diff --git a/Gemfile.lock b/Gemfile.lock
index 5961226b4..6ddfe014f 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -339,11 +339,11 @@ GEM
       net-protocol
     netrc (0.11.0)
     nio4r (2.7.4)
-    nokogiri (1.18.4-arm64-darwin)
+    nokogiri (1.18.8-arm64-darwin)
       racc (~> 1.4)
-    nokogiri (1.18.4-x86_64-darwin)
+    nokogiri (1.18.8-x86_64-darwin)
       racc (~> 1.4)
-    nokogiri (1.18.4-x86_64-linux-gnu)
+    nokogiri (1.18.8-x86_64-linux-gnu)
       racc (~> 1.4)
     oauth2 (1.4.7)
       faraday (>= 0.8, < 2.0)
diff --git a/app/javascript/lib/validation/ontology-validation.js b/app/javascript/lib/validation/ontology-validation.js
index 1d7661844..fe3250622 100644
--- a/app/javascript/lib/validation/ontology-validation.js
+++ b/app/javascript/lib/validation/ontology-validation.js
@@ -12,9 +12,7 @@
 
 import { decompressSync, strFromU8 } from 'fflate'
 
-import {
-  metadataSchema, REQUIRED_CONVENTION_COLUMNS
-} from './shared-validation'
+import { metadataSchema } from './shared-validation'
 
 // TODO: Replace "development" with "main" after next ingest release
 const ONTOLOGY_BASE_URL =
@@ -136,24 +134,32 @@ export async function fetchOntologies() {
   return ontologies
 }
 
-/** Get lowercase shortnames for all required ontologies */
-function getOntologyShortNames() {
-  let requiredOntologies = []
-
-  // Validate IDs for species, organ, disease, and library preparation protocol
-  for (let i = 0; i < REQUIRED_CONVENTION_COLUMNS.length; i++) {
-    const column = REQUIRED_CONVENTION_COLUMNS[i]
-    if (!column.endsWith('__ontology_label')) {continue}
-    const key = column.split('__ontology_label')[0]
-    const ontologies = getAcceptedOntologies(key, metadataSchema)
-    requiredOntologies = requiredOntologies.concat(ontologies)
-  }
+/** Get lowercase shortnames for all supported ontologies */
+export function getOntologyShortNames() {
+  let supportedOntologies = []
 
-  requiredOntologies = Array.from(
-    new Set(requiredOntologies.map(o => o.toLowerCase()))
-  )
+  // get all ontology-based properties, ignoring organ_region as it isn't minified
+  const properties = getOntologyBasedProps()
+  for (let i = 0; i < properties.length; i++) {
+    const prop = properties[i]
+    const ontologies = getAcceptedOntologies(prop, metadataSchema)
+    supportedOntologies = supportedOntologies.concat(ontologies)
+  }
+  return Array.from(new Set(supportedOntologies.map(o => o.toLowerCase())))
+}
 
-  return requiredOntologies
+/** get all metadata properties that are ontology-based */
+export function getOntologyBasedProps() {
+  const ontologyProps = []
+  // ignore organ_region as it isn't a supported minified ontology
+  const properties = Object.keys(metadataSchema.properties).filter(p => p !== 'organ_region')
+  for (let i = 0; i < properties.length; i++) {
+    const prop = properties[i]
+    if (metadataSchema.properties[prop].ontology) {
+      ontologyProps.push(prop)
+    }
+  }
+  return ontologyProps
 }
 
 /**
@@ -168,7 +174,7 @@ export function getAcceptedOntologies(key, metadataSchema) {
   const acceptedOntologies =
     olsUrls?.split(',').map(url => url.split('/').slice(-1)[0].toUpperCase())
 
-  if (acceptedOntologies.includes('NCBITAXON')) {
+  if (acceptedOntologies && acceptedOntologies.includes('NCBITAXON')) {
     acceptedOntologies.push('NCBITaxon')
   }
 
diff --git a/app/javascript/lib/validation/shared-validation.js b/app/javascript/lib/validation/shared-validation.js
index 8f902120d..9bc50b00a 100644
--- a/app/javascript/lib/validation/shared-validation.js
+++ b/app/javascript/lib/validation/shared-validation.js
@@ -313,3 +313,13 @@ export function timeOutCSFV(chunker) {
   }
   return issues
 }
+
+/** get ontology shortname from an identifier */
+export function getOntologyShortNameLc(identifier) {
+  return identifier.split(/[_:]/)[0].toLowerCase()
+}
+
+export function getLabelSuffixForOntology(indentifier) {
+  const shortName = getOntologyShortNameLc(indentifier)
+  return shortName === 'uo' ? '_label' : '__ontology_label'
+}
diff --git a/app/javascript/lib/validation/validate-anndata.js b/app/javascript/lib/validation/validate-anndata.js
index 7d71a0ac7..4b5329fdf 100644
--- a/app/javascript/lib/validation/validate-anndata.js
+++ b/app/javascript/lib/validation/validate-anndata.js
@@ -3,10 +3,12 @@ import { openH5File } from 'hdf5-indexed-reader'
 import { getOAuthToken } from '~/lib/scp-api'
 import {
   validateUnique, validateRequiredMetadataColumns,
-  validateAlphanumericAndUnderscores,
+  validateAlphanumericAndUnderscores, getOntologyShortNameLc,
   metadataSchema, REQUIRED_CONVENTION_COLUMNS
 } from './shared-validation'
-import { getAcceptedOntologies, fetchOntologies } from './ontology-validation'
+import { fetchOntologies, getOntologyBasedProps, getAcceptedOntologies } from './ontology-validation'
+
+const ONTOLOGY_PROPS = getOntologyBasedProps()
 
 /** Get ontology ID values for key in AnnData file */
 async function getOntologyIds(key, hdf5File) {
@@ -26,7 +28,7 @@ async function getOntologyIds(key, hdf5File) {
   if (internalCategories) {
     resolvedCategories = await Promise.all(internalCategories.values)
   }
-  const group = resolvedCategories.find(o => o.name.endsWith(key))
+  const group = resolvedCategories.find(o => findMatchingGroup(o, key))
   if (group) {
     let categories
     if (internalCategories) {
@@ -40,6 +42,11 @@ async function getOntologyIds(key, hdf5File) {
   return ontologyIds
 }
 
