Machine learning prediction of 18 date palm polyphenol protection against biomolecular damage

This study investigated the diverse antioxidant and enzyme-inhibiting properties of 18 date palm cultivars, correlating these bioactivities with polyphenol profiles using biochemical methods and machine learning (ML). Maktoomi exhibited the highest phenolic content (759.42 mg GAE/100g), while Fard s...

Full description

Saved in:
Bibliographic Details
Main Authors: Nashi K. Alqahtani, Tareq M. Alnemr, Rania Ismail, Hosam M. Habib
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Journal of Agriculture and Food Research
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666154325003904
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849254449198923776
author Nashi K. Alqahtani
Tareq M. Alnemr
Rania Ismail
Hosam M. Habib
author_facet Nashi K. Alqahtani
Tareq M. Alnemr
Rania Ismail
Hosam M. Habib
author_sort Nashi K. Alqahtani
collection DOAJ
description This study investigated the diverse antioxidant and enzyme-inhibiting properties of 18 date palm cultivars, correlating these bioactivities with polyphenol profiles using biochemical methods and machine learning (ML). Maktoomi exhibited the highest phenolic content (759.42 mg GAE/100g), while Fard showed strong ferric-reducing antioxidant power (FRAP) activity (2456.13 mmol/100g). Significant enzyme inhibition variation was observed, Jabri (8.69 % AChE inhibition), Shikat alkahlas (21.06 % α-amylase inhibition), and Barhe (51.39 % tyrosinase inhibition). Maghool provided the highest protein protection (95–100 % BSA). These bioactivity data were integrated into an extreme gradient boosting (XGBoost) ML model to connect chemical features with experimental outcomes. The model demonstrated high predictive capability (R2 ∼ 0.9–0.95) for amylase, acetylcholine, and 2,2-diphenyl-1-picrylhydrazyl (DPPH) assays, but lower values (R2 < 0.9) for more complex assays involving DNA or superoxide systems, indicating data quality limitations. This highlights targeted method improvements. These findings demonstrate that certain date components offer higher specific bioactivity, and the ML approach validates these methods, revealing benefits and limitations. Date extracts possess therapeutic potential, and the combined approach of experimental testing and ML mapping provides a framework for multi-parameter analysis of complex biological systems. However, further in-vivo validation is needed.
format Article
id doaj-art-3cb6f249ec434ff4ad9d4b090fe026cd
institution Kabale University
issn 2666-1543
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Journal of Agriculture and Food Research
spelling doaj-art-3cb6f249ec434ff4ad9d4b090fe026cd2025-08-20T03:56:04ZengElsevierJournal of Agriculture and Food Research2666-15432025-08-012210201910.1016/j.jafr.2025.102019Machine learning prediction of 18 date palm polyphenol protection against biomolecular damageNashi K. Alqahtani0Tareq M. Alnemr1Rania Ismail2Hosam M. Habib3Department of Food and Nutrition Sciences, College of Agricultural and Food Sciences, King Faisal University, P.O. Box 400, Al-Ahsa, 31982, Saudi Arabia; Date Palm Research Center of Excellence, King Faisal University, P.O. Box 400, Al-Ahsa, 31982, Saudi ArabiaDepartment of Food and Nutrition Sciences, College of Agricultural and Food Sciences, King Faisal University, P.O. Box 400, Al-Ahsa, 31982, Saudi ArabiaFaculty of Computer Science &amp; Engineering, Alamein International University (AIU), Alameen City, 5060310, EgyptResearch &amp; Innovation Hub, Alamein International University (AIU), Alameen City, 5060310, Egypt; Corresponding author.This study investigated the diverse antioxidant and enzyme-inhibiting properties of 18 date palm cultivars, correlating these bioactivities with polyphenol profiles using biochemical methods and machine learning (ML). Maktoomi exhibited the highest phenolic content (759.42 mg GAE/100g), while Fard showed strong ferric-reducing antioxidant power (FRAP) activity (2456.13 mmol/100g). Significant enzyme inhibition variation was observed, Jabri (8.69 % AChE inhibition), Shikat alkahlas (21.06 % α-amylase inhibition), and Barhe (51.39 % tyrosinase inhibition). Maghool provided the highest protein protection (95–100 % BSA). These bioactivity data were integrated into an extreme gradient boosting (XGBoost) ML model to connect chemical features with experimental outcomes. The model demonstrated high predictive capability (R2 ∼ 0.9–0.95) for amylase, acetylcholine, and 2,2-diphenyl-1-picrylhydrazyl (DPPH) assays, but lower values (R2 < 0.9) for more complex assays involving DNA or superoxide systems, indicating data quality limitations. This highlights targeted method improvements. These findings demonstrate that certain date components offer higher specific bioactivity, and the ML approach validates these methods, revealing benefits and limitations. Date extracts possess therapeutic potential, and the combined approach of experimental testing and ML mapping provides a framework for multi-parameter analysis of complex biological systems. However, further in-vivo validation is needed.http://www.sciencedirect.com/science/article/pii/S2666154325003904Polyphenol profilingBioactive compoundsIn Silico screeningPredictive modelingOxidative stress mitigationNutraceutical development
spellingShingle Nashi K. Alqahtani
Tareq M. Alnemr
Rania Ismail
Hosam M. Habib
Machine learning prediction of 18 date palm polyphenol protection against biomolecular damage
Journal of Agriculture and Food Research
Polyphenol profiling
Bioactive compounds
In Silico screening
Predictive modeling
Oxidative stress mitigation
Nutraceutical development
title Machine learning prediction of 18 date palm polyphenol protection against biomolecular damage
title_full Machine learning prediction of 18 date palm polyphenol protection against biomolecular damage
title_fullStr Machine learning prediction of 18 date palm polyphenol protection against biomolecular damage
title_full_unstemmed Machine learning prediction of 18 date palm polyphenol protection against biomolecular damage
title_short Machine learning prediction of 18 date palm polyphenol protection against biomolecular damage
title_sort machine learning prediction of 18 date palm polyphenol protection against biomolecular damage
topic Polyphenol profiling
Bioactive compounds
In Silico screening
Predictive modeling
Oxidative stress mitigation
Nutraceutical development
url http://www.sciencedirect.com/science/article/pii/S2666154325003904
work_keys_str_mv AT nashikalqahtani machinelearningpredictionof18datepalmpolyphenolprotectionagainstbiomoleculardamage
AT tareqmalnemr machinelearningpredictionof18datepalmpolyphenolprotectionagainstbiomoleculardamage
AT raniaismail machinelearningpredictionof18datepalmpolyphenolprotectionagainstbiomoleculardamage
AT hosammhabib machinelearningpredictionof18datepalmpolyphenolprotectionagainstbiomoleculardamage