Interpretable DIS+ AI framework for variant pathogenicity
Fuente:
Zenodo
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Recurso digital |
| Publicado: |
Zenodo
2025
|
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866901519268315136 |
|---|---|
| author | Hao, Yun Marvin, Tess |
| author_facet | Hao, Yun Marvin, Tess |
| contents | <p dir="ltr">DIS+ is the first disease-specific, AI-informed, and interpretable score for variant pathogenicity. DIS+ provides predictions for genome-wide regulatory variants across more than 100 diseases. DIS+ addresses a central unmet need in precision genomics: moving from disease-agnostic deleteriousness scores to disease-specific pathogenicity. With DIS+, instead of receiving a largely conservation-based assessment of a variant’s generic deleteriousness, researchers obtain a precise, disease-specific pathogenicity score with biochemical feature-level interpretation. </p> <p dir="ltr">Methodologically, DIS+ couples ancestry-informed pre-training with disease-ontology-guided fine-tuning in a visible AI framework reflecting the hierarchical relationship among diseases. Uniquely, DIS+ quantifies variant pathogenicity separately for transcriptional and post-transcriptional regulation, capturing disease-specific differences in the molecular mechanisms that drive pathogenesis. DIS+ also offers an interpretation module that computes feature-level attributions across thousands of regulatory features, including transcriptional factors and RNA-binding proteins. This design enables robust performance in data-scarce settings and reveals which regulatory programs drive disease risk. In addition to providing a disease-specific assessment and mechanistic interpretation, DIS+ significantly outperforms widely used, disease-agnostic predictors.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17902015 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Interpretable DIS+ AI framework for variant pathogenicity Hao, Yun Marvin, Tess <p dir="ltr">DIS+ is the first disease-specific, AI-informed, and interpretable score for variant pathogenicity. DIS+ provides predictions for genome-wide regulatory variants across more than 100 diseases. DIS+ addresses a central unmet need in precision genomics: moving from disease-agnostic deleteriousness scores to disease-specific pathogenicity. With DIS+, instead of receiving a largely conservation-based assessment of a variant’s generic deleteriousness, researchers obtain a precise, disease-specific pathogenicity score with biochemical feature-level interpretation. </p> <p dir="ltr">Methodologically, DIS+ couples ancestry-informed pre-training with disease-ontology-guided fine-tuning in a visible AI framework reflecting the hierarchical relationship among diseases. Uniquely, DIS+ quantifies variant pathogenicity separately for transcriptional and post-transcriptional regulation, capturing disease-specific differences in the molecular mechanisms that drive pathogenesis. DIS+ also offers an interpretation module that computes feature-level attributions across thousands of regulatory features, including transcriptional factors and RNA-binding proteins. This design enables robust performance in data-scarce settings and reveals which regulatory programs drive disease risk. In addition to providing a disease-specific assessment and mechanistic interpretation, DIS+ significantly outperforms widely used, disease-agnostic predictors.</p> |
| title | Interpretable DIS+ AI framework for variant pathogenicity |
| url | https://doi.org/10.5281/zenodo.17902015 |