Flavoromics integrated with machine learning to elucidate key aroma compounds in aroma-directed chili peppers and predict sensory quality

Sep 29, 2026

Improving chili pepper aroma quality is essential for industry transformation and high-value development. The complex volatile composition and its quantitative relationship with sensory quality limit targeted breeding of aroma-directed varieties. This work integrates quantitative descriptive analysis, E-nose, and HS-SPME-GC-MS with chemometrics, OAV values, and machine learning to compare aroma-directed and commercial peppers. It identifies key aroma compounds and builds an AWCR model linking them to sensory attributes, improving prediction accuracy and providing breeding targets.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Contents lists available at ScienceDirect

Current Research in Food Science

Current Research in Food Science 12 (2026) 101274 Contents lists available at ScienceDirect Current Research in Food Science journal [homepage:](homepage: www.sciencedirect.com/journal/current-research-in-food-science)[ www.sciencedirect.com/journal/current-research-in-food-science](homepage: www.sciencedirect.com/journal/current-research-in-food-science) | Flavoromics integrated with machine learning to elucidate key aroma compounds in aroma-directed chili peppers and predict sensory quality
Ziyang Wu a,b,d,e,1, Hang Wei a,1, Yinhui Qiuc, Ruiru Sia, Baoyu Konga, Ling Fanga,
Huiling Wengb,d,e, Weiming Lia,b,d,e, Jianwei Fu a,*
a Institute of Quality Standards and Testing Technology for Agro-Products, Fujian Key Laboratory of Agro-Products Quality and Safety, Fujian Academy of Agricultural Sciences, Fuzhou, 350003, China
b College of Food Science, Fujian Agriculture and Forestry University, Fuzhou, 350002, China
c Sanming Academy of Agricultural Sciences, Fujian Key Laboratory of Crop Genetic Improvement and Innovative Utilization for Mountain Area, Sanming, 365509, China
d Fujian Provincial Key Laboratory of Quality Science and Processing Technology in Special Starch, Fujian Agriculture and Forestry University, Fuzhou, 350002, China e Engineering Research Centre of Fujian-Taiwan Special Marine Food Processing and Nutrition (Ministry of Education), Fujian Agriculture and Forestry University, Fuzhou, 350002, China | | | | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | Handling Editor: Professor Aiqian Ye | | Improving chili pepper aroma quality is essential for industry transformation and high-value development. However, the complex volatile composition and its quantitative relationship with sensory quality remains unresolved, limiting targeted breeding of aroma-directed varieties. This study employed quantitative descriptive analysis, E-nose, and HS-SPME-GC-MS combined with chemometrics, OAV values, and machine learning to systematically analyze aroma differences between three aroma-directed (MJ7, MJ8, MJ9) and three commercial chili peppers. Aroma-directed varieties significantly outperformed traditional peppers in fruity, floral, and sweet attributes, with MJ7 achieving a floral score of 8.44 and MJ9 a fruity score of 8.16. Among 202 identified volatile components, aroma-directed peppers predominantly contained esters and ketones, while traditional varieties were alkane-rich. OPLS-DA identified characteristic compounds including β-caryophyllene and 2-methylcarbazole, with 30 key aroma compounds identified through OAV-based quantification. An Adaptive Weighted Consensus Regression (AWCR) model established quantitative relationships between key compounds and sensory attributes, showing 33.3 % improved prediction accuracy over single machine learning approaches. Feature importance analysis revealed phenylacetaldehyde as the core compound for fruity aroma and linalool for floral notes, providing precise targets for molecular breeding of aroma-directed chili peppers. | | Keywords:
Chili pepper Flavoromics
Key aroma compounds Machine learning Sensory prediction Breeding target screening | | | 1. Introduction Chili pepper (Capsicum spp.), as an important spice crop with extensive global cultivation area and high economic value, is highly favored by consumers for its unique pungent taste, rich nutritional components, and diverse culinary applications (Salehi et al., 2018). Fora long time, chili pepper research has primarily focused on agronomic traits such as yield, stress resistance, fruit morphology, and pungency, which have dominated the selection direction and quality evaluation standards in chili pepper breeding (Stoleru et al., 2023). However, with the transformation and upgrading of global consumer markets and the refinement of people’s sensory preferences, consumer expectations for chili pepper quality have gradually shifted from pursuing “pungency stimulation” to

FAQs

How does the study connect chili pepper aroma volatiles with sensory quality?

It combines HS-SPME-GC-MS and E-nose data with chemometrics and OAV-based quantification, then uses machine learning to relate key compounds to sensory attributes.

What differences in aroma attributes were observed between aroma-directed and traditional chili peppers?

Aroma-directed varieties scored higher in fruity, floral, and sweet attributes, with MJ7 reaching a floral score of 8.44 and MJ9 a fruity score of 8.16.

Which compounds were identified as core drivers for specific aroma notes?

Feature importance analysis highlighted phenylacetaldehyde as the core compound for fruity aroma and linalool for floral notes.

Sep 29, 2026

Upload by McGucket