mlsanityData to 7 Oct 2026

Retrieval-Augmented Foundation Models for Matched Molecular Pair Transformations to Recapitulate Medicinal Chemistry Intuition

arXiv 2602.16684 ↗First posted 18 Feb 2026cs.LGcited by 0

On the map: Retrieval-augmented generation → Medical and biomedical RAG

Abstract (arXiv)

Matched molecular pairs (MMPs) capture the local chemical edits that medicinal chemists routinely use to design analogs, but existing ML approaches either operate at the whole-molecule level with limited edit controllability or learn MMP-style edits from restricted settings and small models. We propose a variable-to-variable formulation of analog generation and train a foundation model on large-scale MMP transformations (MMPTs) to generate diverse variables conditioned on an input variable. To enable practical control, we develop prompting mechanisms that let the users specify preferred transformation patterns during generation. We further introduce MMPT-RAG, a retrieval-augmented framework that uses external reference analogs as contextual guidance to steer generation and generalize from project-specific series. Experiments on general chemical corpora and patent-specific datasets demonstrate improved diversity, novelty, and controllability, and show that our method recovers realistic analog structures in practical discovery scenarios.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 7 of its 47 references that are in the map. First posted on arXiv 18 Feb 2026.

Builds on

7 of 47 references.

References · 7

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  3. 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 264
  4. 2024LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Datasetcited by 124
  5. 2023Unifying Molecular and Textual Representations via Multi-task Language Modellingcited by 92
  6. 2024Efficient Evolutionary Search Over Chemical Space with Large Language Modelscited by 59
  7. 2024Molecule Generation with Fragment Retrieval Augmentationcited by 22

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MolE-RAG: Molecular Structure-Enhanced Retrieval-Augmented Generation for Chemistry
  2. 2025SynCraft: Guiding Large Language Models to Predict Edit Sequences for Molecular Synthesizability Optimization
  3. 2025Atom-anchored LLMs speak Chemistry: A Retrosynthesis Demonstration
  4. 2024Crossing New Frontiers: Knowledge-Augmented Large Language Model Prompting for Zero-Shot Text-Based De Novo Molecule Design
  5. 2026Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization
  6. 2024MolReFlect: Towards In-Context Fine-grained Alignments between Molecules and Texts
  7. 2026Chemical Language Models for Natural Products: A State-Space Model Approach
  8. 2026HiRes: Inspectable Precedent Memory for Reaction Condition Recommendation