Molecular Representation Learning

Follow this topic Ask about this topic

Molecular representation learning studies how to encode molecules and biomolecules so models can recognize chemical structure, predict properties, and support tasks such as drug screening and molecular design. Approaches range from fingerprints and molecular graphs to SMILES language models, 3D equivariant networks, fragment-based methods, and multimodal models combining structure with spectra, text, or biological measurements. Self-supervised and contrastive pretraining are common ways to learn from unlabeled structures, while supervised models use task-specific labels for properties such as solubility, binding affinity, or toxicity. A central challenge is reliable transfer to new chemical scaffolds and biological settings: larger pretrained models do not always beat simpler fingerprints or descriptors, and results depend strongly on data splits, representation choices, and whether physical and chemical information is preserved.

Latest papers

207 papers23 papers in the last four weeks, up 5% on the four weeks before. 0.1% of all new papers.

Aligning Molecular Graph Explanations with Chemical Identity via InChIfied Invariants
May 23, 2026Emanuele Guidotti, Sara PuglioliMolecular Property Prediction Invariant Representation Learning
University of Lugano, Switzerland · Philochem AG, Switzerland
TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval
May 23, 2026Yuhang Zhang, Keyan Ding, Peilin Chen +5Cross-Modal Retrieval Information Retrieval
University of Science and Technology of China · 2City University of Hong Kong · 3Zhejiang University
Representation-Guided Discrete Molecular Graph Retrosynthesis
May 23, 2026Jiahai Huang, Anjie Qiao, Zhen Wang +2Diffusion Model Guidance Molecular Graph Generation
Sun Yat-sen University Guangzhou, China · University of Science and Technology of China Hefei, China
SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules
May 21, 2026Yuxuan Chen, Changwei Lv, Yunduo Xiao +5AI-Assisted Scientific Research Chemical Reaction Prediction
School of Electronic and Computer Engineering, Peking University, Shenzhen, China · Tsinghua University, Beijing, China · School of Intelligence Science and Technology, Nanjing University, Suzhou, China
Atom-level Protein Representation Learning Improves Protein Structure Prediction
May 21, 2026Taewon Kim, Hyosoon Jang, Hyunjin Seo +6Protein Structure Prediction Self-Supervised Pre-Training
Graduate School of AI, KAIST · Department of Chemistry, KAIST · HITS Inc. +3
HiRes: Inspectable Precedent Memory for Reaction Condition Recommendation
May 20, 2026Shreyas Vinaya Sathyanarayana, Raja Sekhar Pappala, Deepak WarrierRepresentation Learning Molecular Representation Learning
Mstack AI Bangalore, India
Training distribution determines the ceiling of drug-blind cancer sensitivity prediction
May 20, 2026Taekyung HeoTraining Data Selection Clinical Prediction
Protein Fold Classification at Scale: Benchmarking and Pretraining
May 18, 2026Dexiong Chen, Andrei Manolache, Mathias Niepert +1Masked Autoencoders Self-Supervised Pre-Training
Max Planck Institute of Biochemistry, Martinsried, Germany · Computer Science Department, University of Stuttgart, Germany · Bitdefender, Romania
VQ-Atom: Semantic Discretization of Local Atomic Environments for Molecular Representation Learning
May 16, 2026Takayuki KimuraVector Quantization Molecular Representation Learning
Atoms as Language, LLC
Cross-Domain Molecular Relational Learning: Leveraging Chemical Structure-Activity Analysis
May 16, 2026Peiliang Zhang, Jingling Yuan, Shiqing Wu +4Domain-Adversarial Learning Cross-Modal Representation Learning
Wuhan University of Technology Wuhan, Hubei, China · Hubei Key Laboratory of Transportation Internet of Things State Key Laboratory of Silicate Materials for Architectures Wuhan University of Technology Wuhan, Hubei, China · Yonsei University Seoul, Republic of Korea +3
GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
May 15, 2026Roman Bresson, Konstantinos Divriotis, Johannes F. Lutzeyer +2Molecular Generation Molecular Representation Learning
Mohamed bin Zayed University of Artificial Intelligence · LIX, CNRS, École Polytechnique, IP Paris
MoleCode unlocks structural intelligence in large language models
May 15, 2026Zhiyuan Yan, Chen Liu, Boxuan Zhao +8Molecular Generation Large Language Model-Guided Scientific Discovery
Peking University Shenzhen Graduage School
Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Prediction
May 15, 2026Xiayu Liu, Zhengyi Lu, Hou-biao LiSelf-Supervised Pre-Training Hierarchical Representation Learning
School of Mathematical Sciences, University of Electronic Science and Technology of China, No.2006, Xiyuan Avenue, West Hi-tech Zone,2026 611731, Chengdu, China · Department of Computer Science and Engineering, Oakland University, 201 Meadow Brook RD, Rochester Hills, 48309, MI, USA
Reading the Cell, Designing the Cure: Perturbation-Conditioned Molecular Diffusion for Function-Oriented Drug Design
May 14, 2026Ziyu Xu, Zijian Zhang, Liang Wang +4Molecular Generation Conditional Diffusion Models
NLPR, MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China +1
