The Coming of Age of AI/ML in Drug Discovery, Development, Clinical Testing, and Manufacturing: The FDA Perspectives

Drug Design Development and Therapy, Год журнала: 2023, Номер Volume 17, С. 2691 - 2725

Опубликована: Сен. 1, 2023

Abstract: Artificial intelligence (AI) and machine learning (ML) represent significant advancements in computing, building on technologies that humanity has developed over millions of years—from the abacus to quantum computers. These tools have reached a pivotal moment their development. In 2021 alone, U.S. Food Drug Administration (FDA) received 100 product registration submissions heavily relied AI/ML for applications such as monitoring improving human performance compiling dossiers. To ensure safe effective use drug discovery manufacturing, FDA numerous other federal agencies issued continuously updated, stringent guidelines. Intriguingly, these guidelines are often generated or updated with aid themselves. The overarching goal is expedite discovery, enhance safety profiles existing drugs, introduce novel treatment modalities, improve manufacturing compliance robustness. Recent publications offer an encouraging outlook potential tools, emphasizing need careful deployment. This expanded market opportunities retraining personnel handling enabled innovative emerging therapies gene editing, CRISPR-Cas9, CAR-T cells, mRNA-based treatments, personalized medicine. summary, maturation testament ingenuity. Far from being autonomous entities, created by humans designed solve complex problems now future. paper aims present status technologies, along examples future applications. Keywords: FDA, artificial intelligence, learning, development, advanced

Язык: Английский

---

Review of AlphaFold 3: Transformative Advances in Drug Design and Therapeutics

Cureus, Год журнала: 2024, Номер unknown

Опубликована: Июль 2, 2024

Google DeepMind Technologies Limited (London, United Kingdom) recently released its new version of the biomolecular structure predictor artificial intelligence (AI) model named AlphaFold 3. Superior in accuracy and more powerful than predecessor 2, this innovation has astonished world with capacity speed. It takes humans years to determine various proteins how shape works receptors but 3 predicts same seconds. The version's utility is unimaginable field drug discoveries, vaccines, enzymatic processes, determining rate effect different biological processes. uses similar machine learning deep models such as Gemini (Google Limited). already established itself a turning point computational biochemistry development along receptor modulation development. With help this, researchers will gain unparalleled insights into structural dynamics their interactions, opening up avenues for scientists doctors exploit benefit patient. integration AI like 3, bolstered by rigorous validation against high-standard research publications, set catalyze further innovations offer glimpse future biomedicine.

Язык: Английский

---

Easy and accurate protein structure prediction using ColabFold

Nature Protocols, Год журнала: 2024, Номер unknown

Опубликована: Окт. 14, 2024

Язык: Английский

---

AI-Driven Deep Learning Techniques in Protein Structure Prediction

International Journal of Molecular Sciences, Год журнала: 2024, Номер 25(15), С. 8426 - 8426

Опубликована: Авг. 1, 2024

Protein structure prediction is important for understanding their function and behavior. This review study presents a comprehensive of the computational models used in predicting protein structure. It covers progression from established modeling to state-of-the-art artificial intelligence (AI) frameworks. The paper will start with brief introduction structures, modeling, AI. section on discuss homology ab initio threading. next deep learning-based models. introduces some AI models, such as AlphaFold (AlphaFold, AlphaFold2, AlphaFold3), RoseTTAFold, ProteinBERT, etc. also discusses how techniques have been integrated into frameworks like Swiss-Model, Rosetta, I-TASSER. model performance compared using rankings CASP14 (Critical Assessment Structure Prediction) CASP15. CASP16 ongoing, its results are not included this review. Continuous Automated Model EvaluatiOn (CAMEO) complements biennial CASP experiment. Template score (TM-score), global distance test total (GDT_TS), Local Distance Difference Test (lDDT) discussed too. then acknowledges ongoing difficulties emphasizes necessity additional searches dynamic behavior, conformational changes, protein-protein interactions. In application section, applications various fields drug design, industry, education, novel development. summary, provides overview latest advancements predictions. significant achieved by identifies potential areas further investigation.

