What question did this study set out to answer?

The study aims to develop a multimodal learning framework that integrates various omics data for improved slide-level predictions in oncology.

April 5, 2026

Abstract 4207: Omics-aware patch aggregation via multimodal co-training with a scalable multi-omics encoder for slide-level prediction across an oncology biomarker panel

Key Points

The study aims to develop a multimodal learning framework that integrates various omics data for improved slide-level predictions in oncology.
Developed an omics-aware patch aggregator leveraging a contrastive objective.
Utilized a Multi-Omics Encoder (MOE) that tokenizes and concatenates omics modalities.
Conducted multimodal pretraining with approximately 20,000 partially paired whole-slide images and omics profiles.
Employed a Slide Encoder (SE) that processes multiple patches while incorporating positional bias.
Achieved area under the ROC curve (AUC) values for various biomarkers, with notable results like CD274 at 0.98 and FOLR1 at 0.93.
Lung adenocarcinoma showed AUCs of 0.87 for EGFR mutation and 0.70 for tumor mutational burden.
Breast cancer subtyping resulted in AUC values of 0.95 for ER and 0.88 for PR.
Achieved precise predictions across multiple cancer types using diverse datasets.

Abstract

Abstract Background: Whole-slide images (WSIs) are widely available, but matched multi-omics profiles are limited, especially when multiple modalities are required. We developed a multimodal learning framework that integrates RNA expression and DNA mutation with H colorectal cancer 0.99 for microsatellite instability; breast cancer 0.95, 0.88, and 0.81 for ER, PR, and HER2 protein subtyping and 0.74 and 0.86 for TP53 and PIK3CA mutations; renal cell carcinoma 0.60 for PBRM1 and 0.74 for BAP1 mutations; and colon adenocarcinoma 0.88 for KRAS and 0.89 for TP53 mutations. Gene overexpression tasks used The Cancer Genome Atlas with five-fold cross-validation across four seeds; lung and colorectal models used Samsung Medical Center cohorts; breast subtyping used the BCNB cohort; and renal and colon tasks used Clinical Proteomic Tumor Analysis Consortium data. Conclusions: An omics-aware patch aggregation framework co-trained with a scalable multi-omics encoder and WSIs enables accurate slide-level prediction for diverse biomarkers and tumor types and illustrates how partially paired multi-omics data can strengthen digital pathology models. AI was used for language editing only; authors are responsible for all content and approved the final version. Citation Format: Hwanil Choi, Tae Hyun Hwang, Soonyoung Lee, Jongseong Jang. Omics-aware patch aggregation via multimodal co-training with a scalable multi-omics encoder for slide-level prediction across an oncology biomarker panel abstract. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 4207.

Demander à l'IA

Bookmark