Meta-learning for transformer-based prediction of potent compounds

Artificial intelligence (AI) has grown widely into diverse areas of research over the last decade. Publications distributed over the years disclose that biochemistry and analytical chemistry are incorporating AI to the utmost level. Enormous complex data sets are produced by analytical instruments comprising a treasure of information which is very helpful to analytical chemists in characterization. Despite this, we lack capabilities in data analysis and algorithms, which restricts our aptitude to discover and employ this data entirely. Machine learning and AI are being instigated to deal with this current challenge by accelerating several other applications in analytical chemistry. A critical valuation of illustrative reports amalgamating AI with analytical chemistry, spectroscopies, and several sensors has been discussed widely. This comprehensive review evaluates the AI advancement in data interpretation, the assistance of AI in analyte identification and quantification in proteomics and metabolomics, AI databases for primary and secondary metabolites information, regulatory and ethical guidelines in analytical chemistry incorporating AI, machine learning applications in drug discovery, agriculture, cosmetic, and food and separation techniques. In summary, this current review puts forward a thorough examination concerning the advancements of AI in different domains of chemistry and strives to facilitate comprehension of its forthcoming trajectories.

Introduction Deep generative models are reshaping de novo drug design by enabling creation of novel, property-optimized molecules beyond traditional chemical libraries. Advances in deep learning, molecular representation learning, and structure-aware modeling now enable algorithms to propose molecules that satisfy complex pharmacological constraints, accelerating hit identification. Areas covered This review outlines recent advances in generative molecular design, including neural network-based frameworks, reinforcement learning systems, diffusion models, and language model-based transformers. The authors outline how each class generates and optimizes molecular structures and review generative AI’s practical applications in drug discovery, illustrating translational progress. Current bottlenecks are critically analyzed alongside emerging solutions. This review is based on a systematic literature search conducted in Google Scholar and PubMed, covering studies published up to December 2025. Expert opinion Generative AI’s greatest promise lies not in generating more molecules, but in generating better hypotheses, structures that are synthetically accessible, biologically plausible, optimized across potency, selectivity, and pharmacokinetics. The next phase will be led by multimodal foundation models capable of reasoning jointly about chemistry, protein structure, and cellular response, supported by automated synthesis and high-throughput experimentation. As these components are integrated, generative molecular design will guide lead optimization and reshape how new therapies are discovered and developed.

Undoubtedly, deep learning (DL) has made striking progress in different artificial intelligence research fields in the bygone decade. DL is a subset of artificial intelligence, where models depict mathematical changes over a wide range of layers. DL is rapidly becoming the state-of-the-art execution in a variety of assignments and it has indicated huge potential in different fields, for example, speech recognition, computer vision and natural language processing. It has additionally been effectively applicable in drug discovery which is one of the areas that can acquire many advantages from the accomplishment of DL. Drug discovery and advancement are among the main translational science activities that add to human well-being and prosperity. This chapter highlights fundamentals of DL, challenges, opportunities, and applications in drug discovery.

SummaryAccurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unraveled, and the concepts of actual and observed performances are introduced. In an effort to curtail the gap between actual and observed performances, a quality-oriented data selection method, which evaluates the quality of data and extracts the most accurate part of it through statistical validation, is designed. Applying this method on the largest publicly available solubility database and using a consensus machine learning approach, a top-performing solubility prediction model is achieved.

Molecular docking is a key tool in structural biology and computer-assisted drug design. Molecular docking is a method which predicts the preferred orientation of a ligand when bound in an active site to form a stable complex. It is the most common method used as a structure-based drug design. Here, the authors intend to discuss the various types of docking methods and their development and applications in modern drug discovery. The important basic theories such as sampling algorithm and scoring functions have been discussed briefly. The performances of the different available docking software have also been discussed. This chapter also includes some application examples of docking studies in modern drug discovery such as targeted drug delivery using carbon nanotubes, docking of nucleic acids to find the binding modes and a comparative study between high-throughput screening and structure-based virtual screening.

Exploring new horizons: Empowering computer-assisted drug design with few-shot learning

Both machine learning (ML) and molecular dynamics (MD) techniques have benefited substantially from the growing accessibility to computational resources, enabling more sophisticated ML models and more extensive MD simulations. Over recent years, the use of ML and MD methods has become increasingly prevalent in computer-aided drug discovery. To exploit the synergies between these methodologies, researchers have started to explore approaches that combine ML techniques and MD simulations. We start this chapter with a brief introduction of the basics of MD simulations as well as ML applications in drug discovery. Next, three broad ways of marrying MD with ML are discussed: (1) use of ML to parameterise systems for MD simulations with increased accuracy, (2) use of ML to improve sampling efficiency during MD simulations, and (3) use of ML to post-process MD trajectories in order to gain quantitative insights into molecular processes. We conclude the chapter with our perspective on areas for further development of this emerging interdisciplinary field.

The rapidly advancing field of artificial intelligence (AI) has garnered substantial attention for its potential application in drug discovery and development. This opinion review critically examined the feasibility and prospects of integrating AI as a transformative tool in the pharmaceutical industry. AI, encompassing machine learning algorithms, deep learning, and data analytics, offers unprecedented opportunities to streamline and enhance various stages of drug development. This opinion review delved into the current landscape of AI-driven approaches, discussing their utilization in target identification, lead optimization, and predictive modeling of pharmacokinetics and toxicity. We aimed to scrutinize the integration of large-scale omics data, electronic health records, and chemical informatics, highlighting the power of AI in uncovering novel therapeutic targets and accelerating drug repurposing strategies. Despite the considerable potential of AI, the review also addressed inherent challenges, including data privacy concerns, interpretability of AI models, and the need for robust validation in real-world clinical settings. Additionally, we explored ethical considerations surrounding AI-driven decision-making in drug development. This opinion review provided a nuanced perspective on the transformative role of AI in drug discovery by discussing the existing literature and emerging trends, presenting critical insights and addressing potential hurdles. In conclusion, this study aimed to stimulate discourse within the scientific community and guide future endeavors to harness the full potential of AI in drug development.

