@weng-lab/genomebrowser-ui 0.2.6 → 0.2.8

package/src/TrackSelect/Folders/biosamples/shared/columns.tsx

@@ -5,11 +5,12 @@ import {
   useGridApiContext,
 } from "@mui/x-data-grid-premium";
 import { Stack, capitalize } from "@mui/material";
-import Check from "@mui/icons-material/Check";
 import { AssayIcon, ontologyTypes, assayTypes, lifeStages } from "./constants";
-import { BiosampleRowInfo } from "./types";
+import { BiosampleRowInfo, CollectionType } from "./types";
 
-function CoreCollectionCell(params: GridRenderCellParams<BiosampleRowInfo>) {
+const collectionTypes: CollectionType[] = ["Core", "Ancillary", "Partial"];
+
+function CollectionCell(params: GridRenderCellParams<BiosampleRowInfo>) {
   const apiRef = useGridApiContext();
 
   if (params.rowNode.type !== "group") {
@@ -30,11 +31,7 @@ function CoreCollectionCell(params: GridRenderCellParams<BiosampleRowInfo>) {
     childIds[0],
   ) as BiosampleRowInfo | null;
 
-  if (firstChildRow?.coreCollection) {
-    return <Check color="primary" />;
-  }
-
-  return null;
+  return firstChildRow?.collection ?? null;
 }
 
 const displayNameCol: GridColDef<BiosampleRowInfo> = {
@@ -140,12 +137,13 @@ const lifeStageCol: GridColDef<BiosampleRowInfo> = {
   valueFormatter: (value) => value && capitalize(value),
 };
 
-const coreCollectionCol: GridColDef<BiosampleRowInfo> = {
-  field: "coreCollection",
-  headerName: "Core Collection",
-  type: "boolean",
-  width: 120,
-  renderCell: (params) => <CoreCollectionCell {...params} />,
+const collectionCol: GridColDef<BiosampleRowInfo> = {
+  field: "collection",
+  headerName: "Collection",
+  type: "singleSelect",
+  valueOptions: collectionTypes,
+  width: 100,
+  renderCell: (params) => <CollectionCell {...params} />,
 };
 
 const experimentCol: GridColDef<BiosampleRowInfo> = {
@@ -167,7 +165,7 @@ const idCol: GridColDef<BiosampleRowInfo> = {
 export const sortedByAssayColumns: GridColDef<BiosampleRowInfo>[] = [
   displayNameCol,
   sortedByAssayOntologyCol,
-  coreCollectionCol,
+  collectionCol,
   sampleTypeCol,
   lifeStageCol,
   sortedByAssayAssayCol,
@@ -179,7 +177,7 @@ export const sortedByAssayColumns: GridColDef<BiosampleRowInfo>[] = [
 /** Default columns (ontology as top-level grouping) */
 export const defaultColumns: GridColDef<BiosampleRowInfo>[] = [
   defaultAssayCol,
-  coreCollectionCol,
+  collectionCol,
   sampleTypeCol,
   lifeStageCol,
   defaultOntologyCol,

package/src/TrackSelect/Folders/biosamples/shared/createFolder.ts

@@ -24,7 +24,7 @@ import { BiosampleTreeItem } from "./BiosampleTreeItem";
  * @returns Array of flattened BiosampleRowInfo objects, one per assay
  */
 function flattenTrackIntoRows(track: BiosampleTrackInfo): BiosampleRowInfo[] {
-  const { ontology, lifeStage, sampleType, displayName, core } = track;
+  const { ontology, lifeStage, sampleType, displayName, collection } = track;
 
   // Sort assays so cCRE comes first, then maintain original order for the rest
   const sortedAssays = [...track.assays].sort((a, b) => {
@@ -46,7 +46,7 @@ function flattenTrackIntoRows(track: BiosampleTrackInfo): BiosampleRowInfo[] {
       experimentAccession,
       fileAccession,
       url,
-      coreCollection: core ?? false,
+      collection,
     }),
   );
 }

package/src/TrackSelect/Folders/biosamples/shared/types.ts

@@ -2,6 +2,8 @@
  * Types for biosample folder data
  */
 
+export type CollectionType = "Core" | "Ancillary" | "Partial";
+
 /**
  * Assay information from the JSON data
  */
@@ -23,7 +25,7 @@ export type BiosampleTrackInfo = {
   sampleType: string;
   displayName: string;
   assays: BiosampleAssayInfo[];
-  core?: boolean;
+  collection: CollectionType;
 };
 
