Scholarlink

Discovery of drugs has already been advanced with AI and ML, that have made substantial advances in a few scientific domains, including CADD. DL is excellent at predicting medication qualities, analysing chemical structures, and improving molecular design, particularly when combined with CNNs. Drug interactions are predicted by AI-driven models, which also offer information on possible side effects or synergy. AI models find novel therapeutic applications for current medications by examining large datasets of pharmacological characteristics and clinical results. ML is useful for QSAR models, which uses molecule’s chemical structure for predicting biological activity of the drug. AI speeds up screening large chemical libraries at high throughput, cutting down on the duration of time required to locate possible therapeutic volunteers. AI also helps in creating new therapeutic compounds from the ground up, guaranteeing the necessary qualities while reducing adverse effects. Even with bright futures, issues like interpretability, overfitting, data quality, and computational resource requirements still exist. In conclusion, AI and ML are revolutionizing drug research and advancing the goal of safer, more individualized, and more effective medications.

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

Advances in the Computational Prediction of Absorption Prediction of Pharmaceuticals

  • 章节

  • 发表日期：

    2025年

查看全文
  • Saba Wahid A. M. Khan,
  • Aditi Pandey,
  • Somesh Mishra,
  • Roja Rani Budha,
  • S. N. Koteswara Rao G.

摘要

Discovery of drugs has already been advanced with AI and ML, that have made substantial advances in a few scientific domains, including CADD. DL is excellent at predicting medication qualities, analysing chemical structures, and improving molecular design, particularly when combined with CNNs. Drug interactions are predicted by AI-driven models, which also offer information on possible side effects or synergy. AI models find novel therapeutic applications for current medications by examining large datasets of pharmacological characteristics and clinical results. ML is useful for QSAR models, which uses molecule’s chemical structure for predicting biological activity of the drug. AI speeds up screening large chemical libraries at high throughput, cutting down on the duration of time required to locate possible therapeutic volunteers. AI also helps in creating new therapeutic compounds from the ground up, guaranteeing the necessary qualities while reducing adverse effects. Even with bright futures, issues like interpretability, overfitting, data quality, and computational resource requirements still exist. In conclusion, AI and ML are revolutionizing drug research and advancing the goal of safer, more individualized, and more effective medications.