Leveraging Quantum Chemistry and Machine Learning for the Design of Low-Valent Transition Metal Catalysts in Nitrogen to Ammonia Conversion

https://pubs.acs.org/doi/10.1021/jacs.5c00099

Here, we integrate quantum chemistry, molecular dynamics, and machine learning (ML) to uncover mechanistic features governing nitrogen reduction reaction (NRR) activity and guide catalyst design.

Density functional theory (DFT) and ab initio molecular dynamics reveal that [Fe(CAAC)2] leverages redox noninnocent CAAC ligands to stabilize Fe(I) ([FeI(CAAC)2·–]), with strong antiferromagnetic coupling (JFe-CAAC = −1817 cm–1). Flexibility of bulky Dipp groups found to hinder N2 binding, rationalizing experimental observations. The exothermic formation of [(CAAC(H))2Fe] (ΔG = −4.5 kJ/mol) with in situ generated H2 exposure rationalizes the lower TON observed via catalyst deactivation.

ML models trained on quantum descriptors such as M–C bond lengths, spin density, and frontier orbital energies identify the M–C distance as a key predictor of reactivity. A composite free energy metric (ΔGtot) encompassing cis-trans isomerization (ΔG10), N2 binding (ΔG20), and the first reduction step (ΔG30) enables ranking of candidate catalysts. Moreover, Ti and V complexes show the lowest ΔGtot (24–60 kJ/mol), while late transition and coinage metals exceed 120 kJ/mol, correlating with lower activity.

By providing unprecedented insights into the interplay among ligand design, metal choice, and catalytic efficiency, this work lays a critical foundation for the rational design of homogeneous NRR catalysts, with implications for advancing sustainable ammonia production technologies.

📕Journal of the American Chemical Society (IF=14.4)
#method

Token-Mol 1.0: tokenized drug design with large language models🔥

https://doi.org/10.1038/s41467-025-59628-y

Here, we present Token-Mol, a token-only 3D drug design model that encodes both 2D and 3D structural information, along with molecular properties, into discrete tokens.

The model surpasses existing methods, improving molecular conformation generation by over 10% and 20% across two datasets, while outperforming token-only models by 30% in property prediction. In pocket-based molecular generation, it enhances drug-likeness and synthetic accessibility by approximately 11% and 14%, respectively. Notably, Token-Mol operates 35 times faster than expert diffusion models.

In real-world validation, it improves success rates and, when combined with reinforcement learning, further optimizes affinity and drug-likeness, advancing AI-driven drug discovery.

📕Nature Communications (IF=14.7)
#method

Bridging chemistry and artificial intelligence by a reaction description language

https://doi.org/10.1038/s42256-025-01032-8

Here, we present ReactSeq, a reaction description language that defines molecular editing operations for step-by-step chemical transformation. Based on ReactSeq, language models for retrosynthesis prediction may consistently excel in all benchmark tests, and demonstrate promising emergent abilities in the human-in-the-loop and explainable artificial intelligence. Moreover, ReactSeq has allowed us to obtain universal and reliable representations of chemical reactions, which enable navigation of the reaction space and aid in the recommendation of experimental procedures and prediction of reaction yields. We foresee that ReactSeq can serve as a bridge to narrow the gap between chemistry and artificial intelligence.

📕Nature Machine Intelligence (IF=23.8)
#method

AI Approaches to Homogeneous Catalysis with Transition Metal Complexes🔥

https://doi.org/10.1021/acscatal.5c01202

Artificial intelligence (AI) is transforming research in chemistry, including homogeneous catalysis with transition metals. Over the past 15 years, the number of publications combining AI with catalysis has increased exponentially, reflecting the interest and strength of this strategy in the field. Since this is a broad emerging discipline, it is essential to establish guidelines that clarify the diverse approaches already available.

Initially, models were developed to predict key aspects of the reaction mechanism, aiming at screening catalyst candidates. Subsequent studies have incorporated experimental data to optimize reaction conditions and yields. More recently, generative AI based on deep learning methods has enabled the inverse design of novel catalysts with predefined target properties. While most studies rely on computational data, recent advancements have improved the acquisition of experimental data, enabling AI-driven automated workflows.

This Perspective gives a critical overview on selected studies that reflect the state of the art in the application of AI to homogeneous metal-catalyzed reactions, also highlighting future opportunities and challenges.

📕ACS Catalysis (IF=11.7)
#review

Generalizable, fast, and accurate DeepQSPR with fastprop🔥

https://jcheminf.biomedcentral.com/articles/10.1186/s13321-025-01013-4

This paper introduces fastprop, a software package and general Deep-QSPR framework that combines a cogent set of molecular descriptors with deep learning to achieve state-of-the-art performance on datasets ranging from tens to tens of thousands of molecules.

fastprop provides both a user-friendly Command Line Interface and highly interoperable set of Python modules for the training and deployment of feedforward neural networks for property prediction.