+/** find a group in /obs based on exact name match */
+export function findMatchingGroup(category, key) {
+  return category.name.split('/').slice(-1)[0] === key
+}
+
 /** Get annotation headers for a key (e.g. obs) from an HDF5 file */
 async function getAnnotationHeaders(key, hdf5File) {
   const obsGroup = await hdf5File.get(key)
@@ -122,7 +129,7 @@ export function checkOntologyIdFormat(key, ontologyIds) {
 }
 
 /** Validate author's annotation labels and IDs match those in ontologies */
-async function checkOntologyLabelsAndIds(key, ontologies, groups) {
+export async function checkOntologyLabelsAndIds(key, ontologies, groups) {
   const [ids, idIndexes, labels, labelIndexes] = groups
 
   const issues = []
@@ -138,7 +145,7 @@ async function checkOntologyLabelsAndIds(key, ontologies, groups) {
 
   rawUniques.map(r => {
     let [id, label] = r.split(' || ')
-    const ontologyShortNameLc = id.split(/[_:]/)[0].toLowerCase()
+    const ontologyShortNameLc = getOntologyShortNameLc(id)
     const ontology = ontologies[ontologyShortNameLc]
 
     if (id.includes(':')) {
@@ -146,7 +153,6 @@ async function checkOntologyLabelsAndIds(key, ontologies, groups) {
       const idParts = id.split(':')
       id = `${idParts[0]}_${idParts[1]}`
     }
-
     if (!(id in ontology)) {
       // Register invalid ontology ID
       const msg = `Invalid ontology ID: ${id}`
@@ -174,9 +180,10 @@ async function checkOntologyLabelsAndIds(key, ontologies, groups) {
 }
 
 /** Get ontology ID values for key in AnnData file */
-async function getOntologyIdsAndLabels(requiredName, hdf5File) {
+export async function getOntologyIdsAndLabels(columnName, hdf5File) {
   const obs = await hdf5File.get('obs')
   const obsValues = await Promise.all(obs.values)
+  const isRequired = REQUIRED_CONVENTION_COLUMNS.includes(columnName)
 
   // Old versions of the AnnData spec used __categories as an obs.
   // However, in new versions (since before 2023-01-23) of AnnData spec,
@@ -192,11 +199,14 @@ async function getOntologyIdsAndLabels(requiredName, hdf5File) {
     return null
   }
 
-  const idKey = requiredName
-  const labelKey = `${requiredName}__ontology_label`
+  const idKey = columnName
+  const labelKey = `${columnName}__ontology_label`
+
+  const idGroup = obsValues.find(o => findMatchingGroup(o, idKey))
+  const labelGroup = obsValues.find(o => findMatchingGroup(o, labelKey))
 
-  const idGroup = obsValues.find(o => o.name.endsWith(idKey))
-  const labelGroup = obsValues.find(o => o.name.endsWith(labelKey))
+  // exit when optional metadata isn't found, like cell_type
+  if (!idGroup && !isRequired) { return }
 
   // AnnData organizes each "obs" annotation (e.g. disease__ontology_label,
   // sex) into a container with a `categories` frame and a `code` frame.
@@ -231,15 +241,13 @@ async function validateOntologyLabelsAndIds(hdf5File) {
   const ontologies = await fetchOntologies()
 
   // Validate IDs for species, organ, disease, and library preparation protocol
-  for (let i = 0; i < REQUIRED_CONVENTION_COLUMNS.length; i++) {
-    const column = REQUIRED_CONVENTION_COLUMNS[i]
-    if (!column.endsWith('__ontology_label')) {continue}
-    const key = column.split('__ontology_label')[0]
-    const groups = await getOntologyIdsAndLabels(key, hdf5File)
+  for (let i = 0; i < ONTOLOGY_PROPS.length; i++) {
+    const column = ONTOLOGY_PROPS[i]
+    const groups = await getOntologyIdsAndLabels(column, hdf5File)
 
     if (groups) {
       issues = issues.concat(
-        await checkOntologyLabelsAndIds(key, ontologies, groups)
+        await checkOntologyLabelsAndIds(column, ontologies, groups)
       )
     }
   }
@@ -253,14 +261,12 @@ async function validateOntologyIdFormat(hdf5File) {
   let issues = []
 
   // Validate IDs for species, organ, disease, and library preparation protocol
-  for (let i = 0; i < REQUIRED_CONVENTION_COLUMNS.length; i++) {
-    const column = REQUIRED_CONVENTION_COLUMNS[i]
-    if (!column.endsWith('__ontology_label')) {continue}
-    const key = column.split('__ontology_label')[0]
-    const ontologyIds = await getOntologyIds(key, hdf5File)
+  for (let i = 0; i < ONTOLOGY_PROPS.length; i++) {
+    const column = ONTOLOGY_PROPS[i]
+    const ontologyIds = await getOntologyIds(column, hdf5File)
 
     issues = issues.concat(
-      checkOntologyIdFormat(key, ontologyIds)
+      checkOntologyIdFormat(column, ontologyIds)
     )
   }
 
diff --git a/app/javascript/lib/validation/validate-file-content.js b/app/javascript/lib/validation/validate-file-content.js
index b3e42ebc1..535dacab8 100644
--- a/app/javascript/lib/validation/validate-file-content.js
+++ b/app/javascript/lib/validation/validate-file-content.js
@@ -22,7 +22,8 @@ import {
 } from './shared-validation'
 import { parseDifferentialExpressionFile } from './validate-differential-expression'
 import { parseAnnDataFile } from './validate-anndata'
-
+import { fetchOntologies, getOntologyBasedProps } from '~/lib/validation/ontology-validation'
+import { getOntologyShortNameLc, getLabelSuffixForOntology } from './shared-validation'
 
