Scholarlink

Background <p>Recent progress in molecular biology and information technology has driven significant advancements in molecular simulations, benefiting systems biology, proteomics, bioinformatics, and materials science. Computational methods have long played a role in drug development; however, the past few years have seen a paradigm shift in their adoption. This transformation is fueled by the growing availability of ligand-binding data, high-resolution protein 3D structures, vast computational resources, and libraries of billions of virtual drug-like molecules. Artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), has further revolutionized computer-aided drug design (CADD), enabling the exploration of novel targets, including previously “undruggable” proteins.</p> Main body of the abstract <p>The application of ML algorithms in drug development has become widespread, supported by advancements in computer hardware, software, and data integration techniques. These tools allow more efficient exploration of complex biological interactions and target-specific drug discovery. This review highlights recent advancements in targeting undruggable proteins, representing one of the most significant challenges in drug discovery. Undruggable proteins often lack well-defined binding sites or exhibit structural properties that evade conventional drug design strategies. I examine several innovative approaches addressing these challenges: covalent regulation, allosteric inhibition, disruption of protein–protein and protein-d-DNA interactions, targeted protein degradation, nucleic acid-based therapies, and immunotherapeutic strategies. Each methodology offers unique advantages for modulating undruggable proteins and advancing them toward clinical application. Additionally, we discuss how advancements in AI and computational tools streamline the discovery process by enabling virtual screening, predictive modeling, and structural optimization of drug candidates.</p> Short conclusion <p>The integration of computational methods with AI and ML technologies has revitalized drug discovery, particularly for undruggable targets. These innovations hold tremendous promise for overcoming long-standing challenges in therapeutic development. By combining advanced methodologies and computational resources, the field is rapidly progressing toward creating effective treatments for complex diseases.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Advancing drug discovery: the role of computer-aided design and development in modern pharmaceuticals

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月5日

查看全文
  • Adhi kesava Naidu Neelam

摘要

Background

Recent progress in molecular biology and information technology has driven significant advancements in molecular simulations, benefiting systems biology, proteomics, bioinformatics, and materials science. Computational methods have long played a role in drug development; however, the past few years have seen a paradigm shift in their adoption. This transformation is fueled by the growing availability of ligand-binding data, high-resolution protein 3D structures, vast computational resources, and libraries of billions of virtual drug-like molecules. Artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), has further revolutionized computer-aided drug design (CADD), enabling the exploration of novel targets, including previously “undruggable” proteins.

Main body of the abstract

The application of ML algorithms in drug development has become widespread, supported by advancements in computer hardware, software, and data integration techniques. These tools allow more efficient exploration of complex biological interactions and target-specific drug discovery. This review highlights recent advancements in targeting undruggable proteins, representing one of the most significant challenges in drug discovery. Undruggable proteins often lack well-defined binding sites or exhibit structural properties that evade conventional drug design strategies. I examine several innovative approaches addressing these challenges: covalent regulation, allosteric inhibition, disruption of protein–protein and protein-d-DNA interactions, targeted protein degradation, nucleic acid-based therapies, and immunotherapeutic strategies. Each methodology offers unique advantages for modulating undruggable proteins and advancing them toward clinical application. Additionally, we discuss how advancements in AI and computational tools streamline the discovery process by enabling virtual screening, predictive modeling, and structural optimization of drug candidates.

Short conclusion

The integration of computational methods with AI and ML technologies has revitalized drug discovery, particularly for undruggable targets. These innovations hold tremendous promise for overcoming long-standing challenges in therapeutic development. By combining advanced methodologies and computational resources, the field is rapidly progressing toward creating effective treatments for complex diseases.