opentargets · dependabot · Feb 10, 2026 · Mar 10, 2026 · Mar 10, 2026 · Mar 10, 2026
diff --git a/.vscode/settings.json b/.vscode/settings.json
@@ -39,6 +39,7 @@
     "colocalisation",
     "contig",
     "diffpval",
+    "Ensembl",
     "eqtl",
     "finngen",
     "GCST",

diff --git a/docs/python_api/datasets/molecular_complex.md b/docs/python_api/datasets/molecular_complex.md
@@ -0,0 +1,5 @@
+---
+title: Molecular Complex
+---
+
+::: gentropy.dataset.molecular_complex.MolecularComplex
diff --git a/docs/python_api/datasources/_datasources.md b/docs/python_api/datasources/_datasources.md
@@ -14,6 +14,11 @@ This section contains information about the data source harmonisation tools avai
 
 1. [GTEx (eQTL catalogue)](eqtl_catalogue/_eqtl_catalogue.md)
 2. [UKB PPP (EUR)](ukb_ppp_eur/_ukb_ppp_eur.md)
+3. [deCODE proteomics](deCODE/_decode.md)
+
+## Protein complexes
+
+1. [Complex Portal](complex_portal/_complex_portal.md)
 
 ## Interaction / Interval-based Experiments
 
@@ -39,5 +44,4 @@ This section contains information about the data source harmonisation tools avai
 
 ## Biological samples
 
-1. [Uberon](biosample_ontologies/_uberon.md)
-2. [Cell Ontology](biosample_ontologies/_cell_ontology.md)
+1. [Uberon and Cell Ontology](biosample_ontologies/_biosample_ontologies.md)
diff --git a/docs/python_api/datasources/complex_portal/_complex_portal.md b/docs/python_api/datasources/complex_portal/_complex_portal.md
@@ -0,0 +1,14 @@
+---
+title: Complex Portal
+---
+
+[Complex Portal](https://www.ebi.ac.uk/complexportal/) is a manually curated resource of macromolecular complexes maintained by EMBL-EBI. It provides two complementary datasets:
+
+- **Experimental** – complexes with direct experimental evidence.
+- **Predicted** – computationally predicted complexes.
+
+Both files are distributed in the **ComplexTAB** flat-file format and are filtered to human complexes (NCBI taxonomy ID 9606) during ingestion.
+
+The resulting `MolecularComplex` dataset is used downstream in the deCODE proteomics pipeline to annotate multi-protein SomaScan aptamers with a `molecularComplexId`.
+
+::: gentropy.datasource.complex_portal.ComplexTab
diff --git a/docs/python_api/datasources/deCODE/.pages b/docs/python_api/datasources/deCODE/.pages
@@ -0,0 +1,6 @@
+nav:
+  - _decode.md
+  - manifest.md
+  - aptamer_metadata.md
+  - study_index.md
+  - summary_stats.md
diff --git a/docs/python_api/datasources/deCODE/_decode.md b/docs/python_api/datasources/deCODE/_decode.md
@@ -0,0 +1,15 @@
+---
+title: deCODE proteomics
+---
+
+[deCODE proteomics](https://www.nature.com/articles/s41586-023-06563-x) is a large-scale proteomics dataset generated by deCODE genetics, a biopharmaceutical company based in Iceland. The dataset includes measurements of protein levels in blood samples from thousands of individuals (up to ~36,000 Icelandic participants), using the SomaScan aptamer-based platform.
+
+Two sub-datasets are provided:
+
+- **RAW** (`deCODE-proteomics-raw`): non-SMP-normalised SomaScan measurements.
+- **SMP** (`deCODE-proteomics-smp`): SMP-normalised SomaScan measurements.
+
+For a full description of the dataset and methods, refer to [Eldjarn et al., 2023](https://www.nature.com/articles/s41586-023-06563-x).
+
+::: gentropy.datasource.decode.deCODEDataSource
+::: gentropy.datasource.decode.deCODEPublicationMetadata
diff --git a/docs/python_api/datasources/deCODE/aptamer_metadata.md b/docs/python_api/datasources/deCODE/aptamer_metadata.md
@@ -0,0 +1,5 @@
+---
+title: deCODE Aptamer Metadata
+---
+
+::: gentropy.datasource.decode.aptamer_metadata.AptamerMetadata
diff --git a/docs/python_api/datasources/deCODE/manifest.md b/docs/python_api/datasources/deCODE/manifest.md
@@ -0,0 +1,5 @@
+---
+title: deCODE manifest
+---
+
+::: gentropy.datasource.decode.manifest.deCODEManifest
diff --git a/docs/python_api/datasources/deCODE/study_index.md b/docs/python_api/datasources/deCODE/study_index.md
@@ -0,0 +1,6 @@
+---
+title: deCODE Study Index
+---
+
+::: gentropy.datasource.decode.study_index.deCODEStudyIdParts
+::: gentropy.datasource.decode.study_index.deCODEStudyIndex
diff --git a/docs/python_api/datasources/deCODE/summary_stats.md b/docs/python_api/datasources/deCODE/summary_stats.md
@@ -0,0 +1,6 @@
+---
+title: deCODE Summary Statistics
+---
+
+::: gentropy.datasource.decode.summary_statistics.deCODEHarmonisationConfig
+::: gentropy.datasource.decode.summary_statistics.deCODESummaryStatistics
diff --git a/docs/python_api/steps/biosample_index_step.md b/docs/python_api/steps/biosample_index_step.md
@@ -1,5 +1,5 @@
 ---
-title: biosample_index
+title: Biosample Index Generation
 ---
 
