Multimodal Alignment Improves Generalizability of Genomic Biomarker Prediction in Computational Pathology
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917300435681280 |
|---|---|
| author | Redekop, Ekaterina Zimmermann, Eric Amini, Ava P Lu, Alex X Tenenholtz, Neil Hall, James Brian Crawford, Lorin Severson, Kristen A |
| author_facet | Redekop, Ekaterina Zimmermann, Eric Amini, Ava P Lu, Alex X Tenenholtz, Neil Hall, James Brian Crawford, Lorin Severson, Kristen A |
| contents | Computational pathology models that use digitized histopathology whole-slide images have the potential to become a cost-effective and scalable alternative to molecular assays for the prediction of genomic biomarkers, a key task in precision oncology. However, as new genomic biomarkers are discovered or quantified, large, labeled datasets must be prospectively collected to train new models. To address this challenge, we developed MARBLE, a multimodal contrastive pretraining strategy that integrates structured biomarker knowledge into representation learning of histopathology images. MARBLE aligns histopathology-derived representations with representations of genomic biomarkers generated by a large language model (LLM) and a protein language model (PLM). This biologically informed alignment enables data-efficient generalization to novel, out-of-distribution biomarkers. Using the MSK-IMPACT cohort of over 40,000 patients across multiple biomarker panel versions, we design experiments grounded in real-world data to demonstrate the value of our proposed approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00193 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multimodal Alignment Improves Generalizability of Genomic Biomarker Prediction in Computational Pathology Redekop, Ekaterina Zimmermann, Eric Amini, Ava P Lu, Alex X Tenenholtz, Neil Hall, James Brian Crawford, Lorin Severson, Kristen A Quantitative Methods Computational pathology models that use digitized histopathology whole-slide images have the potential to become a cost-effective and scalable alternative to molecular assays for the prediction of genomic biomarkers, a key task in precision oncology. However, as new genomic biomarkers are discovered or quantified, large, labeled datasets must be prospectively collected to train new models. To address this challenge, we developed MARBLE, a multimodal contrastive pretraining strategy that integrates structured biomarker knowledge into representation learning of histopathology images. MARBLE aligns histopathology-derived representations with representations of genomic biomarkers generated by a large language model (LLM) and a protein language model (PLM). This biologically informed alignment enables data-efficient generalization to novel, out-of-distribution biomarkers. Using the MSK-IMPACT cohort of over 40,000 patients across multiple biomarker panel versions, we design experiments grounded in real-world data to demonstrate the value of our proposed approach. |
| title | Multimodal Alignment Improves Generalizability of Genomic Biomarker Prediction in Computational Pathology |
| topic | Quantitative Methods |
| url | https://arxiv.org/abs/2603.00193 |