From 2015 to 2023 - How Machine Learning Aids Natural Product Analysis

Aug 3, 2026

Upload by Oliver

From 2015 to 2023, conventional chemistry faces constraints in handling the rising complexity and data volume in contemporary research. Computational methodologies provide scalable tools that enable machine-learning models to produce more informative analytical results. This review surveys computational strategies for natural product analysis and proposes a research framework addressing both qualitative and quantitative chemistry problems. The work aims to present a new perspective on the synergy between machine learning and chemistry to drive advancement in the field.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Abstract

Introduction

Natural products and analytical evolution

Machine learning methods in natural product analysis

Role of analytical instruments

From 2015 to 2023: How Machine Learning Aids Natural Product Analysis Suwen Shi 1, *,Ziwei Huang2, Xingxin Gu3, Xu Lin4, Chaoying Zhong5, Junjie Hang6, Jianli Lin7, Claire Chenwen Zhong8, Lin Zhang9, Yu Li 10, Junjie Huang8, * 1. Department of Chemistry, Boston University, Boston, Massachusetts, 02215 United States 2. Department of Physics, Boston University, Boston, Massachusetts, 02215 United States 3. College of Professional Studies, Northeastern University, Boston, Massachusetts, 02215 United States 4. Department of Thoracic Surgery, The First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang , China 5. Department of Electrical Engineering and Automation, Guangdong Ocean University, Guangdong, China 6. Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Guangdong, China. 7. Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China. 8. The Jockey Club School of Public Health and Primary Care, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong SAR, China 9. Suzhou Industrial Park Monash Research Institute of Science and Technology, Suzhou, China 10. Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China Author emails: Suwen Shi: [swshi@bu.edu](swshi@bu.edu),Ziwei Huang: [ziwhuang@bu.edu](ziwhuang@bu.edu), Xingxin Gu: [gu.xingx@northeastern.edu](gu.xingx@northeastern.edu), Xu Lin: [linxu_001@zju.edu.cn](linxu_001@zju.edu.cn), Chaoying Zhong: [zhongcy3@163.com](zhongcy3@163.com), [Junjie Hang: ](Junjie Hang: hjj199141@alumni.sjtu.edu.cn)[hjj199141@alumni.sjtu.edu.cn](Junjie Hang: hjj199141@alumni.sjtu.edu.cn), Jianli Lin: [ljl1501@stu.pku.edu.cn](ljl1501@stu.pku.edu.cn), Claire Chenwen Zhong: [chenwenzhong@cukh.edu.hk](chenwenzhong@cukh.edu.hk), Lin Zhang: [tony1982110@gmail.com](tony1982110@gmail.com), Yu Li: [liyu@cse.cuhk.edu.hk](liyu@cse.cuhk.edu.hk), Junjie Huang: [j](junjiehuang@cuhk.edu.hk)[unjiehuang@cuhk.edu.hk](junjiehuang@cuhk.edu.hk) *Correspondence: Suwen Shi, Department of Chemistry, Boston University; Tel: (857) 445 8290; Email: [swshi@bu.edu](swshi@bu.edu); Address: 590 Commonwealth Ave \# 299, Boston, Massachusetts, 02215 United States Junjie Huang, The Jockey Club School of Public Health and Primary Care, Faculty of Medicine, Chinese University of Hong Kong; Tel: (852) 2252 8707; Email: [j](junjiehuang@cuhk.edu.hk)[unjiehuang@cuhk.edu.hk](junjiehuang@cuhk.edu.hk); Address: 5/F, School of Public Health, Prince of Wales Hospital, Hong Kong Conflict of interests: None Funding: None Abstract In recent years, conventional chemistry techniques have faced significant challenges due to their inherent limitations, struggling to cope with the increasing complexity and volume of data generated in contemporary research endeavors. Computational methodologies represent robust tools in the field of chemistry, offering the capacity to harness potent machine-learning models to yield insightful analytical outcomes. This review delves into the spectrum of computational strategies available for natural product analysis and constructs a research framework for investigating both qualitative and quantitative chemistry problems. Our objective is to present a novel perspective on the symbiosis of machine learning and chemistry, with the potential to catalyze a transformation in the field of natural product analysis. Introduction The utilization of natural products has a long history. 1 The foundational science of natural product chemistry can be tracked back to the isolation of morphine from opium in the early 19th century by Sertürner, who was the founder of alkaloid research. 2 The development of isolation and characterization of natural products accelerated in the 20th century with the advent of instrumental analysis techniques, such as nuclear magnetic resonance sp

FAQs

What limitations of conventional chemistry are highlighted in the review?

Conventional chemistry techniques struggle with increasing complexity and the growing volume of data generated in modern research.

How does machine learning improve natural product analysis compared with traditional methods?

Machine-learning classification can rapidly match patterns in spectral data, improving dereplication efficiency and accuracy, while models can also predict metabolic pathways faster and more precisely than traditional approaches.

What major analytical instrument categories are discussed for natural product analysis?

The review groups methods into those used for quantitative analysis (e.g., HPLC, UV-Vis, NMR) and those used for quantitative evaluation (e.g., MS and IR spectroscopy).

Aug 3, 2026

Upload by Oliver