 ::: gentropy.biosample_index.BiosampleIndexStep
diff --git a/docs/python_api/steps/colocalisation.md b/docs/python_api/steps/colocalisation.md
@@ -1,5 +1,5 @@
 ---
-title: colocalisation
+title: Colocalisation
 ---
 
 ::: gentropy.colocalisation.ColocalisationStep
diff --git a/docs/python_api/steps/credible_set_qc_step.md b/docs/python_api/steps/credible_set_qc_step.md
@@ -1,5 +1,5 @@
 ---
-title: credible_set_qc
+title: Credible Set Quality Control
 ---
 
 ::: gentropy.credible_set_qc.CredibleSetQCStep

diff --git a/docs/python_api/steps/decode_ingestion.md b/docs/python_api/steps/decode_ingestion.md
@@ -0,0 +1,5 @@
+---
+title: deCODE ingestion
+---
+
+::: gentropy.decode_ingestion
diff --git a/docs/python_api/steps/eqtl_catalogue.md b/docs/python_api/steps/eqtl_catalogue.md
@@ -1,5 +1,5 @@
 ---
-title: eQTL Catalogue
+title: eQTL Catalogue ingestion
 ---
 
 ::: gentropy.eqtl_catalogue.EqtlCatalogueStep
diff --git a/docs/python_api/steps/finngen_studies.md b/docs/python_api/steps/finngen_studies.md
@@ -1,5 +1,5 @@
 ---
-title: finngen_studies
+title: FinnGen Study Index generation
 ---
 
 ::: gentropy.finngen_studies.FinnGenStudiesStep
diff --git a/docs/python_api/steps/finngen_sumstat_preprocess.md b/docs/python_api/steps/finngen_sumstat_preprocess.md
@@ -1,5 +1,5 @@
 ---
-title: finngen_sumstat_preprocess
+title: Finngen Summary Statistics Ingestion
 ---
 
 ::: gentropy.finngen_sumstat_preprocess.FinnGenSumstatPreprocessStep
diff --git a/docs/python_api/steps/finngen_ukbb_mvp_meta_step.md b/docs/python_api/steps/finngen_ukbb_mvp_meta_step.md
@@ -1,5 +1,5 @@
 ---
-title: FinnGen UKBB MVP Meta Analysis Step
+title: FinnGen UKBB MVP Meta Analysis ingestion
 ---
 
 ::: gentropy.finngen_ukb_mvp_meta.FinngenUkbMvpMetaSummaryStatisticsIngestionStep
diff --git a/docs/python_api/steps/gwas_catalog_curation.md b/docs/python_api/steps/gwas_catalog_curation.md
@@ -1,5 +1,5 @@
 ---
-title: gwas_catalog_study_curation
+title: GWAS Catalog Study Curation
 ---
 
 ::: gentropy.gwas_catalog_study_curation.GWASCatalogStudyCurationStep
diff --git a/docs/python_api/steps/gwas_catalog_study_index.md b/docs/python_api/steps/gwas_catalog_study_index.md
@@ -1,5 +1,5 @@
 ---
-title: gwas_catalog_study_inclusion
+title: GWAS Catalog Study Inclusion
 ---
 