 /**
  * Gzip decompression requires reading the whole file, given the current
@@ -36,7 +37,7 @@ const MAX_GZIP_FILESIZE = 50 * oneMiB
 
 /** File extensions / suffixes that indicate content must be gzipped */
 const EXTENSIONS_MUST_GZIP = ['gz', 'bam', 'tbi', 'csi']
-
+const ONTOLOGY_PROPS = getOntologyBasedProps()
 
 /**
  * Helper function to verify first pair of headers is NAME or TYPE
@@ -217,7 +218,11 @@ export async function parseMetadataFile(chunker, mimeType, fileOptions) {
   const { headers, delimiter } = await getParsedHeaderLines(chunker, mimeType)
   let issues = validateCapFormat(headers)
   issues = issues.concat(validateNoMetadataCoordinates(headers))
+  let ontologies
+  // keep track of a map of ontology-based errors to avoid duplications
+  const knownErrors = []
   if (fileOptions.use_metadata_convention) {
+    ontologies = await fetchOntologies()
     issues = issues.concat(validateRequiredMetadataColumns(headers))
   }
 
@@ -232,12 +237,87 @@ export async function parseMetadataFile(chunker, mimeType, fileOptions) {
       issues = issues.concat(validateUniqueCellNamesWithinFile(line, isLastLine, dataObj))
       issues = issues.concat(validateMetadataLabelMatches(headers, line, isLastLine, dataObj))
       issues = issues.concat(validateGroupColumnCounts(headers, line, isLastLine, dataObj))
+      if (fileOptions.use_metadata_convention) {
+        issues = issues.concat(validateConventionTerms(headers, line, ontologies, knownErrors))
+      }
     // add other line-by-line validations here
     }
   })
   return { issues, delimiter, numColumns: headers[0].length }
 }
 
+/** validate all ontology-based convention terms in a given line */
+export function validateConventionTerms(headers, line, ontologies, knownErrors) {
+  let issues = []
+  const metadataHeaders = headers[0]
+  for (let i = 0; i < metadataHeaders.length; i++) {
+    const header = metadataHeaders[i]
+    if (ONTOLOGY_PROPS.includes(header)) {
+      const ontologyId = line[i]
+      const labelHeader = `${header}${getLabelSuffixForOntology(ontologyId)}`
+      const labelIdx = metadataHeaders.indexOf(labelHeader)
+      const label = line[labelIdx]
+      issues = issues.concat(validateOntologyTerm(header, ontologyId, label, ontologies, knownErrors))
+    }
+  }
+  return issues
+}
+
+/** validate a single ontology ID against stored ontologies and return issues */
+export function validateOntologyTerm(prop, ontologyId, label, ontologies, knownErrors) {
+  const issues = []
+  const ontologyShortNameLc = getOntologyShortNameLc(ontologyId)
+  const ontology = ontologies[ontologyShortNameLc]
+
+  if (ontologyId.includes(':')) {
+    // Convert colon to underscore for ontology lookup
+    const idParts = ontologyId.split(':')
+    ontologyId = `${idParts[0]}_${idParts[1]}`
+  }
+
+  let errorIdentifier
+  let issue
+
+  if (!ontology) {
+    errorIdentifier = `${ontologyId}-label-lookup-error`
+    const accepted = Object.keys(ontologies).join(', ')
+    const msg =
+      `Ontology ID "${ontologyId}" ` +
+      `is not among accepted ontologies (${accepted}) ` +
+      `for key "${prop}"`
+
+    issue = ['error', 'ontology:label-lookup-error', msg]
+  } else if (!(ontologyId in ontology)) {
+    // Register invalid ontology ID
+    const msg = `Invalid ontology ID: ${ontologyId}`
+    errorIdentifier = `${ontologyId}-invalid-id`
+    issue = [
+      'error', 'ontology:label-lookup-error', msg,
+      { subtype: 'ontology:invalid-id' }
+    ]
+  } else {
+    const validLabels = ontology[ontologyId]
+
+    if (!(validLabels.includes(label))) {
+      errorIdentifier = `${ontologyId}-label-lookup-error`
+      // Register invalid ontology label
+      const prettyLabels = validLabels.join(', ')
+      const validLabelsClause = `Valid labels for ${ontologyId}: ${prettyLabels}`
+      const msg = `Invalid ${prop} label "${label}".  ${validLabelsClause}`
+      issue = [
+        'error', 'ontology:label-not-match-id', msg,
+        { subtype: 'ontology:invalid-label' }
+      ]
+    }
+  }
+  // only store unique instances of errors since we're validating line by line
+  if (issue && knownErrors.indexOf(errorIdentifier) < 0) {
+    issues.push(issue)
+    knownErrors.push(errorIdentifier)
+  }
+  return issues
+}
+
 /** parse a cluster file, and return an array of issues, along with file parsing info */
 export async function parseClusterFile(chunker, mimeType) {
   const { headers, delimiter } = await getParsedHeaderLines(chunker, mimeType)
diff --git a/app/models/ingest_job.rb b/app/models/ingest_job.rb
index 146de3faa..feec299ba 100644
--- a/app/models/ingest_job.rb
+++ b/app/models/ingest_job.rb
@@ -1044,7 +1044,7 @@ def log_to_mixpanel
     mixpanel_log_props = get_job_analytics
     # log job properties to Mixpanel
     MetricsService.log(mixpanel_event_name, mixpanel_log_props, user)
-    report_anndata_summary if study_file.is_viz_anndata? && !%i[ingest_anndata differential_expression].include?(action)
+    report_anndata_summary if study_file.is_viz_anndata?
   end
 
   # set a mixpanel event name based on action
@@ -1087,7 +1087,7 @@ def anndata_summary_props
       commands = client.get_job_command_line(job:)
       commands.detect { |c| c == '--extract' } || client.job_error(job.name).present?
     end.count
-    num_files_extracted += 1 if extracted_raw_counts?(initial_extract)
+    num_files_extracted += 1 if extracted_raw_counts?(initial_extract) && job_status == 'success'
     # event properties for Mixpanel summary event
     {
       perfTime: job_perftime,
@@ -1115,10 +1115,20 @@ def extracted_raw_counts?(job)
     extract_params.include?('raw_counts')
   end
 