Three-Dimensional Quantitative Structure–Activity Relationship Analysis for Human Pregnane X Receptor for the Prediction of CYP3A4 Induction in Human Hepatocytes: Structure-Based Comparative Molecular Field Analysis

Review: [recent developments towards the construction of compound libraries and their application in drug and probe discovery; 86 refs.

Activity- and reactivity-based proteomics: Recent technological advances and applications in drug discovery

IntroductionProviding tools for comprehensively evaluating scintigraphy images could enhance transthyretin amyloid cardiomyopathy (ATTR-CM) diagnosis. This study aims to automatically detect and score ATTR-CM in total body scintigraphy images using deep learning on multi-tracer, multi-scanner, and multi-center datasets.MethodsIn the current study, we employed six datasets (from 12 cameras) for various tasks and purposes. Dataset #1 (93 patients, 99mTc-MDP) was used to develop the 2D-planar segmentation and localization models. Dataset #2 (216 patients, 99mTc-DPD) was used for the detection (grade 0 vs. grades 1, 2, and 3) and scoring (0 and 1 vs. grades 2 and 3) of ATTR-CM. Datasets #3 (41 patients, 99mTc-HDP), #4 (53 patients, 99mTc-PYP), and #5 (129 patients, 99mTc-DPD) were used as external centers. ATTR-CM detection and scouring were performed by two physicians in each center. Moreover, Dataset #6 consisting of 3215 patients without labels, was employed for retrospective model performance evaluation. Different regions of interest were cropped and fed into the classification model for the detection and scoring of ATTR-CM. Ensembling was performed on the outputs of different models to improve their performance. Model performance was measured by classification accuracy, sensitivity, specificity, and AUC. Grad-CAM and saliency maps were generated to explain the models’ decision-making process.ResultsIn the internal test set, all models for detection and scoring achieved an AUC of more than 0.95 and an F1 score of more than 0.90. For detection in the external dataset, AUCs of 0.93, 0.95, and 1 were achieved for datasets 3, 4, and 5, respectively. For the scoring task, AUCs of 0.95, 0.83, and 0.96 were achieved for these datasets, respectively. In dataset #6, we found ten cases flagged as ATTR-CM by the network. Out of these, four cases were confirmed by a nuclear medicine specialist as possibly having ATTR-CM. GradCam and saliency maps showed that the deep-learning models focused on clinically relevant cardiac areas.ConclusionIn the current study, we developed and evaluated a fully automated pipeline to detect and score ATTR-CM using large multi-tracer, multi-scanner, and multi-center datasets, achieving high performance on total body images. This fully automated pipeline could lead to more timely and accurate diagnoses, ultimately improving patient outcomes.

Computational transformation in drug discovery: A comprehensive study on molecular docking and quantitative structure activity relationship (QSAR)

Introduction Drug discovery is a complex and multifaceted process driven by scientific innovation and advanced technologies. Next-Generation Sequencing (NGS) platforms, encompassing both short-read and long-read technologies, have revolutionized the field by enabling the high-throughput and cost-effective analysis of DNA and RNA molecules. Continuous advancements in NGS-based technologies have enabled their seamless integration across preclinical and clinical workflows in drug discovery, encompassing early-stage drug target identification, candidate selection, genetically stratified clinical trials, and pharmacogenetic studies. Area covered This review provides an overview of the current and potential applications of NGS-based technologies in drug discovery and development process, including their roles in novel drug target identification, high-throughput screening, clinical trials, and clinical medication studies. The review is based on literature retrieval from the PubMed and Web of Science databases between 2018 and 2024. Expert opinion As technologies advance rapidly, NGS enhances accuracy and generates vast datasets. These datasets are extensively integrated with other heterogeneous data in systems biology and are mined using machine learning to extract significant insights, thereby driving progress in drug discovery.

Introduction The unique physicochemical properties and chemical diversity of organofluorine compounds have remarkably contributed for their wide utility in the area of pharmaceuticals, materials and agrochemicals. The noteworthy characteristics of fluorine include high electron affinity, lipophilicity and bioavailability, extending the half-life of the drugs. The incorporation of fluorine substituents, particularly trifluoromethyl groups, into organic molecules has led to their high potency against various diseases, including malaria. Hence, organofluorinated molecules offer valuable avenues for the design of new drug candidates against malaria. Areas covered In this review, the authors discuss the importance of fluorine substituents present in the chemical compounds, and their potential applications for antimalarial drug discovery. Expert opinion Fluorinated molecules represent a reliable strategy to develop new antimalarial drugs. Fluorine or fluorinated groups have been identified as a promising precursor, and their presence in approximately twenty-five percent of approved drugs is notable. Selective fluorination of chemical entities has the potential to be applied not only to improve the activity profile against the malaria parasite, but could be extrapolated for favorable pharmacological applications. Hazardous reagents such as HF, F2 and SF4 used for fluorination, are not considered as safe, and therefore, this process remains challenging, particularly for the pharmaceutical industry.