Journal of Cheminformatics最新文献

{"title":"Retrosynthetic crosstalk between single-step reaction and multi-step planning","authors":"Junseok Choe,&nbsp;Hajung Kim,&nbsp;Yan Ting Chok,&nbsp;Mogan Gim,&nbsp;Jaewoo Kang","doi":"10.1186/s13321-025-01088-z","DOIUrl":"10.1186/s13321-025-01088-z","url":null,"abstract":"<div><p>Retrosynthesis—the process of deconstructing complex molecules into simpler, more accessible precursors—is a cornerstone of drug discovery and material design. While machine learning has improved single-step retrosynthesis prediction, generating complete multi-step retrosynthetic routes remains challenging. In this study, we explore the integration of single-step retrosynthesis models with various planning algorithms to improve multi-step retrosynthetic route generation. We expand the exploration space beyond previously limited settings by incorporating combinations of planning algorithms and single-step retrosynthesis models and diverse datasets, enabling a more comprehensive assessment of retrosynthetic strategies. We evaluated synthetic routes based on both solvability, the ability to generate a complete route, and route feasibility, which reflects their practical executability in the laboratory. Our findings show that the model combination with the highest solvability does not always produce the most feasible routes, underscoring the need for more nuanced evaluation. Through a systematic analysis of combinations of planning algorithms and single-step retrosynthesis models, their performance across different datasets, and various practical metrics, our study provides a more comprehensive evaluation of retrosynthetic planning strategies. These insights contribute to a better understanding of computational retrosynthesis and its alignment with real-world applicability.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01088-z","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144910812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comment on “Advancing material property prediction: using physics-informed machine learning models for viscosity”","authors":"Maximilian Fleck,&nbsp;Samir Darouich,&nbsp;Marcelle B. M. Spera,&nbsp;Niels Hansen","doi":"10.1186/s13321-025-01070-9","DOIUrl":"10.1186/s13321-025-01070-9","url":null,"abstract":"<div><p>When data availability is limited, the prediction of properties through purely data-driven machine learning (ML) is challenging. Integrating physically-based modeling techniques into ML methods may lead to better performance. In a recent work by Chew et al. (“<i>Advancing material property prediction: using physics-informed machine learning models for viscosity</i>”) descriptors from classical molecular dynamics (MD) simulations were included into a quantitative structure–property relationship to accurately predict temperature-dependent viscosity of pure liquids. Through feature importance analysis, the authors found that heat of vaporization was the most relevant descriptor for the prediction of viscosity. In this comment, we would like to discuss the physical origin of this finding by referring to Eyring’s rate theory, and develop an alternative modeling approach using a thermodynamic-based architecture that requires less input data.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01070-9","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144910811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Systematic benchmarking of 13 AI methods for predicting cyclic peptide membrane permeability","authors":"Wei Liu,&nbsp;Jianguo Li,&nbsp;Chandra S. Verma,&nbsp;Hwee Kuan Lee","doi":"10.1186/s13321-025-01083-4","DOIUrl":"10.1186/s13321-025-01083-4","url":null,"abstract":"<div><p>Cyclic peptides are promising drug candidates due to their ability to modulate intracellular protein–protein interactions, a property often inaccessible to small molecules. However, their typically poor membrane permeability limits therapeutic applicability. Accurate computational prediction of permeability can accelerate the identification of cell-permeable candidates, reducing reliance on time-consuming and costly experimental screening. Although deep learning has shown potential in predicting molecular properties, its application in permeability prediction remains underexplored. A systematic evaluation of these models is important to assess current capabilities and guide future development. In this study, we conduct a comprehensive benchmark of 13 machine learning models for predicting cyclic peptide membrane permeability. These models cover four types of molecular representations: fingerprints, SMILES strings, molecular graphs, and 2D images. We use experimentally measured PAMPA permeability data from the CycPeptMPDB database, comprising nearly 6000 cyclic peptides, and evaluate performance across three prediction tasks: regression, binary classification, and soft-label classification. Two data-splitting strategies, random split and scaffold split, are used to assess the generalizability of trained models. Our results show that model performance depends strongly on molecular representation and model architecture. Graph-based models, particularly the Directed Message Passing Neural Network (DMPNN), consistently achieve top performance across tasks. Regression generally outperforms classification. Scaffold-based splitting, although intended to more rigorously assess generalization, yields substantially lower model generalizability compared to random splitting. Comparing prediction errors with experimental variability highlights the practical value of current models while also indicating room for further improvement.