Journal of Cheminformatics最新文献

While virtual libraries of synthetically accessible compounds have exploded in size to many billions, our capacity to extract valuable drug leads from these vast databases remains limited by computational resources. To overcome this, we developed SLICE SMARTS and Logic In ChEmistry), a powerful new tool designed for the agile exploration of massive chemical spaces. SLICE enables the fast, “à la carte” generation of virtual compound libraries through chemist-defined reaction chemistries and readily available building blocks. Its user-friendly, no-code graphical interface, the SLICE Designer, allows chemists to easily define SMARTS patterns, configure atom and bond properties, and establish chemical constraints and logic. The resulting XML files are then fed into the SLICE Engine, which generates diverse virtual libraries from specified building blocks at speeds of 0.6–2.5 million compounds per hour. SLICE provides the agility and performance needed to support efficient lead generation within discovery workflows.

Identifying molecular mechanisms that regulate neuronal excitability is essential for developing targeted therapies for neuropsychiatric disorders. The protein–protein interaction (PPI) between fibroblast growth factor 14 (FGF14) and the voltage-gated Na⁺ channel Nav1.6 is critical in regulating neuronal excitability and has emerged as a promising drug target. However, the physicochemical features that drive small-molecule modulation of this interface remain elusive. Here, we apply a descriptor-based chemoinformatics approach to analyze 15 hit compounds identified via high-throughput screening, aiming to elucidate structure–activity relationships influencing their potency and binding affinity. The analysis revealed distinct subsets of physicochemical features strongly associated with either potency or binding affinity values, suggesting that these parameters are governed by largely independent molecular determinants. This independence implies that optimizing a compound for improved affinity need not compromise potency, and vice versa. Together, these findings may guide the rational optimization of first-in-class compounds aimed at controlling neuronal excitability through targeted PPI interface modulation.

Graphical Abstract

Chemical functional group annotation provides a mechanistically meaningful framework to interpret model outcomes and guide synthetic strategies. Here, we present SMARTS-RX—a curated, hierarchical ontology of 406 SMARTS-based functional group descriptors—designed to characterize chemically relevant and reactive functionalities in small molecules. SMARTS-RX achieves a balance between granularity and computational efficiency by focusing on functional groups central to pharmaceutical synthesis and medicinal chemistry. We describe the development of SMARTS-RX, including its systematic nomenclature and SMARTS encoding, which enable precise tracking of chemical environments. The utility of SMARTS-RX for mapping chemical reactivity is demonstrated through analyses of functional group distributions across major reaction types, using large-scale datasets from AstraZeneca’s Electronic Lab Notebooks and Reaxys. Finally, we illustrate how this SMARTS library can be applied to guide building-block selection from commercial catalogues. A public GitHub repository has been created aiming for a continuous improvement of the current SMARTS_RX.

Scientific Contribution: SMARTS-RX introduces a curated, hierarchical ontology of 406 SMARTS-based descriptors prioritizing pharmaceutical relevance and mechanistic interpretability. Distinct from prior efforts, SMARTS-RX encodes detailed chemical environments to improve reactivity mapping and feature extraction for both expert analysis and computational modelling. This resource advances functional group annotation by balancing chemical specificity and computational performance, supporting reproducible and scalable cheminformatics research.

Structure-based molecular generation is an emerging approach in computer-aided drug discovery, enabling the design of compounds that that complement the three-dimensional structure of target proteins. However, most diffusion-based 3D molecular generative models still face several limitations, such as imbalanced protein–ligand representations or reliance on predefined binding pockets. To address these limitations, we propose SGEDiff, a novel subgraph enriched generative framework for 3D molecule generation. Our model hierarchically fuses subgraph and global graph representations to capture both local binding patterns and key structural features of protein pockets. Furthermore, an integrated pocket prediction module identifies binding regions in unseen proteins, eliminating reliance on predefined pocket coordinates. Experimental results show that SGEDiff outperforms baseline diffusion-based methods in generating high-affinity molecules across diverse targets. Moreover, practical applications in de novo drug design demonstrate improved success rates in generating compounds for novel protein targets, underscoring its potential to advance structure-based drug discovery.

