Comprehensive applications of the artificial intelligence technology in new drug research and development.

Purpose: Target-based strategy is a prevalent means of drug research and development (R&D), since targets provide effector molecules of drug action and offer the foundation of pharmacological investigation. Recently, the artificial intelligence (AI) technology has been utilized in various stages of drug R&D, where AI-assisted experimental methods show higher efficiency than sole experimental ones. It is a critical need to give a comprehensive review of AI applications in drug R &D for biopharmaceutical field. Methods: Relevant literatures about AI-assisted drug R&D were collected from the public databases (Including Google Scholar, Web of Science, PubMed, IEEE Xplore Digital Library, Springer, and ScienceDirect) through a keyword searching strategy with the following terms [("Artificial Intelligence" OR "Knowledge Graph" OR "Machine Learning") AND ("Drug Target Identification" OR "New Drug Development")]. Results: In this review, we first introduced common strategies and novel trends of drug R&D, followed by characteristic description of AI algorithms widely used in drug R&D. Subsequently, we depicted detailed applications of AI algorithms in target identification, lead compound identification and optimization, drug repurposing, and drug analytical platform construction. Finally, we discussed the challenges and prospects of AI-assisted methods for drug discovery. Conclusion: Collectively, this review provides comprehensive overview of AI applications in drug R&D and presents future perspectives for biopharmaceutical field, which may promote the development of drug industry.

Unraveling the prognostic significance and molecular characteristics of tumor-infiltrating B lymphocytes in clear cell renal cell carcinoma through a comprehensive bioinformatics analysis.

Introduction: Clear cell renal cell carcinoma (ccRCC) is a prevalent subtype of kidney cancer that exhibits a complex tumor microenvironment, which significantly influences tumor progression and immunotherapy response. In recent years, emerging evidence has underscored the involvement of tumor-infiltrating B lymphocytes (TIL-Bs), a crucial component of adaptive immunity, and their roles in ccRCC as compared to other tumors. Therefore, the present study endeavors to systematically explore the prognostic and molecular features of TIL-Bs in ccRCC. Methods: Initially, xCell algorithm was used to predict TIL-Bs in TCGA-KIRC and other ccRCC transcriptomic datasets. The Log-Rank test and Cox regression were applied to explore the relationship of B-cells with ccRCC survival. Then, we used WGCNA method to identify important modules related to TIL-Bs combining Consensus subcluster and scRNA-seq data analysis. To narrow down the prospective biomarkers, a prognostic signature was proposed. Next, we explored the feature of the signature individual genes and the risk-score. Finally, the potential associations of signature with clinical phenotypes and drugs were investigated. Results: Preliminary, we found ccRCC survival was negatively associated with TIL-Bs, which was confirmed by other datasets. Afterwards, ten co-expression modules were identified and a distinct ccRCC cluster was subsequently detected. Moreover, we assessed the transcriptomic alteration of B-cell in ccRCC and a relevant B-cell subtype was also pinpointed. Based on two core modules (brown, red), a 10-gene signature (TNFSF13B, SHARPIN, B3GAT3, IL2RG, TBC1D10C, STAC3, MICB, LAG3, SMIM29, CTLA4) was developed in train set and validated in test sets. These biomarkers were further investigated with regards to their differential expression and correlation with immune characteristics, along with risk-score related mutations and pathways. Lastly, we established a nomogram combined tumor grade and discovered underlying drugs according to their sensitivity response. Discussion: In our research, we elucidated the remarkable association between ccRCC and B-cells. Then, we detected several key gene modules, together with close patient subcluster and B-cell subtype,which could be responsible for the TIL-Bs in ccRCC. Moreover, we proposed a 10-gene signature and investigated its molecular features from multiple perspectives. Overall, understanding the roles of TIL-Bs could aid in the immunotherapeutic approaches for ccRCC, which deserve further research to clarify the implications for patient prognosis and treatment.

Uncovering neuroinflammation-related modules and potential repurposing drugs for Alzheimer's disease through multi-omics data integrative analysis.