This approach yields improvements in speed and interpretability over existing methods while statistically equaling or exceeding their performance across most of the tested benchmarks.

🖥 https://github.com/jacksonburns/fastprop

📕 Journal of Cheminformatics (IF=7.1)
#method

SurfPro – a curated database and predictive model of experimental properties of surfactants🔥

https://doi.org/10.1039/D4DD00393D

Surfactant data are scattered across many literature sources, and reported in a manner which is often unsuitable as input for predictive models. In this work, we address this limitation by compiling the SurfPro database of surfactant properties. SurfPro consists of 1624 surfactant entries curated from 223 literature sources, containing 1395 CMC values, 972 γCMC values and more than 657 values for Γmax, C20, πCMC and Amin. However, only 647 structures have all reported properties, and for most surfactants multiple properties are missing.

We trained a previously reported graph neural network architecture for single- and multi-property prediction on these incomplete data of all surfactant types in the database to accurately predict pCMC (−log10(CMC)), γCMC, Γmax and pC20. We achieved state-of-the-art performance of these four properties using an ensemble of AttentiveFP models trained on ten different folds of the training data in the multi-property setting. Finally, we leveraged the predictions and uncertainties of the ensemble model to impute all missing properties for all 977 surfactants with an incomplete set of properties. We make our curated SurfPro database, proposed test split and training datasets, the imputed database, as well as our code publicly available.

📕Digital Discovery (IF=6.2)
#dataset

MolecularGPT: Open Large Language Model (LLM) for Few-Shot Molecular Property Prediction🔥

https://doi.org/10.48550/arXiv.2406.12950

Molecular property prediction (MPP) is a fundamental and crucial task in drug discovery. However, prior methods are limited by the requirement for a large number of labeled molecules and their restricted ability to generalize for unseen and new tasks, both of which are essential for real-world applications.

To address these challenges, we present MolecularGPT for few-shot MPP. From a perspective on instruction tuning, we fine-tune large language models (LLMs) based on curated molecular instructions spanning over 1000 property prediction tasks. This enables building a versatile and specialized LLM that can be adapted to novel MPP tasks without any fine-tuning through zero- and few-shot in-context learning (ICL). MolecularGPT exhibits competitive in-context reasoning capabilities across 10 downstream evaluation datasets, setting new benchmarks for few-shot molecular prediction tasks. More importantly, with just two-shot examples, MolecularGPT can outperform standard supervised graph neural network methods on 4 out of 7 datasets. It also excels state-of-the-art LLM baselines by up to 15.7% increase on classification accuracy and decrease of 17.9 on regression metrics (e.g., RMSE) under zero-shot. This study demonstrates the potential of LLMs as effective few-shot molecular property predictors.

arXiv
#method

Advancing molecular machine learning representations with stereoelectronics-infused molecular graphs

https://doi.org/10.1038/s42256-025-01031-9

This work introduces a new approach to infusing quantum-chemical-rich information into molecular graphs via stereoelectronic effects, enhancing expressivity and interpretability. Learning to predict the stereoelectronics-infused representation with a tailored double graph neural network workflow enables its application to any downstream molecular machine learning task without expensive quantum-chemical calculations.

We show that the explicit addition of stereoelectronic information substantially improves the performance of message-passing two-dimensional machine learning models for molecular property prediction. We show that the learned representations trained on small molecules can accurately extrapolate to much larger molecular structures, yielding chemical insight into orbital interactions for previously intractable systems, such as entire proteins, opening new avenues of molecular design.

Finally, we have developed a web application (simg.cheme.cmu.edu) where users can rapidly explore stereoelectronic information for their own molecular systems.

@GPTyrannosaurus поздравляем с крутейшей публикацией!

📕 Nature Machine Intelligence (IF=18.8)
#method

Cross-disciplinary perspectives on the potential for artificial intelligence across chemistry🔥

https://doi.org/10.1039/D5CS00146C

Here, we present ten diverse perspectives on the impact of AI coming from those with a range of backgrounds from experimental chemistry, computational chemistry, computer science, engineering and across different areas of chemistry, including drug discovery, catalysis, chemical automation, chemical physics, materials chemistry.

The ten perspectives presented here cover a range of themes, including AI for computation, facilitating discovery, supporting experiments, and enabling technologies for transformation. We highlight and discuss imminent challenges and ways in which we are redefining problems to accelerate the impact of chemical research via AI.

📕Chemical Society Reviews (IF = 40.4)
#review

Ab initio structure solutions from nanocrystalline powder diffraction data via diffusion models 🔥

https://www.nature.com/articles/s41563-025-02220-y

A major challenge in materials science is the determination of the structure of nanometre-sized objects. Here we present an approach that uses a generative machine learning model based on diffusion processes that are trained on 45,229 known structures.