In recent years, machine learning models have shown substantial progress in predicting molecular properties. However, integrating molecular graph structures with sequence information continues to present a significant challenge. In this paper, we introduce Multi-MoleScale, a novel multi-scale framework designed to address this challenge. By combining Graph Contrastive Learning (GCL) with sequence-based models like BERT, Multi-MoleScale enhances the prediction of molecular properties by capturing both structural and contextual representations of molecules. Specifically, the model leverages GCL to effectively capture the intrinsic graph-based features of molecules while utilizing BERT’s pretraining capabilities to learn the contextual relationships within molecular sequences. The contrastive learning component enables Multi-MoleScale to distinguish between relevant and irrelevant molecular features, thereby enhancing its predictive accuracy across diverse molecular types. To assess the performance of our method, we conducted experiments on several widely used public datasets, including 12 molecular property datasets, the ADMET dataset, and 14 breast cancer cell line datasets. The results show that Multi-MoleScale consistently outperforms existing deep learning and self-supervised learning approaches. Notably, the model does not require handcrafted features, making it highly adaptable and versatile for a variety of molecular discovery tasks. This makes Multi-MoleScale a promising tool for applications in drug discovery, materials science, and other molecular research fields. Our data and code are available at https://github.com/pdssunny/Multi-MoleScale.

Quantification is a challenge for non-targeted analysis (NTA) with liquid chromatography–high resolution mass spectrometry (LC–HRMS), due to the lack of analytical standards. Quantification via structure-based predicted ionization efficiency (IE) has been shown to provide the highest accuracy in estimating concentration. However, achieving confident analyte identification is a challenging task, as multiple candidate structures may be likely. This uncertainty in identification limits the reliability of structure-based IE prediction models, since quantification can be severely compromised in cases of wrongly (tentatively) identified chemicals or lack of candidate structures. Here we investigate the possibility of using cumulative neutral losses from fragmentation spectra (i.e. MS2) to predict the logIE. The first model was based on molecular fingerprints and was applied on structurally identified analytes. PubChem fingerprints performed the best with the root-mean-square error (RMSE) of 0.72 logIE for the test set. The second model was based on the MS2 spectrum, expressed as cumulative neutral losses. This approach is applicable to analytes with unknown structures and showed promising results with RMSE of 0.79 logIE for the test set and 0.62 logIE for chromatographic features extracted from LC-HRMS data of tea extracts spiked with pesticides. The prediction models were compiled in a Julia package, which is publicly available on GitHub, and may be used as part of a quantification workflow to estimate concentrations of identified and unidentified compounds in NTA.

Scientific contribution: This study expands the possibilities of standard free quantification for HRMS. It aims to provide reliable IE prediction for known substances by robust fingerprint calculation, and more importantly IE prediction for unknown substances using their MS2 fragmentation pattern. These workflows employ minimal method-specific variables, highlighting the tool generalizability.

Background

Chemical reactions form densely connected networks, and exploring these networks is essential for designing efficient and sustainable synthetic routes. As reaction data from literature, patents, and high-throughput experimentation continue to grow, so does the need for tools that can navigate and mine these large-scale datasets. Graph-based representations capture the topology of reaction space, yet few open-source tools exist for building and querying such networks. To address this, we developed NOCTIS, an open-source toolkit for constructing and analyzing reaction data as graphs.

Results

NOCTIS is an open-source Python package for building Networks of Organic Chemistry (NOCs) from reaction strings. It supports graph-based analysis, parallel processing of large datasets, and export to common Python formats (e.g., NetworkX, pandas). Built on Neo4j technology, it features a modular, extensible architecture with open-source dependencies. We also provide a companion plugin for exhaustive route enumeration. It traverses graph-encoded reactions to assemble all valid synthetic routes, helping prevent redundant exploration and supporting knowledge reuse in synthesis planning. The underlying algorithm is documented in detail along with its current limitations. Using the MIT USPTO-480k dataset (Adv Neural Inf Process Syst 30, 2017), we demonstrate the plugin’s route mining capabilities, analyze network connectivity, and assess synthetic trees.

Conclusion

Built on LinChemIn (J Chem Inf Model 64(6):1765–1771, 2024), NOCTIS serves as an open and extensible toolkit for network-based reaction analysis and route mining, laying the groundwork for data-driven route design at scale. Future work will extend query capabilities and improve the efficiency of route extraction.

