@sjcrh/proteinpaint-types 2.81.0 → 2.81.5

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sjcrh/proteinpaint-types",
-  "version": "2.81.0",
+  "version": "2.81.5",
   "type": "module",
   "description": "Shared type definitions between ProteinPaint server and client code",
   "main": "src/index.ts",

package/src/dataset.ts

@@ -70,9 +70,9 @@ type InfoFieldEntry = {
 
 /*
 type GenomicPositionEntry = {
-		chr: string
-		start: number
-		stop: number
+                chr: string
+                start: number
+                stop: number
 }
 */
 
@@ -138,12 +138,12 @@ type GdcApi = {
 type SnvIndelFormat = {
 	[index: string]: {
 		/* has value for a non-GT field indicating the variant 
-		is annotated to this sample*/
+        is annotated to this sample*/
 		ID: string
 		Description: string
 		/** 'R' or 1. do not parse values here based on Number="R"
-		as we don't need to compute on the format values on backend
-		client will parse the values for display */
+        as we don't need to compute on the format values on backend
+        client will parse the values for display */
 		Number: string | number
 		Type: string
 	}
@@ -260,8 +260,8 @@ type SnvIndelQuery = {
 	variant_filter?: VariantFilter
 	populations?: Population[]
 	/** NOTE **
-	this definition can appear either in queries.snvindel{} or termdb{}
-	so that it can work for a termdb-less ds, e.g. clinvar, where termdbConfig cannot be made */
+this definition can appear either in queries.snvindel{} or termdb{}
+so that it can work for a termdb-less ds, e.g. clinvar, where termdbConfig cannot be made */
 	ssmUrl?: UrlTemplateSsm
 	m2csq?: {
 		gdcapi?: boolean
@@ -415,21 +415,21 @@ type TrackLstEntry = {
 type CnvSegment = {
 	byrange: CnvSegmentByRange
 	/****** rendering parameters ****
-	not used as query parameter to filter segments
-	value range for color scaling. default to 5. cnv segment value>this will use solid color
-	*/
+not used as query parameter to filter segments
+value range for color scaling. default to 5. cnv segment value>this will use solid color
+*/
 	absoluteValueRenderMax?: number
 	gainColor?: string
 	lossColor?: string
 
 	/*** filtering parameters ***
-	default max length setting to restrict to focal events; if missing show all */
+default max length setting to restrict to focal events; if missing show all */
 	cnvMaxLength?: number
 
 	/** TODO define value type, if logratio, or copy number */
 
 	/** following two cutoffs only apply to log ratio, cnv gain value is positive, cnv loss value is negative
-	if cnv is gain, skip if value<this cutoff */
+if cnv is gain, skip if value<this cutoff */
 	cnvGainCutoff?: number
 	/** if cnv is loss, skip if value>this cutoff */
 	cnvLossCutoff?: number
@@ -448,13 +448,16 @@ for a given region, the median signal from probes in the region is used to make
 this is alternative to CnvSegment
 
 type Probe2Cnv = {
-		file: string
+                file: string
 }
 */
 
 type RnaseqGeneCount = {
+	/** Name of the HDF5 or text file */
 	file: string
 	samplesFile?: string
+	/** Storage_type for storing data (HDF5 or text). Will deprecate text files in the future */
+	storage_type: 'text' | 'HDF5'
 }
 
 /** the metabolite query */
@@ -486,7 +489,10 @@ export type GeneExpressionQueryNative = {
 	get?: (param: any) => void
 	/** This dictionary is used to store/cache the default bins calculated for a geneExpression term when initialized in the fillTermWrapper */
 	geneExpression2bins?: { [index: string]: any }
+	/** Type of data format HDF5 or bed */
+	storage_type?: 'HDF5' | 'bed'
 }
+
 export type GeneExpressionQuery = GeneExpressionQueryGdc | GeneExpressionQueryNative
 
 export type SingleCellGeneExpressionNative = {
@@ -509,11 +515,11 @@ export type SingleCellSamplesNative = {
 	src: 'native'
 
