TTD: Therapeutic Target Database describing target druggability information

Nucleic Acids Research, Journal Year: 2023, Volume and Issue: 52(D1), P. D1465 - D1477

Published: Sept. 15, 2023

Target discovery is one of the essential steps in modern drug development, and identification promising targets fundamental for developing first-in-class drug. A variety methods have emerged target assessment based on druggability analysis, which refers to likelihood a being effectively modulated by drug-like agents. In therapeutic database (TTD), nine categories established characteristics were thus collected 426 successful, 1014 clinical trial, 212 preclinical/patented, 1479 literature-reported via systematic review. These characteristic classified into three distinct perspectives: molecular interaction/regulation, human system profile cell-based expression variation. With rapid progression technology concerted effort discovery, TTD other databases highly expected facilitate explorations validation innovative target. now freely accessible at: https://idrblab.org/ttd/.

Language: Английский

---

Artificial Intelligence in Pharmaceutical Sciences

Engineering, Journal Year: 2023, Volume and Issue: 27, P. 37 - 69

Published: April 28, 2023

Drug discovery and development affects various aspects of human health dramatically impacts the pharmaceutical market. However, investments in a new drug often go unrewarded due to long complex process research (R&D). With advancement experimental technology computer hardware, artificial intelligence (AI) has recently emerged as leading tool analyzing abundant high-dimensional data. Explosive growth size biomedical data provides advantages applying AI all stages R&D. Driven by big biomedicine, led revolution R&D, its ability discover drugs more efficiently at lower cost. This review begins with brief overview common models field discovery; then, it summarizes discusses depth their specific applications such target discovery, design, preclinical research, automated synthesis, influences Finally, major limitations R&D are fully discussed possible solutions proposed.

Language: Английский

---

Advances in artificial intelligence for drug delivery and development: A comprehensive review

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 178, P. 108702 - 108702

Published: June 7, 2024

Language: Английский

---

TheMarker: a comprehensive database of therapeutic biomarkers

Nucleic Acids Research, Journal Year: 2023, Volume and Issue: 52(D1), P. D1450 - D1464

Published: Oct. 18, 2023

Abstract Distinct from the traditional diagnostic/prognostic biomarker (adopted as indicator of disease state/process), therapeutic (ThMAR) has emerged to be very crucial in clinical development and practice all therapies. There are five types ThMAR that have been found play indispensable roles various stages drug discovery, such as: Pharmacodynamic Biomarker essential for guaranteeing pharmacological effects a therapy, Safety critical assessing extent or likelihood therapy-induced toxicity, Monitoring guiding management by serially measuring patients’ status, Predictive maximizing outcome therapy specific individuals, Surrogate Endpoint fundamental accelerating approval therapy. However, these data ThMARs not comprehensively described any existing databases. Herein, database, named ‘TheMarker’, was therefore constructed (a) systematically offer used at different development, (b) describe information largest number drugs among available databases, (c) extensively cover widest classes just focusing on anticancer These TheMarker expected great implication significant impact discovery practice, it is freely accessible without login requirement at: https://idrblab.org/themarker.

Language: Английский

---

ADCdb: the database of antibody–drug conjugates

Nucleic Acids Research, Journal Year: 2023, Volume and Issue: 52(D1), P. D1097 - D1109

Published: Oct. 13, 2023

Abstract Antibody-drug conjugates (ADCs) are a class of innovative biopharmaceutical drugs, which, via their antibody (mAb) component, deliver and release potent warhead (a.k.a. payload) at the disease site, thereby simultaneously improving efficacy delivered therapy reducing its off-target toxicity. To design ADCs promising efficacy, it is crucial to have critical data pharma-information biological activities for each ADC. However, no such database has been constructed yet. In this study, named ADCdb focusing on providing ADC information (especially activities) from multiple perspectives was thus developed. Particularly, total 6572 (359 approved by FDA or in clinical trial pipeline, 501 preclinical test, 819 with in-vivo testing data, 1868 cell line/target 3025 without in-vivo/cell data) together explicit collected provided. Moreover, 9171 literature-reported were discovered, which identified diverse pipelines, model organisms, patient/cell-derived xenograft models, etc. Due significance relevant new expected attract broad interests research fields current drug discovery. The now publicly accessible at: https://idrblab.org/adcdb/.