Язык: Английский

---

Conformationally adaptive therapeutic peptides for diseases caused by intrinsically disordered proteins (IDPs). New paradigm for drug discovery: Target the target, not the arrow

Pharmacology & Therapeutics, Год журнала: 2025, Номер unknown, С. 108797 - 108797

Опубликована: Янв. 1, 2025

The traditional model of protein structure determined by the amino acid sequence is today seriously challenged fact that approximately half human proteome made up proteins do not have a stable 3D structure, either partially or in totality. These proteins, called intrinsically disordered (IDPs), are involved numerous physiological functions and associated with severe pathologies, e.g. Alzheimer, Parkinson, Creutzfeldt-Jakob, amyotrophic lateral sclerosis (ALS), type 2 diabetes. Targeting these challenging for two reasons: i) we need to preserve their functions, ii) drug design molecular docking possible due lack reliable starting conditions. Faced this challenge, solutions proposed artificial intelligence (AI) such as AlphaFold clearly unsuitable. Instead, suggest an innovative approach consisting mimicking, short synthetic peptides, conformational flexibility IDPs. which call adaptive derived from domains IDPs become structured after interacting ligand. Adaptive peptides designed aim selectively antagonizing harmful effects IDPs, without targeting them directly but through selected ligands, affecting properties. This"target target, arrow" strategy promised open new route discovery currently undruggable proteins.

Язык: Английский

---

Using AlphaFold Predictions in Viral Research

Current Issues in Molecular Biology, Год журнала: 2023, Номер 45(4), С. 3705 - 3732

Опубликована: Апрель 21, 2023

Elucidation of the tertiary structure proteins is an important task for biological and medical studies. AlphaFold, a modern deep-learning algorithm, enables prediction protein to high level accuracy. It has been applied in numerous studies various areas biology medicine. Viruses are entities infecting eukaryotic procaryotic organisms. They can pose danger humans economically significant animals plants, but they also be useful control, suppressing populations pests pathogens. AlphaFold used molecular mechanisms viral infection facilitate several activities, including drug design. Computational analysis bacteriophage receptor-binding contribute more efficient phage therapy. In addition, predictions discovery enzymes origin that able degrade cell wall bacterial The use assist fundamental research, evolutionary ongoing development improvement ensure its contribution study will future.

Язык: Английский

---

Large language models in plant biology

Trends in Plant Science, Год журнала: 2024, Номер 29(10), С. 1145 - 1155

Опубликована: Май 26, 2024

Язык: Английский

---

Precision enzyme discovery through targeted mining of metagenomic data

Natural Products and Bioprospecting, Год журнала: 2024, Номер 14(1)

Опубликована: Янв. 11, 2024

Abstract Metagenomics has opened new avenues for exploring the genetic potential of uncultured microorganisms, which may serve as promising sources enzymes and natural products industrial applications. Identifying with improved catalytic properties from vast amount available metagenomic data poses a significant challenge that demands development novel computational functional screening tools. The all are primarily dictated by their structures, predominantly determined amino acid sequences. However, this aspect not been fully considered in enzyme bioprospecting processes. With accumulating number sequences increasing demand discovering biocatalysts, structural modeling can be employed to identify properties. Recent efforts discover polysaccharide-degrading rumen metagenome using homology-based searches machine learning-based models have shown promise. Here, we will explore various approaches screen shortlist metagenome-derived biocatalyst candidates, conjunction wet lab analytical methods traditionally used characterization.

Язык: Английский

---

Virtual Screening of Peptide Libraries: The Search for Peptide-Based Therapeutics Using Computational Tools

International Journal of Molecular Sciences, Год журнала: 2024, Номер 25(3), С. 1798 - 1798

Опубликована: Фев. 1, 2024

Over the last few decades, we have witnessed growing interest from both academic and industrial laboratories in peptides as possible therapeutics. Bioactive a high potential to treat various diseases with specificity biological safety. Compared small molecules, represent better candidates inhibitors (or general modulators) of key protein–protein interactions. In fact, undruggable proteins containing large smooth surfaces can be more easily targeted conformational plasticity peptides. The discovery bioactive peptides, working against disease-relevant protein targets, generally requires high-throughput screening libraries, silico approaches are highly exploited for their low-cost incidence efficiency. present review reports on challenges linked employment therapeutics describes computational approaches, mainly structure-based virtual (SBVS), support identification novel therapeutic implementations. Cutting-edge SBVS strategies reviewed along examples applications focused diverse classes (i.e., anticancer, antimicrobial/antiviral blocking amyloid fiber formation).

Язык: Английский

---

Revolutionizing protein–protein interaction prediction with deep learning

Current Opinion in Structural Biology, Год журнала: 2024, Номер 85, С. 102775 - 102775

Опубликована: Фев. 7, 2024

Язык: Английский

---