Journal of Cheminformatics最新文献

{"title":"When does global attention help: a unified empirical study on atomistic graph learning","authors":"Arindam Chowdhury,&nbsp;Massimiliano Lupo Pasini","doi":"10.1186/s13321-026-01171-z","DOIUrl":"10.1186/s13321-026-01171-z","url":null,"abstract":"<div><p>Graph neural networks (GNNs) are widely used as surrogates for costly experiments and first-principles simulations to study the behavior of compounds at atomistic scale, and their architectural complexity is constantly increasing to enable the modeling of complex physics. While most recent GNNs combine more traditional message passing neural networks (MPNNs) layers to model short-range interactions with more advanced graph transformers (GTs) with global attention mechanisms to model long-range interactions, it is still unclear when global attention mechanisms provide real benefits over well-tuned MPNN layers due to inconsistent implementations, features, or hyperparameter tuning. We introduce the first unified, reproducible benchmarking framework–built on HydraGNN–that enables seamless switching among four controlled model classes: MPNN, MPNN with chemistry/topology encoders, GPS-style hybrids of MPNN with global attention, and fully fused localglobal models with encoders. Using seven diverse open-source datasets for benchmarking across regression and classification tasks, we systematically isolate the contributions of message passing, global attention, and encoder-based feature augmentation. Our study shows that encoder-augmented MPNNs form a robust baseline, while fused localglobal models yield the clearest benefits for properties governed by long-range interaction effects. We further quantify the accuracycompute trade-offs of attention, reporting its overhead in memory. Together, these results establish the first controlled evaluation of global attention in atomistic graph learning and provide a reproducible testbed for future model development.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01171-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147796374","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":"LEP-AD: language embedding of proteins and attention to drugs predicts drug-target interactions","authors":"Reem Alsulami,&nbsp;Robert Lehmann,&nbsp;Anuj Daga,&nbsp;Sumeer A. Khan,&nbsp;Raik Grünberg,&nbsp;Ahmed Abogosh,&nbsp;David Gomez Cabrero,&nbsp;Stefan T. Arold,&nbsp;Robert Hoehndorf,&nbsp;Jesper Tegner,&nbsp;Narsis A. Kiani","doi":"10.1186/s13321-026-01167-9","DOIUrl":"10.1186/s13321-026-01167-9","url":null,"abstract":"<div><h3>Introduction</h3><p>Predicting drug–target interactions remains a significant challenge in drug development and lead optimization. Recent advances have leveraged machine learning algorithms to model drug–target interactions from molecular and sequence data.</p><h3>Materials and Methods</h3><p>In this work, we use Evolutionary Scale Modeling (ESM-3) to construct a transformer-based protein language representation for drug–target interaction prediction. We introduce LEP-AD (Language Embedding of Proteins and Attention to Drugs), a modular architecture that combines pretrained protein language models with graph-based molecular encoders to predict binding affinity values.</p><h3>Results</h3><p>We systematically benchmark LEP-AD alongside a range of established deep learning methods across multiple datasets—Davis, KIBA, DTC, Metz, ToxCast, and STITCH. To assess predictive validity, we compare model-derived rankings of drug–target interactions with experimental results reported in the literature. In addition, we perform new experimental assays to evaluate the binding of three ATP-competitive Src kinase inhibitors—Dasatinib, UM-164, and Saracatinib—where experimentally measured IC₅₀ and pKᵢ values are consistent with the predicted rankings.</p><h3>Conclusion</h3><p>In summary, our benchmark highlights the strengths and limitations of current drug–target interaction models across diverse datasets and evaluation settings. The results emphasize the impact of pretrained protein and molecular representations on predictive performance and illustrate the persistent challenges of generalization, while the modular LEP-AD framework provides a flexible reference point for comparative evaluation.</p><h3>Scientific Contribution</h3><p>This study presents LEP-AD, a modular deep learning framework for drug–target interaction prediction that integrates pretrained protein language representations with graph-based molecular encoders. Beyond introducing the architecture, we provide a systematic benchmark under similarity-aware evaluation settings and experimental validation, highlighting the impact of pretrained protein embeddings on predictive behavior across diverse datasets.