Wiley Interdisciplinary Reviews: Computational Molecular Science最新文献

The cover image is based on the article Computation of Protein Thermostability and Epistasis by Gonzalo Jimenez-Oses et al., https://doi.org/10.1002/wcms.70045.

Explainable artificial intelligence (XAI) is increasingly essential in drug discovery, where interpretability and trust must accompany predictive accuracy. As deep learning models, particularly, deep neural networks (DNNs) and graph neural networks (GNNs), enhance molecular property prediction, de novo design, and toxicity estimation, transparent, mechanistically meaningful insights become critical. This article classifies major XAI strategies in computational molecular science, including gradient-based attribution, perturbation analysis, surrogate modeling, counterfactual reasoning, and self-explaining architectures. Molecular representations, such as fingerprints, SMILES, molecular graphs, and latent embeddings, are evaluated for their impact on explanation fidelity. An evaluation framework is outlined using metrics like fidelity, stability, completeness, sparsity, and usability, with emphasis on integration into drug discovery workflows. The discussion also highlights emerging directions, including neuro-symbolic systems and physics-informed networks that embed mechanistic constraints into statistical models. By aligning algorithmic transparency with pharmacological reasoning, XAI not only demystifies black-box models but also supports scientific insight, regulatory compliance, and ethical AI deployment in pharmaceutical research.

This article is categorized under:

By bridging molecular-level insights with macroscopic performance metrics, computational strategies are poised to transform how we design next-generation 3D-printable materials with enhanced precision, functionality, and sustainability. We present a critical overview examining the role of computational methods in advancing the design and application of 3D-printable polymers. We cover key considerations—including solvation behavior, viscosity, gel point, mechanical properties, and polymer structure—as well as the design of new polymer functionalities. We highlight how a spectrum of physics-based methods, ranging from quantum chemical to coarse-grained simulations, can be leveraged to interrogate relevant polymer properties at multiple scales. In particular, we illustrate the growing impact of machine learning in accelerating polymer discovery and optimization. Such methods, whether applied independently or integrated into multi-scale modeling frameworks, offer powerful tools for pre-screening and selecting optimal formulations tailored to diverse 3D printing technologies and applications. Although challenges remain to integrate different approaches into workable prediction pipelines, the rate of advance and improvements in methods, data interoperability, and data quality, offer great promise of a ‘concept to print’ pipeline in the future.

This article is categorized under:

Heterogeneous catalysis has a wide range of applications in chemical manufacturing and sustainable technologies. It uses solid catalysis to enable efficient chemical transformations. Traditional research on active sites and reaction mechanisms relies heavily on experiments and computational methods, such as density functional theory calculations. However, the volume of scientific literature and data is growing fast. This rapid growth has made it increasingly difficult to capture, process, and act on emerging insights systematically. Recently, large language models (LLMs) have emerged as powerful tools to support various stages in catalysis research. Their ability to understand and generate natural language helps them extract useful information from vast amounts of text, assist in catalyst design, aid in planning experiments, and clarify complex descriptors. In this advanced review, we first analyze recent progress in applying LLMs to heterogeneous catalysis, focusing on four key areas: literature mining and knowledge extraction, catalyst design and screening, experiment automation and workflow optimization, and the interpretation of high-dimensional descriptors. We then highlight the challenges in this field despite these advances, most notably the need for domain-specific fine-tuning and the improvement of molecular representation. We conclude by discussing future opportunities for integrating LLMs with complementary machine learning approaches and expert-in-the-loop systems, toward accelerating the rational discovery of next-generation catalysts.

This article is categorized under:

The large and steadily increasing volume of scientific publications presents a challenge in accessing and utilizing data due to their unstructured nature. Toxicology, in particular, depends on structured data from diverse study types for study evaluation, weight-of-evidence chemical assessments, and validation of new approach methodologies (NAMs). Manual data extraction is time and labor-intensive. This work presents an automated data extraction workflow using large language models (LLMs) within the KNIME platform. The workflow integrates document parsing tools with LLMs to extract variables from scientific publications and general PDF files. Two execution modes are available: text mode and image mode. Text mode applies tools for extracting text and tables, while image mode uses multimodal LLMs to process non-linear layouts and graphical content. The workflow achieves 81.14% accuracy in text mode for scientific publications and up to 98.54% in image mode for general PDF files. The KNIME platform ensures accessibility through a user-friendly interface, allowing non-experts to use advanced data extraction methods. This automated approach facilitates toxicological research by improving the retrieval of structured data. By democratizing access to LLM-powered workflows, this approach paves the way for significant advancements in knowledge synthesis to support biomedical research.

This article is categorized under:

The ability to computationally predict changes in protein thermostability upon mutation is crucial for advancing protein design and engineering, with applications ranging from therapeutics to biocatalysis. This review provides a comprehensive overview of the significant challenges and diverse computational strategies for predicting protein stability and understanding epistatic interactions across protein variants. A primary obstacle to this goal is the scarcity of high-quality, large-scale thermodynamic datasets, which are often biased toward single-point, destabilizing mutations and lack standardized experimental metrics. This limitation directly impacts the performance and generalizability of data-driven methods, from early machine learning approaches to modern deep learning architectures such as ThermoMPNN and protein language models. Physics-based approaches, such as those employing Rosetta and FoldX energy functions, offer valuable insights but are often limited by their reliance on static structures and oversimplified representations of the unfolded state. While molecular dynamics simulations can capture the critical role of protein flexibility and dynamics in thermostabilization, their computational cost restricts their application in high-throughput screening. Accurately predicting the effects of multiple mutations is further complicated by epistasis, where nonadditive interactions can significantly alter stability and function. Overcoming these hurdles requires a synergistic approach, integrating AI-driven predictions with physics-based simulations and accurate conformational sampling methods. Promising future directions include the development of more comprehensive and unbiased datasets, and improved modeling of epistasis and the (un)folded states and their ensembles. Such advancements are essential for enhancing the reliability of thermostability predictions and navigating the complex stability–activity trade-offs inherent in protein optimization and design.

This article is categorized under:

Complex diseases often share genetic susceptibility factors, molecular pathways, and pathological mechanisms. Understanding these commonalities through systematic cross-disease comparisons can reveal both disease-specific and shared biomarkers, potentially suggesting new therapeutic targets and opportunities for drug repurposing. In recent years, the growth of multi-omics datasets across diverse diseases, coupled with advances in computational systems biology, has enabled sophisticated cross-disease analyses. New methodological frameworks have emerged for integrating and comparing disease-specific molecular signatures, from gene-level analyses to complex network-based approaches. Here, we present a comprehensive framework for computational cross-disease comparison and integration of omics data, covering established and emerging methodologies. These include gene-level comparative analyses, pathway-based approaches, network biology methods, matrix factorization techniques, and machine learning approaches. We examine important aspects of data preprocessing, normalization, and integration, suggesting practical solutions to common technical challenges. We provide a detailed overview of relevant software tools and databases, discussing their strengths, limitations, and optimal use cases for cross-disease analysis. Finally, we explore current trends in cross-disease omics analysis, particularly through deep learning methods, highlighting new opportunities for methodological innovation and biological discovery in this field. This compilation of computational methods and practical insights aims to serve as a resource both for bioinformaticians seeking guidance on optimal method selection and biomedical researchers interested in applied cross-disease analyses. In addition to highlighting practical recommendations and common pitfalls, it provides an entry point to the extensive literature in the field, supporting readers in identifying and further exploring suitable methods for their research needs.

This article is categorized under: