Machine learning reveals signatures of promiscuous microbial amidases for micropollutant biotransformations
Loading...
Author (Corporation)
Publication date
04.12.2024
Typ of student thesis
Course of study
Collections
Type
01A - Journal article
Editors
Editor (Corporation)
Supervisor
Parent work
ACS Environmental Au
Special issue
DOI of the original publication
Link
Series
Series number
Volume
5
Issue / Number
1
Pages / Duration
114-127
Patent number
Publisher / Publishing institution
American Chemical Society
Place of publication / Event location
Edition
Version
Programming language
Assignee
Practice partner / Client
Abstract
Organic micropollutants, including pharmaceuticals, personal care products, pesticides, and food additives, are widespread in the environment, causing potentially toxic effects. Human waste is a direct source of micropollutants, with the majority of pharmaceuticals being excreted through urine. Urine contains its own microbiota with the potential to catalyze micropollutant biotransformations. Amidase signature (AS) enzymes are known for their promiscuous activity in micropollutant biotransformations, but the potential for AS enzymes from the urinary microbiota to transform micropollutants is not known. Moreover, the characterization of AS enzymes to identify key chemical and enzymatic features associated with biotransformation profiles is critical for developing benign-by-design chemicals and micropollutant removal strategies. Here, to uncover the signatures of AS enzyme–substrate specificity, we tested 17 structurally diverse compounds against a targeted enzyme library consisting of 40 AS enzyme homologues from diverse urine microbial isolates. The most promiscuous enzymes were active on nine different substrates, while 16 enzymes had activity on at least one substrate and exhibited diverse substrate specificities. Using an interpretable gradient boosting machine learning model, we identified chemical and amino acid features associated with AS enzyme biotransformations. Key chemical features from our substrates included the molecular weight of the amide carbonyl substituent and the number of formal charges in the molecule. Four of the identified amino acid features were located in close proximity to the substrate tunnel entrance. Overall, this work highlights the understudied potential of urine-derived microbial AS enzymes for micropollutant biotransformation and offers insights into substrate and protein features associated with micropollutant biotransformations for future environmental applications.
Keywords
Micropollutant biotransformations, Amidase signature enzymes, Urinary microbiota, Paracetamol, Acetylsulfamethoxazole, Capecitabine, Machine learning
Subject (DDC)
Event
Exhibition start date
Exhibition end date
Conference start date
Conference end date
Date of the last check
ISBN
ISSN
2694-2518
Language
English
Created during FHNW affiliation
Yes
Strategic action fields FHNW
Publication status
Published
Review
Peer review of the complete publication
Open access category
Gold
License
Citation
Marti, T. D., Schweizer, D., Yu, Y., Schärer, M. R., Probst, S. I., & Robinson, S. L. (2024). Machine learning reveals signatures of promiscuous microbial amidases for micropollutant biotransformations. ACS Environmental Au, 5(1), 114–127. https://doi.org/10.1021/acsenvironau.4c00066