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13397736/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147759213","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":"Assigning the stereochemistry of natural products by machine learning","authors":"Markus Orsi,&nbsp;Jean-Louis Reymond","doi":"10.1186/s13321-026-01205-6","DOIUrl":"10.1186/s13321-026-01205-6","url":null,"abstract":"<div><p>Nature has settled for L-chirality for proteinogenic amino acids and D-chirality for the carbohydrate backbone of nucleotides. Further stereochemical patterns exist among natural products produced by common biosynthetic pathways. Here we asked the question whether these regularities might be sufficiently prevalent among natural products (NPs) such that their stereochemistry could be machine learned and assigned automatically. Indeed, we report that a language model can be trained to assign the stereochemistry of NPs using the open access NP database COCONUT. In detail, our language model, called <b>NPstereo</b>, translates an NP structure written as absolute SMILES into the corresponding isomeric SMILES notation containing stereochemical information, with 80.2% per-stereocenter accuracy for full assignments and 85.9% per-stereocenter accuracy for partial assignments, across various NP classes including secondary metabolites such as alkaloids, polyketides, lipids and terpenes. <b>NPstereo</b> might be useful to assign or correct the stereochemistry of newly discovered NPs.</p><h3>Graphical Abstract</h3>\u0000<div><figure><div><div><picture><source><img></source></picture><span>The alternative text for this image may have been generated using AI.</span></div></div></figure></div></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01205-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147759202","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":"ProQSAR: A modular and reproducible framework for small-data QSAR modeling with fit-and-use models","authors":"Tuyet-Minh Phan,&nbsp;Tieu-Long Phan,&nbsp;Phuoc-Chung Van-Nguyen,&nbsp;Lai Hoang Son Le,&nbsp;Van-Thinh To,&nbsp;Tuyen Ngoc Truong,&nbsp;Daniel Merkle,&nbsp;Peter F. Stadler","doi":"10.1186/s13321-026-01175-9","DOIUrl":"10.1186/s13321-026-01175-9","url":null,"abstract":"<div><h3>Background</h3><p>Quantitative structure-activity relationship (QSAR) models are central to computer-aided drug discovery and predictive toxicology, but practical adoption is often impeded by ad-hoc tooling, inconsistent validation protocols, and poor reproducibility.</p><h3>Objective</h3><p>We introduce <span>ProQSAR</span>, a modular, reproducible workbench that formalizes end-to-end QSAR development while permitting independent use of each component.</p><h3>Methods</h3><p><span>ProQSAR</span> composes interchangeable modules for standardization, feature generation, splitting (including scaffold- and cluster-aware splits), preprocessing, outlier handling, scaling, feature selection, model training and tuning, statistical comparison, conformal calibration, and applicability-domain assessment. The pipeline can run end-to-end to produce versioned artifact bundles (serialized models) and analyst-oriented reports suitable for deployment and audit.</p><h3>Results</h3><p>On representative <span>MoleculeNet</span> benchmarks evaluated under Bemis–Murcko scaffold split, <span>ProQSAR</span> attains state-of-the-art descriptor-based performance: the lowest mean RMSE across the regression suite (<span>ESOL</span>, <span>FreeSolv</span>, <span>Lipophilicity</span>; mean RMSE <span>(0.658pm 0.11)</span>), including a substantial improvement on <span>FreeSolv</span> (RMSE <span>(0.494)</span> vs. <span>(0.731)</span> for a leading graph method). On quantum mechanical benchmarks, <span>ProQSAR</span> demonstrated superior performance on the single-task dataset <span>QM7</span> and maintained competitive results on the multi-task <span>QM8</span> dataset. For classification, <span>ProQSAR</span> achieves the top ROC–AUC on <span>ClinTox</span> (91.4%) while remaining competitive across other benchmark (overall classification average <span>(70.4pm 11.6)</span>). Crucially, all predictions are accompanied by cross-conformal prediction and explicit applicability-domain flags that identify out-of-distribution entries, enabling calibrated and decision support.</p><h3>Availability</h3><p><span>ProQSAR</span> is released on <span>PyPI</span>, <span>Conda</span>, and <span>Docker Hub</span>; all releases embed full provenance (parameters, package versions, checksums) to ensure reproducibility.</p><h3>Scientific contribution</h3><p><span>ProQSAR</span> (i) enforces best-practice, group-aware validation together with formal statistical comparisons across models, (ii) integrates calibrated uncertainty quantification (cross-conformal prediction) and applicability-domain diagnostics for interpretable, risk-aware predictions, and (iii) exposes both a composable developer API and a one-click pipeline that generates deployment-ready artifacts and human-readable reports, demonstrated on representative benchmarks.