 	/** logic to decide sample table columns (the one shown on singlecell app ui, displaying a table of samples with sc data)
-	a sample table will always have a sample column, to show sample.sample value
-	firstColumnName allow to change name of 1st column from "Sample" to different, e.g. "Case" for gdc
-	the other two properties allow to declare additional columns to be shown in table, that are for display only
-	when sample.experiments[] are used, a last column of experiment id will be auto added
-	*/
+a sample table will always have a sample column, to show sample.sample value
+firstColumnName allow to change name of 1st column from "Sample" to different, e.g. "Case" for gdc
+the other two properties allow to declare additional columns to be shown in table, that are for display only
+when sample.experiments[] are used, a last column of experiment id will be auto added
+*/
 	firstColumnName?: string
 
 	/** do not use for native ds! gdc-only property. kept as optional to avoid tsc err */
@@ -548,11 +554,8 @@ export type SingleCellDataGdc = {
 export type SingleCellDEgeneGdc = {
 	src: 'gdcapi'
 	/** Column name.
-	this must be the colorColumn from one of the plots. so that at the client app, 
-	as soon as the plot data have been loaded and maps rendered, client will find 
-	out the cell groups based on this columnName value, and show a drop down of 
-	these groups on UI. user selects a group, and pass it as request body to backend 
-	to get DE genes for this group */
+this must be the colorColumn from one of the plots. so that at the client app, as soon as the plot data have been loaded and maps rendered, client will find out the cell groups based on this columnName value, and show a drop down of these groups on UI. user selects a group, and pass it as request body to backend to get DE genes for this group
+*/
 	columnName: string
 }
 
@@ -560,6 +563,8 @@ type GDCSingleCellPlot = {
 	name: string
 	colorColumns: ColorColumn[]
 	coordsColumns: { x: number; y: number }
+	/** if true the plot is shown by default. otherwise hidden */
+	selected?: boolean
 }
 
 type ColorColumn = {
@@ -576,21 +581,23 @@ type SingleCellPlot = {
 	/** type of the plot, e.g. tsne or umap, also display as plot name on ui */
 	name: string
 	/** folder in which per-sample files are stored.
-	each file is a tabular text file with all cells (rows) from that sample.
-	all files must have same set of columns
-	file columns include cell types and x/y coords, as described by other parameters
-	*/
+each file is a tabular text file with all cells (rows) from that sample.
+all files must have same set of columns
+file columns include cell types and x/y coords, as described by other parameters
+*/
 	folder: string
 	/** optional suffix to locate the file for a sample, via ${folder}/${sampleName}${fileSuffix}
-	assumes that file name always start with sample name.
-	if not introduce filePrefix
-	*/
+assumes that file name always start with sample name.
+if not introduce filePrefix
+*/
 	fileSuffix?: string
 	/** list of columns in tabular text file that define cell categories and can be used to color the cells in the plot. must have categorical values
 	 */
 	colorColumns: ColorColumn[]
 	/** 0-based column number for x/y coordinate for this plot */
 	coordsColumns: { x: number; y: number }
+	/** if true the plot is shown by default. otherwise hidden */
+	selected?: boolean
 }
 export type SingleCellDataNative = {
 	src: 'native'
@@ -610,9 +617,9 @@ export type SingleCellDataNative = {
 
 export type SingleCellQuery = {
 	/** methods to identify samples with singlecell data,
-	this data allows client-side to display a table with these samples for user to choose from
-	also, sampleView uses this to determine if to invoke the sc plot for a sample
-	*/
+this data allows client-side to display a table with these samples for user to choose from
+also, sampleView uses this to determine if to invoke the sc plot for a sample
+*/
 	samples: SingleCellSamplesGdc | SingleCellSamplesNative
 	/** defines tsne/umap type of clustering maps for each sample
 	 */
@@ -764,8 +771,11 @@ type SelectCohortValuesEntry = {
 	note?: string
 }
 
