Artificial Intelligence for Drug Discovery: Are We There Yet?

The Annual Review of Pharmacology and Toxicology, Journal Year: 2023, Volume and Issue: 64(1), P. 527 - 550

Published: Sept. 22, 2023

Drug discovery is adapting to novel technologies such as data science, informatics, and artificial intelligence (AI) accelerate effective treatment development while reducing costs animal experiments. AI transforming drug discovery, indicated by increasing interest from investors, industrial academic scientists, legislators. Successful requires optimizing properties related pharmacodynamics, pharmacokinetics, clinical outcomes. This review discusses the use of in three pillars discovery: diseases, targets, therapeutic modalities, with a focus on small molecule drugs. technologies, generative chemistry, machine learning, multi-property optimization, have enabled several compounds enter trials. The scientific community must carefully vet known information address reproducibility crisis. full potential can only be realized sufficient ground truth appropriate human intervention at later pipeline stages.

Language: Английский

---

Atomically accurate de novo design of single-domain antibodies

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: March 18, 2024

Despite the central role that antibodies play in modern medicine, there is currently no way to rationally design novel bind a specific epitope on target. Instead, antibody discovery involves time-consuming immunization of an animal or library screening approaches. Here we demonstrate fine-tuned RFdiffusion network capable designing de novo variable heavy chains (VHH's) user-specified epitopes. We experimentally confirm binders four disease-relevant epitopes, and cryo-EM structure designed VHH bound influenza hemagglutinin nearly identical model both configuration CDR loops overall binding pose.

Language: Английский

---

Tribulations and future opportunities for artificial intelligence in precision medicine

Journal of Translational Medicine, Journal Year: 2024, Volume and Issue: 22(1)

Published: April 30, 2024

Abstract Upon a diagnosis, the clinical team faces two main questions: what treatment, and at dose? Clinical trials' results provide basis for guidance support official protocols that clinicians use to base their decisions. However, individuals do not consistently demonstrate reported response from relevant trials. The decision complexity increases with combination treatments where drugs administered together can interact each other, which is often case. Additionally, individual's treatment varies changes in condition. In practice, drug dose selection depend significantly on medical protocol team's experience. As such, are inherently varied suboptimal. Big data Artificial Intelligence (AI) approaches have emerged as excellent decision-making tools, but multiple challenges limit application. AI rapidly evolving dynamic field potential revolutionize various aspects of human life. has become increasingly crucial discovery development. enhances across different disciplines, such medicinal chemistry, molecular cell biology, pharmacology, pathology, practice. addition these, contributes patient population stratification. need healthcare evident it aids enhancing accuracy ensuring quality care necessary effective treatment. pivotal improving success rates increasing significance discovery, development, trials underscored by many scientific publications. Despite numerous advantages AI, advancing Precision Medicine (PM) remote monitoring, unlocking its full requires addressing fundamental concerns. These concerns include quality, lack well-annotated large datasets, privacy safety issues, biases algorithms, legal ethical challenges, obstacles related cost implementation. Nevertheless, integrating medicine will improve diagnostic outcomes, contribute more efficient delivery, reduce costs, facilitate better experiences, making sustainable. This article reviews applications development sustainable, highlights limitations applying AI.

Language: Английский

---

Development and use of machine learning algorithms in vaccine target selection

npj Vaccines, Journal Year: 2024, Volume and Issue: 9(1)

Published: Jan. 20, 2024

Computer-aided discovery of vaccine targets has become a cornerstone rational design. In this article, I discuss how Machine Learning (ML) can inform and guide key computational steps in design concerned with the identification B T cell epitopes correlates protection. provide examples ML models, as well types data predictions for which they are built. argue that interpretable potential to improve immunogens also tool scientific discovery, by helping elucidate molecular processes underlying vaccine-induced immune responses. outline limitations challenges terms availability method development need be addressed bridge gap between advances their translational application

Language: Английский

---

Sparks of function by de novo protein design

Nature Biotechnology, Journal Year: 2024, Volume and Issue: 42(2), P. 203 - 215

Published: Feb. 1, 2024

Language: Английский

---

Bispecific antibodies: advancing precision oncology

Trends in cancer, Journal Year: 2024, Volume and Issue: 10(10), P. 893 - 919

Published: Aug. 30, 2024

Bispecific antibodies (bsAbs) are engineered molecules designed to target two different epitopes or antigens. The mechanism of action is determined by the bsAb molecular targets and structure (or format), which can be manipulated create variable novel functionalities, including linking immune cells with tumor cells, dual signaling pathway blockade. Several bsAbs have already changed treatment landscape hematological malignancies select solid cancers. However, mechanisms resistance these agents understudied management toxicities remains challenging. Herein, we review principles in engineering, current understanding resistance, data for clinical application, provide a perspective on ongoing challenges future developments this field.

