Skip to content
Preprint

MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models

Aug 2026 · 0 citations · 53 references
Computer Science

TL;DR

This work introduces \textbf{MolEmb}, a lightweight framework that adapts MLLMs by aligning molecular profiles with textual descriptions in a shared embedding space using a bidirectional contrastive objective, and finds that context-aware molecular embedding is primarily a data property of the supervision.

Abstract

Molecular embedding models can serve as foundational infrastructure for computational chemistry and drug discovery, where reusable vector representations support property prediction, virtual screening, and retrieval. Most molecular encoders are specialist models built around a single molecular view, producing unconditional vectors with no language interface for varying the representation. We ask whether multimodal large language models (MLLMs), which natively process images, text, and symbolic inputs, can instead serve as \emph{general molecular embedding models} that produce embeddings conditioned on both a molecular profile and a natural-language semantic context. We introduce \textbf{MolEmb}, a lightweight framework that adapts MLLMs by aligning molecular profiles with textual descriptions in a shared embedding space using a bidirectional contrastive objective. The resulting embedding model is competitive on molecular property prediction and supports cross-modal molecule--text retrieval in the same space. We further introduce \textbf{MolCAR}, a diagnostic benchmark for context-aware retrieval, and find that context-aware molecular embedding is primarily a data property of the supervision. These results suggest that MLLMs are not merely chemistry assistants or generators, but a viable and extensible route to general molecular embedding models.

View source

Similar papers

#artificial intelligence Preprint Aug 2026

Domain-Adapted Molecular Language Models for Efficient Search of Make-on-Demand Libraries

Pretrained molecular language models are increasingly used as molecular encoders for learning structure-property relationships. However, their practical suitability for molecular discovery within and beyond their pretraining domain remains unclear. Herein, we systematically benchmark four molecular language models across six virtual molecular libraries spanning drug discovery, organic materials, and catalysis. Native molecular language model embeddings show substantial variation in discovery performance across libraries, whereas molecular fingerprints provide a consistently strong and robust baseline. Consistent with a potential domain-representation mismatch, we show that explicit domain adaptation substantially improves representation performance. Fine-tuning molecular language model encoders on structures from the target virtual library consistently improves sample efficiency, with several adapted encoders emerging as the top-performing representations across the benchmark tasks. These results show that molecular representation quality depends strongly on the target domain and that explicit adaptation can improve the practical utility of molecular foundation models. More broadly, our findings establish domain-adapted molecular representations as a promising strategy for sample-efficient adaptive decision making in virtual screening and self-driving laboratories.

Henrik Wille, Luis-Finley Schütz, Felix Strieth-Kalthoff · 0 citations
Open access Jul 2026

FragBERTa: a fragment-aware molecular representation model with sequential attachment-based fragment embeddings

FragBERTa is introduced, a molecular fragment-aware transformer-based representation language model pretrained using masked language modeling on Sequential Attachment-based Fragment Embedding (SAFE) representations, suggesting that fragment-based string representations offer advantages over atom-level representations for scaffold-sensitive and interaction-driven tasks.

Neerav Kaushal, Ajay Mnv Penmatsa · 0 citations
Preprint Aug 2026

Multi-Granular Rationale-Guided Molecular LLM for Property Prediction

This is the first method to expose GNN-derived attributions to an LLM as evidence for property prediction, and achieves the best overall results among generalist models and narrows the gap to specialist models tuned for each task.

Junwoo Park, Minyoung Shin, C. Lee et al. · 0 citations
Open access Jul 2026

Navigating chemical-linguistic sharing space with heterogeneous molecular encoding

HME is presented, a framework that combines multiple views of molecules to improve molecular understanding and design and enables bidirectional navigation of the chemical-linguistic space, achieving consistent improvements across molecular comprehension and design tasks over strong baselines.

Liuzhenghao Lv, Hao Li, Yu Wang et al. · 0 citations
Jul 2026

TextDTI: A Multimodal Context Representation Learning Framework for Drug-Target Interaction Prediction.

This paper proposes TextDTI, a multimodal framework that simultaneously exploits sequential and structural representations and enhances feature alignment through adversarial learning and contrastive loss, resulting in robust and high-performance DTI prediction.

Jiaqi Deng, Senyu Tang, Jijun Tang et al. · 0 citations
Aug 2026

Speaking the Native Language of LLMs: A Discrete Architecture for Molecular Comprehension.

MolLingua, a token-centric, dual-modal framework designed for native molecular understanding, uses a dual-branch Residual Vector Quantization engine to discretize heterogeneous, high-dimensional spatial 2D and 3D features into compact code sequences rather than relying solely on continuous projections.

Haoyang Liu, Xikang Feng, Fei Guo et al. · 0 citations