Platform for Representation and Integration of multimodal Molecular Embeddings

TL;DR

This paper introduces PRISME, a framework that integrates diverse molecular embeddings from multiple data sources into a unified representation, improving performance on biomedical tasks.

Contribution

The study presents a novel workflow using an autoencoder to combine heterogeneous molecular embeddings, enabling comprehensive and robust representations across biological contexts.

Findings

PRISME outperforms individual embeddings in benchmark tasks.

Integrated embeddings capture more complete biological signals.

The approach enhances missing value imputation accuracy.

Abstract

Existing machine learning methods for molecular (e.g., gene) embeddings are restricted to specific tasks or data modalities, limiting their effectiveness within narrow domains. As a result, they fail to capture the full breadth of gene functions and interactions across diverse biological contexts. In this study, we have systematically evaluated knowledge representations of biomolecules across multiple dimensions representing a task-agnostic manner spanning three major data sources, including omics experimental data, literature-derived text data, and knowledge graph-based representations. To distinguish between meaningful biological signals from chance correlations, we devised an adjusted variant of Singular Vector Canonical Correlation Analysis (SVCCA) that quantifies signal redundancy and complementarity across different data modalities and sources. These analyses reveal that existing embeddings capture largely non-overlapping molecular signals, highlighting the value of embedding integration. Building on this insight, we propose Platform for Representation and Integration of multimodal Molecular Embeddings (PRISME), a machine learning based workflow using an autoencoder to integrate these heterogeneous embeddings into a unified multimodal representation. We validated this approach across various benchmark tasks, where PRISME demonstrated consistent performance, and outperformed individual embedding methods in missing value imputations. This new framework supports comprehensive modeling of biomolecules, advancing the development of robust, broadly applicable multimodal embeddings optimized for downstream biomedical machine learning applications.