+  # determine if this job qualifies for sending an ingestSummary event
+  # will return false if summary exists, this is a DE job, or
+  # a successful AnnData extract (meaning downstream jobs are running)
+  def skip_anndata_summary?
+    study_file.has_anndata_summary? ||
+      action == :differential_expression ||
+      should_retry? ||
+      (!failed? && action == :ingest_anndata)
+  end
+
   # report a summary of all AnnData extraction for this file to Mixpanel, if this is the last job
   def report_anndata_summary
     study_file.reload
-    return false if study_file.has_anndata_summary? # don't bother checking if summary is already sent
+    return false if skip_anndata_summary?
 
     file_identifier = "#{study_file.upload_file_name} (#{study_file.id})"
     Rails.logger.info "Checking AnnData summary for #{file_identifier} after #{action}"
diff --git a/package.json b/package.json
index 434ab4617..73291a722 100644
--- a/package.json
+++ b/package.json
@@ -105,7 +105,7 @@
     "prop-types": "^15.7.2",
     "react-select-event": "^5.3.0",
     "stylelint-prettier": "^1.1.2",
-    "vite": "^4.5.10",
+    "vite": "^4.5.13",
     "vite-plugin-ruby": "^3.0.5"
   }
 }
diff --git a/test/js/lib/ontology-validation.test.js b/test/js/lib/ontology-validation.test.js
index f0f06e171..b461cb469 100644
--- a/test/js/lib/ontology-validation.test.js
+++ b/test/js/lib/ontology-validation.test.js
@@ -1,7 +1,8 @@
 const fetch = require('node-fetch')
 
+import { metadataSchema } from 'lib/validation/shared-validation'
 import {
-  fetchOntologies
+  fetchOntologies, getOntologyShortNames, getOntologyBasedProps
 } from 'lib/validation/ontology-validation'
 
 import {
@@ -9,6 +10,7 @@ import {
 } from './node-web-api'
 
 describe('Client-side file validation for AnnData', () => {
+  const expectedOntologyNames = ['cl', 'uo', 'mondo', 'pato', 'hancestro', 'efo', 'uberon', 'ncbitaxon']
   beforeAll(() => {
     global.fetch = fetch
 
@@ -20,9 +22,21 @@ describe('Client-side file validation for AnnData', () => {
 
   it('Parses minified ontologies', async () => {
     const ontologies = await fetchOntologies()
-    const expectedOntologyNames = ['mondo', 'pato', 'efo', 'uberon', 'ncbitaxon']
     expect(Object.keys(ontologies)).toEqual(expectedOntologyNames)
     const expectedSpeciesNames = ['Homo sapiens', 'human']
     expect(ontologies.ncbitaxon['NCBITaxon_9606']).toEqual(expectedSpeciesNames)
   })
+
+  it('finds all ontology-based metadata properties', () => {
+    const propNames = Object.keys(metadataSchema.properties).filter(p => {
+      return p !== 'organ_region' && metadataSchema.properties[p].ontology
+    })
+    const ontologyProps = getOntologyBasedProps()
+    expect(propNames).toEqual(ontologyProps)
+  })
+
+  it('loads all ontology shortnames', () => {
+    const shortNames = getOntologyShortNames()
+    expect(shortNames).toEqual(expectedOntologyNames)
+  })
 })
diff --git a/test/js/lib/validate-anndata.test.js b/test/js/lib/validate-anndata.test.js
index 71232650a..f2e686c87 100644
--- a/test/js/lib/validate-anndata.test.js
+++ b/test/js/lib/validate-anndata.test.js
@@ -1,10 +1,26 @@
 import {
-  getHdf5File, parseAnnDataFile, getAnnDataHeaders, checkOntologyIdFormat
+  getHdf5File, parseAnnDataFile, getAnnDataHeaders, checkOntologyIdFormat, getOntologyIdsAndLabels,
+  checkOntologyLabelsAndIds, findMatchingGroup
 } from 'lib/validation/validate-anndata'
+import { fetchOntologies } from '~/lib/validation/ontology-validation'
+const fetch = require('node-fetch')
+import {
+  nodeCaches, nodeHeaders, nodeRequest, nodeResponse
+} from './node-web-api'
 
 const BASE_URL = 'https://github.com/broadinstitute/single_cell_portal_core/raw/development/test/test_data/anndata'
 
 describe('Client-side file validation for AnnData', () => {
+  beforeAll(() => {
+    jest.setTimeout(10000)
+    global.fetch = fetch
+
+    global.caches = nodeCaches;
+    global.Response = nodeResponse
+    global.Request = nodeRequest
+    global.Headers = nodeHeaders
+  })
+
   it('Parses AnnData headers', async () => {
     const url = `${BASE_URL}/valid.h5ad`
     const expectedHeaders = [
@@ -78,6 +94,35 @@ describe('Client-side file validation for AnnData', () => {
     expect(parseResults.issues[0]).toEqual(expectedIssue)
   })
 
