Update LoF curations

browser/help/faq/general/what-features-are-not-yet-in-v4-and-where-can-i-find-them.md

@@ -13,6 +13,5 @@ Below is a list of all features not included in the v4 MVP and where to find the
 | Genetic ancestry subgroups (prevously subpops) | v2 variant page                                       |
 | Multi Nucleotide (MNV) calls                   | v2 variant table and variant page                     |
 | Variant co-occurrence                          | v2 gene page                                          |
-| Manual LoF curation                            | v2 variant table and variant page                     |
 | Regional Missense Constraint                   | Now available on v2 gene page                         |
 | Linkage disequilibrium scores                  | [v2](/downloads/#v2-linkage-disequilibrium) downloads |

browser/src/DataPage/GnomadV4Downloads.tsx

@@ -600,6 +600,52 @@ const GnomadV4Downloads = () => {
           </ListItem>
         </FileList>
       </DownloadsSection>
+
+      <SectionTitle id="v4-secondary-analyses" theme={{ type: 'datasets' }}>
+        Secondary Analyses
+      </SectionTitle>
+      <StyledParagraph>
+        Additional research analyses created using the core gnomAD releases in collaboration with
+        members of the gnomAD steering committee.
+      </StyledParagraph>
+
+      <DownloadsSection>
+        <SectionTitle id="v4-lof-curation-results">Loss-of-function curation results</SectionTitle>
+        <p>
+          For information on v4 loss-of-function curation results, see{' '}
+          {/* @ts-expect-error TS(2769) FIXME: No overload matches this call. */}
+          <ExternalLink href="https://doi.org/10.1038/s41586-020-2308-7">
+            <em>The mutational constraint spectrum quantified from variation in 141,456 humans.</em>{' '}
+            Nature 581, 434–443 (2020)
+          </ExternalLink>{' '}
+          (all homozygous LoF curation results),{' '}
+          {/* @ts-expect-error TS(2769) FIXME: No overload matches this call. */}
+          <ExternalLink href="https://doi.org/10.1038/s41586-020-2329-2">
+            <em>Transcript expression-aware annotation improves rare variant interpretation.</em>{' '}
+            Nature 581, 452–458 (2020)
+          </ExternalLink>{' '}
+          (haploinsufficient genes LoF curation results), and{' '}
+          {/* @ts-expect-error TS(2769) FIXME: No overload matches this call. */}
+          <ExternalLink href="https://pubmed.ncbi.nlm.nih.gov/37633279/">
+            <em>
+              Advanced variant classification framework reduces the false positive rate of predicted
+              loss-of-function variants in population sequencing data.
+            </em>{' '}
+            Am J Hum Genet 110, 1496-1508 (2023)
+          </ExternalLink>
+          .
+        </p>
+
+        <FileList>
+          {/* @ts-expect-error TS(2745) FIXME: This JSX tag's 'children' prop expects type 'never... Remove this comment to see the full error message */}
+          <ListItem>
+            <DownloadLinks
+              label="Incomplete penetrance LoF curation results"
+              path="/release/4.1/lof_curation/incomplete_penetrance_curation_results.csv"
+            />
+          </ListItem>
+        </FileList>
+      </DownloadsSection>
     </>
   )
 }

