Scholarlink

<p>Bowel cancer remains a major cause of cancer-related mortality, underscoring the need for improved computational tools to support drug discovery and therapeutic prioritization. This study presents a hybrid fuzzy computational framework that integrates Fuzzy Artificial Neural Networks (Fuzzy ANNs) with the Fuzzy Analytic Hierarchy Process (Fuzzy AHP) to predict anticancer drug properties and rank potential therapeutic candidates. Fuzzy ANNs were employed to model nonlinear relationships between molecular descriptors and anticancer activity, leveraging fuzzy logic to address uncertainty and ambiguity in pharmacological data. The optimized model demonstrated strong predictive performance, achieving an <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(R^2=0.92\)</EquationSource> </InlineEquation> and RMSE = 0.18, outperforming the baseline ANN. To complement property prediction, Fuzzy AHP was used to rank candidate drugs under multi-criteria decision-making settings, incorporating efficacy, toxicity, and pharmacokinetic parameters. Consistency and robustness of the ranking process were confirmed using sensitivity analysis, with all comparison matrices satisfying <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(CR&lt;0.1\)</EquationSource> </InlineEquation>. The combined strengths of Fuzzy ANNs in prediction and Fuzzy AHP in prioritization offer a unified and interpretable strategy for evaluating anticancer compounds under uncertain or incomplete data conditions. This hybrid fuzzy model provides a promising direction for accelerating computational drug assessment in oncology, particularly for bowel cancer, where reliable decision-support systems are essential for guiding early-stage therapeutic development.</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

A Soft Computing Strategy Combining Fuzzy Analytic Hierarchy and Fuzzy Artificial Neural Networks for Predictive Modeling and Therapeutic Ranking in Bowel Cancer Drug Development

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月19日

查看全文
  • Wakeel Ahmed,
  • Amman Farzeen,
  • Ghulamullah Saeedi,
  • Shahid Zaman,
  • Kashif Ali,
  • Emad E. Mahmoud

摘要

Bowel cancer remains a major cause of cancer-related mortality, underscoring the need for improved computational tools to support drug discovery and therapeutic prioritization. This study presents a hybrid fuzzy computational framework that integrates Fuzzy Artificial Neural Networks (Fuzzy ANNs) with the Fuzzy Analytic Hierarchy Process (Fuzzy AHP) to predict anticancer drug properties and rank potential therapeutic candidates. Fuzzy ANNs were employed to model nonlinear relationships between molecular descriptors and anticancer activity, leveraging fuzzy logic to address uncertainty and ambiguity in pharmacological data. The optimized model demonstrated strong predictive performance, achieving an \(R^2=0.92\) and RMSE = 0.18, outperforming the baseline ANN. To complement property prediction, Fuzzy AHP was used to rank candidate drugs under multi-criteria decision-making settings, incorporating efficacy, toxicity, and pharmacokinetic parameters. Consistency and robustness of the ranking process were confirmed using sensitivity analysis, with all comparison matrices satisfying \(CR<0.1\) . The combined strengths of Fuzzy ANNs in prediction and Fuzzy AHP in prioritization offer a unified and interpretable strategy for evaluating anticancer compounds under uncertain or incomplete data conditions. This hybrid fuzzy model provides a promising direction for accelerating computational drug assessment in oncology, particularly for bowel cancer, where reliable decision-support systems are essential for guiding early-stage therapeutic development.