 /**
@@ -39,7 +41,7 @@ export type BiosampleRowInfo = {
   experimentAccession: string;
   fileAccession: string;
   url: string;
-  coreCollection: boolean;
+  collection: CollectionType;
 };
 
 /**

package/src/TrackSelect/Folders/biosamples/data/formatBiosamples.go

@@ -1,254 +0,0 @@
-package main
-
-import (
-	"encoding/json"
-	"fmt"
-	"os"
-	"path"
-	"strings"
-)
-
-type RNASeqTrack struct {
-	ID                        string `json:"id"`
-	Title                     string `json:"title"`
-	URL                       string `json:"url"`
-	RNASeqExperimentAccession string `json:"rnaseq_experiment_accession"`
-	RNASeqFileAccession       string `json:"rnaseq_file_accession"`
-}
-
-type OldBiosample struct {
-	Name                       string        `json:"name"`
-	Ontology                   string        `json:"ontology"`
-	LifeStage                  string        `json:"lifeStage"`
-	SampleType                 string        `json:"sampleType"`
-	DisplayName                string        `json:"displayName"`
-	DNaseExperimentAccession   *string       `json:"dnase_experiment_accession"`
-	H3K4Me3ExperimentAccession *string       `json:"h3k4me3_experiment_accession"`
-	H3K27AcExperimentAccession *string       `json:"h3k27ac_experiment_accession"`
-	CTCFExperimentAccession    *string       `json:"ctcf_experiment_accession"`
-	ATACExperimentAccession    *string       `json:"atac_experiment_accession"`
-	DNaseFileAccession         *string       `json:"dnase_file_accession"`
-	H3K4Me3FileAccession       *string       `json:"h3k4me3_file_accession"`
-	H3K27AcFileAccession       *string       `json:"h3k27ac_file_accession"`
-	CTCFFileAccession          *string       `json:"ctcf_file_accession"`
-	ATACFileAccession          *string       `json:"atac_file_accession"`
-	DNaseSignalURL             string        `json:"dnase_signal_url,omitempty"`
-	H3K4Me3SignalURL           string        `json:"h3k4me3_signal_url,omitempty"`
-	H3K27AcSignalURL           string        `json:"h3k27ac_signal_url,omitempty"`
-	CTCFSignalURL              string        `json:"ctcf_signal_url,omitempty"`
-	ATACSignalURL              string        `json:"atac_signal_url,omitempty"`
-	ChromHMM                   string        `json:"chromhmm,omitempty"`
-	ChromHMMURL                string        `json:"chromhmm_url,omitempty"`
-	RNASeqTracks               []RNASeqTrack `json:"rna_seq_tracks"`
-	BigBedURL                  string        `json:"bigbedurl,omitempty"`
-}
-
-type Assay struct {
-	ID                  string `json:"id"`
-	Assay               string `json:"assay"`
-	URL                 string `json:"url"`
-	ExperimentAccession string `json:"experimentAccession"`
-	FileAccession       string `json:"fileAccession"`
-}
-
-type NewBiosample struct {
-	Name        string  `json:"name"`
-	Ontology    string  `json:"ontology"`
-	LifeStage   string  `json:"lifeStage"`
-	SampleType  string  `json:"sampleType"`
-	DisplayName string  `json:"displayName"`
-	Assays      []Assay `json:"assays"`
-}
-
-func main() {