-type SelectCohortEntry = {
+export type SelectCohortEntry = {
 	term: { id: string; type: string }
+	/** Title above the cohort introduction/content in the about tab */
+	title?: string
+	/** Text above radio cohort options in the about tab. */
 	prompt: string
 	values: SelectCohortValuesEntry[]
 	description?: string
@@ -803,9 +813,9 @@ type ScatterPlotsEntry = {
 	colorTW?: { id: string }
 	colorColumn?: ColorColumn
 	/** provide a sampletype term to filter for specific type of samples for subjects with multiple samples and show in the plot.
-	e.g. to only show D samples from all patients
-	this is limited to only one term and doesn't allow switching between multiple terms
-	*/
+e.g. to only show D samples from all patients
+this is limited to only one term and doesn't allow switching between multiple terms
+*/
 	sampleCategory?: {
 		/** categorical term like "sampleType" which describes types of multiple samples from the same subject */
 		tw: { id: string }
@@ -867,7 +877,7 @@ type SortPriorityEntry = {
 }
 
 type SurvivalSettings = {
-	/** filters out all the survival data with Time-to-Event longer than this maxTimeToEvent */
+	/** The max time-to-event to be displayed in plot, hide all the samples with Time-to-Event longer than this maxTimeToEvent */
 	maxTimeToEvent?: number
 }
 
@@ -985,11 +995,10 @@ type UrlTemplateBase = {
 }
 export type UrlTemplateSsm = UrlTemplateBase & {
 	/** to create separate link, but not directly on chr.pos.ref.alt string.
-	name of link is determined by either namekey or linkText. former allows 
-	to retrieve a name per m that's different from chr.pos.xx */
+    name of link is determined by either namekey or linkText. former allows to retrieve a name per m that's different from chr.pos.xx */
 	shownSeparately?: boolean
 	/** optional name of link, if set, same name will be used for all links. e.g. "ClinVar".
-	if missing, name is value of m[url.namekey], as used in url itself (e.g. snp rsid) */
+if missing, name is value of m[url.namekey], as used in url itself (e.g. snp rsid) */
 	linkText?: string
 }
 
@@ -1013,25 +1022,26 @@ type Termdb = {
 	selectCohort?: SelectCohortEntry
 
 	/** quick fix to convert category values from a term to lower cases for comparison (case insensitive comparison)
-	for gdc, graphql and rest apis return case-mismatching strings for the same category e.g. "Breast/breast"
-	keep this setting here for reason of:
-	- in mds3.gdc.js, when received all-lowercase values from graphql, it's hard to convert them to Title case for comparison
-	- mds3.variant2samples consider this setting, allows to handle other datasets of same issue
-	  */
+for gdc, graphql and rest apis return case-mismatching strings for the same category e.g. "Breast/breast"
+keep this setting here for reason of:
+- in mds3.gdc.js, when received all-lowercase values from graphql, it's hard to convert them to Title case for comparison
+- mds3.variant2samples consider this setting, allows to handle other datasets of same issue
+  */
 	useLower?: boolean
 
 	scatterplots?: Scatterplots
 	matrix?: Matrix
 	survival?: Survival
 	logscaleBase2?: boolean
-	chartConfigByType?: ChartConfigByType
+	plotConfigByCohort?: PlotConfigByCohort
 	/** Functionality */
 	dataDownloadCatch?: DataDownloadCatch
 	helpPages?: URLEntry[]
 	multipleTestingCorrection?: MultipleTestingCorrection
-	/** regression settings for neuro-oncology datasets:
-	- no interaction terms
-	- hide type III stats and miscellaneous statistical tests */
+	/** regression settings for neuro-oncology portals:
+- no interaction terms
+- report event counts of cox coefficients
+- hide type III stats and miscellaneous statistical tests */
 	neuroOncRegression?: boolean
 	urlTemplates?: {
 		/** gene link definition */
@@ -1061,10 +1071,9 @@ type Termdb = {
 	hierCluster?: any
 
 	/** ds customization of rules in TermTypeSelect on what term type to exclude for a usecase.
-	used by gdc in that gene exp cannot be used for filtering 
-	note this applies to left-side term type tabs, but not terms in dict tree. latter 
-	is controlled by excludeTermtypeByTarget
-	*/
+    used by gdc in that gene exp cannot be used for filtering
+    note this applies to left-side term type tabs, but not terms in dict tree. latter is controlled by excludeTermtypeByTarget
+    */
 	useCasesExcluded?: {
 		/** key is target name (todo restrict values), value is array of 1 or more term
 		 * types (todo restrict values) */
@@ -1094,12 +1103,13 @@ type SampleType = {
 	parent_id: string
 }
 