Background: Neuroinflammation is one of the key factors leading to neuron death and synapse dysfunction in Alzheimer's disease (AD). Amyloid-ß (Aß) is thought to have an association with microglia activation and trigger neuroinflammation in AD. However, inflammation response in brain disorders is heterogenous, and thus, it is necessary to unveil the specific gene module of neuroinflammation caused by Aß in AD, which might provide novel biomarkers for AD diagnosis and help understand the mechanism of the disease. Methods: Transcriptomic datasets of brain region tissues from AD patients and the corresponding normal tissues were first used to identify gene modules through the weighted gene co-expression network analysis (WGCNA) method. Then, key modules highly associated with Aß accumulation and neuroinflammatory response were pinpointed by combining module expression score and functional information. Meanwhile, the relationship of the Aß-associated module to the neuron and microglia was explored based on snRNA-seq data. Afterward, transcription factor (TF) enrichment and the SCENIC analysis were performed on the Aß-associated module to discover the related upstream regulators, and then a PPI network proximity method was employed to repurpose the potential approved drugs for AD. Results: A total of 16 co-expression modules were primarily obtained by the WGCNA method. Among them, the green module was significantly correlated with Aß accumulation, and its function was mainly involved in neuroinflammation response and neuron death. Thus, the module was termed the amyloid-ß induced neuroinflammation module (AIM). Moreover, the module was negatively correlated with neuron percentage and showed a close association with inflammatory microglia. Finally, based on the module, several important TFs were recognized as potential diagnostic biomarkers for AD, and then 20 possible drugs including ibrutinib and ponatinib were picked out for the disease. Conclusion: In this study, a specific gene module, termed AIM, was identified as a key sub-network of Aß accumulation and neuroinflammation in AD. Moreover, the module was verified as having an association with neuron degeneration and inflammatory microglia transformation. Moreover, some promising TFs and potential repurposing drugs were presented for AD based on the module. The findings of the study shed new light on the mechanistic investigation of AD and might make benefits the treatment of the disease.

Three-dimensional chromatin architecture datasets for aging and Alzheimer's disease.

Recently, increasing studies are indicating a close association between dysregulated enhancers and neurodegenerative diseases, such as Alzheimer's disease (AD). However, their contributions were poorly defined for lacking direct links to disease genes. To bridge this gap, we presented the Hi-C datasets of 4 AD patients, 4 dementia-free aged and 3 young subjects, including 30 billion reads. As applications, we utilized them to link the AD risk SNPs and dysregulated epigenetic marks to the target genes. Combining with epigenetic data, we observed more detailed interactions among regulatory regions and found that many known AD risk genes were under long-distance promoter-enhancer interactions. For future AD and aging studies, our datasets provide a reference landscape to better interpret findings of association and epigenetic studies for AD and aging process.

FL-DTD: an integrated pipeline to predict the drug interacting targets by feedback loop-based network analysis.

Drug target discovery is an essential step to reveal the mechanism of action (MoA) underlying drug therapeutic effects and/or side effects. Most of the approaches are usually labor-intensive while unable to identify the tissue-specific interacting targets, especially the targets with weaker drug binding affinity. In this work, we proposed an integrated pipeline, FL-DTD, to predict the drug interacting targets of novel compounds in a tissue-specific manner. This method was built based on a hypothesis that cells under a status of homeostasis would take responses to drug perturbation by activating feedback loops. Therefore, the drug interacting targets can be predicted by analyzing the network responses after drug perturbation. We evaluated this method using the expression data of estrogen stimulation, gene manipulation and drug perturbation and validated its good performance to identify the annotated drug targets. Using STAT3 as a target protein, we applied this method to drug perturbation data of 500 natural compounds and predicted five compounds with STAT3 interacting activities. Experimental assay validated the STAT3-interacting activities of four compounds. Overall, our evaluation suggests that FL-DTD predicts the drug interacting targets with good accuracy and can be used for drug target discovery.