-	if len(os.Args) < 3 {
-		fmt.Println("Usage: go run format.go <input.json> <output.json>")
-		os.Exit(1)
-	}
-
-	inputFile := os.Args[1]
-	outputFile := os.Args[2]
-
-	data, err := os.ReadFile(inputFile)
-	if err != nil {
-		fmt.Printf("Error reading input file: %v\n", err)
-		os.Exit(1)
-	}
-
-	var inputWrapper struct {
-		Data struct {
-			CCREBiosampleQuery struct {
-				Biosamples []OldBiosample `json:"biosamples"`
-			} `json:"ccREBiosampleQuery"`
-		} `json:"data"`
-	}
-	if err := json.Unmarshal(data, &inputWrapper); err != nil {
-		fmt.Printf("Error parsing JSON: %v\n", err)
-		os.Exit(1)
-	}
-	oldSamples := inputWrapper.Data.CCREBiosampleQuery.Biosamples
-
-	var newSamples []NewBiosample
-	for _, old := range oldSamples {
-		newSample := NewBiosample{
-			Name:        old.Name,
-			Ontology:    old.Ontology,
-			LifeStage:   old.LifeStage,
-			SampleType:  old.SampleType,
-			DisplayName: old.DisplayName,
-			Assays:      []Assay{},
-		}
-
-		// Add DNase assay if present
-		if old.DNaseFileAccession != nil {
-			url := old.DNaseSignalURL
-			if url == "" {
-				url = "https://downloads.wenglab.org/Registry-V4/" + *old.DNaseFileAccession + ".bigWig"
-			}
-			newSample.Assays = append(newSample.Assays, Assay{
-				ID:                  "dnase-" + *old.DNaseFileAccession,
-				Assay:               "dnase",
-				URL:                 url,
-				ExperimentAccession: ptrToString(old.DNaseExperimentAccession),
-				FileAccession:       *old.DNaseFileAccession,
-			})
-		}
-
-		// Add H3K4me3 assay if present
-		if old.H3K4Me3FileAccession != nil {
-			url := old.H3K4Me3SignalURL
-			if url == "" {
-				url = "https://downloads.wenglab.org/Registry-V4/" + *old.H3K4Me3FileAccession + ".bigWig"
-			}
-			newSample.Assays = append(newSample.Assays, Assay{
-				ID:                  "h3k4me3-" + *old.H3K4Me3FileAccession,
-				Assay:               "h3k4me3",
-				URL:                 url,
-				ExperimentAccession: ptrToString(old.H3K4Me3ExperimentAccession),
-				FileAccession:       *old.H3K4Me3FileAccession,
-			})
-		}
-
-		// Add H3K27ac assay if present
-		if old.H3K27AcFileAccession != nil {
-			url := old.H3K27AcSignalURL
-			if url == "" {
-				url = "https://downloads.wenglab.org/Registry-V4/" + *old.H3K27AcFileAccession + ".bigWig"
-			}
-			newSample.Assays = append(newSample.Assays, Assay{
-				ID:                  "h3k27ac-" + *old.H3K27AcFileAccession,
-				Assay:               "h3k27ac",
-				URL:                 url,
-				ExperimentAccession: ptrToString(old.H3K27AcExperimentAccession),
-				FileAccession:       *old.H3K27AcFileAccession,
-			})
-		}
-
-		// Add CTCF assay if present
-		if old.CTCFFileAccession != nil {
-			url := old.CTCFSignalURL
-			if url == "" {
-				url = "https://downloads.wenglab.org/Registry-V4/" + *old.CTCFFileAccession + ".bigWig"
-			}
-			newSample.Assays = append(newSample.Assays, Assay{
-				ID:                  "ctcf-" + *old.CTCFFileAccession,
-				Assay:               "ctcf",
-				URL:                 url,