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01175-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147733768","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":"Predicting enzyme-compound associations for enzyme-catalysed reactions","authors":"Liam Brydon-Brown,&nbsp;Gillian Dobbie,&nbsp;Katerina Taškova,&nbsp;Jörg Simon Wicker","doi":"10.1186/s13321-026-01190-w","DOIUrl":"10.1186/s13321-026-01190-w","url":null,"abstract":"<div><p>Enzyme-catalysed reactions are common in many areas, including pharmaceutical metabolism and agricultural chemical biodegradation. Analysing and predicting how these reactions occur is increasingly important for identifying toxic by-products and achieving regulatory approval. Incorporating enzyme information into these predictions has been shown to improve prediction capabilities. However, existing methods require knowledge of the enzyme to perform prediction, and in many situations, especially biodegradation, the complexities of the reaction environment mean the exact enzymes are not known. In this paper, we alleviate this issue by proposing a framework to train and evaluate a hierarchical multi-label classifier to predict the association between enzyme commission numbers and chemical compounds. Our method achieves a hierarchical F1-score of up to 93.2%, outperforming existing methodologies. Additionally, we examine how including true and predicted enzyme information impacts product prediction performance compared to not using enzyme information. In our case study utilising biodegradation reaction data, we find that including enzyme commission numbers improve product prediction performance by approximately two percentage points.</p><p><b>Scientific contribution</b></p><p>We contribute a novel method for predicting enzyme-compound associations using a hierarchical multi-label classifier framework. Our method is self tuning to find the best hyperparameters for a given dataset and achieves higher F1 scores than existing methods. We also contribute an investigation into including enzyme information into product prediction algorithms, showing that including this information can improve product prediction performance.</p><h3>Graphical abstract</h3><div><figure><div><div><picture><source><img></source></picture><span>The alternative text for this image may have been generated using AI.</span></div></div></figure></div></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01190-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147733776","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":"Generalizable deep-learning-based mRNA-protein interaction prediction strongly depends on protein diversity","authors":"Yu-Huai Yu,&nbsp;Han-Ting Hong,&nbsp;Tzu-Hsien Yang","doi":"10.1186/s13321-026-01197-3","DOIUrl":"10.1186/s13321-026-01197-3","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;Background&lt;/h3&gt;&lt;p&gt;Proteins regulate diverse biological processes through interactions with other molecules, including RNAs. RNA-binding proteins (RBPs) are essential regulators of gene expression, forming specific mRNA-protein interactions (mRPIs) that influence mRNA processing, translation, and stability. Recently, deep-learning models have been proposed to predict mRPIs using only sequence information, with some reporting near-perfect accuracy. However, such performance appears inconsistent with the biological complexity of RNA recognition by proteins, which is often influenced by protein tertiary structures that are computationally challenging to predict. In related fields such as protein-protein interaction prediction, data leakage, particularly caused by overlapping proteins between training and test sets, has been shown to substantially inflate performance metrics. Nevertheless, whether similar issues affect mRPI prediction has not yet been systematically investigated.&lt;/p&gt;&lt;h3&gt;Results&lt;/h3&gt;&lt;p&gt;We constructed an mRPI benchmark dataset from CLIP experiments and implemented two data partitioning schemes: a random interaction-level split and an RBP-aware split in which pairs of all test RBPs were excluded from training. Three RBP sequence encoding strategies were evaluated within an attention-based deep-learning framework under both partitioning settings: sequence-based one-hot encoding, language model-derived encoding, and structure-aware encoding. Across all models, performance remained high only when test RBPs were also present in the training data. When predicting interactions for unseen RBPs, performance dropped substantially, indicating limited generalization. Even replacing RBPs with their most similar counterparts from the training set did not meaningfully improve generalization. These results suggest that additional protein features beyond sequence information are required to achieve robust mRPI prediction. Overall, our study demonstrated that existing mRPI prediction models are largely overfitted to their original training RBPs and fail to generalize to unseen proteins.