 ::: gentropy.gwas_catalog_study_index.GWASCatalogStudyIndexGenerationStep
diff --git a/docs/python_api/steps/gwas_catalog_sumstat_preprocess.md b/docs/python_api/steps/gwas_catalog_sumstat_preprocess.md
@@ -1,5 +1,5 @@
 ---
-title: gwas_catalog_sumstat_preprocess
+title: GWAS Catalog Summary Statistics ingestion
 ---
 
 ::: gentropy.gwas_catalog_sumstat_preprocess.GWASCatalogSumstatsPreprocessStep
diff --git a/docs/python_api/steps/gwas_catalog_top_hits.md b/docs/python_api/steps/gwas_catalog_top_hits.md
@@ -1,5 +1,5 @@
 ---
-title: GWAS Catalog Top Hits Ingestion Step
+title: GWAS Catalog Top Hits ingestion
 ---
 
 ::: gentropy.gwas_catalog_top_hits.GWASCatalogTopHitIngestionStep
diff --git a/docs/python_api/steps/ld_clump.md b/docs/python_api/steps/ld_clump.md
@@ -1,5 +1,5 @@
 ---
-title: ld_based_clumping
+title: Linkage Disequilibrium Based Clumping
 ---
 
 ::: gentropy.ld_based_clumping.LDBasedClumpingStep
diff --git a/docs/python_api/steps/ld_index.md b/docs/python_api/steps/ld_index.md
@@ -1,5 +1,5 @@
 ---
-title: GnomAD Linkage data ingestion
+title: GnomAD Linkage Disequilibrium Index generation
 ---
 
 ::: gentropy.gnomad_ingestion.LDIndexStep
diff --git a/docs/python_api/steps/locus_breaker_clumping.md b/docs/python_api/steps/locus_breaker_clumping.md
@@ -1,5 +1,5 @@
 ---
-title: locus_breaker_clumping
+title: Locus Breaker Clumping
 ---
 
 ::: gentropy.locus_breaker_clumping.LocusBreakerClumpingStep
diff --git a/docs/python_api/steps/molecular_complex.md b/docs/python_api/steps/molecular_complex.md
@@ -0,0 +1,5 @@
+---
+title: Molecular complex ingestion
+---
+
+::: gentropy.molecular_complex
diff --git a/docs/python_api/steps/pics.md b/docs/python_api/steps/pics.md
@@ -1,5 +1,5 @@
 ---
-title: pics
+title: PICS
 ---
 
 ::: gentropy.pics.PICSStep
diff --git a/docs/python_api/steps/pqtl_study.md b/docs/python_api/steps/pqtl_study.md
@@ -0,0 +1,5 @@
+---
+title: pQTL study index transformation
+---
+
+::: gentropy.pqtl_study
diff --git a/docs/python_api/steps/summary_statistics_qc.md b/docs/python_api/steps/summary_statistics_qc.md
@@ -1,5 +1,5 @@
 ---
-title: summary_statistics_qc
+title: Summary Statistics QC
 ---
 
 ::: gentropy.sumstat_qc_step.SummaryStatisticsQCStep
diff --git a/docs/python_api/steps/ukb_ppp_eur_sumstat_preprocess.md b/docs/python_api/steps/ukb_ppp_eur_sumstat_preprocess.md
@@ -1,5 +1,5 @@
 ---
-title: ukb_ppp_eur_sumstat_preprocess
+title: UKB PPP EUR Summary Statistics ingestion
 ---
 
 ::: gentropy.ukb_ppp_eur_sumstat_preprocess.UkbPppEurStep
diff --git a/docs/python_api/steps/variant_annotation_step.md b/docs/python_api/steps/variant_annotation_step.md
@@ -1,5 +1,5 @@
 ---
-title: GnomAD variant data ingestion
+title: GnomAD Variant Index generation
 ---
 
 ::: gentropy.gnomad_ingestion.GnomadVariantIndexStep
diff --git a/docs/python_api/steps/variant_index_step.md b/docs/python_api/steps/variant_index_step.md
@@ -1,5 +1,5 @@
 ---
-title: variant_index
+title: Variant Index generation
 ---
 