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01083-4","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144909733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"xBitterT5: an explainable transformer-based framework with multimodal inputs for identifying bitter-taste peptides","authors":"Nguyen Doan Hieu Nguyen,&nbsp;Nhat Truong Pham,&nbsp;Duong Thanh Tran,&nbsp;Leyi Wei,&nbsp;Adeel Malik,&nbsp;Balachandran Manavalan","doi":"10.1186/s13321-025-01078-1","DOIUrl":"10.1186/s13321-025-01078-1","url":null,"abstract":"<div><p>Bitter peptides (BPs), derived from the hydrolysis of proteins in food, play a crucial role in both food science and biomedicine by influencing taste perception and participating in various physiological processes. Accurate identification of BPs is essential for understanding food quality and potential health impacts. Traditional machine learning approaches for BP identification have relied on conventional feature descriptors, achieving moderate success but struggling with the complexities of biological sequence data. Recent advances utilizing protein language model embedding and meta-learning approaches have improved the accuracy, but frequently neglect the molecular representations of peptides and lack interpretability. In this study, we propose xBitterT5, a novel multimodal and interpretable framework for BP identification that integrates pretrained transformer-based embeddings from BioT5+ with the combination of peptide sequence and its SELFIES molecular representation. Specifically, incorporating both peptide sequences and their molecular strings, xBitterT5 demonstrates superior performance compared to previous methods on the same benchmark datasets. Importantly, the model provides residue-level interpretability, highlighting chemically meaningful substructures that significantly contribute to its bitterness, thus offering mechanistic insights beyond black-box predictions. A user-friendly web server (https://balalab-skku.org/xBitterT5/) and a standalone version (https://github.com/cbbl-skku-org/xBitterT5/) are freely available to support both computational biologists and experimental researchers in peptide-based food and biomedicine.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01078-1","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144880932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ReactionT5: a pre-trained transformer model for accurate chemical reaction prediction with limited data","authors":"Tatsuya Sagawa,&nbsp;Ryosuke Kojima","doi":"10.1186/s13321-025-01075-4","DOIUrl":"10.1186/s13321-025-01075-4","url":null,"abstract":"<div><p>Accurate chemical reaction prediction is critical for reducing both cost and time in drug development. This study introduces ReactionT5, a transformer-based chemical reaction foundation model pre-trained on the Open Reaction Database—a large publicly available reaction dataset. In benchmarks for product prediction, retrosynthesis, and yield prediction, ReactionT5 outperformed existing models. Specifically, ReactionT5 achieved 97.5% accuracy in product prediction, 71.0% in retrosynthesis, and a coefficient of determination of 0.947 in yield prediction. Remarkably, ReactionT5, when fine-tuned with only a limited dataset of reactions, achieved performance on par with models fine-tuned on the complete dataset. Additionally, the visualization of ReactionT5 embeddings illustrates that the model successfully captures and represents the chemical reaction space, indicating effective learning of reaction properties.</p><h3>Graphical Abstract</h3>\u0000<div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01075-4","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144868633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving drug-induced liver injury prediction using graph neural networks with augmented graph features from molecular optimisation","authors":"Taeyeub Lee,&nbsp;Joram M. Posma","doi":"10.1186/s13321-025-01068-3","DOIUrl":"10.1186/s13321-025-01068-3","url":null,"abstract":"<div><h3>Purpose</h3><p>Drug-induced liver injury (DILI) is a significant concern in drug development, often leading to the discontinuation of clinical trials and the withdrawal of drugs from the market. This study explores the application of graph neural networks (GNNs) for DILI prediction, using molecular graph representations as the primary input.</p><h3>Methods</h3><p>We evaluated several GNN architectures, including Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs), Graph Sample and Aggregation (GraphSAGE), and Graph Isomorphism Networks (GINs), using the latest FDA DILI dataset and other molecular property prediction datasets. We introduce a novel approach that creates a custom graph dataset, driven by molecular optimisation, that incorporates detailed and realistic chemical features such as bond lengths and partial charges as input into the GNN models. We have named our model approach DILIGeNN.