&lt;/p&gt;&lt;h3&gt;Conclusions&lt;/h3&gt;&lt;p&gt;Overall, we provided a curated benchmark dataset, a rigorous evaluation framework, and an attention-based model that achieves the best generalization performance among currently available methods, with an approximately 8.5% auROC improvement over existing tools. These resources will facilitate the development of more reliable and broadly applicable mRPI prediction tools.&lt;/p&gt;&lt;h3&gt;Scientific contribution&lt;/h3&gt;&lt;p&gt;This work presented the first systematic investigation of data leakage and generalization in mRNA-protein interaction prediction, demonstrating that most reported near-perfect performance is largely driven by RBP overlap between training and test sets. By introducing an RBP-aware evaluation framework and a benchmark dataset, we revealed that most sequence-based models fail to generalize to unseen RBPs, even when enhanced with protein","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01197-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147731409","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":"Predictive machine learning models for rational permeability design in de novo macrocycle engineering: a review","authors":"M. Taleb Albrijawi,&nbsp;Reda Alhajj","doi":"10.1186/s13321-026-01189-3","DOIUrl":"10.1186/s13321-026-01189-3","url":null,"abstract":"&lt;div&gt;&lt;p&gt;Small molecule drug discovery has been highly successful across many therapeutic areas over decades of progress; however, many disease-relevant proteins remain difficult to target. In particular, intracellular proteins with large, shallow, or flexible interaction surfaces are poorly addressed by classical drug-like compounds. For these reasons, drug discovery efforts have shifted toward alternative molecular classes. This has led to growing interest in macrocyclic compounds in recent years, which have emerged as an important class of therapeutic molecules, particularly for targets that are out of reach for conventional small molecules. These compounds operate within the chemical space beyond Lipinski’s Rule of Five (bRo5) and offer new opportunities for modulating difficult intracellular targets. At the same time, their size, flexibility, and structural complexity introduce significant challenges, among which the accurate prediction of membrane permeability remains one of the persistent limitations in their rational design, particularly for orally bioavailable candidates. This review examines 11 published studies, specifically those focusing on machine learning (ML) and deep learning (DL) driven methodologies for predicting macrocycle permeability. Contemporary ML models utilize a diverse array of molecular representations, including two-dimensional descriptors, three-dimensional conformational features, molecular graphs, and Simplified Molecular Input Line Entry System (SMILES) sequences, all aimed at accelerating prediction pipelines. The architectural range of these models spans from classical Quantitative Structure-Permeability Relationship (QSPR) algorithms to advanced deep learning frameworks, including Transformer-based models, Graph Neural Networks (GNNs), and vision-based approaches. Significant progress in this domain has been largely powered by the establishment of the CycPeptMPDB (Cyclic Peptide Membrane Permeability Database), which provides standardized permeability annotations for thousands of cyclic peptides and has facilitated progress in predictive modeling. Nevertheless, several substantial challenges remain, such as issues of poor generalizability across different chemical scaffolds, the inherent limitations in interpretability characteristic of deep learning models, and biases frequently introduced by dataset imbalance or the particular details of permeability assays. Non-peptidic macrocycles are of growing relevance in drug discovery, but there are remarkably few proposed models that have been developed for this particular subclass. The recent introduction of NPMMPD, a curated dataset focusing on non-peptidic scaffolds offers a promising path toward further advances. This database will allow the development of ML models for the early-stage screening and rational design of orally available non-peptidic macrocycles. Ultimately, these advancements highlight the critical importance of