Preprint scanner project / Issue 2026-08-26

Useful Chemistry

A weekly review of arXiv, ChemRxiv, and bioRxiv for ai-enabled methodological advances. Up to twenty papers reviewed every week; a quiet week may publish none.

20 selected / 117 reviewed Aug 19, 2026–Aug 25, 2026
Groups
Group roll call
96 followed groups Research-group roll call
  • Milad Abolhasani Abolhasani Lab North Carolina State University Site ↗
  • Surl-Hee (Shirley) Ahn Ahn Lab University of California, Davis Site ↗
  • Mohammed AlQuraishi AlQuraishi Laboratory Columbia University Site ↗
  • Sayan Banerjee Banerjee Group University of Tennessee, Knoxville Site ↗
  • Christopher J. Bartel Bartel Research Group University of Minnesota Twin Cities Site ↗
  • Jan-Niklas Boyn Boyn Research Group University of Minnesota Twin Cities Site ↗
  • Ting Cao Cao Group University of Washington Site ↗
  • Timothy Cernak Cernak Lab University of Michigan Site ↗
  • Ming Chen Ming Chen Group Purdue University Site ↗
  • Po-Yen Chen Chen Research Group University of Maryland, College Park Site ↗
  • Bingqing Cheng Cheng Group University of California, Berkeley Site ↗
  • Brian Cleary Algorithmic Lens on Experimental Biology Laboratory Boston University Site ↗
  • Connor W. Coley Coley Research Group Massachusetts Institute of Technology Site ↗
  • Yamil J. Colón Colón Group University of Notre Dame Site ↗
  • César de la Fuente Machine Biology Group University of Pennsylvania Site ↗
  • Julia Dshemuchadse Cape Crystal Cornell University Site ↗
  • Thomas P. Fay Fay Group University of California, Los Angeles Site ↗
  • Kara D. Fong Fong Lab California Institute of Technology Site ↗
  • Thomas E. Gartner III Gartner Group Lehigh University Site ↗
  • Rafael Gómez-Bombarelli Learning Matter Massachusetts Institute of Technology Site ↗
  • Jonathan Gootenberg Gootenberg Laboratory Harvard University Site ↗
  • Prashun Gorai 3D Materials Lab Rensselaer Polytechnic Institute Site ↗
  • Diptarka Hait Hait Group Columbia University Site ↗
  • Brian Hie Laboratory of Evolutionary Design Stanford University Site ↗
  • Guoxiang Hu Hu Group Georgia Institute of Technology Site ↗
  • Yong-Jie Hu Materials Computation and Informatics Group Drexel University Site ↗
  • Yifei Huang Huang Lab Pennsylvania State University Site ↗
  • Yunha Hwang Hwang Lab Massachusetts Institute of Technology Site ↗
  • Nicholas E. Jackson AI for Materials Group University of Illinois Urbana-Champaign Site ↗
  • William M. Jacobs Jacobs Group Princeton University Site ↗
  • Dipti Jasrasaria Jasrasaria Group University of Chicago Site ↗
  • Anupama Jha Jha Lab Yale University Site ↗
  • Kaiyi Jiang Jiang Lab Princeton University Site ↗
  • Adrian Jinich Jinich Lab University of California, San Diego Site ↗
  • Felipe Jornada Jornada Research Group Stanford University Site ↗
  • Kalli Kappel Kappel Lab University of California, Los Angeles Site ↗
  • Joshua Kretchmer Kretchmer Research Group Georgia Institute of Technology Site ↗
  • Aditi S. Krishnapriyan Krishnapriyan Research Group University of California, Berkeley Site ↗
  • Sebastian Kube Kube Lab University of Wisconsin–Madison Site ↗
  • Heather J. Kulik Kulik Research Group Massachusetts Institute of Technology Site ↗
  • Ambarish R. Kulkarni Kulkarni Research Group University of California, Davis Site ↗
  • Joseph S. Kwon Kwon Research Group The Ohio State University Site ↗
  • Joonho Lee Lee Group Harvard University Site ↗
  • Can Li Li Research Group Purdue University Site ↗
  • Wanlu Li Wanlu Li Research Group University of California, San Diego Site ↗
  • Rebecca K. Lindsey Lindsey Lab University of Michigan Site ↗
  • Ge Liu Ge Liu Group University of Illinois Urbana-Champaign Site ↗
  • Yuanyue Liu Yuanyue Liu Group The University of Texas at Austin Site ↗
  • Yang Lu Lu Lab University of Wisconsin–Madison Site ↗
