Qi Yu, Ruitao Ma, Chen Qu, Riccardo Conte, Apurba Nandi, Priyanka Pandey, Paul L Houston, Dong H Zhang, Joel M Bowman
{"title":"Extending atomic decomposition and many-body representation with a chemistry-motivated approach to machine learning potentials.","authors":"Qi Yu, Ruitao Ma, Chen Qu, Riccardo Conte, Apurba Nandi, Priyanka Pandey, Paul L Houston, Dong H Zhang, Joel M Bowman","doi":"10.1038/s43588-025-00790-0","DOIUrl":"https://doi.org/10.1038/s43588-025-00790-0","url":null,"abstract":"<p><p>Most widely used machine learning potentials for condensed-phase applications rely on many-body permutationally invariant polynomial or atom-centered neural networks. However, these approaches face challenges in achieving chemical interpretability in atomistic energy decomposition and fully matching the computational efficiency of traditional force fields. Here we present a method that combines aspects of both approaches and balances accuracy and force-field-level speed. This method utilizes a monomer-centered representation, where the potential energy is decomposed into the sum of chemically meaningful monomeric energies. The structural descriptors of monomers are described by one-body and two-body effective interactions, enforced by appropriate sets of permutationally invariant polynomials as inputs to the feed-forward neural networks. Systematic assessments of models for gas-phase water trimer, liquid water, methane-water cluster and liquid carbon dioxide are performed. The improved accuracy, efficiency and flexibility of this method have promise for constructing accurate machine learning potentials and enabling large-scale quantum and classical simulations for complex molecular systems.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":12.0,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144065335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multimodal learning for mapping genotype-phenotype dynamics.","authors":"Farhan Khodaee, Rohola Zandie, Elazer R Edelman","doi":"10.1038/s43588-024-00765-7","DOIUrl":"10.1038/s43588-024-00765-7","url":null,"abstract":"<p><p>How complex phenotypes emerge from intricate gene expression patterns is a fundamental question in biology. Integrating high-content genotyping approaches such as single-cell RNA sequencing and advanced learning methods such as language models offers an opportunity for dissecting this complex relationship. Here we present a computational integrated genetics framework designed to analyze and interpret the high-dimensional landscape of genotypes and their associated phenotypes simultaneously. We applied this approach to develop a multimodal foundation model to explore the genotype-phenotype relationship manifold for human transcriptomics at the cellular level. Analyzing this joint manifold showed a refined resolution of cellular heterogeneity, uncovered potential cross-tissue biomarkers and provided contextualized embeddings to investigate the polyfunctionality of genes shown for the von Willebrand factor (VWF) gene in endothelial cells. Overall, this study advances our understanding of the dynamic interplay between gene expression and phenotypic manifestation and demonstrates the potential of integrated genetics in uncovering new dimensions of cellular function and complexity.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":"333-344"},"PeriodicalIF":12.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143061684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fanjie Xu, Wentao Guo, Feng Wang, Lin Yao, Hongshuai Wang, Fujie Tang, Zhifeng Gao, Linfeng Zhang, Weinan E, Zhong-Qun Tian, Jun Cheng
{"title":"Toward a unified benchmark and framework for deep learning-based prediction of nuclear magnetic resonance chemical shifts.","authors":"Fanjie Xu, Wentao Guo, Feng Wang, Lin Yao, Hongshuai Wang, Fujie Tang, Zhifeng Gao, Linfeng Zhang, Weinan E, Zhong-Qun Tian, Jun Cheng","doi":"10.1038/s43588-025-00783-z","DOIUrl":"10.1038/s43588-025-00783-z","url":null,"abstract":"<p><p>The study of structure-spectrum relationships is essential for spectral interpretation, impacting structural elucidation and material design. Predicting spectra from molecular structures is challenging due to their complex relationships. Here we introduce NMRNet, a deep learning framework using the SE(3) Transformer for atomic environment modeling, following a pretraining and fine-tuning paradigm. To support the evaluation of nuclear magnetic resonance chemical shift prediction models, we have established a comprehensive benchmark based on previous research and databases, covering diverse chemical systems. Applying NMRNet to these benchmark datasets, we achieve competitive performance in both liquid-state and solid-state nuclear magnetic resonance datasets, demonstrating its robustness and practical utility in real-world scenarios. Our work helps to advance deep learning applications in analytical and structural chemistry.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":"292-300"},"PeriodicalIF":12.