Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2603.25855 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918411465916416 |
|---|---|
| author | Jiang, Cheng Ryan, Brady Crow, Megan Fletez-Brant, Kipper Doshi, Kashish Carlos, Sandra Melo Huang, Kexin Hoeckendorf, Burkhard Yao, Heming Richmond, David |
| author_facet | Jiang, Cheng Ryan, Brady Crow, Megan Fletez-Brant, Kipper Doshi, Kashish Carlos, Sandra Melo Huang, Kexin Hoeckendorf, Burkhard Yao, Heming Richmond, David |
| contents | Genome-Wide Association Studies (GWAS) identify associations between genetic variants and disease; however, moving beyond associations to causal mechanisms is critical for therapeutic target prioritization. The recently proposed Knowledge Graph GWAS (KGWAS) framework addresses this challenge by linking genetic variants to downstream gene-gene interactions via a knowledge graph (KG), thereby improving detection power and providing mechanistic insights. However, the original KGWAS implementation relies on a large general-purpose KG, which can introduce spurious correlations. We hypothesize that cell-type specific KGs from disease-relevant cell types will better support disease mechanism discovery. Here, we show that the general-purpose KG in KGWAS can be substantially pruned with no loss of statistical power on downstream tasks, and that performance further improves by incorporating gene-gene relationships derived from perturb-seq data. Importantly, using a sparse, context-specific KG from direct perturb-seq evidence yields more consistent and biologically robust disease-critical networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25855 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Incorporating contextual information into KGWAS for interpretable GWAS discovery Jiang, Cheng Ryan, Brady Crow, Megan Fletez-Brant, Kipper Doshi, Kashish Carlos, Sandra Melo Huang, Kexin Hoeckendorf, Burkhard Yao, Heming Richmond, David Machine Learning Genome-Wide Association Studies (GWAS) identify associations between genetic variants and disease; however, moving beyond associations to causal mechanisms is critical for therapeutic target prioritization. The recently proposed Knowledge Graph GWAS (KGWAS) framework addresses this challenge by linking genetic variants to downstream gene-gene interactions via a knowledge graph (KG), thereby improving detection power and providing mechanistic insights. However, the original KGWAS implementation relies on a large general-purpose KG, which can introduce spurious correlations. We hypothesize that cell-type specific KGs from disease-relevant cell types will better support disease mechanism discovery. Here, we show that the general-purpose KG in KGWAS can be substantially pruned with no loss of statistical power on downstream tasks, and that performance further improves by incorporating gene-gene relationships derived from perturb-seq data. Importantly, using a sparse, context-specific KG from direct perturb-seq evidence yields more consistent and biologically robust disease-critical networks. |
| title | Incorporating contextual information into KGWAS for interpretable GWAS discovery |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.25855 |