The model factors measured the diffraction pattern as well as the relevant statistical priors on the unit cell of atomic cluster structures. Conditioned only on the chemical formula and the information-scarce finite-sized broadened powder diffraction pattern, we find that our model, PXRDnet, can successfully solve the simulated nanocrystals as small as 10 Å across 200 materials of varying symmetries and complexities, including structures from all seven crystal systems.

We show that our model can successfully and verifiably determine structural candidates four out of five times, with an average error among these candidates being only 7% (as measured by the post-Rietveld refinement R-factor). Furthermore, PXRDnet is capable of solving structures from noisy diffraction patterns gathered in real-world experiments.

🖥 https://github.com/gabeguo/cdvae_xrd

📕Nature Materials (IF = 37.2)
#method

Design of circularly polarized phosphorescence materials guided by transfer learning 🔥

https://doi.org/10.1038/s41467-025-60310-6

Herein, we propose a strategy to customized design of circularly polarized phosphorescent materials based on large language models and transfer learning methods, which not only enables efficient identification of suitable synthesis precursors, but also provides valuable guidance for experimental procedures.

We demonstrate the significant advantages of transfer learning with limited chemical data, and precisely fabricate films with high glum (1.86), narrow full-width at half-maximum (49 nm) and customized circularly polarized phosphorescent performance with targeted spectral position.

📕Nature Communications (IF=14.7)
#method

Known Unknowns: Out-of-Distribution (OOD) Property Prediction in Materials and Molecules🔥

https://arxiv.org/abs/2502.05970

Our objective is to train predictor models that extrapolate zero-shot to higher ranges than in the training data, given the chemical compositions of solids or molecular graphs and their property values. We propose using a transductive approach to OOD property prediction, achieving improvements in prediction accuracy.

In particular, the True Positive Rate (TPR) of OOD classification of materials and molecules improved by 3x and 2.5x, respectively, and precision improved by 2x and 1.5x compared to non-transductive baselines. Our method leverages analogical input-target relations in the training and test sets, enabling generalization beyond the training target support, and can be applied to any other material and molecular tasks.

arXiv
#method

A framework for evaluating the chemical knowledge and reasoning abilities of large language models against the expertise of chemists🔥

https://www.nature.com/articles/s41557-025-01815-x

Here we introduce ChemBench, an automated framework for evaluating the chemical knowledge and reasoning abilities of state-of-the-art LLMs against the expertise of chemists. We curated more than 2,700 question–answer pairs, evaluated leading open- and closed-source LLMs and found that the best models, on average, outperformed the best human chemists in our study.

However, the models struggle with some basic tasks and provide overconfident predictions. These findings reveal LLMs’ impressive chemical capabilities while emphasizing the need for further research to improve their safety and usefulness. They also suggest adapting chemistry education and show the value of benchmarking frameworks for evaluating LLMs in specific domains.

📕 Nature Chemistry (IF = 19.2)
#method

Effective and Explainable Molecular Property Prediction by Chain-of-Thought Enabled Large Language Models and Multi-Modal Molecular Information Fusion

https://pubs.acs.org/doi/10.1021/acs.jcim.5c00577

This paper presents LLM-MPP, a new, effective, and explainable LLM-driven multimodal method for drug molecular property prediction, which leverages 1D SMILES strings, 2D molecular graph structures, and molecular textual descriptions of molecular properties as training data.

By incorporating the chain-of-thought (CoT) technique, we enhance the interpretability and transparency of the proposed method, while promoting alignment and feature extraction across multiple modalities. Cross-attention and contrastive learning are adopted to effectively fuse multimodal molecular representations for property prediction.

Experiments on nine benchmark data sets for molecular property prediction demonstrate that our method achieves state-of-the-art performance on 5 and ranks second on 1 of the 9 data sets, surpassing 22 existing baselines. Ablation experiments validate the effectiveness of our innovative modules, effectively addressing the limitations of existing models.

🖥 https://github.com/jinchang1223/LLM-MPP

📕Journal of Chemical Information and Modeling (IF=5.6)
#method

📚Приходите писать ко мне диплом!📚

Я знаю, что меня довольно много читает людей с химфака МГУ. Поэтому, возможно, кому-то будет интересно. Актуально для окончивших 4-й и 5 курс студентов кафедры медицинской химии и ТОС, ещё не определившихся с темой диплома, беспокоящихся о его судьбе и желающих поделать что-то полезное для диплома этим летом на переднем крае хемоинформатической науки с научным руководителем из индустрии.

