Evaluation and application of machine learning-based retention time prediction for suspect screening of pesticides and pesticide transformation products in LC-HRMS.

Chemosphere

Shanghai Municipal Center for Disease Control and Prevention, Shanghai, 200336, China; State Environmental Protection Key Laboratory of Environmental Health Impact Assessment of Emerging Contaminants, Shanghai, 200336, China. Electronic address:

Published: May 2021

Computational QSAR models have gradually been preferred for retention time prediction in data mining of emerging environmental contaminants using liquid chromatography coupled with mass spectrometry. Generally, the model performance relies on the components such as machine learning algorithms, chemical features, and example data. In this study, we evaluated the performances of four algorithms on three feature sets, using 321 and 77 pesticides as the training and validation sets, respectively. The results were varied with different combinations of algorithms on distinct feature sets. Two strategies including enhancing the complexity of chemical features and enlarging the size of the training set were proved to improve the results. XGBoost, Random Forest, and lightGBM algorithms exhibited the best results when built on a large-scale chemical descriptors, while the Keras algorithm preferred fingerprints. These four models have comparable prediction accuracies that at least 90% of pesticides in validation set can be successfully predicted with ΔRT <1.0 min. Meanwhile, a blended prediction strategy using average results from four models presented a better result than any single model. This strategy was used for assisting identification of pesticides and pesticide transformation products in 120 strawberry samples from a national survey of food contamination. Twenty pesticides and twelve pesticide transformation products were tentatively identified, where all pesticides and two pesticide transformation products (bifenazate diazene and spirotetramat-enol) were confirmed by standard materials. The outcome of this study suggested that retention time prediction is a valuable approach in compound identification when integrated with in silico MS spectra and other MS identification strategies.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.chemosphere.2020.129447DOI Listing

Publication Analysis

Top Keywords

retention time
8
time prediction
8
chemical features
8
feature sets
8
evaluation application
4
application machine
4
machine learning-based
4
learning-based retention
4
prediction suspect
4
suspect screening
4

Similar Publications

.) .

J Food Sci Technol

January 2025

Agri Business Incubator, Department of Agricultural Engineering, College of Agriculture, Kerala Agricultural University, Thrissur, 680656 India.

Unlabelled: The present work investigates the impact of pressure (; 300-600 MPa) and holding time (; 5-20 min) on the quality attributes and microbial stability of jackfruit shreds. The results revealed that the and had significantly affected physico-chemcial and bioactive composition of the jackfruit shreds. Higher levels of and increased the firmness of the shreds.

View Article and Find Full Text PDF

Expression of kiwifruit-derived actinidin in leaves.

Front Plant Sci

January 2025

Department of Integrative Food, Bioscience and Biotechnology, Chonnam National University, Gwangju, Republic of Korea.

Kiwifruit ()-derived actinidin, a cysteine protease, is renowned for its meat-tenderizing and milk-clotting activities. Despite its potential in various biotechnological applications, an efficient expression platform for actinidin production has not yet been developed. Instead, actinidin has traditionally been purified directly from the fruits of various plants.

View Article and Find Full Text PDF

Objective: This study aimed to qualitatively study the main chemical components of apple peel in APORT, Kazakhstan, by ultra-performance liquid chromatography-quadrupole-time-of-flight mass spectrometry (UPLC-Q-TOF-MS/MS) and to compare the components of apple peels with different provenances.

Methods: An ACQUITY UPLC HSS T3 (100 mm × 2.1 mm, 1.

View Article and Find Full Text PDF

Background: Mentoring, advising, and coaching are essential components of resident education and professional development. Despite their importance, there is limited literature exploring how anesthesiology faculty perceive these practices and their role in supporting residents.

Objective: This study aims to investigate anesthesiology faculty perspectives on the significance, implantation strategies, and challenges associated with mentorship, advising, and coaching in resident education.

View Article and Find Full Text PDF

A multifunctional hydrogel with outstanding mechanical properties and excellent ionic conductivity holds immense potential for applications in various fields, such as healthcare monitoring, and various devices, such as wearable devices and flexible electronics. However, developing hydrogels that combine high mechanical strength with efficient electrical conductivity remains a considerable challenge. Herein, an ion-conductive hydrogel with excellent mechanical properties and ionic conductivity is successfully created.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!