-				ExperimentAccession: ptrToString(old.CTCFExperimentAccession),
-				FileAccession:       *old.CTCFFileAccession,
-			})
-		}
-
-		// Add ATAC assay if present
-		if old.ATACFileAccession != nil {
-			url := old.ATACSignalURL
-			if url == "" {
-				url = "https://downloads.wenglab.org/Registry-V4/" + *old.ATACFileAccession + ".bigWig"
-			}
-			newSample.Assays = append(newSample.Assays, Assay{
-				ID:                  "atac-" + *old.ATACFileAccession,
-				Assay:               "atac",
-				URL:                 url,
-				ExperimentAccession: ptrToString(old.ATACExperimentAccession),
-				FileAccession:       *old.ATACFileAccession,
-			})
-		}
-
-		// Add ChromHMM assay if present
-		if old.ChromHMMURL != "" {
-			chromhmmAccession := extractAccessionFromURL(old.ChromHMMURL)
-			newSample.Assays = append(newSample.Assays, Assay{
-				ID:            "chromhmm-" + chromhmmAccession,
-				Assay:         "chromhmm",
-				URL:           old.ChromHMMURL,
-				FileAccession: chromhmmAccession,
-			})
-		}
-
-		// Add RNA-seq tracks
-		for _, rna := range old.RNASeqTracks {
-			url := rna.URL
-			if url == "" {
-				url = "https://downloads.wenglab.org/Registry-V4/" + rna.RNASeqFileAccession + ".bigWig"
-			}
-			newSample.Assays = append(newSample.Assays, Assay{
-				ID:                  "rnaseq-" + rna.RNASeqFileAccession,
-				Assay:               "rnaseq",
-				URL:                 url,
-				ExperimentAccession: rna.RNASeqExperimentAccession,
-				FileAccession:       rna.RNASeqFileAccession,
-			})
-		}
-
-		// Add cCRE bigBed as an assay
-		if old.BigBedURL != "" {
-			ccreAccession := extractAccessionFromURL(old.BigBedURL)
-			newSample.Assays = append(newSample.Assays, Assay{
-				ID:            "ccre-" + ccreAccession,
-				Assay:         "ccre",
-				URL:           old.BigBedURL,
-				FileAccession: ccreAccession,
-			})
-		}
-
-		newSamples = append(newSamples, newSample)
-	}
-
-	// Wrap in object with "tracks" key to match expected format
-	wrapper := struct {
-		Tracks []NewBiosample `json:"tracks"`
-	}{
-		Tracks: newSamples,
-	}
-
-	output, err := json.MarshalIndent(wrapper, "", "  ")
-	if err != nil {
-		fmt.Printf("Error marshaling JSON: %v\n", err)
-		os.Exit(1)
-	}
-
-	if err := os.WriteFile(outputFile, output, 0644); err != nil {
-		fmt.Printf("Error writing output file: %v\n", err)
-		os.Exit(1)
-	}
-
-	fmt.Printf("Successfully converted %d biosamples to %s\n", len(newSamples), outputFile)
-}
-
-func ptrToString(s *string) string {
-	if s == nil {
-		return ""
-	}
-	return *s
-}
-
-// extractAccessionFromURL extracts the file accession from a URL
-// e.g., "https://downloads.wenglab.org/Registry-V4/ENCFF170YYM.bigBed" -> "ENCFF170YYM"
-// e.g., "https://downloads.wenglab.org/Registry-V4/ENCFF606INL_ENCFF501ILD.bigBed" -> "ENCFF606INL_ENCFF501ILD"
-func extractAccessionFromURL(url string) string {
-	// Get the filename from the URL
-	filename := path.Base(url)
-	// Remove the extension
-	ext := path.Ext(filename)
-	return strings.TrimSuffix(filename, ext)
-}