+  it('validates ontology ids for given column', async () => {
+    const ontologies = await fetchOntologies()
+    const url = `${BASE_URL}/valid.h5ad`
+    const remoteProps = { url }
+    const hdf5File = await getHdf5File(url, remoteProps)
+    const key = 'disease'
+    const groups = await getOntologyIdsAndLabels(key, hdf5File)
+    let issues = await checkOntologyLabelsAndIds(key, ontologies, groups)
+    expect(issues).toHaveLength(0)
+  })
+
+  it('finds invalidate ontology entries for a given column', async () => {
+    const ontologies = await fetchOntologies()
+    const url = `${BASE_URL}/invalid_disease_label.h5ad`
+    const remoteProps = { url }
+    const hdf5File = await getHdf5File(url, remoteProps)
+    const key = 'disease'
+    const groups = await getOntologyIdsAndLabels(key, hdf5File)
+    let issues = await checkOntologyLabelsAndIds(key, ontologies, groups)
+    expect(issues).toHaveLength(1)
+  })
+
+  it('finds the correct obs group based on name', () => {
+    const validGroup = { name: '/obs/cell_type' }
+    const invalidGroup = { name: '/obs/author_cell_type' }
+    expect(findMatchingGroup(validGroup, 'cell_type')).toBeTruthy()
+    expect(findMatchingGroup(invalidGroup, 'cell_type')).not.toBeTruthy()
+  })
+
   // TODO (SCP-5813): Uncomment this test upon completing "Enable ontology validation for remote AnnData"
   //
   // it('Parses AnnData rows and reports invalid ontology labels', async () => {
diff --git a/test/js/lib/validate-file-content.test.js b/test/js/lib/validate-file-content.test.js
index 7f888b6c1..dc7e3c050 100644
--- a/test/js/lib/validate-file-content.test.js
+++ b/test/js/lib/validate-file-content.test.js
@@ -1,9 +1,14 @@
 import React from 'react'
+const fetch = require('node-fetch')
 import { render, screen } from '@testing-library/react'
 import '@testing-library/jest-dom/extend-expect'
 
 import ValidateFile from 'lib/validation/validate-file'
-import { REQUIRED_CONVENTION_COLUMNS } from 'lib/validation/shared-validation'
+import { fetchOntologies } from 'lib/validation/ontology-validation'
+import { validateConventionTerms, validateOntologyTerm } from 'lib/validation/validate-file-content'
+import {
+  REQUIRED_CONVENTION_COLUMNS, getOntologyShortNameLc, getLabelSuffixForOntology
+} from 'lib/validation/shared-validation'
 import { getLogProps } from 'lib/validation/log-validation'
 import ValidationMessage from 'components/validation/ValidationMessage'
 import * as MetricsApi from 'lib/metrics-api'
@@ -13,7 +18,20 @@ import { createMockFile } from './file-mock-utils'
 
 const validateLocalFile = ValidateFile.validateLocalFile
 
+import {
+  nodeCaches, nodeHeaders, nodeRequest, nodeResponse
+} from './node-web-api'
+
 describe('Client-side file validation', () => {
+  beforeAll(() => {
+    global.fetch = fetch
+
+    global.caches = nodeCaches;
+    global.Response = nodeResponse
+    global.Request = nodeRequest
+    global.Headers = nodeHeaders
+  })
+
   jest
     .spyOn(UserProvider, 'getFeatureFlagsWithDefaults')
     .mockReturnValue({
@@ -333,7 +351,6 @@ describe('Client-side file validation', () => {
   it('does not catch gzipped RDS file without .gz extension', async () => {
     const file = createMockFile({ fileName: 'foo.rds', content: '\x1F\x2E3lkjf3' })
     const [{ errors }] = await validateLocalFile(file, { file_type: 'Cluster' })
-    console.log('errors', errors)
     const hasMissingGzipExtensionError = errors.some(
       error => error[1] === 'encoding:missing-gz-extension'
     )
@@ -464,6 +481,15 @@ it('Catches disallowed characters in metadata header', async () => {
 