Language: Английский

---

Computational Methods in Immunology and Vaccinology: Design and Development of Antibodies and Immunogens

Journal of Chemical Theory and Computation, Journal Year: 2023, Volume and Issue: 19(16), P. 5315 - 5333

Published: Aug. 1, 2023

The design of new biomolecules able to harness immune mechanisms for the treatment diseases is a prime challenge computational and simulative approaches. For instance, in recent years, antibodies have emerged as an important class therapeutics against spectrum pathologies. In cancer, immune-inspired approaches are witnessing surge thanks better understanding tumor-associated antigens their engagement or evasion from human system. Here, we provide summary main state-of-the-art that used antigens, parallel, review key methodologies epitope identification both B- T-cell mediated responses. A special focus devoted description structure- physics-based models, privileged over purely sequence-based We discuss implications novel methods engineering with tailored immunological properties possible therapeutic uses. Finally, highlight extraordinary challenges opportunities presented by integration emerging Artificial Intelligence technologies prediction epitopes, antibodies.

Language: Английский

---

Therapeutic Antibodies in Medicine

Molecules, Journal Year: 2023, Volume and Issue: 28(18), P. 6438 - 6438

Published: Sept. 5, 2023

Antibody engineering has developed into a wide-reaching field, impacting multitude of industries, most notably healthcare and diagnostics. The seminal work on developing the first monoclonal antibody four decades ago witnessed exponential growth in last 10–15 years, where regulators have approved antibodies as therapeutics for several diagnostic applications, including remarkable attention it garnered during pandemic. In recent become fastest-growing class biological drugs treatment wide range diseases, from cancer to autoimmune conditions. This review discusses field therapeutic stands today. It summarizes outlines clinical relevance application treating landscape diseases different disciplines medicine. nomenclature, various approaches therapies, evolution therapeutics. also risk profile adverse immune reactions associated with sheds light future applications perspectives drug discovery.

Language: Английский

---

A survey of generative AI for de novo drug design: new frontiers in molecule and protein generation

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

Published: May 23, 2024

Artificial intelligence (AI)-driven methods can vastly improve the historically costly drug design process, with various generative models already in widespread use. Generative for de novo design, particular, focus on creation of novel biological compounds entirely from scratch, representing a promising future direction. Rapid development field, combined inherent complexity creates difficult landscape new researchers to enter. In this survey, we organize into two overarching themes: small molecule and protein generation. Within each theme, identify variety subtasks applications, highlighting important datasets, benchmarks, model architectures comparing performance top models. We take broad approach AI-driven allowing both micro-level comparisons within subtask macro-level observations across different fields. discuss parallel challenges approaches between applications highlight directions as whole. An organized repository all covered sources is available at https://github.com/gersteinlab/GenAI4Drug.

Language: Английский

---

Leveraging Artificial Intelligence to Expedite Antibody Design and Enhance Antibody–Antigen Interactions

Bioengineering, Journal Year: 2024, Volume and Issue: 11(2), P. 185 - 185

Published: Feb. 15, 2024

This perspective sheds light on the transformative impact of recent computational advancements in field protein therapeutics, with a particular focus design and development antibodies. Cutting-edge methods have revolutionized our understanding protein-protein interactions (PPIs), enhancing efficacy therapeutics preclinical clinical settings. Central to these is application machine learning deep learning, which offers unprecedented insights into intricate mechanisms PPIs facilitates precise control over functions. Despite advancements, complex structural nuances antibodies pose ongoing challenges their optimization. Our review provides comprehensive exploration latest approaches, including language models diffusion techniques, role surmounting challenges. We also present critical analysis methods, offering drive further progress this rapidly evolving field. The paper includes practical recommendations for supplemented independent benchmark studies. These studies key performance metrics such as accuracy ease program execution, providing valuable resource researchers engaged antibody development. Through detailed perspective, we aim contribute advancement design, equipping tools knowledge navigate complexities

Language: Английский

---