integrating mechanistic biophysical","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01189-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147731408","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":"ChemScreener: an active learning enabled hit discovery workflow with WDR5 inhibitor case study","authors":"Lingling Shen,&nbsp;Jian Fang,&nbsp;Lulu Liu,&nbsp;Rena Wang,&nbsp;Jeremy L. Jenkins,&nbsp;He Wang","doi":"10.1186/s13321-026-01204-7","DOIUrl":"10.1186/s13321-026-01204-7","url":null,"abstract":"<div><p>Active deep learning offers a promising approach for hit discovery starting from limited data by iteratively updating and improving models during screening by applying new data and adapting decisions. Key open questions include how best to explore chemical space, how it compares to non-iterative methods, and how to use it under data scarcity. We present ChemScreener, a multi-task active learning workflow for early drug discovery across large, diverse libraries or chemical spaces. Its Balanced-Ranking acquisition strategy leverages ensemble uncertainty to explore novel chemistry while maintaining hit rate enrichment by prioritizing predicted activity. In five iterative single-dose HTRF screens on WDR5 protein, ChemScreener increased hit rates from 0.49% (primary HTS screen) to 3–10% (average 5.91%; 104 hits from 1760 compounds). Hits were consolidated, retested with close analogs together in the 269 compounds set and clustered; 44 hit compounds from 81 clusters of 269 compounds set advanced to dose–response and filtered by counter HTRF assays. Over 50% of those with IC50 &lt; 45 μM were validated as WDR5 binders by DSF. We de novo identified three scaffold series and three singleton scaffolds as the hits. Overall, we demonstrated that ChemScreener can accelerate early hit discovery and yield more diverse chemotypes.</p><p><b>Scientific contribution</b></p><p>Hit identification is a costly, time-intensive stage in drug discovery. We developed ChemScreener, a scalable active learning workflow for early hit discovery that improves hit rate enrichment through iterative screening of small number of compounds and expands chemical diversity by de novo hit scaffolds identified. ChemScreener offers a generalizable, target-specific, ligand-based virtual screening framework that accelerates early discovery and enhances effectiveness across large, diverse chemical libraries.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2026-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01204-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147727987","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":"CheMLT-F: multitask learning in biochemistry through transformer fusion","authors":"Vladislav Mun,&nbsp;Siamac Fazli","doi":"10.1186/s13321-026-01199-1","DOIUrl":"10.1186/s13321-026-01199-1","url":null,"abstract":"","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2026-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01199-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147695262","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":"CReM-pharm: de novo 3D pharmacophore-based design with synthetic accessibility awareness","authors":"Alina Denzler,&nbsp;Dinesh Kumar Sriramulu,&nbsp;Jozef Pecha,&nbsp;Pavel Polishchuk","doi":"10.1186/s13321-026-01195-5","DOIUrl":"10.1186/s13321-026-01195-5","url":null,"abstract":"<div><p>De novo design methodologies have the potential to significantly enhance the exploration of chemical space in the search for promising ligands featuring novel chemotypes. This exploration can be directed through various computational strategies. 3D pharmacophore models, which represent the interaction patterns critical for protein–ligand recognition, can serve as valuable tools for the design of novel compounds. A common limitation of many generative approaches is the low synthetic feasibility of the generated molecular structures. In the present study, we developed a method capable of controllably generating compounds with a relatively high degree of synthetic accessibility by leveraging the CReM framework, while explicitly conforming to a specified 3D pharmacophore model. Evaluation of this approach across a diverse set of protein targets and pharmacophore models of varying complexity demonstrated its effectiveness and highlighted its advantages over the PGMG method, which employs a deep neural network architecture to generate ligands that may exhibit desired 3D geometries upon embedding. The proposed method has been implemented as an open-source tool, CReM-pharm, available at https://github.com/ci-lab-cz/crem-pharm.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01195-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685116","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}