Scholarlink

<p>Potency (IC<sub>50</sub>) prediction of small molecules is pivotal for anticancer drug development. This study benchmarked five deep learning (DL) models for IC<sub>50</sub> prediction—DeepCDR, DrugCell, PaccMann, Precily, and tCNN—against a simple mean-based Baseline using standardized GDSC datasets and recently published anticancer compounds. To ensure practicality, conventional error metrics were supplemented with percentage error, log error, three-sigma limit, and a newly proposed Experimental Variability-Aware Prediction Accuracy statistic. The models performed well on randomly split data and unseen cell lines but showed sharply reduced accuracy for unseen compounds. Though all DL models exhibited similar performance trends, DeepCDR, DrugCell, and tCNN held a slight edge in most testing scenarios. Interestingly, several DL algorithms could not significantly outperform the Baseline model in many tests. Assessing prediction error against physicochemical and biological properties of compounds and cell lines revealed weak correlation, highlighting an underexplored aspect of model performance. A user-friendly web server (<a href="https://nlplab1.isical.ac.in/ic50.php">https://nlplab1.isical.ac.in/ic50.php</a>) was also developed for IC<sub>50</sub> prediction of new compounds against cancer cell lines.</p><p></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

Benchmarking deep learning models for predicting anticancer drug potency (IC50) with insights for medicinal chemists

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月29日

查看全文
  • Udbhas Garai,
  • Aditya S. Pal,
  • Koyel Ghosh,
  • Deepak B. Salunke,
  • Utpal Garain

摘要

Potency (IC50) prediction of small molecules is pivotal for anticancer drug development. This study benchmarked five deep learning (DL) models for IC50 prediction—DeepCDR, DrugCell, PaccMann, Precily, and tCNN—against a simple mean-based Baseline using standardized GDSC datasets and recently published anticancer compounds. To ensure practicality, conventional error metrics were supplemented with percentage error, log error, three-sigma limit, and a newly proposed Experimental Variability-Aware Prediction Accuracy statistic. The models performed well on randomly split data and unseen cell lines but showed sharply reduced accuracy for unseen compounds. Though all DL models exhibited similar performance trends, DeepCDR, DrugCell, and tCNN held a slight edge in most testing scenarios. Interestingly, several DL algorithms could not significantly outperform the Baseline model in many tests. Assessing prediction error against physicochemical and biological properties of compounds and cell lines revealed weak correlation, highlighting an underexplored aspect of model performance. A user-friendly web server (https://nlplab1.isical.ac.in/ic50.php) was also developed for IC50 prediction of new compounds against cancer cell lines.