# Platform for Representation and Integration of multimodal Molecular Embeddings

arXiv: https://arxiv.org/abs/2507.07367 · HTML: https://mlsanity.com/paper/2507.07367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 10 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023)
- [struc2vec: Learning Node Representations from Structural Identity](https://mlsanity.com/paper/1704.03165/) (2017)
- [LinkBERT: Pretraining Language Models with Document Links](https://mlsanity.com/paper/2203.15827/) (2022)
- [Multi-relational Poincar'e Graph Embeddings](https://mlsanity.com/paper/1905.09791/) (2019)
- [Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations](https://mlsanity.com/paper/1906.05017/) (2019)
- [Large Language Models Streamline Automated Machine Learning for Clinical Studies](https://mlsanity.com/paper/2308.14120/) (2023)
- [Know2BIO: A Comprehensive Dual-View Benchmark for Evolving Biomedical Knowledge Graphs](https://mlsanity.com/paper/2310.03221/) (2023)
- [Does your model understand genes? A benchmark of gene properties for biological and text models](https://mlsanity.com/paper/2412.04075/) (2024)

## Abstract (arXiv)

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.