Language: Английский

---

Computational drug repurposing by exploiting large-scale gene expression data: Strategy, methods and applications

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 155, P. 106671 - 106671

Published: Feb. 12, 2023

Language: Английский

---

G-K BertDTA: A graph representation learning and semantic embedding-based framework for drug-target affinity prediction

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 173, P. 108376 - 108376

Published: March 25, 2024

Language: Английский

---

Advancing drug-response prediction using multi-modal and -omics machine learning integration (MOMLIN): a case study on breast cancer clinical data

Briefings in Bioinformatics, Journal Year: 2024, Volume and Issue: 25(4)

Published: May 23, 2024

Abstract The inherent heterogeneity of cancer contributes to highly variable responses any anticancer treatments. This underscores the need first identify precise biomarkers through complex multi-omics datasets that are now available. Although much research has focused on this aspect, identifying associated with distinct drug responders still remains a major challenge. Here, we develop MOMLIN, multi-modal and -omics machine learning integration framework, enhance drug-response prediction. MOMLIN jointly utilizes sparse correlation algorithms class–specific feature selection algorithms, which identifies -omics–associated interpretable components. was applied 147 patients’ breast (clinical, mutation, gene expression, tumor microenvironment cells molecular pathways) analyze class predictions for non-responders responders. Notably, achieves an average AUC 0.989, is at least 10% greater when compared current state-of-the-art (data analysis biomarker discovery using latent components, factor analysis, canonical analysis). Moreover, not only detects known individual such as genes mutation/expression level, most importantly, it correlates network each response class. For example, interaction between ER-negative-HMCN1-COL5A1 mutations-FBXO2-CSF3R expression-CD8 emerge multimodal responders, potentially affecting antimicrobial peptides FLT3 signaling pathways. In contrast, resistance cases, combination lymph node-TP53 mutation-PON3-ENSG00000261116 lncRNA expression-HLA-E-T-cell exclusions emerged biomarkers, possibly impacting neurotransmitter release cycle pathway. therefore, expected advance precision medicine, detect context–specific better predict classifications.

Language: Английский

---

Application of artificial intelligence in drug design: A review

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 179, P. 108810 - 108810

Published: July 10, 2024

Language: Английский

---

Computational Chemistry in Structure-Based Solute Carrier Transporter Drug Design: Recent Advances and Future Perspectives

Journal of Chemical Information and Modeling, Journal Year: 2024, Volume and Issue: 64(5), P. 1433 - 1455

Published: Jan. 31, 2024

Solute carrier transporters (SLCs) are a class of important transmembrane proteins that involved in the transportation diverse solute ions and small molecules into cells. There approximately 450 SLCs within human body, more than quarter them emerging as attractive therapeutic targets for multiple complex diseases, e.g., depression, cancer, diabetes. However, only 44 unique (∼9.8% SLC superfamily) with 3D structures specific binding sites have been reported. To design innovative effective drugs targeting SLCs, there number obstacles need to be overcome. computational chemistry, including physics-based molecular modeling machine learning- deep learning-based artificial intelligence (AI), provides an alternative complementary way classical drug discovery approach. Here, we present comprehensive overview on recent advances existing challenges techniques structure-based from three main aspects: (i) characterizing conformations during functional process transportation, (ii) identifying druggability especially cryptic allosteric ones substrates binding, (iii) discovering or synthetic protein binders sites. This work is expected provide guidelines understanding structure function superfamily facilitate rational novel modulators aid state-of-the-art chemistry technologies intelligence.

Language: Английский

---