</p><h3>Results</h3><p>DILIGeNN achieved an AUC of 0.897 on the DILI dataset, surpassing the current state-of-the-art model in the DILI prediction task. Furthermore, DILIGeNN outperformed the state-of-the-art in other graph-based molecular prediction tasks, achieving an AUC of 0.918 on the Clintox dataset, 0.993 on the BBBP dataset, and 0.953 on the BACE dataset, indicating strong generalisation and performance across different datasets.</p><h3>Conclusion</h3><p>DILIGeNN, utilising a single graph representation as input, outperforms the state-of-the-art methods in DILI prediction that incorporate both molecular fingerprint and graph-structured data. These findings highlight the effectiveness of our molecular graph generation and the GNN training approach as a powerful tool for early-stage drug development and drug repurposing pipeline.</p><p>Scientific Contribution: DILIGeNN is a GNN framework that extracts graph features from 3D optimised molecular structures as is done in target-based drug discovery and molecular docking simulation. Our method is the first to encode spatial and electrostatic information into a single graph representation, as opposed to other work that require multiple graphs or additional chemical descriptors for feature representation. Our approach, using warm starts following repeated early stopping during training, outperforms the current state-of-the-art methods in liver toxicity (DILI), permeability (BBBP) and activity (BACE) prediction tasks.</p><h3>Graphic Abstract</h3><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01068-3","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144861405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cycle-configuration descriptors: a novel graph-theoretic approach to enhancing molecular inference","authors":"Bowen Song,&nbsp;Jianshen Zhu,&nbsp;Naveed Ahmed Azam,&nbsp;Kazuya Haraguchi,&nbsp;Liang Zhao,&nbsp;Tatsuya Akutsu","doi":"10.1186/s13321-025-01042-z","DOIUrl":"10.1186/s13321-025-01042-z","url":null,"abstract":"<div><p>Inference of molecules with desired activities/properties is one of the key and challenging issues in cheminformatics and bioinformatics. For that purpose, our research group has recently developed a state-of-the-art framework <span>mol-infer</span> for molecular inference. This framework first constructs a prediction function for a fixed property using machine learning models, which is then simulated by mixed-integer linear programming to infer desired molecules. The accuracy of the framework heavily relies on the representation power of the descriptors. In this study, we highlight a typical class of non-isomorphic chemical graphs with reasonably different property values that cannot be distinguished by the standard “two-layered (2L) model\" of <span>mol-infer</span>. To address this distinguishability problem of the 2L model, we propose a novel family of descriptors, named <i>cycle-configuration (CC)</i>, which captures the notion of ortho/meta/para patterns that appear in aromatic rings, which was impossible in the framework so far. Extensive computational experiments show that with the new descriptors, we can construct prediction functions with similar or better performance for all 44 tested chemical properties, including 27 regression datasets and 17 classification datasets comparing with our previous studies, confirming the effectiveness of the CC descriptors. For inference, we also provide a system of linear constraints to formulate the CC descriptors as linear constraints. We demonstrate that a chemical graph with up to 50 non-hydrogen vertices can be inferred within a practical time frame. </p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01042-z","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144861404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-fidelity graph neural networks for predicting toluene/water partition coefficients","authors":"Thomas Nevolianis, Jan G. Rittig, Alexander Mitsos, Kai Leonhard","doi":"10.1186/s13321-025-01057-6","DOIUrl":"https://doi.org/10.1186/s13321-025-01057-6","url":null,"abstract":"Accurate prediction of toluene/water partition coefficients of neutral species is crucial in drug discovery and separation processes; however, data-driven modeling of these coefficients remains challenging due to limited available experimental data. To address the limitation of available data, we apply multi-fidelity learning approaches leveraging a quantum chemical dataset (low fidelity) of approximately 9000 entries generated by COSMO-RS and an experimental dataset (high fidelity) of about 250 entries collected from the literature. We explore the transfer learning, feature-augmented learning, and multi-target learning approaches in combination with graph neural networks, validating them on two external datasets: one with molecules similar to training data (EXT-Zamora) and one with more challenging molecules (EXT-SAMPL9). Our results show that multi-target learning