Scholarlink

<p>There is a paucity of work on the integration of light-weight predictive models with diversified screening datasets, coupled with computational validation, for anti-malaria activity-prediction. To bridge these gaps, we trained predictive models (Random Forest (RF) classifier and XGBoost classifier) using public data from ChEMBL and PubChem. The RF (AUC = 0.912) was used to classify ~ 1.9 million compounds from the drug-bank, natural-products and Enamine-Real databases into actives or inactives. The predicted actives were validated using docking and molecular dynamics against high-priority <i>Plasmodium falciparum</i> targets. Free energy calculations (MMGBSA; kcal/mol) revealed compounds EN52 (− 48.05 ± 3.91) and NP83 (− 52.67 ± 4.43) that are energetically more favored than the co-crystalized ligands, WLK (− 35.05 ± 3.47) and MMV (− 43.08 ± 3.14) for PfPKG and F/GGPPS proteins, respectively. We deployed Mal-Predict, a tool to classify compounds as actives (or inactive), and further predict vina-scores for select <i>P. falciparum</i> protein targets. These findings would support prioritizing candidates for further anti-malaria activity investigations in early-stage drug discovery for researchers.</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

Machine learning-guided rapid virtual screening and molecular dynamics validation of compounds against select Plasmodium falciparum targets

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月5日

查看全文
  • Shadrach C. Eze,
  • Munachiso C. Elekwa,
  • Wande M. Oluyemi,
  • Adeniyi T. Adewumi,
  • Onyebuchi O. Offor,
  • Stephen C. Nnemolisa,
  • Phoebe T. Osunbumi,
  • Shalom O. Adeyemi,
  • Salerwe Mosebi

摘要

There is a paucity of work on the integration of light-weight predictive models with diversified screening datasets, coupled with computational validation, for anti-malaria activity-prediction. To bridge these gaps, we trained predictive models (Random Forest (RF) classifier and XGBoost classifier) using public data from ChEMBL and PubChem. The RF (AUC = 0.912) was used to classify ~ 1.9 million compounds from the drug-bank, natural-products and Enamine-Real databases into actives or inactives. The predicted actives were validated using docking and molecular dynamics against high-priority Plasmodium falciparum targets. Free energy calculations (MMGBSA; kcal/mol) revealed compounds EN52 (− 48.05 ± 3.91) and NP83 (− 52.67 ± 4.43) that are energetically more favored than the co-crystalized ligands, WLK (− 35.05 ± 3.47) and MMV (− 43.08 ± 3.14) for PfPKG and F/GGPPS proteins, respectively. We deployed Mal-Predict, a tool to classify compounds as actives (or inactive), and further predict vina-scores for select P. falciparum protein targets. These findings would support prioritizing candidates for further anti-malaria activity investigations in early-stage drug discovery for researchers.