Есть хорошая тема для дипломной работы в области хемоинформатики химических реакций и анализа химических данных, и я готов взять научное руководство этой дипломной работой! Похожая дипломная работа под моим руководством была успешно защищена на кафедре медицинской химии и ТОС в 2023 году, по итогам работы написана статья, а разработанный алгоритм стал частью модели синтетической доступности ReRSA, встроенной в Chemistry42.

Если кому-то релевантно — пишите мне в личку @theodoricus1 до 1️⃣5️⃣ июня с тегом #дипломнаяработа, описывайте ваш опыт в программировании (базового питона хватит + чат гпт, клод, курсор вам в помощь). Если кандидатов будет несколько, то проведем собеседования, выберем одного.

LAMBench: A Benchmark for Large Atomic Models🔥

https://arxiv.org/abs/2504.19578

In this study, we introduce LAMBench, a benchmarking system designed to evaluate Large atomic models (LAMs) in terms of their generalizability, adaptability, and applicability. These attributes are crucial for deploying LAMs as ready-to-use tools across a diverse array of scientific discovery contexts.

We benchmark eight state-of-the-art LAMs released prior to April 1, 2025, using LAMBench. Our findings reveal a significant gap between the current LAMs and the ideal universal potential energy surface. They also highlight the need for incorporating cross-domain training data, supporting multi-fidelity modeling, and ensuring the models' conservativeness and differentiability.

As a dynamic and extensible platform, LAMBench is intended to continuously evolve, thereby facilitating the development of robust and generalizable LAMs capable of significantly advancing scientific research. Аn interactive leaderboard is available at https://www.aissquare.com/openlam?tab=Benchmark

🖥 https://github.com/deepmodeling/lambench

arXiv
#method

Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries

https://pubs.acs.org/doi/10.1021/acs.chemrev.4c00678

Свежий обзор от сотрудников Йельского университета, Moderna и NVIDIA:

This Review specifically explores the potential of quantum neural networks on gate-based quantum computers within the context of drug discovery. We discuss the theoretical foundations of quantum machine learning, including data encoding, variational quantum circuits, and hybrid quantum-classical approaches.

Applications to drug discovery are highlighted, including molecular property prediction and molecular generation. We provide a balanced perspective, emphasizing both the potential benefits and the challenges that must be addressed.

📕Chemical Reviews (IF=51.4)
#review

Graph Neural Networks in Modern AI-aided Drug Discovery🔥

https://arxiv.org/abs/2506.06915

Свежий обзор от 7 июня на 219 страниц и 675 ссылок:

This review provides a comprehensive overview of the methodological foundations and representative applications of GNNs in drug discovery, spanning tasks such as molecular property prediction, virtual screening, molecular generation, biomedical knowledge graph construction, and synthesis planning.

Particular attention is given to recent methodological advances, including geometric GNNs, interpretable models, uncertainty quantification, scalable graph architectures, and graph generative frameworks.

We also discuss how these models integrate with modern deep learning approaches, such as self-supervised learning, multi-task learning, meta-learning and pre-training.

Throughout this review, we highlight the practical challenges and methodological bottlenecks encountered when applying GNNs to real-world drug discovery pipelines, and conclude with a discussion on future directions.

#review

ASKCOS: Open-Source, Data-Driven Synthesis Planning

https://pubs.acs.org/doi/10.1021/acs.accounts.5c00155

In this Account, we describe the range of data-driven methods and models that have been incorporated into the newest version of ASKCOS, an open-source software suite for synthesis planning that we have been developing since 2016.

This ongoing effort has been driven by the importance of bridging the gap between research and development, making research advances available through a freely available practical tool. ASKCOS integrates modules for retrosynthetic planning, modules for complementary capabilities of condition prediction and reaction product prediction, and several supplementary modules and utilities with various roles in synthesis planning.

📕 Accounts of Chemical Research (IF = 17.7)
#method

Polymer design for solvent separations by integrating simulations, experiments and known physics via machine learning🔥

https://doi.org/10.1038/s41524-025-01681-8

This study guides the discovery of sustainable high-performance polymer membranes for organic binary solvent separations. We focus on solvent diffusivity in polymers, a key factor in quantifying solvent transport.

We fuse experimental and simulated diffusivity data to train physics-enforced multi-task ML models, achieving more robust predictions in unseen chemical spaces and outperforming single-task models in data-limited scenarios. Next, we address the challenge of identifying optimal membranes for a model toluene-heptane separation, identifying polyvinyl chloride (PVC) as the optimal membrane among 13,000 polymers, consistent with literature findings, thereby validating our methodology. Expanding our search, we screen 1 million publicly available and 7 million chemically recyclable polymers, identifying greener halogen-free alternatives to PVC. This capability is expected to advance membrane design for solvent separations.

📕npj computational materials (IF=9.4)
#method