-type ChartConfigByType = {
-	[index: string]: ChartConfig
-}
-
-type ChartConfig = {
-	[key: string]: any
+/** predefined configuration objects per subcohort per plot type */
+type PlotConfigByCohort = {
+	/** key is subcohort string */
+	[index: string]: {
+		/** key is plot type as in mass/charts.js */
+		[key: string]: object
+	}
 }
 
 /** modified version of termwrapper*/
@@ -1303,9 +1313,9 @@ type Svcnv = BaseTrack & {
 
 type KeyLabelFull = {
 	/* Used in: 
-			queries.genefpkm.boxplotbysamplegroup.attributes
-			cohort.hierarchies.lst[i].levels
-	*/
+                queries.genefpkm.boxplotbysamplegroup.attributes
+                cohort.hierarchies.lst[i].levels
+*/
 	k: string
 	label: string
 	full?: string

package/src/index.ts

@@ -20,6 +20,7 @@ export * from './routes/hicgenome.ts'
 export * from './routes/hicstat.ts'
 export * from './routes/sampledzimages.ts'
 export * from './routes/samplewsimages.ts'
+export * from './routes/termdb.boxplot.ts'
 export * from './routes/termdb.categories.ts'
 export * from './routes/termdb.cluster.ts'
 export * from './routes/termdb.DE.ts'

package/src/routes/genesetOverrepresentation.ts

@@ -7,6 +7,8 @@ export type genesetOverrepresentationRequest = {
 	genome: string
 	/** msigdb branch term name. all genesets under this branch will be analyzed */
 	geneSetGroup: string
+	/** Boolean variable describing if non-coding genes should be filtered */
+	filter_non_coding_genes: boolean
 }
 
 export type genesetOverrepresentationResponse = {
@@ -29,4 +31,6 @@ export type gene_overrepresentation_input = {
 	gene_set_group: string
 	/** Path to gene db */
 	genedb: string
+	/** Boolean variable describing if non-coding genes should be filtered */
+	filter_non_coding_genes: boolean
 }

package/src/routes/termdb.DE.ts

@@ -9,10 +9,29 @@ export type DERequest = {
 	min_count: number
 	/** Minimum total read count required for each sample */
 	min_total_count: number
+	/** Storage_type for storing data. Will deprecate text files */
+	storage_type: 'text' | 'HDF5'
 	/** Method of DE used wilcoxon/edgeR */
 	method?: string
 }
 
+export type ExpressionInput = {
+	/** Case samples separated by , */
+	case: string
+	/** Control samples separated by , */
+	control: string
+	/** data_type instructs rust to carry out differential gene expression analysis */
+	data_type: 'do_DE'
+	/** File containing raw gene counts for DE analysis */
+	input_file: string
+	/** Relative cpm cutoff for filtering a gene compared to all samples and genes in dataset */
+	min_count: number
+	/** Minimum total read count required for each sample */
+	min_total_count: number
+	/** Type of storage file: HDF5 or text. Text will be deprecated in the future */
+	storage_type: 'HDF5' | 'text'
+}
+
 export type DEResponse = {
 	/** Array containing objects of each gene containing foldchange, gene name, gene symbol, original pvalue, adjusted pvalue */
 	data: string

package/src/routes/termdb.boxplot.ts

@@ -0,0 +1,40 @@
+export type BoxPlotRequest = {
+	//TOOD: define request
+	tw: any
+}
+
+export type BoxPlotResponse = {
+	plots: BoxPlotEntry[]
+	/** Absolute min value for all plots */
+	absMin: number
+	/** Absolute max value for all plots */
+	absMax: number
+	/** Longest label length for all plots */
+	maxLabelLgth: number
+}
+
+export type BoxPlotEntry = {
+	boxplot: BoxPlotData
+	/** Label to show */
+	label: string
+	// /** Number of samples */
+	// plotValueCount: number
+	/** TODO: Is this needed? */
+	values: number[]
+	/** Lowest min for the scale domain */
+	min: number
+	/** Highest max for the scale domain */
+	max: number
+}
+
+export type BoxPlotData = {
+	w1: number
+	w2: number
+	p05: number
+	p25: number
+	p50: number
+	p75: number
+	p95: number
+	iqr: number
+	out: { value: number }[]
+}