 // With the client side file validation feature flag set to false expect invalid files to pass
 describe('Client-side file validation feature flag is false', () => {
+  beforeAll(() => {
+    global.fetch = fetch
+
+    global.caches = nodeCaches;
+    global.Response = nodeResponse
+    global.Request = nodeRequest
+    global.Headers = nodeHeaders
+  })
+
   beforeEach(() => {
     jest
       .spyOn(UserProvider, 'getFeatureFlagsWithDefaults')
@@ -518,3 +544,102 @@ describe('Client-side file validation feature flag is false', () => {
   })
 }
 )
+
+describe('validates file contents against minified ontologies', () => {
+  beforeAll(() => {
+    global.fetch = fetch
+
+    global.caches = nodeCaches;
+    global.Response = nodeResponse
+    global.Request = nodeRequest
+    global.Headers = nodeHeaders
+  })
+
+  beforeEach(() => {
+    jest
+      .spyOn(UserProvider, 'getFeatureFlagsWithDefaults')
+      .mockReturnValue({
+        clientside_validation: true
+      })
+  })
+
+  it('validates classic metadata file', async () => {
+    const content = [
+      "NAME\tbiosample_id\tCellID\tdisease\tdisease__ontology_label\tdonor_id\tlibrary_preparation_protocol" +
+      "\tlibrary_preparation_protocol__ontology_label\torgan\torgan__ontology_label\tsex\tspecies\tspecies__ontology_label",
+      "TYPE\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup",
+      "CELL_0001\tid1\tcell1\tMONDO_0000001\tdisease or disorder\tdonor1\tEFO_0008919\tSeq-Well\tUBERON_0001913" +
+      "\tmilk\tfemale\tNCBITaxon_9606\tHomo sapiens"
+    ]
+    const file = createMockFile({
+      fileName: 'metadata_valid.tsv',
+      content: content.join("\n")
+    })
+    const [{ errors }] = await validateLocalFile(file, { file_type: 'Metadata', use_metadata_convention: true })
+    expect(errors).toHaveLength(0)
+  })
+
+  it('finds ontology error in classic metadata file', async () => {
+    const content = [
+      "NAME\tbiosample_id\tCellID\tdisease\tdisease__ontology_label\tdonor_id\tlibrary_preparation_protocol" +
+      "\tlibrary_preparation_protocol__ontology_label\torgan\torgan__ontology_label\tsex\tspecies\tspecies__ontology_label",
+      "TYPE\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup\tgroup",
+      "CELL_0001\tid1\tcell1\tMONDO_0000001\tdisease or disorder\tdonor1\tEFO_0008919\tnot label\tUBERON_0001913" +
+      "\tmilk\tfemale\tNCBITaxon_9606\tfoo"
+    ]
+    const file = createMockFile({
+      fileName: 'metadata_valid.tsv',
+      content: content.join("\n")
+    })
+    const [{ errors }] = await validateLocalFile(file, { file_type: 'Metadata', use_metadata_convention: true })
+    expect(errors).toHaveLength(2)
+  })
+
+  it('validates single line or term from a metadata file', async() => {
+    const ontologies = await fetchOntologies()
+    const headers = [
+      [ "NAME", "species", "species__ontology_label","disease", "disease__ontology_label"],
+      ["TYPE", "group", "group", "group", "group"]
+    ]
+    // validate whole line
+    const line = ["CELL_0001", "NCBITaxon_9606", "Homo sapiens", "MONDO_0000001", "disease or disorder"]
+    let knownErrors = []
+    let issues = validateConventionTerms(headers, line, ontologies, knownErrors)
+    expect(issues).toHaveLength(0)
+    const badLine = ["CELL_0001", "NCBITaxon_9606", "not the label","MONDO_0000001", "also not label"]
+    issues = validateConventionTerms(headers, badLine, ontologies, knownErrors)
+    expect(issues.length).toBe(2)
+    expect(knownErrors.length).toBe(2)
+    // validate single term
+    let prop = 'library_preparation_protocol'
+    let ontologyId = 'EFO_0008919'
+    let label = 'Seq-Well'
+    knownErrors = []
+    issues = validateOntologyTerm(prop, ontologyId, label, ontologies, knownErrors)
+    expect(issues.length).toBe(0)
+    prop = 'cell_type'
+    ontologyId = 'CL_0000066'
+    label = 'bad label'
+    issues = validateOntologyTerm(prop, ontologyId, label, ontologies, knownErrors)
+    expect(issues.length).toBe(1)
+    expect(knownErrors.length).toBe(1)
+    prop = 'organ'
+    ontologyId = 'foobar'
+    label = 'bad label'
+    issues = validateOntologyTerm(prop, ontologyId, label, ontologies, knownErrors)
+    expect(issues.length).toBe(1)
+    expect(knownErrors.length).toBe(2)
+  })
+
+  it('gets ontology shortname from ID', () => {
+    const ontologyId = "EFO_0008919"
+    expect("efo").toEqual(getOntologyShortNameLc(ontologyId))
+  })
+
+  it('gets label suffix depending on ontology', () => {
+    const efoId = "EFO_0008919"
+    expect("__ontology_label").toEqual(getLabelSuffixForOntology(efoId))
+    const uoId = "UO_0000036"
+    expect("_label").toEqual(getLabelSuffixForOntology(uoId))
+  })
+})
diff --git a/test/js/upload-wizard/upload-new-study.test.js b/test/js/upload-wizard/upload-new-study.test.js
index 472adf0fb..a7f1d495f 100644
--- a/test/js/upload-wizard/upload-new-study.test.js
+++ b/test/js/upload-wizard/upload-new-study.test.js
@@ -12,9 +12,10 @@ import {
 import {
   renderWizardWithStudy, getSelectByLabelText, saveButton, mockCreateStudyFile
 } from './upload-wizard-test-utils'
-import fetch from 'node-fetch'
+const fetch = require('node-fetch')
 import { setMetricsApiMockFlag } from 'lib/metrics-api'
 import { getTokenExpiry } from './upload-wizard-test-utils'
+import { nodeCaches, nodeHeaders, nodeRequest, nodeResponse } from '../lib/node-web-api'
 
 const processedFileName = 'example_processed_dense.txt'
 const rawCountsFileName = 'example_raw_counts.txt'
@@ -23,8 +24,13 @@ describe('creation of study files', () => {
   beforeAll(() => {
     jest.restoreAllMocks()
     // This test is long--running all steps in series as if it was a user uploading a new study from scratch--so allow extra time
-    jest.setTimeout(10000)
+    jest.setTimeout(20000)
     global.fetch = fetch
+
+    global.caches = nodeCaches;
+    global.Response = nodeResponse
+    global.Request = nodeRequest
+    global.Headers = nodeHeaders
     setMetricsApiMockFlag(true)
     window.SCP = {
       readOnlyTokenObject: {
@@ -39,6 +45,9 @@ describe('creation of study files', () => {
   afterEach(() => {
     // Restores all mocks back to their original value
     jest.restoreAllMocks()
+  })
+
+  afterAll(() => {
     jest.setTimeout(5000)
   })
 
@@ -209,11 +218,22 @@ async function testMetadataUpload({ createFileSpy }) {
 
 
   const goodFileName = 'metadata-good.txt'
+  const goodContent = [
+    'NAME,disease,disease__ontology_label,species,species__ontology_label,library_preparation_protocol,'+
+    'library_preparation_protocol__ontology_label,organ,organ__ontology_label,sex,ethnicity__ontology_label,' +
+    'ethnicity,donor_id,biosample_id',
+    'TYPE,group,group,group,group,group,group,group,group,group,group,group,group,group',
+    'CELL_0001,MONDO_0000001,disease or disorder,NCBITaxon_9606,Homo sapiens,EFO_0008919,' +
+    'Seq-Well,UBERON_0001913,milk,female,European ancestry,HANCESTRO_0005,BM01,BM01_16dpp_r3'
+  ]
   fireFileSelectionEvent(screen.getByTestId('file-input'), {
     fileName: goodFileName,
-    content: 'NAME,cell_type,cell_type__ontology_label,organism_age,disease,disease__ontology_label,species,species__ontology_label,geographical_region,geographical_region__ontology_label,library_preparation_protocol,library_preparation_protocol__ontology_label,organ,organ__ontology_label,sex,is_living,organism_age__unit,organism_age__unit_label,ethnicity__ontology_label,ethnicity,race,race__ontology_label,sample_type,donor_id,biosample_id,biosample_type,preservation_method\nTYPE,group,group,numeric,group,group,group,group,group,group,group,group,group,group,group,group,group,group,group,group,group,group,group,group,group,group,group'
+    content: goodContent.join('\n')
   })
-  await waitForElementToBeRemoved(() => screen.getByTestId('file-validation-spinner'))
+  await waitForElementToBeRemoved(
+    () => screen.getByTestId('file-validation-spinner'),
+    { timeout: 20000 }
+  )
   expect(screen.getByTestId('file-selection-name')).toHaveTextContent(goodFileName)
   expect(saveButton()).not.toBeDisabled()
 