Over the past decade, computer-assisted chemical synthesis has resurfaced as a prominent research subject. Even though the idea of utilizing computers to assist chemical synthesis has existed for nearly as long as computers themselves, the inherent complexity repeatedly exceeded the available resources. However, recent machine learning approaches have exhibited the potential to break this tendency. The performance of such approaches is heavily dependent on data that suffers from limited quantity, quality, visibility, and accessibility, posing significant challenges to potential scientific breakthroughs. This research addresses these issues by consolidating all relevant open-source computer-assisted chemical synthesis data into a comprehensive database, providing a practical overview of the state of data in the process. The computer-assisted chemical synthesis or CaCS database is designed to be a central repository for storing and analyzing data, with the primary objective being easy integration and utilization within existing research projects. It provides the users with a programmatic interface to retrieve the data required for various tasks like predicting the outcomes of chemical synthesis and retrosynthetic analysis or retrosynthesis, estimating the synthesizability of chemical compounds, and planning and optimizing the chemical synthesis routes. The database archives the original data to ensure reusability and traceability in downstream tasks and stores the processed data in a more efficient manner. The advantages and disadvantages are highlighted through a realistic case study of how such a database would be utilized within a computer-assisted chemical synthesis research project today. The code and documentation relevant to the CaCS database are available on GitHub under the MIT license at https://github.com/neo-chem-synth-wave/ncsw-data.

Scientific contribution: The primary scientific contribution of this research is the consolidation of all relevant open-source computer-assisted chemical synthesis data into a comprehensive database. The database archives the original data to ensure reusability and traceability in downstream tasks, efficiently stores the processed data, and provides the users with a programmatic interface to manage and query the stored data. Rather than improving the existing or introducing new data, such a database provides a systematic overview of the existing open data sources and an easily reproducible environment for transparent processing and benchmarking purposes.

RNA-targeted therapeutics represent a promising frontier for expanding the druggable genome beyond conventional protein targets. However, computational prediction of RNA-compound interactions remains challenging due to limited experimental data and the inherent complexity of RNA structures. Here, we present DeepRNA-DTI, a novel sequence-based deep learning approach for RNA-compound interaction prediction with binding site interpretability. Our model leverages transfer learning from pretrained embeddings, RNA-FM for RNA sequences and Mole-BERT for compounds, and employs a multitask learning framework that simultaneously predicts both presence of interactions and nucleotide-level binding sites. This dual prediction strategy provides mechanistic insights into RNA-compound recognition patterns. Trained on a comprehensive dataset integrating resources from the Protein Data Bank and literature sources, DeepRNA-DTI demonstrates superior performance compared to existing methods. The model shows consistent effectiveness across diverse RNA subtypes, highlighting its robust generalization capabilities. Application to high-throughput virtual screening of over 48 million compounds against oncogenic pre-miR-21 successfully identified known binders and novel chemical scaffolds with RNA-specific physicochemical properties. By combining sequence-based predictions with binding site interpretability, DeepRNA-DTI advances our ability to identify promising RNA-targeting compounds and offers new opportunities for RNA-directed drug discovery. The codes and data are publicly available at https://github.com/GIST-CSBL/DeepRNA-DTI/.

Advancing protein design is crucial for breakthroughs in medicine and biotechnology. Traditional approaches for protein sequence representation often rely solely on the 20 canonical amino acids, limiting the representation of non-canonical amino acids and residues that undergo post-translational modifications. This work explores discrete diffusion models for generating novel protein sequences using the all-atom chemical representation SELFIES. By encoding the atomic composition of each amino acid in the protein, this approach expands the design possibilities beyond standard sequence representations. Using a modified ByteNet architecture within the discrete diffusion D3PM framework, we evaluate the impact of this all-atom representation on protein quality, diversity, and novelty, compared to conventional amino acid-based models. To this end, we develop a comprehensive assessment pipeline to determine whether generated SELFIES sequences translate into valid proteins containing both canonical and non-canonical amino acids. Additionally, we examine the influence of two noise schedules within the diffusion process—uniform (random replacement of tokens) and absorbing (progressive masking)—on generation performance. While models trained on the all-atom representation struggle to consistently generate fully valid proteins, the successfully generated proteins show improved novelty and diversity compared to their amino acid-based model counterparts. Furthermore, the all-atom representation achieves structural foldability results comparable to those of amino acid-based models. Lastly, our results highlight the absorbing noise schedule as the most effective for both representations. Data and code are available at https://github.com/Intelligent-molecular-systems/All-Atom-Protein-Sequence-Generation.