectures.csv b/...rsk__full-test__missing_architectures.csv → ...rsk__full-test__missing_architectures.csv
diff --git a/...rum_Free__run1_vs_Dexamethasone__run1.csv → ...rum_Free__run1_vs_Dexamethasone__run1.csv b/...rum_Free__run1_vs_Dexamethasone__run1.csv → ...rum_Free__run1_vs_Dexamethasone__run1.csv
diff --git a/...ethasone__run1__missing_architectures.csv → ...ethasone__run1__missing_architectures.csv b/...ethasone__run1__missing_architectures.csv → ...ethasone__run1__missing_architectures.csv
diff --git a/...ise_res/Serum_Free__run1_vs_FBS__run1.csv → ...ise_res/Serum_Free__run1_vs_FBS__run1.csv b/...ise_res/Serum_Free__run1_vs_FBS__run1.csv → ...ise_res/Serum_Free__run1_vs_FBS__run1.csv
diff --git a/...1_vs_FBS__run1__missing_architectures.csv → ...1_vs_FBS__run1__missing_architectures.csv b/...1_vs_FBS__run1__missing_architectures.csv → ...1_vs_FBS__run1__missing_architectures.csv
diff --git a/new_data/sequences.csv → data/sequences.csv b/new_data/sequences.csv → data/sequences.csv
diff --git a/data/test_csv.csv b/data/test_csv.csv
diff --git a/data/volcano_data/pcDNA3.1_vs_GPR162_high_.json b/data/volcano_data/pcDNA3.1_vs_GPR162_high_.json
diff --git a/js/alpha.js b/js/alpha.js
@@ -1,5 +1,6 @@
 class Alpha{
-    constructor(all_data,globalApplicationState,volcano){
+    constructor(all_data,globalApplicationState,volcano, h){
+
 
         //**********************************************************************************************
         //                                      CONSTANTS 
@@ -27,6 +28,7 @@ class Alpha{
         this.globalApplicationState = globalApplicationState
 
         this.all_data = all_data
+        this.h = h
 
         this.volcano = volcano
         this.alpha_div = d3.select("#alpha-div") 
@@ -70,9 +72,6 @@ class Alpha{
         //                                 SELECTORS
         //**********************************************************************************************
 
-
-
-
         //For getting unique values for base a stimulated
         function onlyUnique(value, index, self) {
             return self.indexOf(value) === index;
@@ -146,7 +145,6 @@ class Alpha{
             d3.select("#control_check").property('checked', false)
             that.drawAlphaScatter()
             that.points.selectAll("circle")
-                // .style("opacity", d => (+d[that.max_rank_name] <= 5) )
                 .filter(d => +d[that.max_rank_name] > n | d[that.max_rank_name] == "")
                 .remove();
         } 
@@ -245,7 +243,7 @@ class Alpha{
         // Get inititial min and max for scales (Will change upon selection)
         //***************************************
 
-        this.min =  0
+        this.min = -.5
         this.max =  5
 
         this.x_scale = d3.scaleLinear()
@@ -271,7 +269,8 @@ class Alpha{
         .attr("id", "base_text")
         .attr("transform","translate(" + this.WIDTH / 2 + " ," + (this.HEIGHT - 10) + ")")
         .style("text-anchor", "middle")
-        .text("Basal Alpha");
+        .text("Basal Alpha")
+        .style('fill', '#6C4343');
 
         this.alphaSvg
         .append("text")
@@ -280,7 +279,8 @@ class Alpha{
         .attr("y", 15)
         .attr("x",-(this.HEIGHT/2))
         .style("text-anchor", "middle")
-        .text("Stimulated Alpha");
+        .text("Stimulated Alpha")
+        .style('fill', '#00429d');
 
 
         this.alphaSvg
@@ -342,8 +342,6 @@ class Alpha{
 
             d3.selectAll('.child-div').style("opacity", "1").style("pointer-events", "all")
 
-
-
             //Remove everything before drawing again
             this.points
                 .selectAll('circle')
@@ -358,9 +356,8 @@ class Alpha{
             this.stim_name = "alpha__"+stim_treatment+"__"+stim_run
             this.base_name = "alpha__"+base_treatment+"__"+base_run
             this.max_rank_name = "maxRank__" +base_treatment+"__"+base_run+"_vs_"+stim_treatment+"__"+stim_run
-            let max_name = "max__" +base_treatment+"__"+base_run+"_vs_"+stim_treatment+"__"+stim_run
-            let logFC_col = "logFC__"+this.globalApplicationState.selected_comparison
-            let pval_col = "statistic__"+this.globalApplicationState.selected_comparison
+            this.n_rna_stim_name = "RNA_barcodes__" +stim_treatment+"__"+stim_run
+            this.n_rna_base_name = "RNA_barcodes__" +base_treatment+"__"+base_run
 
 
             d3.select("#base_text").text("Basal Alpha "+base_treatment + " ("+ base_run +")")
@@ -369,21 +366,21 @@ class Alpha{
             this.globalApplicationState.selected_comparison = base_treatment+"__"+base_run+"_vs_"+stim_treatment+"__"+stim_run
 
             const that = this
-            let selected_data = this.all_data.filter(function(d){return d[that.base_name]!= "";})
-            selected_data = selected_data.filter(function(d){return d[that.stim_name] != "";})
 