 ::: gentropy.variant_index.VariantIndexStep
diff --git a/docs/python_api/steps/window_based_clumping.md b/docs/python_api/steps/window_based_clumping.md
@@ -1,5 +1,5 @@
 ---
-title: window_based_clumping
+title: Window based clumping
 ---
 
 ::: gentropy.window_based_clumping.WindowBasedClumpingStep
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -14,7 +14,7 @@ plugins:
       handlers:
         python:
           options:
-            filters: ["!^_", "!__new__", "__init__"]
+            filters: ["!^_", "!__new__", "!__init__"]
             show_signature_annotations: true
             show_root_heading: true
             heading_level: 3

diff --git a/pyproject.toml b/pyproject.toml
@@ -15,7 +15,7 @@ dependencies = [
   "pyliftover (>=0.4.1, <0.5.0)",
   "numpy>=2.3.0",
   "omegaconf (>=2.3.0, <2.4.0)",
-  "scikit-learn (>=1.6.1, <1.8.0)",
+  "scikit-learn (>=1.6.1, <1.9.0)",
   "pandas[gcp,parquet] (>=2.2.3, <2.4.0)",
   "skops (>=0.13.0, <0.14.0)",
   "shap>=0.50.0",
@@ -27,6 +27,7 @@ dependencies = [
   "xgboost>=3.0.4 ; platform_machine == 'x86_64' and sys_platform == 'darwin'",
   "huggingface-hub>=0.27.1",
   "wandb (>=0.19.4, <0.26.0)",
+  "pydantic>=2.12.4",
 ]
 classifiers = [
   "Programming Language :: Python :: 3.11",

diff --git a/src/gentropy/assets/data/gwas_population_2_LD_panel_map.json b/src/gentropy/assets/data/gwas_population_2_LD_panel_map.json
@@ -18,5 +18,6 @@
   "NR": "nfe",
   "Finnish": "fin",
   "African": "afr",
-  "Admixed American": "amr"
+  "Admixed American": "amr",
+  "Icelandic": "nfe"
 }
diff --git a/src/gentropy/assets/schemas/molecular_complex.json b/src/gentropy/assets/schemas/molecular_complex.json
@@ -0,0 +1,104 @@
+{
+  "fields": [
+    { "metadata": {}, "name": "id", "nullable": true, "type": "string" },
+    {
+      "metadata": {},
+      "name": "description",
+      "nullable": true,
+      "type": "string"
+    },
+    {
+      "metadata": {},
+      "name": "properties",
+      "nullable": true,
+      "type": "string"
+    },
+    { "metadata": {}, "name": "assembly", "nullable": true, "type": "string" },
+    {
+      "metadata": {},
+      "name": "components",
+      "nullable": true,
+      "type": {
+        "containsNull": false,
+        "elementType": {
+          "fields": [
+            {
+              "metadata": {},
+              "name": "id",
+              "nullable": false,
+              "type": "string"
+            },
+            {
+              "metadata": {},
+              "name": "stoichiometry",
+              "nullable": false,
+              "type": "string"
+            },
+            {
+              "metadata": {},
+              "name": "source",
+              "nullable": false,
+              "type": "string"
+            }
+          ],
+          "type": "struct"
+        },
+        "type": "array"
+      }
+    },
+    {
+      "metadata": {},
+      "name": "evidenceCodes",
+      "nullable": true,
+      "type": {
+        "containsNull": false,
+        "elementType": "string",
+        "type": "array"
+      }
+    },
+    {
+      "metadata": {},
+      "name": "crossReferences",
+      "nullable": true,
+      "type": {
+        "containsNull": false,
+        "elementType": {
+          "fields": [
+            {
+              "metadata": {},
+              "name": "source",
+              "nullable": false,
+              "type": "string"
+            },
+            {
+              "metadata": {},
+              "name": "id",
+              "nullable": false,
+              "type": "string"
+            }
+          ],
+          "type": "struct"
+        },
+        "type": "array"
+      }
+    },
+    {
+      "metadata": {},
+      "name": "source",
+      "nullable": false,
+      "type": {
+        "fields": [
+          { "metadata": {}, "name": "id", "nullable": true, "type": "string" },
+          {
+            "metadata": {},
+            "name": "source",
+            "nullable": true,
+            "type": "string"
+          }
+        ],
+        "type": "struct"
+      }
+    }
+  ],
+  "type": "struct"
+}