  • Jiankun Lyu Evnin Family Laboratory of Computational Molecular Discovery The Rockefeller University Site ↗
  • Cong Ma Cong Ma Lab University of Michigan Site ↗
  • Arkajit Mandal Mandal Group Texas A&M University Site ↗
  • Andrew J. Medford Medford Research Group Georgia Institute of Technology Site ↗
  • Ilias Mitrai Systems and AI Lab The University of Texas at Austin Site ↗
  • Jeetain Mittal Mittal Group Texas A&M University Site ↗
  • Joel A. Paulson Paulson Lab University of Wisconsin–Madison Site ↗
  • Elisa Pieri Pieri Lab University of North Carolina at Chapel Hill Site ↗
  • Doran Raccah MesoScience Lab The University of Texas at Austin Site ↗
  • Phillip Rauscher Rauscher Group New York University Site ↗
  • Wesley Reinhart Reinhart Group Pennsylvania State University Site ↗
  • Gabriel J. Rocklin Rocklin Lab Northwestern University Site ↗
  • Andrew S. Rosen Rosen Research Group Princeton University Site ↗
  • Grant M. Rotskoff Rotskoff Group Stanford University Site ↗
  • Janani Sampath Sampath Research Group University of Florida Site ↗
  • Elvira Sayfutyarova Sayfutyarova Group Pennsylvania State University Site ↗
  • Martin Seifrid Seifrid Group North Carolina State University Site ↗
  • Thomas P. Senftle Senftle Group Rice University Site ↗
  • Karthik Shekhar Shekhar Lab University of California, Berkeley Site ↗
  • Zachary M. Sherman Z Lab University of Washington Site ↗
  • Krishna Shrinivas Shrinivas Lab Northwestern University Site ↗
  • Rohit Singh Singh Lab Duke University Site ↗
  • Micheline Soley Soley Group University of Wisconsin–Madison Site ↗
  • Kevin V. Solomon Solomon Laboratory University of Delaware Site ↗
  • Jeff Spence Spence Lab University of California, San Francisco Site ↗
  • Kayla G. Sprenger Rational Design of Interfaces Lab University of Colorado Boulder Site ↗
  • Chong Sun Sun Lab Rutgers University–New Brunswick Site ↗
  • Yidan Sun Sun Lab Washington University in St. Louis Site ↗
  • Daniel Tabor Tabor Research Group Texas A&M University Site ↗
  • Ming Tang Mesoscale Materials Science Group Rice University Site ↗
  • Roel Tempelaar Tempelaar Team Northwestern University Site ↗
  • Erik Thiede Thiede Lab Cornell University Site ↗
  • Pratyush Tiwary Artificial Chemical Intelligence@Maryland University of Maryland, College Park Site ↗
  • Brian Trippe Trippe Lab Stanford University Site ↗
  • Alexander Urban Urban Research Group Columbia University Site ↗
  • David Van Valen Van Valen Lab California Institute of Technology Site ↗
  • Vojtech Vlcek Vlcek Group University of California, Santa Barbara Site ↗
  • Allon Wagner Wagner Lab University of California, Berkeley Site ↗
  • Shunzhi Wang Wang Lab New York University Site ↗
  • Michael A. Webb Webb Research Group Princeton University Site ↗
  • Mingjian Wen Wen Research Group University of Houston Site ↗
  • Hong-Zhou Ye Ye Group University of Maryland, College Park Site ↗
  • Shuwen Yue Yue Research Group Cornell University Site ↗
  • Daiwei (David) Zhang Daiwei Zhang Lab University of North Carolina at Chapel Hill Site ↗
  • Hongbo Zhao Zhao Research Group University of California, San Diego Site ↗
  • Jian Zhou Zhou Lab University of Chicago Site ↗
  • Tianyu Zhu Zhu Group Yale University Site ↗

Issue 2026-08-26

Highlights from this week

#01 arXiv v1 / preprint

Preprint—not peer reviewed

JANUS: A Multi-modal Foundation Neural Sampler for Disordered Materials

Denis Blessing, Mouyang Cheng, Maximilian Schebek, Jutta Rogal, Mingda Li, Carles Domingo-Enrich, Yuanqi Du

JANUS jointly samples atomic identities, structure, and volume with coupled discrete and continuous diffusion. In alloy benchmarks, the authors report recovery of equilibrium observables, free energies, and phase behavior using far fewer energy evaluations. Joint composition and structure sampling can make thermodynamic exploration and inverse design more accessible for disordered materials.