browser/src/DataPage/__snapshots__/DataPage.spec.tsx.snap

@@ -7300,6 +7300,145 @@ exports[`Data Page has no unexpected changes 1`] = `
         </li>
       </ul>
     </section>
+    <span
+      className="c8"
+    >
+      <h2
+        className="c9"
+      >
+        <a
+          aria-hidden="true"
+          className="c10 c11"
+          href="#v4-secondary-analyses"
+          id="v4-secondary-analyses"
+        >
+          <img
+            alt=""
+            aria-hidden="true"
+            height={12}
+            src="test-file-stub"
+            width={12}
+          />
+        </a>
+        Secondary Analyses
+      </h2>
+    </span>
+    <p
+      className="c12"
+    >
+      Additional research analyses created using the core gnomAD releases in collaboration with members of the gnomAD steering committee.
+    </p>
+    <section
+      className="c16"
+    >
+      <span
+        className="c8"
+      >
+        <h2
+          className="c17"
+        >
+          <a
+            aria-hidden="true"
+            className="c10 c11"
+            href="#v4-lof-curation-results"
+            id="v4-lof-curation-results"
+          >
+            <img
+              alt=""
+              aria-hidden="true"
+              height={12}
+              src="test-file-stub"
+              width={12}
+            />
+          </a>
+          Loss-of-function curation results
+        </h2>
+      </span>
+      <p>
+        For information on v4 loss-of-function curation results, see
+
+        <a
+          className="c7"
+          href="https://doi.org/10.1038/s41586-020-2308-7"
+          rel="noopener noreferrer"
+          target="_blank"
+        >
+          <em>
+            The mutational constraint spectrum quantified from variation in 141,456 humans.
+          </em>
+
+          Nature 581, 434–443 (2020)
+        </a>
+
+        (all homozygous LoF curation results),
+
+        <a
+          className="c7"
+          href="https://doi.org/10.1038/s41586-020-2329-2"
+          rel="noopener noreferrer"
+          target="_blank"
+        >
+          <em>
+            Transcript expression-aware annotation improves rare variant interpretation.
+          </em>
+
+          Nature 581, 452–458 (2020)
+        </a>
+
+        (haploinsufficient genes LoF curation results), and
+
+        <a
+          className="c7"
+          href="https://pubmed.ncbi.nlm.nih.gov/37633279/"
+          rel="noopener noreferrer"
+          target="_blank"
+        >
+          <em>
+            Advanced variant classification framework reduces the false positive rate of predicted loss-of-function variants in population sequencing data.
+          </em>
+
+          Am J Hum Genet 110, 1496-1508 (2023)
+        </a>
+        .
+      </p>
+      <ul
+        className="c20"
+      >
+        <li
+          className="c21"
+        >
+          <span>
+            Incomplete penetrance LoF curation results
+          </span>
+          <br />
+          <span>
+            Download from
+
+            <a
+              aria-label="Download Incomplete penetrance LoF curation results from Google"
+              className="c7"
+              href="https://storage.googleapis.com/gcp-public-data--gnomad/release/4.1/lof_curation/incomplete_penetrance_curation_results.csv"
+              onClick={[Function]}
+              rel="noopener noreferrer"
+              target="_blank"
+            >
+              Google
+            </a>
+             / 
+            <a
+              aria-label="Download Incomplete penetrance LoF curation results from Amazon"
+              className="c7"
+              href="https://gnomad-public-us-east-1.s3.amazonaws.com/release/4.1/lof_curation/incomplete_penetrance_curation_results.csv"
+              onClick={[Function]}
+              rel="noopener noreferrer"
+              target="_blank"
+            >
+              Amazon
+            </a>
+          </span>
+        </li>
+      </ul>
+    </section>
     <span
       className="c8"
     >

browser/src/help/__snapshots__/HelpPage.spec.tsx.snap

@@ -1248,7 +1248,6 @@ Below is a list of all features not included in the v4 MVP and where to find the
 | Genetic ancestry subgroups (prevously subpops) | v2 variant page                                       |
 | Multi Nucleotide (MNV) calls                   | v2 variant table and variant page                     |
 | Variant co-occurrence                          | v2 gene page                                          |
-| Manual LoF curation                            | v2 variant table and variant page                     |
 | Regional Missense Constraint                   | Now available on v2 gene page                         |
 | Linkage disequilibrium scores                  | [v2](/downloads/#v2-linkage-disequilibrium) downloads |
 ",

data-pipeline/src/data_pipeline/datasets/gnomad_v2/gnomad_v2_lof_curation.py

@@ -30,8 +30,10 @@
     "not_lof": "Not LoF",
 }
 
+VERDICT_MAPPINGS_CLEAN = VERDICT_MAPPING.values()
 
-def import_gnomad_v2_lof_curation_results(curation_result_paths, genes_path):
+
+def import_gnomad_lof_curation_results(curation_result_paths, genes_path, reference_genome="GRCh37"):
     all_flags = set()
 
     with hl.hadoop_open("/tmp/import_temp.tsv", "w") as temp_output_file:
@@ -52,8 +54,13 @@ def import_gnomad_v2_lof_curation_results(curation_result_paths, genes_path):
 
                 for row in reader:
                     [chrom, pos, ref, alt] = row["Variant ID"].split("-")
+                    chrom = f"chr{chrom}" if reference_genome == "GRCh38" else chrom
 
-                    variant_flags = [FLAG_MAPPING.get(f, f) for f in raw_dataset_flags if row[f"Flag {f}"] == "TRUE"]
+                    variant_flags = [
+                        FLAG_MAPPING.get(f, f)
+                        for f in raw_dataset_flags
+                        if row.get(f"Flag {f}") == "TRUE" or row.get(f"FLAG {f}") == "1"
+                    ]
 
                     genes = [gene_id for (gene_id, gene_symbol) in (gene.split(":") for gene in row["Gene"].split(";"))]
 
@@ -62,7 +69,8 @@ def import_gnomad_v2_lof_curation_results(curation_result_paths, genes_path):
                     if verdict == "inufficient_evidence":
                         verdict = "insufficient_evidence"
 