ENSEMBITS: an alphabet of protein conformational ensembles
May 13, 2026Kaiwen Shi, Carlos OliverProtein Language Models Protein Representation Learning
Department of Computer Science, Vanderbilt University · Center for AI in Protein Dynamics, Vanderbilt University · Department of Molecular Physiology and Biophysics, Vanderbilt University
Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction
May 13, 2026Deepak Warrier, Raja Sekhar PappalaTransformer Geometric Representation Learning
MSTACK AI
Set-Aggregated Genome Embeddings for Microbiome Abundance Prediction
May 12, 2026Younhun Kim, Georg K. Gerber, Travis E. GibsonRepresentation Learning Genomics
1Brigham and Women’s Hospital, Boston, MA, USA · 2Harvard Medical School, Boston, MA, USA
Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition
May 12, 2026Mingqing Wang, Zhiwei Nie, Athanasios V. Vasilakos +2Representation Disentanglement Protein Function Prediction
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Pengcheng Laboratory, Shenzhen, China · School of Electronic and Computer Engineering, Peking University, Shenzhen, China +2
On Improving Graph Neural Networks for QSAR by Pre-training on Extended-Connectivity Fingerprints
May 11, 2026Sam Money-Kyrle, Markus Dablander, Thierry Hanser +3Graph Neural Networks OOD Generalization
Department of Statistics, University of Oxford, 24-29 St Giles’, Oxford, OX1 3LB, United Kingdom. · Mathematical Institute, University of Oxford, Andrew Wiles Building, Woodstock Road, Oxford, OX2 6GG, United Kingdom. · Molecular Informatics and AI, Lhasa Limited, Granary Wharf House,May 2 Canal Wharf, Leeds, LS11 5PS, United Kingdom.
It's All Connected: Topology-Aware Structural Graph Encoding Improves Performance on Polymer Prediction
May 11, 2026H. Ibrahim Erdogan, Punith Raviswamy, Nikita Agrawal +5Graph Representation Learning Materials Property Prediction
University of Bayreuth, Germany · Faculty of Engineering Science, University of Bayreuth, Germany · Faculty of Mathematics, Physics & Computer Science, University of Bayreuth, Germany +5
Physical probes expose and alleviate chemical-environment collapse in molecular representations
May 11, 2026Jiebin Fang, Zidi Yan, Churu Mao +7Contrastive Learning Cross-Modal Representation Learning
Hainan Institute, Zhejiang University, Sanya 572025, China · Institute of Marine Biology and Pharmacology, Ocean College, Zhejiang University, Zhoushan 316021, China · School of Food and Pharmacy, Zhejiang Ocean University, Zhoushan 316021, China +2
MolSight: Molecular Property Prediction with Images
May 11, 2026Aaditya Baranwal, Akshaj Gupta, Yogesh S Rawat +1Curriculum Learning Molecular Property Prediction
University of Central Florida, Orlando, Florida, USA · Birla Institute of Technology and Science, Pilani, Rajasthan, India
From Syntax to Semantics: Unveiling the Emergence of Chirality in SMILES Translation Models
May 11, 2026Zehao Li, Yasuhiro Yoshikai, Shumpei Nemoto +2Chemical Language Models Transformer Interpretability
Laboratory of Molecular Pharmacokinetics, Graduate School of Pharmaceutical Sciences, The University of Tokyo, 7-3-1 Hongo, Bunkyo, Tokyo, Japan · The Institute of Statistical Mathematics (ISM), Research Organization of Information and Systems, 190-8562 Tachikawa, Tokyo, Japan
SCOPE: Siamese Contrastive Operon Pair Embeddings for Functional Sequence Representation and Classification
May 10, 2026Akarsh Gupta, Kenneth Rodrigues, Sagnik ChatterjeeGenomics Molecular Representation Learning
Toward Better Geometric Representations for Molecule Generative Models
May 8, 2026Shaoheng Yan, Zian Li, Cai Zhou +3Geometric Representation Learning 3D Molecular Generation
Institute for Artificial Intelligence, PKU · ByteDance AI Drug Discovery · School of Intelligence Science and Technology, PKU +3
ProtSent: Protein Sentence Transformers
May 7, 2026Dan Ofer, Oriel Perets, Michal Linial +1Contrastive Learning Protein Language Models
Department of Biological Chemistry The Hebrew University of Jerusalem · Department of Computer and Information Science Ben-Gurion University of the Negev
Molecules Meet Language: Confound-Aware Representation Learning and Chemical Property Steering in Transformer-VAE Latent Spaces
May 7, 2026Zakaria Elabid, Jan Andrzejewski, Bartosz Brzoza +1Variational Autoencoders Molecular Generation
Helmholtz-Zentrum Dresden-Rossendorf Center for Advanced Systems Understanding
Bolek: A Multimodal Language Model for Molecular Reasoning
May 4, 2026Frederic Grabowski, Jacek Szczerbiński, Maciej Jaśkowski +4LLM Grounding Scientific Reasoning
1Ingenix.ai, Warsaw, Poland · Laboratory of Bioinformatics and Computational Genomics, Warsaw University of Technology, Warsaw, Poland
Molecular Representations for Large Language Models
May 3, 2026Nicholas T. Runcie, Fergus Imrie, Charlotte M. DeaneLLM Evaluation Large Language Model-Guided Scientific Discovery
Department of Statistics University of Oxford Oxford, UK
PRIME: Protein Representation via Physics-Informed Multiscale Equivariant Hierarchies
May 2, 2026Viet Thanh Duy Nguyen, John K. Johnstone, Truong-Son HyGraph Representation Learning Hierarchical Representation Learning
University of Alabama at Birmingham Birmingham, Alabama, USA