AI–materials Atomistic modelingGenerative design
Abstract brief CC0 Preprint
#02 arXiv v1 / preprint

Preprint—not peer reviewed

UBio-MolFM: Enabling Biomolecular Dynamics at DFT Accuracy and $10^5$ Atoms with One Untuned Potential

Lin Huang, Frank Peng, JiaJun Cheng, Zion Wang, Hao Yin, Hao Li, Ji Zhang, Jack Jia, Junping Zhao, Arthur Jiang, Jia Zhang

UBio-MolFM is a quantum-chemical foundation model whose receptive field spans non-covalent distances at near-linear cost. The authors report near-20 meV/Å force error past a thousand atoms for one untuned potential. This may broaden simulations where electronic structure affects ion conduction, membrane permeation, and metal recognition.

AI–biochemistryAI–chemistry Atomistic modelingFoundation modelsNeural potentials
Abstract brief CC0 Preprint
#03 arXiv v2 / preprint

Preprint—not peer reviewed

Universal Machine-learning Molecular Dynamics at the Speed of Empirical Potentials

Tiancheng Li, Jianming Xue, Linfeng Zhang, Duo Zhang, Han Wang

DPA4C is an equivariant interatomic potential co-designed with compressed computing operators for accuracy and efficiency. The authors report that its compact variant reduced energy, force, and stress errors while increasing saturated throughput relative to a fast universal potential. This moves universal molecular dynamics toward system sizes and speeds usually associated with empirical potentials.

AI–materials Atomistic modelingNeural potentials
Abstract brief CC0 Preprint
#04 arXiv v1 / preprint

Preprint—not peer reviewed

First-Principles Electron-Magnon Coupling with Machine-Learning Hamiltonians: From Band Renormalization to Transport

Shixu Liu, Xingding Li, Haozhe Li, Yang Zhong, Hongjun Xiang, Xin-Gao Gong, Ji-Hui Yang

The framework couples a first-principles EMC formalism with machine-learning spinful Hamiltonians. For α-Fe, the authors report a full T² resistivity component whose coefficient agrees quantitatively with measurement. The result can help separate EMC from EPC-EMC interplay in magnetic transport.

AI–materials Electronic structureSurrogate modeling
Abstract brief CC0 Preprint
#05 arXiv v1 / preprint

Preprint—not peer reviewed

Learning the Kohn-Sham map with neural operators for quasi-linear scaling density functional theory

Danish Khan, Maurice D. Hanisch, Nikolai Argatoff, Evan Xie, Sandeep Sharma, Anima Anandkumar

A symmetry-aware Fourier neural operator learns the density part of the Kohn-Sham map from potentials on real-space grids. The authors report that one model generalizes to out-of-distribution organic molecules, insulators, and metals. Learning this map could reduce dependence on orbital diagonalization in density functional calculations across distinct systems.

AI–materials Electronic structureSurrogate modeling
Abstract brief CC0 Preprint
#06 arXiv v1 / preprint

Preprint—not peer reviewed

Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis

Bogdan Zagribelnyy, Ivan Ilin, Nikita Bondarev, Maksim Kuznetsov, Mathieu Reymond, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov

Top-K prompting is a training and inference approach for producing diverse plausible reaction predictions. With ChemCensor-based and novelty-oriented rewards, the authors report state-of-the-art results on the OOD URSA-expert-2026 benchmark. This may make single-step retrosynthesis evaluation better reflect its one-to-many nature.

