A Reproducible Multi-Target Computational Framework for Prioritizing Plant-Derived Natural Products in Alzheimer’s Disease

Alzheimer’s disease (AD) is biologically heterogeneous, and plant-derived natural products provide chemically diverse starting points for multi-target discovery. Reproducible prioritization is needed to distinguish literature-supported evidence from candidate-specific predictions not yet generated. Our objective was to develop a reproducible, evidence-informed framework for prioritizing plant-derived natural products in AD and define a transparent candidate library and prespecified screening set for subsequent computational and experimental evaluation. Completed work included selection of an AD target panel (AChE/BChE, BACE1, GSK-3β and MAO-B), synthesis of a published target-specific machine-learning (ML) benchmark, curation of a 20-compound candidate library with traceable chemical identities and literature support, and selection of a 13-compound prespecified screening set. Published performance metrics were treated solely as external benchmark evidence. Study-specific model training, prospective ML screening, molecular docking, BBB/drug-likeness and ADMET evaluation, multi-objective ranking, and experimental validation were prespecified as future work and were not performed. The framework links mechanistically justified targets, published ML benchmarks, a chemically diverse 20-compound library, and a 13-compound set for future screening. The library includes evidence-rich reference compounds and comparatively underexplored scaffolds; no candidate-specific computational ranking or selection outcome is reported. This study presents an evidence-informed, multi-target computational framework for prioritizing plant-derived natural products in Alzheimer’s disease. Its methodological contribution lies in integrating a mechanistically defined target panel, published machine-learning benchmarks, a traceable 20-compound candidate library, and a prespecified 13-compound screening set within a transparent prospective evaluation strategy. By distinguishing completed framework-development activities from future computational and experimental analyses, the study establishes a structured foundation for subsequent model validation, multi-objective prioritization, and experimental investigation.

Authors

Institutions

Publication Details

Journal
Biophysica
Published
2026-11-13
DOI
https://doi.org/10.3390/biophysica6060113
Primary Topic
Computational Drug Discovery Methods
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Reproducible Multi-Target Computational Framework for Prioritizing Plant-Derived Natural Products in Alzheimer’s Disease

Eman S. Allahyani
3 links
Biophysica
Computational Drug Discovery Methods
article

A Reproducible Multi-Target Computational Framework for Prioritizing Plant-Derived Natural Products in Alzheimer’s Disease

Eman S. Allahyani
article en

Abstract

Alzheimer’s disease (AD) is biologically heterogeneous, and plant-derived natural products provide chemically diverse starting points for multi-target discovery. Reproducible prioritization is needed to distinguish literature-supported evidence from candidate-specific predictions not yet generated. Our objective was to develop a reproducible, evidence-informed framework for prioritizing plant-derived natural products in AD and define a transparent candidate library and prespecified screening set for subsequent computational and experimental evaluation. Completed work included selection of an AD target panel (AChE/BChE, BACE1, GSK-3β and MAO-B), synthesis of a published target-specific machine-learning (ML) benchmark, curation of a 20-compound candidate library with traceable chemical identities and literature support, and selection of a 13-compound prespecified screening set. Published performance metrics were treated solely as external benchmark evidence. Study-specific model training, prospective ML screening, molecular docking, BBB/drug-likeness and ADMET evaluation, multi-objective ranking, and experimental validation were prespecified as future work and were not performed. The framework links mechanistically justified targets, published ML benchmarks, a chemically diverse 20-compound library, and a 13-compound set for future screening. The library includes evidence-rich reference compounds and comparatively underexplored scaffolds; no candidate-specific computational ranking or selection outcome is reported. This study presents an evidence-informed, multi-target computational framework for prioritizing plant-derived natural products in Alzheimer’s disease. Its methodological contribution lies in integrating a mechanistically defined target panel, published machine-learning benchmarks, a traceable 20-compound candidate library, and a prespecified 13-compound screening set within a transparent prospective evaluation strategy. By distinguishing completed framework-development activities from future computational and experimental analyses, the study establishes a structured foundation for subsequent model validation, multi-objective prioritization, and experimental investigation.

BiophysicaVol. 6(6)
Umm al-Qura University (SA)
Good health and well-being
Computational Drug Discovery Methods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon