Scholarlink

Generative Adversarial Networks (GANs) are used in drug discovery by offering a computational framework to generate novel molecular structures with preferred properties. This paper highlights GANs’ role in accelerating de novo drug design, enhancing virtual screening, and addressing data scarcity challenges. Evaluating chemical validity, diversity, and bioactivity prediction, GANs provide a versatile platform for generating molecules that align with pharmaceutical requirements. This paper emphasizes the ethical considerations, stability, and interpretability of GAN-generated structures, positioning GANs as a transformative force in reshaping and expediting drug discovery processes. The use of GANs in drug discovery holds promise for accelerating the identification of lead compounds, optimizing existing molecules, and exploring new avenues in pharmaceutical research. We have effectively tested our proposed model with various parameters to obtain the usability and efficiency.

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

Generative Adversarial Networks (GANs) for Drug Discovery

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Kiran Sree Pokkuluri,
  • Ramesh Babu Gurujukota,
  • Phaneendra Varma Chintalapati,
  • P. B. V. Raja Rao,
  • P. J. R. Shalem Raju,
  • Maddula Prasad,
  • N. SSSN Usha Devi,
  • Poppoppula T. Satyanarayana Murthy

摘要

Generative Adversarial Networks (GANs) are used in drug discovery by offering a computational framework to generate novel molecular structures with preferred properties. This paper highlights GANs’ role in accelerating de novo drug design, enhancing virtual screening, and addressing data scarcity challenges. Evaluating chemical validity, diversity, and bioactivity prediction, GANs provide a versatile platform for generating molecules that align with pharmaceutical requirements. This paper emphasizes the ethical considerations, stability, and interpretability of GAN-generated structures, positioning GANs as a transformative force in reshaping and expediting drug discovery processes. The use of GANs in drug discovery holds promise for accelerating the identification of lead compounds, optimizing existing molecules, and exploring new avenues in pharmaceutical research. We have effectively tested our proposed model with various parameters to obtain the usability and efficiency.