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143744553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Active twisting for adaptive droplet collection.","authors":"Yifan Yang, Zhijun Dai, Yuzhen Chen, Fan Xu","doi":"10.1038/s43588-025-00786-w","DOIUrl":"https://doi.org/10.1038/s43588-025-00786-w","url":null,"abstract":"<p><p>Many xeric plant leaves exhibit bending and twisting morphology, which may contribute to their important biological and physical functions adapted to drought and desert conditions. Revealing the relationships between various morphologies and functionalities can inspire device designs for meeting increasingly stringent environmental requirements. Here, demonstrated on the biomimetic bilayer ribbons made of liquid crystal elastomers, we reveal that the stimulus-induced morphological evolution of bending, spiraling, twisting and various coupling states among them can be selectively achieved and precisely tuned by designing the director orientations in liquid crystal elastomer bilayers. The mathematical models and analytical solutions are developed to quantify the morphology selection and phase transition of these liquid crystal elastomer ribbons for material design, as confirmed by experiments. Moreover, we show that, under activation and control of external stimuli, the twisting configuration can be harnessed to effectively collect and guide the transportation of droplets, and enhance the structural stiffness for resisting wind blow and rainfall to achieve the optimal configuration for water collection. Our results reveal the interesting functions correlated with bending, spiraling and twisting morphologies widely present in the natural world, by providing fundamental insights into their shape transformation and controlling factors. This work also demonstrates a potential application with integrating morphogenesis-environment interactions into devices or equipments.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"5 4","pages":"313-321"},"PeriodicalIF":12.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12021652/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144052816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Christopher Jurich, Qianzhen Shao, Xinchun Ran, Zhongyue J Yang
{"title":"Physics-based modeling in the new era of enzyme engineering.","authors":"Christopher Jurich, Qianzhen Shao, Xinchun Ran, Zhongyue J Yang","doi":"10.1038/s43588-025-00788-8","DOIUrl":"https://doi.org/10.1038/s43588-025-00788-8","url":null,"abstract":"<p><p>Enzyme engineering is entering a new era characterized by the integration of computational strategies. While bioinformatics and artificial intelligence methods have been extensively applied to accelerate the screening of function-enhancing mutants, physics-based modeling methods, such as molecular mechanics and quantum mechanics, are essential complements in many objectives. In this Perspective, we highlight how physics-based modeling will help the field of computational enzyme engineering reach its full potential by exploring current developments, unmet challenges and emerging opportunities for tool development.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"5 4","pages":"279-291"},"PeriodicalIF":12.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144037960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Andreas Luttens, Israel Cabeza de Vaca, Leonard Sparring, José Brea, Antón Leandro Martínez, Nour Aldin Kahlous, Dmytro S Radchenko, Yurii S Moroz, María Isabel Loza, Ulf Norinder, Jens Carlsson
{"title":"Rapid traversal of vast chemical space using machine learning-guided docking screens.","authors":"Andreas Luttens, Israel Cabeza de Vaca, Leonard Sparring, José Brea, Antón Leandro Martínez, Nour Aldin Kahlous, Dmytro S Radchenko, Yurii S Moroz, María Isabel Loza, Ulf Norinder, Jens Carlsson","doi":"10.1038/s43588-025-00777-x","DOIUrl":"10.1038/s43588-025-00777-x","url":null,"abstract":"<p><p>The accelerating growth of make-on-demand chemical libraries provides unprecedented opportunities to identify starting points for drug discovery with virtual screening. However, these multi-billion-scale libraries are challenging to screen, even for the fastest structure-based docking methods. Here we explore a strategy that combines machine learning and molecular docking to enable rapid virtual screening of databases containing billions of compounds. In our workflow, a classification algorithm is trained to identify top-scoring compounds based on molecular docking of 1 million compounds to the target protein. The conformal prediction framework is then used to make selections from the multi-billion-scale library, reducing the number of compounds to be scored by docking. The CatBoost classifier showed an optimal balance between speed and accuracy and was used to adapt the workflow for screens of ultralarge libraries. Application to a library of 3.5 billion compounds demonstrated that our protocol can reduce the computational cost of structure-based virtual screening by more than 1,000-fold. Experimental testing of predictions identified ligands of G protein-coupled receptors and demonstrated that our approach enables discovery of compounds with multi-target activity tailored for therapeutic effect.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":"301-312"},"PeriodicalIF":12.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12021657/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143627187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Generative molecular design and discovery on the rise.","authors":"","doi":"10.1038/s43588-025-00802-z","DOIUrl":"https://doi.org/10.1038/s43588-025-00802-z","url":null,"abstract":"","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"5 4","pages":"269-270"},"PeriodicalIF":12.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144061708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}