Scholarlink

Drug resistance in Plasmodium is a significant issue for the present antimalarial drugs. Designing and modifying antimalarial drugs by estimating the activity of the compounds is a key function of quantitative structure–activity relationship (QSAR) modeling. In this study, we used convolutional neural network architecture to develop QSAR model on imidazolopiperazine analog series to identify hit molecules against malaria. The statistical results showed the value of the test dataset’s predicted correlation coefficient R2 of 0.81, mean squared error of 0.43, and mean absolute error MAE of 0.61. Our CNN-based QSAR model predicted biological activity (pIC50) values in between 5.00 to 9.00 for natural product NCI diversity set IV and FDA-Approved drugs. As a result, this research opens up new perspectives for developing the CNN-based QSAR model provides small molecule therepeuitcs for malaria.

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

Development of Convolutional Neural Network-Based Quantitative Structure–Activity Relationship Model of Imidazolopiperazines to Identify Drug Candidates Against Malaria

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Madhulata Kumari,
  • Jesus Eduardo Lugo,
  • Jocelyn Faubert,
  • Khashayar Misaghian,
  • Kanad Ray

摘要

Drug resistance in Plasmodium is a significant issue for the present antimalarial drugs. Designing and modifying antimalarial drugs by estimating the activity of the compounds is a key function of quantitative structure–activity relationship (QSAR) modeling. In this study, we used convolutional neural network architecture to develop QSAR model on imidazolopiperazine analog series to identify hit molecules against malaria. The statistical results showed the value of the test dataset’s predicted correlation coefficient R2 of 0.81, mean squared error of 0.43, and mean absolute error MAE of 0.61. Our CNN-based QSAR model predicted biological activity (pIC50) values in between 5.00 to 9.00 for natural product NCI diversity set IV and FDA-Approved drugs. As a result, this research opens up new perspectives for developing the CNN-based QSAR model provides small molecule therepeuitcs for malaria.