-
-            //Filter the same way we filter volcano data so all points are in each 
-            selected_data = selected_data.filter(function(d){return d[pval_col]!= "";})
-            selected_data = selected_data.filter(function(d){return d[logFC_col] != "";})
 
-            this.globalApplicationState.motifs = [...new Set(selected_data.map((item) => item.motif))];
+            let filter_res = this.h.filter_comparison_data(
+                this.all_data, 
+                base_treatment, 
+                stim_treatment, 
+                base_run, 
+                stim_run, 
+                selected_motif, 
+                this.globalApplicationState.min_RNA, 
+                this.globalApplicationState.min_DNA)
+
+            let selected_data = filter_res[0]
+            this.globalApplicationState.motifs = filter_res[1]
 
-            if (selected_motif != ""){
-                selected_data = selected_data.filter(function(d){return d.motif == selected_motif})
-            }
-
-
             let max_base =  d3.max(selected_data.map(d => +d[this.base_name]))
             let max_stim =  d3.max(selected_data.map(d => +d[this.stim_name]))
 

diff --git a/js/helper.js b/js/helper.js
@@ -0,0 +1,64 @@
+const helpers = {
+    filter_comparison_data: function(all_data, base_treatment, stim_treatment, base_run, stim_run, selected_motif, min_RNA, min_DNA){
+        //Takes all the data from for alpha/volcano and filters it.
+        //Returns filtered data frame.
+
+        let selected_comparison = base_treatment+"__"+base_run+"_vs_"+stim_treatment+"__"+stim_run
+        let stim_name = "alpha__"+stim_treatment+"__"+stim_run
+        let base_name = "alpha__"+base_treatment+"__"+base_run
+        let n_rna_stim_name = "RNA_barcodes__" +stim_treatment+"__"+stim_run
+        let n_rna_base_name = "RNA_barcodes__" +base_treatment+"__"+base_run
+        let n_dna_stim_name = "DNA_barcodes__" +stim_treatment+"__"+stim_run
+        let n_dna_base_name = "DNA_barcodes__" +base_treatment+"__"+base_run
+        let logFC_col = "logFC__"+selected_comparison
+        let pval_col = "statistic__"+selected_comparison
+        let statistic_name = "statistic__"+selected_comparison
+
+        //Make sure that the log fc and pval are there
+        //For some architectures MPRAnalyze doesn't call an alpha or fc
+        //We don't want those 
+        let selected_data = all_data.filter(function(d){return d[base_name]!= "";})
+        selected_data = selected_data.filter(function(d){return d[stim_name] != "";})
+        selected_data = selected_data.filter(function(d){return d[pval_col]!= "";})
+        selected_data = selected_data.filter(function(d){return d[logFC_col] != "";})
+
+        //Filter for DNA and RNA counts
+        selected_data = selected_data.filter(function(d){return Math.floor(d[n_rna_stim_name]) >= Math.ceil(min_RNA)})
+        selected_data = selected_data.filter(function(d){return Math.floor(d[n_rna_base_name]) >= Math.ceil(min_RNA)})
+        selected_data = selected_data.filter(function(d){return Math.floor(d[n_dna_stim_name]) >= Math.ceil(min_DNA)})
+        selected_data = selected_data.filter(function(d){return Math.floor(d[n_dna_base_name]) >= Math.ceil(min_DNA)})
+
+        //Get max and min statistics before filtering for motif
+        let max_statistic = d3.max(selected_data.map(d => +d[statistic_name]))
+        let min_statistic = d3.min(selected_data.map(d => +d[statistic_name]))
+
+        let log_fold_changes = selected_data.map(d => d[logFC_col])
+        let max_fc = d3.max(log_fold_changes.map(d=> Number(d)))
+        let min_fc = d3.min(log_fold_changes.map(d=> Number(d)))
+
+        if (min_statistic >= 0){
+            min_statistic = 0
+        }
+        else{ //Get the lower quartile
+            min_statistic = d3.max([-(.2*max_statistic), min_statistic])
+        }
+
+        //Cut off anything that will dip below the min pval
+        selected_data = selected_data.filter(function(d){return d[statistic_name]>=min_statistic;})
+        let motifs = [...new Set(selected_data.map((item) => item.motif))];
+
+
+        // If there is a highlighted motif, filter for it.
+        if (selected_motif != ""){
+            selected_data = selected_data.filter(function(d){return d.motif == selected_motif})
+        }
+
+        return [selected_data, motifs, max_statistic, min_statistic, max_fc, min_fc]
+
+
+
+    }
+
+}
+
+export default helpers;