significantly improves predictive accuracy, achieving a root-mean-square error of 0.44 $$log {P}$$ units for the EXT-Zamora, compared to a root-mean-square error of 0.63 $$log {P}$$ units for single-task models. For the EXT-SAMPL9 dataset, multi-target learning achieves a root-mean-square error of 1.02 $$log {P}$$ units, indicating reasonable performance even for more complex molecular structures. These findings highlight the potential of multi-fidelity learning approaches that leverage quantum chemical data to improve toluene/water partition coefficient predictions and address challenges posed by limited experimental data. We expect the applicability of the methods used beyond just toluene/water partition coefficients. We investigate the benefits of transfer learning, feature-augmented learning, and multi-target learning approaches in combination with graph neural networks for the prediction of toluene–water partition coefficients. We show how a combination of a large number of cheap data from the semi-empirical COSMO-RS model with a few high-fidelity experimental data and multi-target learning efficiently leads to machine learning models with broad applicability and low uncertainties of 0.44 to 1.02 log units in the partition coefficient, depending on the test set.\u0000","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"27 1","pages":""},"PeriodicalIF":8.6,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144797314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced machine learning for innovative drug discovery","authors":"Igor V. Tetko, Djork-Arné Clevert","doi":"10.1186/s13321-025-01061-w","DOIUrl":"https://doi.org/10.1186/s13321-025-01061-w","url":null,"abstract":"This editorial presents an analysis of the articles published in the Journal of Cheminformatics Special Issue “AI in Drug Discovery”. We review how novel machine learning developments are enhancing structural-based drug discovery; providing better forecasts of molecular properties while also improving various elements of chemical reaction prediction. Methodological developments focused on increasing the accuracy of models via pre-training, estimating the accuracy of predictions, tuning model hyperparameters while avoiding overfitting, in addition to a diverse range of other novel and interesting methodological aspects, including the incorporation of human expert knowledge to analysing the susceptibility of models to adversary attacks, were explored in this Special Issue. In summary, the Special Issue brought together an excellent collection of articles that collectively demonstrate how machine learning methods have become an essential asset in modern drug discovery, with the potential to advance autonomous chemistry labs in the near future. ","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"80 1","pages":""},"PeriodicalIF":8.6,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144797318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nanodesigner: resolving the complex-CDR interdependency with iterative refinement","authors":"Melissa Maria Rios Zertuche, Şenay Kafkas, Dominik Renn, Magnus Rueping, Robert Hoehndorf","doi":"10.1186/s13321-025-01069-2","DOIUrl":"https://doi.org/10.1186/s13321-025-01069-2","url":null,"abstract":"Camelid heavy-chain only antibodies consist of two heavy chains and single variable domains (VHHs), which retain antigen-binding functionality even when isolated. The term “nanobody” is now more generally used for describing small, single-domain antibodies. Several antibody generative models have been developed for the sequence and structure co-design of the complementarity-determining regions (CDRs) based on the binding interface with a target antigen. However, these models are not tailored for nanobodies and are often constrained by their reliance on experimentally determined antigen–antibody structures, which are labor-intensive to obtain. Here, we introduce NanoDesigner, a tool for nanobody design and optimization based on generative AI methods. NanoDesigner integrates key stages—structure prediction, docking, CDR generation, and side-chain packing—into an iterative framework based on an expectation maximization (EM) algorithm. The algorithm effectively tackles an interdependency challenge where accurate docking presupposes a priori knowledge of the CDR conformation, while effective CDR generation relies on accurate docking outputs to guide its design. NanoDesigner approximately doubles the success rate of de novo nanobody designs through continuous refinement of docking and CDR generation. We developed a novel method for the design and optimization of nanobodies using generative AI. We use an iterative approach to address the problem that design of CDRs relies on knowledge of a complex consisting of nanobody and protein target, and accurate prediction of the complex relies on knowledge of the CDRs. We demonstrate that our method improves over the state of the art by direct comparison.","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"16 1","pages":""},"PeriodicalIF":8.6,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144797315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}