@@ -221,9 +241,9 @@ async function testMetadataUpload({ createFileSpy }) {
   await waitForElementToBeRemoved(() => screen.getByTestId('file-save-spinner'))
 
   expect(createFileSpy).toHaveBeenLastCalledWith(expect.objectContaining({
-    chunkEnd: 627,
+    chunkEnd: 487,
     chunkStart: 0,
-    fileSize: 627,
+    fileSize: 487,
     isChunked: false,
     studyAccession: 'SCP1',
     studyFileData: formData
@@ -439,5 +459,3 @@ async function testSequenceFileUpload({ createFileSpy }) {
   }))
   expect(screen.getByTestId('sequence-status-badge')).toHaveClass('complete')
 }
-
-COORDINATE_LABEL_FILE
diff --git a/test/models/ingest_job_test.rb b/test/models/ingest_job_test.rb
index 65869e16c..4d270c19d 100644
--- a/test/models/ingest_job_test.rb
+++ b/test/models/ingest_job_test.rb
@@ -443,7 +443,8 @@ class IngestJobTest < ActiveSupport::TestCase
     )
     job_mock = Minitest::Mock.new
     2.times { job_mock.expect :object, cluster_job }
-    dummy_job = Google::Apis::BatchV1::Job.new(status: Google::Apis::BatchV1::JobStatus.new(state: 'RUNNING'))
+    dummy_job = Google::Apis::BatchV1::Job.new(name: pipeline_name,
+                                               status: Google::Apis::BatchV1::JobStatus.new(state: 'RUNNING'))
 
     pipeline_mock = Minitest::Mock.new
     pipeline_mock.expect :get_job, dummy_job, [pipeline_name]
@@ -452,11 +453,15 @@ class IngestJobTest < ActiveSupport::TestCase
     DelayedJobAccessor.stub :find_jobs_by_handler_type, [Delayed::Job.new] do
       DelayedJobAccessor.stub :dump_job_handler, job_mock do
         ApplicationController.stub :batch_api_client, pipeline_mock do
-          metadata_job.report_anndata_summary
-          job_mock.verify
-          pipeline_mock.verify
-          ann_data_file.reload
-          assert_not ann_data_file.has_anndata_summary?
+          metadata_job.stub :failed?, false do
+            metadata_job.stub :should_retry?, false do
+              metadata_job.report_anndata_summary
+              job_mock.verify
+              pipeline_mock.verify
+              ann_data_file.reload
+              assert_not ann_data_file.has_anndata_summary?
+            end
+          end
         end
       end
     end
@@ -481,10 +486,95 @@ class IngestJobTest < ActiveSupport::TestCase
     DelayedJobAccessor.stub :find_jobs_by_handler_type, [] do
       MetricsService.stub :log, metrics_mock do
         cluster_job.stub :anndata_summary_props, mock_job_props do
-          cluster_job.report_anndata_summary
-          ann_data_file.reload
-          assert ann_data_file.has_anndata_summary?
-          metrics_mock.verify
+          cluster_job.stub :should_retry?, false do
+            cluster_job.stub :failed?, false do
+              cluster_job.report_anndata_summary
+              ann_data_file.reload
+              assert ann_data_file.has_anndata_summary?
+              metrics_mock.verify
+            end
+          end
+        end
+      end
+    end
+  end
+
+  test 'should determine when to skip AnnData summary' do
+    study = FactoryBot.create(
+      :detached_study, name_prefix: 'ingestSummary skip test', user: @user, test_array: @@studies_to_clean
+    )
+    ann_data_file = FactoryBot.create(:ann_data_file, name: 'matrix.h5ad', study:)
+    ann_data_file.ann_data_file_info.reference_file = false
+    ann_data_file.options[:anndata_summary] = false
+    ann_data_file.save
+    pipeline_name = SecureRandom.uuid
+    job = IngestJob.new(
+      pipeline_name:, study:, user: @user, study_file: ann_data_file, action: :ingest_anndata
+    )
+
+    job.stub :failed?, true do
+      job.stub :should_retry?, false do
+        assert_not job.skip_anndata_summary?
+      end
+    end
+
+    job.stub :failed?, false do
+      job.stub :should_retry?, false do
+        assert job.skip_anndata_summary?
+        job.action = :differential_expression
+        assert job.skip_anndata_summary?
+        ann_data_file.options[:anndata_summary] = true
+        job.action = :ingest_cluster
+        assert job.skip_anndata_summary?
+      end
+    end
+  end
+
+  test 'should report AnnData summary on extraction failure' do
+    study = FactoryBot.create(
+      :detached_study, name_prefix: 'ingestSummary report', user: @user, test_array: @@studies_to_clean
+    )
+    ann_data_file = FactoryBot.create(:ann_data_file, name: 'matrix.h5ad', study:)
+    ann_data_file.ann_data_file_info.reference_file = false
+    ann_data_file.upload_file_size = 1.megabyte
+    ann_data_file.options[:anndata_summary] = false
+    ann_data_file.save
+    params = AnnDataIngestParameters.new(
+      anndata_file: ann_data_file.gs_url, file_size: ann_data_file.upload_file_size,
+      extract_raw_counts: true, raw_location: '.raw'
+    )
+    pipeline_name = SecureRandom.uuid
+    job = IngestJob.new(
+      pipeline_name:, study:, user: @user, study_file: ann_data_file, action: :ingest_anndata
+    )
+    mock_job_props = {
+      perfTime: 60000,
+      fileName: ann_data_file.name,
+      fileType: 'AnnData',
+      fileSize: ann_data_file.upload_file_size,
+      studyAccession: study.accession,
+      trigger: ann_data_file.upload_trigger,
+      jobStatus: 'failed',
+      numFilesExtracted: 0,
+      machineType: params.machine_type,
+      action: :ingest_pipeline,
+      ingest_action: :ingest_anndata,
+      exitCode: 1
+    }
+    metrics_mock = Minitest::Mock.new
+    metrics_mock.expect :call, true, ['ingestSummary', mock_job_props, @user]
+
+    DelayedJobAccessor.stub :find_jobs_by_handler_type, [] do
+      MetricsService.stub :log, metrics_mock do
+        job.stub :anndata_summary_props, mock_job_props do
+          job.stub :failed?, true do
+            job.stub :should_retry?, false do
+              job.report_anndata_summary
+              ann_data_file.reload
+              assert ann_data_file.has_anndata_summary?
+              metrics_mock.verify
+            end
+          end
         end
       end
     end
@@ -979,7 +1069,7 @@ class IngestJobTest < ActiveSupport::TestCase
 