-                    verdict = VERDICT_MAPPING[verdict]
+                    if verdict not in VERDICT_MAPPINGS_CLEAN:
+                        verdict = VERDICT_MAPPING[verdict]
 
                     output_row = [
                         chrom,
@@ -81,7 +89,7 @@ def import_gnomad_v2_lof_curation_results(curation_result_paths, genes_path):
     ds = hl.import_table("/tmp/import_temp.tsv")
 
     ds = ds.transmute(
-        locus=hl.locus(ds.chrom, hl.int(ds.position)),
+        locus=hl.locus(ds.chrom, hl.int(ds.position), reference_genome),
         alleles=[ds.ref, ds.alt],
     )
 

data-pipeline/src/data_pipeline/pipelines/export_to_elasticsearch.py

@@ -38,8 +38,8 @@
 from data_pipeline.pipelines.gnomad_v3_short_tandem_repeats import pipeline as gnomad_v3_short_tandem_repeats_pipeline
 from data_pipeline.pipelines.gnomad_v4_variants import pipeline as gnomad_v4_variants_pipeline
 from data_pipeline.pipelines.gnomad_v4_coverage import pipeline as gnomad_v4_coverage_pipeline
-
 from data_pipeline.pipelines.gnomad_v4_cnvs import pipeline as gnomad_v4_cnvs_pipeline
+from data_pipeline.pipelines.gnomad_v4_lof_curation_results import pipeline as gnomad_v4_lof_curation_results_pipeline
 
 
 logger = logging.getLogger("gnomad_data_pipeline")
@@ -145,6 +145,18 @@ def add_liftover_document_id(ds):
     #     ),
     #     "args": {"index": "gnomad_v4_genome_coverage", "id_field": "xpos", "num_shards": 2, "block_size": 10_000},
     # },
+    "gnomad_v4_lof_curation_results": {
+        "get_table": lambda: add_variant_document_id(
+            hl.read_table(gnomad_v4_lof_curation_results_pipeline.get_output("lof_curation_results").get_output_path())
+        ),
+        "args": {
+            "index": "gnomad_v4_lof_curation_results",
+            "index_fields": ["document_id", "variant_id", "locus", "lof_curations.gene_id"],
+            "id_field": "document_id",
+            "num_shards": 1,
+            "block_size": 1_000,
+        },
+    },
     ##############################################################################################################
     # gnomAD v4 CNVs
     ##############################################################################################################

data-pipeline/src/data_pipeline/pipelines/gnomad_v2_lof_curation_results.py

@@ -1,6 +1,6 @@
 from data_pipeline.pipeline import Pipeline, run_pipeline
 
-from data_pipeline.datasets.gnomad_v2.gnomad_v2_lof_curation import import_gnomad_v2_lof_curation_results
+from data_pipeline.datasets.gnomad_v2.gnomad_v2_lof_curation import import_gnomad_lof_curation_results
 
 from data_pipeline.pipelines.genes import pipeline as genes_pipeline
 
@@ -9,7 +9,7 @@
 
 pipeline.add_task(
     "prepare_gnomad_v2_lof_curation_results",
-    import_gnomad_v2_lof_curation_results,
+    import_gnomad_lof_curation_results,
     "/gnomad_v2/gnomad_v2_lof_curation_results.ht",
     {"genes_path": genes_pipeline.get_output("genes_grch37")},
     {

data-pipeline/src/data_pipeline/pipelines/gnomad_v4_lof_curation_results.py

@@ -0,0 +1,36 @@
+from data_pipeline.pipeline import Pipeline, run_pipeline
+
+from data_pipeline.datasets.gnomad_v2.gnomad_v2_lof_curation import import_gnomad_lof_curation_results
+
+from data_pipeline.pipelines.genes import pipeline as genes_pipeline
+
+
+pipeline = Pipeline()
+
+pipeline.add_task(
+    "prepare_gnomad_v4_lof_curation_results",
+    import_gnomad_lof_curation_results,
+    "/gnomad_v4/gnomad_v4_lof_curation_results.ht",
+    {"genes_path": genes_pipeline.get_output("genes_grch38")},
+    {
+        # If a result for a variant/gene pair is present in more than one file,
+        # the result in the first file in this list takes precedence.
+        "curation_result_paths": [
+            "gs://gnomad-v4-data-pipeline/inputs/lof_curation/gnomAD_v4/gnomAD_incomplete_penetrance_final_results.csv",
+        ],
+        "reference_genome": "GRCh38",
+    },
+)
+
+###############################################
+# Outputs
+###############################################
+
+pipeline.set_outputs({"lof_curation_results": "prepare_gnomad_v4_lof_curation_results"})
+
+###############################################
+# Run
+###############################################
+
+if __name__ == "__main__":
+    run_pipeline(pipeline)