# Hierarchical Molecular Language Models (HMLMs)

arXiv: https://arxiv.org/abs/2512.00696 · HTML: https://mlsanity.com/paper/2512.00696/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 52 references that are in the map.
- First posted on arXiv 30 Nov 2025.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Does Explainable Artificial Intelligence Improve Human Decision-Making?](https://mlsanity.com/paper/2006.11194/) (2020)

## Built on by (most cited first, 4 of 4)

- [Attention mechanisms in neural networks](https://mlsanity.com/paper/2601.03329/) (2026)
- [Selective Synchronization Attention](https://mlsanity.com/paper/2602.14445/) (2026)
- [RAG-GNN: Integrating Retrieved Knowledge with Graph Neural Networks for Precision Medicine](https://mlsanity.com/paper/2602.00586/) (2026)
- [Hebbian-Oscillatory Co-Learning](https://mlsanity.com/paper/2603.08731/) (2026)

## Abstract (arXiv)

Artificial intelligence (AI) is reshaping computational and network biology by enabling new approaches to decode cellular communication networks. We introduce Hierarchical Molecular Language Models (HMLMs), a novel framework that models cellular signaling as a specialized molecular language, where signaling molecules function as tokens, protein interactions define syntax, and functional consequences constitute semantics. HMLMs employ a transformer-based architecture adapted to accommodate graph-structured signaling networks through information transducers, mathematical entities that capture how molecules receive, process, and transmit signals. The architecture integrates multi-modal data sources across molecular, pathway, and cellular scales through hierarchical attention mechanisms and scale-bridging operators that enable information flow across biological hierarchies. Applied to a complex network of cardiac fibroblast signaling, HMLMs outperformed traditional approaches in temporal dynamics prediction, particularly under sparse sampling conditions. Attention-based analysis revealed biologically meaningful crosstalk patterns, including previously uncharacterized interactions between signaling pathways. By bridging molecular mechanisms with cellular phenotypes through AI-driven molecular language representation, HMLMs establish a foundation for biology-oriented large language models (LLMs) that could be pre-trained on comprehensive pathway datasets and applied across diverse signaling systems and tissues, advancing precision medicine and therapeutic discovery.