AI–chemistry Foundation modelsSynthesis planning
Abstract brief CC0 Preprint
#07 arXiv v1 / preprint

Preprint—not peer reviewed

Accurate and Transferable Intermolecular Potential Based on Machine-Learned Molecular Electron Density

Dahvyd Wing, Mihail Bogojeski, Szabolcs Goger, Klaus-Robert Müller, Alexandre Tkatchenko

DensIP represents intermolecular interactions using machine-learned electron densities and four universal parameters. The authors report sub-kcal/mol errors for dimers with molecules missing from training, including non-equilibrium conformations. It could provide accurate synthetic training data when high-quality reference calculations are expensive.

AI–chemistry Neural potentials
Abstract brief CC0 Preprint
#08 arXiv v1 / preprint

Preprint—not peer reviewed

Machine-learned exchange-correlation functionals for molecules, solids, and reactive surfaces

Mohamed S. Abdallah, Zhuotao Jin, Boris Kozinsky, Kyle Bystrom

CIDER26SS combines machine learning with nonlocal physical descriptors in an exchange-correlation functional designed for broad transferability. The authors report correct carbon monoxide binding on platinum with accurate adsorption energy, lattice constant, and surface energy. A functional that retains accuracy beyond its training domain could improve calculations for reactive metal surfaces.

AI–chemistryAI–materials Electronic structure
Abstract brief CC0 Preprint
#09 arXiv v1 / preprint

Preprint—not peer reviewed

Scalable photoexcitation-induced molecular dynamics with machine-learned Hamiltonians

Leyu Cai, Yunzhe Jia, Daqiang Chen, Sheng Meng

TDAP-eML combines machine-learned electronic structure with atomistic propagation for photoexcited lattice dynamics. The authors report reproduction of key lattice responses from time-dependent density functional calculations in silicon and FeSe. Its cost advantage with system size could broaden simulations that connect electronic excitation to structural motion.

AI–materials Atomistic modelingElectronic structure
Abstract brief CC0 Preprint
#10 arXiv v2 / preprint

Preprint—not peer reviewed

The parity gap in crystal tensor prediction

Can Polat, Mustafa Kurban, Erchin Serpedin, Hasan Kurban

The parity gap quantifies piezoelectric tensor freedom that proper rotations allow and inversion symmetry removes. The authors report systematic forbidden non-zero responses from unconstrained SO(3) models in centrosymmetric crystal classes. The metric may help distinguish prediction error from exact structural compliance with physical law.

AI–materials Datasets + benchmarksMaterials representation
Abstract brief CC0 Preprint
#11 arXiv v1 / preprint

Preprint—not peer reviewed

ReCurveflow: A Flow Matching Framework that Learns Curved Reaction Trajectories to Predict Transition State Geometries

Seungheun Baek, Mogan Gim, Jaewoo Kang

ReCurveflow learns transition-state geometries along curved reference paths derived from molecular geometry bands. Across data splits and evaluation metrics, the authors report the best result for most split-metric comparisons against seven baselines. Curved trajectories and off-path correction target the mismatch between reaction paths and straight interpolation.

AI–chemistry Generative designReaction modeling
Abstract brief CC0 Preprint
#12 arXiv v1 / preprint

Preprint—not peer reviewed

ChemDIRT: A Diversified Instruction, Representation, and Task Benchmark for Robust Chemistry-LLM Evaluation

Eric Inae, Tim Gunn, Chris Bond, Meng Jiang

ChemDIRT evaluates chemical reasoning under controlled changes in instructions and molecular representations across chemistry tasks. The authors report substantial prompt sensitivity, representation dependence, and uneven performance across task families among tested language models. This benchmark makes robustness to scientific problem formulation a measurable part of chemistry model assessment.

AI–chemistry Datasets + benchmarksFoundation models
Abstract brief CC0 Preprint
#13 arXiv v2 / preprint

Preprint—not peer reviewed

Diagnosing and narrowing the simulation-to-real gap in powder X-ray diffraction with a wet-dry agentic loop

Shaoguang Wang, Weiyu Guo, Ben Fei, Xiaohong Shao, Zhihui Wang, Wanli Ouyang

Xtalyst joins phase identification, refinement, and calibrated property prediction in an agent-orchestrated system. On its held-out partition, the authors report that each module reproduced its development finding across both splits. This approach may make the simulation-to-real gap more tractable in PXRD analysis.

