ReactEmbed: A Plug-and-Play Module for Unifying Protein-Molecule Representations Guided by Biochemical Reaction Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sicherman, Amitay, Radinsky, Kira
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914595158884352
author Sicherman, Amitay
Radinsky, Kira
author_facet Sicherman, Amitay
Radinsky, Kira
contents State-of-the-art models represent proteins and molecules in separate embedding manifolds, limiting the modeling of systemic biological processes. We introduce ReactEmbed, a lightweight, plug-and-play module that bridges this gap. ReactEmbed leverages biochemical reaction networks as a source of functional context, based on the principle that co-participation in reactions defines a shared functional scope. The module aligns frozen embeddings from models like ESM-3 and MolFormer into a unified space using a weighted reaction graph and a specialized sampling strategy. This process enriches unimodal embeddings and enables strong performance on cross-domain benchmarks. ReactEmbed offers a practical method to unify biological representations without costly retraining. The code and database are available for open use\footnote{https://github.com/amitaysicherman/ReactEmbeded}.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18278
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReactEmbed: A Plug-and-Play Module for Unifying Protein-Molecule Representations Guided by Biochemical Reaction Networks
Sicherman, Amitay
Radinsky, Kira
Machine Learning
State-of-the-art models represent proteins and molecules in separate embedding manifolds, limiting the modeling of systemic biological processes. We introduce ReactEmbed, a lightweight, plug-and-play module that bridges this gap. ReactEmbed leverages biochemical reaction networks as a source of functional context, based on the principle that co-participation in reactions defines a shared functional scope. The module aligns frozen embeddings from models like ESM-3 and MolFormer into a unified space using a weighted reaction graph and a specialized sampling strategy. This process enriches unimodal embeddings and enables strong performance on cross-domain benchmarks. ReactEmbed offers a practical method to unify biological representations without costly retraining. The code and database are available for open use\footnote{https://github.com/amitaysicherman/ReactEmbeded}.
title ReactEmbed: A Plug-and-Play Module for Unifying Protein-Molecule Representations Guided by Biochemical Reaction Networks
topic Machine Learning
url https://arxiv.org/abs/2501.18278