Medicinal chemistry (Shariqah (United Arab Emirates)) · 2025
Integrated Artificial Intelligence and Physics-Based Methods for the De novo Design of Spleen Tyrosine Kinase (SYK) Inhibitors.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Pawar Atul Darasing, Abdelghani Heba Taha M, Deka Hemchandra, Battula Monishka Srinivas, Maiti Surajit, Patil Pritee Chunarkar, Bhowmick Shovonlal, Chikhale Rupesh V
Аннотация
INTRODUCTION: SYK (Spleen Tyrosine Kinase) regulates immune response and is a promising target for cancer, sepsis, and allergy therapies. This study aims to create novel compounds that serve as alternative inhibitors for cancer treatments targeting SYK.
METHODS: A thorough combination of machine learning (ML) and physics-based methods was employed to achieve these goals, encompassing de novo design, multitier molecular docking, absolute binding affinity computation, and molecular dynamics (MD) simulation.
RESULTS: A total of 5576 novel molecules with key pharmacophoric features were generated using an ML-driven de novo approach against 21 diaminopyrimidine carboxamide analogs. Pharmacokinetic and toxicity evaluation assisted by the ML approach revealed that 4353 chemical entities fulfilled the acceptable pharmacokinetic and toxicity profiles. By screening through binding energy threshold from the physics-based multitier molecular docking, and ML-assisted absolute binding affinity identified the top four molecules such as RI809 (2-([1,1'-biphenyl]-3-ylmethyl)-4-((2- aminocyclohexyl)oxy)benzamide), RI1393 (4-((2-aminocyclohexyl)amino)-2-(3-(1-methyl-1Hpyrazol- 5-yl)-4-(trifluoromethyl)benzyl)benzamide), RI2765 (2-([1,1'-biphenyl]-3-ylmethyl)-4-((4- aminocyclohexyl)methyl)benzamide), and RI3543 (2-([1,1'-biphenyl]-2-ylmethyl)-4-(piperidin-3- yloxy)benzamide). The final molecules identified exhibit a strong affinity for SYK, attributed to their structural diversity and notable pharmacophoric characteristics. All-atom MD simulations showed that each final molecule retained significant binding interactions with SYK and stability in dynamic states, indicating their potential as anticancer agents. Calculated binding free energy for selected molecules using molecular mechanics with generalized Born and surface area (MMGBSA) ranged from -6 to -35 kcal/mol, indicating strong SYK affinity.
CONCLUSION: In conclusion, the integration of AI and physics-based methods successfully developed promising SYK inhibitors with significant potential. The molecules reported could be vital anticancer agents subjected to experimental validation.
METHODS: A thorough combination of machine learning (ML) and physics-based methods was employed to achieve these goals, encompassing de novo design, multitier molecular docking, absolute binding affinity computation, and molecular dynamics (MD) simulation.
RESULTS: A total of 5576 novel molecules with key pharmacophoric features were generated using an ML-driven de novo approach against 21 diaminopyrimidine carboxamide analogs. Pharmacokinetic and toxicity evaluation assisted by the ML approach revealed that 4353 chemical entities fulfilled the acceptable pharmacokinetic and toxicity profiles. By screening through binding energy threshold from the physics-based multitier molecular docking, and ML-assisted absolute binding affinity identified the top four molecules such as RI809 (2-([1,1'-biphenyl]-3-ylmethyl)-4-((2- aminocyclohexyl)oxy)benzamide), RI1393 (4-((2-aminocyclohexyl)amino)-2-(3-(1-methyl-1Hpyrazol- 5-yl)-4-(trifluoromethyl)benzyl)benzamide), RI2765 (2-([1,1'-biphenyl]-3-ylmethyl)-4-((4- aminocyclohexyl)methyl)benzamide), and RI3543 (2-([1,1'-biphenyl]-2-ylmethyl)-4-(piperidin-3- yloxy)benzamide). The final molecules identified exhibit a strong affinity for SYK, attributed to their structural diversity and notable pharmacophoric characteristics. All-atom MD simulations showed that each final molecule retained significant binding interactions with SYK and stability in dynamic states, indicating their potential as anticancer agents. Calculated binding free energy for selected molecules using molecular mechanics with generalized Born and surface area (MMGBSA) ranged from -6 to -35 kcal/mol, indicating strong SYK affinity.
CONCLUSION: In conclusion, the integration of AI and physics-based methods successfully developed promising SYK inhibitors with significant potential. The molecules reported could be vital anticancer agents subjected to experimental validation.