May 23, 2026J/K move · Enter open · S save

Aligning Molecular Graph Explanations with Chemical Identity via InChIfied Invariants

Emanuele Guidotti, Sara Puglioli

University of Lugano, Switzerland · Philochem AG, Switzerland

Molecular Property Prediction Invariant Representation Learning GNN Explainability Molecular Representation Learning

Open paper AskPDF arXiv

Obtaining consistent explanations for machine learning on molecular graphs requires predictions and attributions to be aligned with chemical identity. However, chemically equivalent drawings of the same molecule can induce different molecular representations, leading to inconsistent predictions and explanations. Here, we introduce InChIfied Invariants, a class of node, edge, and graph features based on the International Chemical Identifier (InChI) and designed to be invariant under transformations that preserve chemical identity. Using one million molecular graphs from PubChem Substances, we show that InChIfied Invariants produce identical representations for chemically equivalent graphs in 99.62% of cases, whereas standard Daylight invariants do so in only 0.35% of cases. Across MoleculeNet tasks, InChIfied Invariants preserve predictive performance while significantly improving prediction consistency across alternative graph depictions of the same molecules. We further perform a quantitative attribution analysis and show that explanations produced with standard molecular featurization methods vary substantially across chemically equivalent graphs, while InChIfied Invariants enforce consistent attributions by construction. We release open-source software implementing InChIfied Invariants, which can be used as a drop-in replacement for standard molecular graph features.