     # must mock batch_api_client getting pipeline metadata
     client_mock = Minitest::Mock.new
-    4.times { client_mock.expect :exit_code_from_task, 137, [pipeline_name] }
+    5.times { client_mock.expect :exit_code_from_task, 137, [pipeline_name] }
     client_mock.expect :get_job_resources, vm_info, [], job: dummy_job
     client_mock.expect :get_job_command_line, commands, [], job: dummy_job
     # new pipeline mock is resubmitted job with larger machine_type
diff --git a/test/test_data/validation/metadata_bad_v3-0-0.tsv b/test/test_data/validation/metadata_bad_v3-0-0.tsv
new file mode 100644
index 000000000..ffe3f1536
--- /dev/null
+++ b/test/test_data/validation/metadata_bad_v3-0-0.tsv
@@ -0,0 +1,32 @@
+NAME	cell_type	cell_type__ontology_label	organism_age	disease	disease__ontology_label	species	species__ontology_label	library_preparation_protocol	library_preparation_protocol__ontology_label	organ	organ__ontology_label	sex	is_living	organism_age__unit	organism_age__unit_label	ethnicity__ontology_label	ethnicity	sample_type	donor_id	biosample_id	biosample_type	preservation_method
+TYPE	group	group	numeric	group	group	group	group	group	group	group	group	group	group	group	group	group	group	group	group	group	group	group
+CELL_0001	CL_0000066	epithelial cell	1	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0002	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0003	CL_0000066	epithelial cell	12	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0004	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0005	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0006	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0007	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0008	CL_0000066	epithelial cell	61	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0009	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00010	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00011	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00012	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00013	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00014	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00015	CL_0000066	epithelial cell	58	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0001t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0002t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0003t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0004t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0005t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0006t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0007t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0008t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0009t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	invalid label	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00010t	CL_0000066	epithelial cell	103	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	invalid label	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00011t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	invalid label	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00012t	CL_0000066	not the label	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00013t	CL_0000066	not the label	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00014t	CL_0000066	epithelial cell	99	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00015t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
diff --git a/test/test_data/validation/metadata_good_v3-0-0.tsv b/test/test_data/validation/metadata_good_v3-0-0.tsv
new file mode 100644
index 000000000..47ed307e9
--- /dev/null
+++ b/test/test_data/validation/metadata_good_v3-0-0.tsv
@@ -0,0 +1,32 @@
+NAME	cell_type	cell_type__ontology_label	organism_age	disease	disease__ontology_label	species	species__ontology_label	library_preparation_protocol	library_preparation_protocol__ontology_label	organ	organ__ontology_label	sex	is_living	organism_age__unit	organism_age__unit_label	ethnicity__ontology_label	ethnicity	sample_type	donor_id	biosample_id	biosample_type	preservation_method
+TYPE	group	group	numeric	group	group	group	group	group	group	group	group	group	group	group	group	group	group	group	group	group	group	group
+CELL_0001	CL_0000066	epithelial cell	1	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0002	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0003	CL_0000066	epithelial cell	12	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0004	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0005	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0006	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0007	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0008	CL_0000066	epithelial cell	61	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0009	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00010	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00011	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00012	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00013	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00014	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00015	CL_0000066	epithelial cell	58	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0001t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0002t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0003t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0004t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0005t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0006t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0007t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0008t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_0009t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00010t	CL_0000066	epithelial cell	103	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00011t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00012t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00013t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00014t	CL_0000066	epithelial cell	99	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
+CELL_00015t	CL_0000066	epithelial cell	31	MONDO_0000001	disease or disorder	NCBITaxon_9606	Homo sapiens	EFO_0008919	Seq-Well	UBERON_0001913	milk	female	yes	UO_0000036	year	European ancestry	HANCESTRO_0005	direct from donor - fresh	BM01	BM01_16dpp_r3	PrimaryBioSample_BodyFluid	Fresh
diff --git a/yarn.lock b/yarn.lock
index d24e2d593..3ed99cc23 100644
--- a/yarn.lock
+++ b/yarn.lock
@@ -9471,10 +9471,10 @@ vite-plugin-ruby@^3.0.5:
     debug "^4.3.4"
     fast-glob "^3.2.12"
 
-vite@^4.5.10:
-  version "4.5.10"
-  resolved "https://registry.yarnpkg.com/vite/-/vite-4.5.10.tgz#fc6823d5347fd171a25ae6379f05b0be700d303e"
-  integrity sha512-f2ueoukYTMI/5kMMT7wW+ol3zL6z6PjN28zYrGKAjnbzXhRXWXPThD3uN6muCp+TbfXaDgGvRuPsg6mwVLaWwQ==
+vite@^4.5.13:
+  version "4.5.13"
+  resolved "https://registry.yarnpkg.com/vite/-/vite-4.5.13.tgz#778534a947112c6c455e89737730fae5d458a294"
+  integrity sha512-Hgp8IF/yZDzKsN1hQWOuQZbrKiaFsbQud+07jJ8h9m9PaHWkpvZ5u55Xw5yYjWRXwRQ4jwFlJvY7T7FUJG9MCA==
   dependencies:
     esbuild "^0.18.10"
     postcss "^8.4.27"