Recently, attention mechanism and derived models have gained significant traction in drug development due to their outstanding performance and interpretability in handling complex data structures. This review offers an in-depth exploration of the principles underlying attention-based models and their advantages in drug discovery. We further elaborate on their applications in various aspects of drug development, from molecular screening and target binding to property prediction and molecule generation. Finally, we discuss the current challenges faced in the application of attention mechanisms and Artificial Intelligence technologies, including data quality, model interpretability and computational resource constraints, along with future directions for research. Given the accelerating pace of technological advancement, we believe that attention-based models will have an increasingly prominent role in future drug discovery. We anticipate that these models will usher in revolutionary breakthroughs in the pharmaceutical domain, significantly accelerating the pace of drug development.

With the dramatic development of single-cell RNA sequencing (scRNA-seq) technologies, the systematic decoding of cell-cell communication has received great research interest. To date, several in-silico methods have been developed, but most of them lack the ability to predict the communication pathways connecting the insides and outsides of cells. Here, we developed CellCall, a toolkit to infer inter- and intracellular communication pathways by integrating paired ligand-receptor and transcription factor (TF) activity. Moreover, CellCall uses an embedded pathway activity analysis method to identify the significantly activated pathways involved in intercellular crosstalk between certain cell types. Additionally, CellCall offers a rich suite of visualization options (Circos plot, Sankey plot, bubble plot, ridge plot, etc.) to present the analysis results. Case studies on scRNA-seq datasets of human testicular cells and the tumor immune microenvironment demonstrated the reliable and unique functionality of CellCall in intercellular communication analysis and internal TF activity exploration, which were further validated experimentally. Comparative analysis of CellCall and other tools indicated that CellCall was more accurate and offered more functions. In summary, CellCall provides a sophisticated and practical tool allowing researchers to decipher intercellular communication and related internal regulatory signals based on scRNA-seq data. CellCall is freely available at https://github.com/ShellyCoder/cellcall.

Snake venom contains many toxic proteins that can destroy the circulatory system or nervous system of prey. Studies have found that these snake venom proteins have the potential to treat cardiovascular and nervous system diseases. Therefore, the study of snake venom protein is conducive to the development of related drugs. The research technologies based on traditional biochemistry can accurately identify these proteins, but the experimental cost is high and the time is long. Artificial intelligence technology provides a new means and strategy for large-scale screening of snake venom proteins from the perspective of computing. In this paper, we developed a sequence-based computational method to recognize snake toxin proteins. Specially, we utilized three different feature descriptors, namely g-gap, natural vector and word 2 vector, to encode snake toxin protein sequences. The analysis of variance (ANOVA), gradient-boost decision tree algorithm (GBDT) combined with incremental feature selection (IFS) were used to optimize the features, and then the optimized features were input into the deep learning model for model training. The results show that our model can achieve a prediction performance with an accuracy of 82.00% in 10-fold cross-validation. The model is further verified on independent data, and the accuracy rate reaches to 81.14%, which demonstrated that our model has excellent prediction performance and robustness.

Toxicity risk assessment plays a crucial role in determining the clinical success and market potential of drug candidates. Traditional animal-based testing is costly, time-consuming, and ethically controversial, which has led to the rapid development of computational toxicology. This review surveys over 20 ADMET prediction platforms, categorizing them into rule/statistical-based methods, machine learning (ML) methods, and graph-based methods. We also summarize major toxicological databases into four types: chemical toxicity, environmental toxicology, alternative toxicology, and biological toxin databases, highlighting their roles in model training and validation. Furthermore, we review recent advancements in ML and artificial intelligence (AI) applied to toxicity prediction, covering acute toxicity, organ-specific toxicities, and carcinogenicity. The field is transitioning from single-endpoint predictions to multi-endpoint joint modeling, incorporating multimodal features. We also explore the application of generative modeling techniques and interpretability frameworks to improve the accuracy and credibility of predictions. Additionally, we discuss the use of network toxicology in evaluating the safety of traditional Chinese medicines (TCMs) and the potential of large language models (LLMs) in literature mining, knowledge integration, and molecular toxicity prediction. Finally, we address current challenges, including data quality, model interpretability, and causal inference, and propose future directions such as multi-omics integration, interpretable AI models, and domain-specific LLMs, aiming to provide more efficient and precise technical support for preclinical toxicity assessments in drug development.

The global pandemic of coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2, has led to a dramatic loss of human life worldwide. Despite many efforts, the development of effective drugs and vaccines for this novel virus will take considerable time. Artificial intelligence (AI) and machine learning (ML) offer promising solutions that could accelerate the discovery and optimization of new antivirals. Motivated by this, in this paper, we present an extensive survey on the application of AI and ML for combating COVID-19 based on the rapidly emerging literature. Particularly, we point out the challenges and future directions associated with state-of-the-art solutions to effectively control the COVID-19 pandemic. We hope that this review provides researchers with new insights into the ways AI and ML fight and have fought the COVID-19 outbreak.

RNA endowed with both protein-coding and noncoding functions is referred to as ‘dual-function RNA’, ‘binary functional RNA (bifunctional RNA)’ or ‘cncRNA (coding and noncoding RNA)’. Recently, an increasing number of cncRNAs have been identified, including both translated ncRNAs (ncRNAs with coding functions) and untranslated mRNAs (mRNAs with noncoding functions). However, an appropriate database for storing and organizing cncRNAs is still lacking. Here, we developed cncRNAdb, a manually curated database of experimentally supported cncRNAs, which aims to provide a resource for efficient manipulation, browsing and analysis of cncRNAs. The current version of cncRNAdb documents about 2600 manually curated entries of cncRNA functions with experimental evidence, involving more than 2,000 RNAs (including over 1300 translated ncRNAs and over 600 untranslated mRNAs) across over 20 species. In summary, we believe that cncRNAdb will help elucidate the functions and mechanisms of cncRNAs and develop new prediction methods. The database is available at http://www.rna-society.org/cncrnadb/.