AI–materials Scientific agents
Abstract brief CC0 Preprint
#14 bioRxiv v2 / preprint

Preprint—not peer reviewed

A mechanism-annotated benchmark reveals limited fidelity to drug-response signatures in single-cell perturbation models

Li, L., Duan, S., Zha, X., Ye, F., Zhang, Y., Zhang, X., Cao, Y., Liu, C., Fang, B.

The authors present an annotated resource that connects matched profiles before and after treatment with directional evidence for key genes. The authors find weak agreement between expression-similarity metrics and MFS across models, baselines, and data splits. It may help distinguish reconstruction quality from preservation of drug-response signatures.

AI–biochemistry Datasets + benchmarks
Abstract brief CC BY Preprint
#15 arXiv v1 / preprint

Preprint—not peer reviewed

Monroe: A Molecular Foundation Model for In-Context Probabilistic Inference

Blazej Banaszewski, Andrew W. Fitzgibbon

Monroe combines large-scale molecular pretraining, stereochemical graph representation, and an in-context downstream predictor. On established benchmarks, the authors report that Monroe matches or exceeds existing molecular foundation models. Its downstream adaptation strategy may be useful where bioassay prediction is limited by scarce experimental data.

AI–chemistry Foundation modelsMolecular representation
Abstract brief CC0 Preprint
#16 arXiv v4 / preprint

Preprint—not peer reviewed

Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules

Florian Rottach, Sebastian Schieferdecker, William Rudman, Randall Balestriero, Carsten Eickhoff

Mol-JEPA uses modality masking to learn from molecular structures, cellular phenotypes, binding affinities, and other discovery data. The authors report strong benchmark performance from representations learned through latent-space prediction. This approach makes biochemical context part of a shared molecular representation instead of treating each data modality in isolation.

AI–chemistry Foundation modelsMolecular representation
Abstract brief CC0 Preprint
#17 arXiv v1 / preprint

Preprint—not peer reviewed

Structure-Agnostic Prediction of the Electronic Density of States with a Chemical Language Model

Ivan D. Rubtsov, Ivan V. Dudakov, Vadim V. Korolev

DOSSIER predicts a density-of-states spectrum from elemental composition through a chemical language model. The authors report useful band-gap and d-band descriptors from spectra predicted on an extended Materials Project dataset. This could aid composition screening before a crystal structure is available.

AI–materials Electronic structure
Abstract brief CC0 Preprint
#18 arXiv v1 / preprint

Preprint—not peer reviewed

FAR-DPO: Feasibility-Aware and Robust Direct Preference Optimization for Cyclic Peptide Design

Guofeng Zhang, Rong Han, Xiaoyu Wang, Zhiyun Li, Zongbo Han, Xiaohong Liu, Guangyu Wang

FAR-DPO steers generators toward structurally and biophysically feasible cyclic peptide designs using feasibility-aware preferences and difficulty-aware optimization. Under a fixed generation budget, the authors report increased overall success rate for PepGLAD and PepFlow. The method may improve design feasibility for especially challenging targets.

AI–biochemistry Biomolecular designGenerative design
Abstract brief CC0 Preprint
#19 bioRxiv v1 / preprint

Preprint—not peer reviewed

De novo Design of Macrocyclic Molecular Glues

Brunner, A., Wierbilowicz, K., Daumiller, D., Bexell, D., Karlsson, K., Sangfelt, O., Bryant, P.

EvoBind-multimer generates macrocyclic peptides that connect selected protein pairs from sequence without prior interface information. The authors report live-cell proximity for both tested protein pairs and functional ternary complexes capable of degradation. The differing behavior in patient-derived models underscores that designed proximity can remain context-dependent after a complex is formed.

AI–biochemistry Biomolecular designGenerative design
Abstract brief CC BY Preprint
#20 bioRxiv v1 / preprint

Preprint—not peer reviewed

PhageLysData: an evidence-aware and AI-ready dataset of phage lytic enzymes and depolymerases

Medina-Ortiz, D., Olivera-Nappa, A., Lienqueo, M. E., Opazo, R., Romero, J.

PhageLysData combines multiple sources with provenance tracking and exact-sequence consolidation for phage lytic enzymes and depolymerases. The release separates an evidence-supported Core from prediction-only candidates while retaining context entities for provenance. That separation can make dataset construction and candidate retrieval more explicit about the type of underlying support.

AI–biochemistry Datasets + benchmarks
Abstract brief CC BY Preprint