package/src/TrackSelect/Folders/biosamples/data/mark_core.go

@@ -1,158 +0,0 @@
-//go:build ignore
-
-package main
-
-import (
-	"bufio"
-	"encoding/json"
-	"fmt"
-	"os"
-	"regexp"
-	"strings"
-)
-
-type Assay struct {
-	ID                  string `json:"id"`
-	Assay               string `json:"assay"`
-	URL                 string `json:"url"`
-	ExperimentAccession string `json:"experimentAccession"`
-	FileAccession       string `json:"fileAccession"`
-}
-
-type Track struct {
-	Name        string  `json:"name"`
-	Core        bool    `json:"core,omitempty"`
-	Ontology    string  `json:"ontology"`
-	LifeStage   string  `json:"lifeStage"`
-	SampleType  string  `json:"sampleType"`
-	DisplayName string  `json:"displayName"`
-	Assays      []Assay `json:"assays"`
-}
-
-type BiosampleData struct {
-	Tracks []Track `json:"tracks"`
-}
-
-// CoreSample represents a sample to be marked as core, with donor ID and display name
-type CoreSample struct {
-	DonorID     string
-	DisplayName string
-}
-
-func main() {
-	// Extract core samples from test.txt (donor ID + display name pairs)
-	coreSamples, err := extractCoreSamples("test.txt")
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "Error reading test.txt: %v\n", err)
-		os.Exit(1)
-	}
-	fmt.Printf("Found %d core samples to mark\n", len(coreSamples))
-
-	// Load human.json
-	data, err := os.ReadFile("human.json")
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "Error reading human.json: %v\n", err)
-		os.Exit(1)
-	}
-
-	var biosampleData BiosampleData
-	if err := json.Unmarshal(data, &biosampleData); err != nil {
-		fmt.Fprintf(os.Stderr, "Error parsing human.json: %v\n", err)
-		os.Exit(1)
-	}
-	fmt.Printf("Loaded %d tracks\n", len(biosampleData.Tracks))
-
-	// Mark tracks as core if they match both donor ID and display name
-	markedCount := 0
-	alreadyCore := 0
-	for i := range biosampleData.Tracks {
-		track := &biosampleData.Tracks[i]
-		for _, sample := range coreSamples {
-			// Check if track name ends with the donor ID AND display name matches (case-insensitive)
-			if strings.HasSuffix(track.Name, "_"+sample.DonorID) &&
-				strings.EqualFold(track.DisplayName, sample.DisplayName) {
-				if track.Core {
-					alreadyCore++
-				} else {
-					track.Core = true
-					markedCount++
-				}
-				break
-			}
-		}
-	}
-	fmt.Printf("Marked %d tracks as core (already core: %d)\n", markedCount, alreadyCore)
-
-	// Write to temp file
-	output, err := json.MarshalIndent(biosampleData, "", "  ")
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "Error marshaling JSON: %v\n", err)
-		os.Exit(1)
-	}
-
-	if err := os.WriteFile("human_updated.json", output, 0644); err != nil {
-		fmt.Fprintf(os.Stderr, "Error writing human_updated.json: %v\n", err)
-		os.Exit(1)
-	}
-	fmt.Println("Wrote updated data to human_updated.json")
-}
-
-// extractCoreSamples parses test.txt and extracts donor ID + display name pairs
-// Format: "Organ \t Type \t ENCDO... \t DisplayName: (1) cCREs \t Data format"
-func extractCoreSamples(filename string) ([]CoreSample, error) {
-	file, err := os.Open(filename)
-	if err != nil {
-		return nil, err
-	}
-	defer file.Close()
-
-	var samples []CoreSample
-	donorRe := regexp.MustCompile(`ENCDO\w+`)
-
-	scanner := bufio.NewScanner(file)
-	for scanner.Scan() {
-		line := scanner.Text()
-		if strings.TrimSpace(line) == "" {
-			continue
-		}
-
-		// Find the donor ID
-		donorMatch := donorRe.FindString(line)
-		if donorMatch == "" {
-			continue
-		}
-
-		// Extract display name: it's after the donor ID, before ": (1)"
-		// Split by donor ID to get the part after it
-		parts := strings.SplitN(line, donorMatch, 2)
-		if len(parts) < 2 {
-			continue
-		}
-
-		afterDonor := parts[1]
-		// Remove leading tab/whitespace
-		afterDonor = strings.TrimLeft(afterDonor, " \t")
-
-		// Extract the display name (before ": (1)" or ":(1)")
-		displayName := afterDonor
-		if idx := strings.Index(afterDonor, ": ("); idx != -1 {
-			displayName = afterDonor[:idx]
-		} else if idx := strings.Index(afterDonor, ":("); idx != -1 {
-			displayName = afterDonor[:idx]
-		}
-
-		displayName = strings.TrimSpace(displayName)
-		if displayName != "" {
-			samples = append(samples, CoreSample{
-				DonorID:     donorMatch,
-				DisplayName: displayName,
-			})
-		}
-	}
-
-	if err := scanner.Err(); err != nil {
-		return nil, err
-	}
-
-	return samples, nil
-}