Exploration of machine learning algorithms for predicting the changes in abundance of antibiotic resistance genes in anaerobic digestion
Copyright © 2022 Elsevier B.V. All rights reserved..
The land application of digestate from anaerobic digestion (AD) is considered a significant route for transmitting antibiotic resistance genes (ARGs) and mobile genetic elements (MGEs) to ecosystems. To date, efforts towards understanding complex non-linear interactions between AD operating parameters with ARG/MGE abundances rely on experimental investigations due to a lack of mechanistic models. Herein, three different machine learning (ML) algorithms, Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN), were compared for their predictive capacities in simulating ARG/MGE abundance changes during AD. The models were trained and cross-validated using experimental data collected from 33 published literature. The comparison of model performance using coefficients of determination (R2) and root mean squared errors (RMSE) indicated that ANN was more reliable than RF and XGBoost. The mode of operation (batch/semi-continuous), co-digestion of food waste and sewage sludge, and residence time were identified as the three most critical features in predicting ARG/MGE abundance changes. Moreover, the trained ANN model could simulate non-linear interactions between operational parameters and ARG/MGE abundance changes that could be interpreted intuitively based on existing knowledge. Overall, this study demonstrates that machine learning can enable a reliable predictive model that can provide a holistic optimization tool for mitigating the ARG/MGE transmission potential of AD.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:839 |
|---|---|
| Enthalten in: |
The Science of the total environment - 839(2022) vom: 15. Sept., Seite 156211 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Haffiez, Nervana [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Anaerobic digestion |
|---|
| Anmerkungen: |
Date Completed 23.06.2022 Date Revised 23.06.2022 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.scitotenv.2022.156211 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM341458325 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM341458325 | ||
| 003 | DE-627 | ||
| 005 | 20231226011827.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.scitotenv.2022.156211 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1138.xml |
| 035 | |a (DE-627)NLM341458325 | ||
| 035 | |a (NLM)35623518 | ||
| 035 | |a (PII)S0048-9697(22)03308-3 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Haffiez, Nervana |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Exploration of machine learning algorithms for predicting the changes in abundance of antibiotic resistance genes in anaerobic digestion |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 23.06.2022 | ||
| 500 | |a Date Revised 23.06.2022 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2022 Elsevier B.V. All rights reserved. | ||
| 520 | |a The land application of digestate from anaerobic digestion (AD) is considered a significant route for transmitting antibiotic resistance genes (ARGs) and mobile genetic elements (MGEs) to ecosystems. To date, efforts towards understanding complex non-linear interactions between AD operating parameters with ARG/MGE abundances rely on experimental investigations due to a lack of mechanistic models. Herein, three different machine learning (ML) algorithms, Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN), were compared for their predictive capacities in simulating ARG/MGE abundance changes during AD. The models were trained and cross-validated using experimental data collected from 33 published literature. The comparison of model performance using coefficients of determination (R2) and root mean squared errors (RMSE) indicated that ANN was more reliable than RF and XGBoost. The mode of operation (batch/semi-continuous), co-digestion of food waste and sewage sludge, and residence time were identified as the three most critical features in predicting ARG/MGE abundance changes. Moreover, the trained ANN model could simulate non-linear interactions between operational parameters and ARG/MGE abundance changes that could be interpreted intuitively based on existing knowledge. Overall, this study demonstrates that machine learning can enable a reliable predictive model that can provide a holistic optimization tool for mitigating the ARG/MGE transmission potential of AD | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Anaerobic digestion | |
| 650 | 4 | |a Antibiotic resistance genes | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Mobile genetic elements | |
| 650 | 7 | |a Anti-Bacterial Agents |2 NLM | |
| 650 | 7 | |a Sewage |2 NLM | |
| 700 | 1 | |a Chung, Tae Hyun |e verfasserin |4 aut | |
| 700 | 1 | |a Zakaria, Basem S |e verfasserin |4 aut | |
| 700 | 1 | |a Shahidi, Manjila |e verfasserin |4 aut | |
| 700 | 1 | |a Mezbahuddin, Symon |e verfasserin |4 aut | |
| 700 | 1 | |a Maal-Bared, Rasha |e verfasserin |4 aut | |
| 700 | 1 | |a Dhar, Bipro Ranjan |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The Science of the total environment |d 1972 |g 839(2022) vom: 15. Sept., Seite 156211 |w (DE-627)NLM000215562 |x 1879-1026 |7 nnns |
| 773 | 1 | 8 | |g volume:839 |g year:2022 |g day:15 |g month:09 |g pages:156211 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.scitotenv.2022.156211 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 839 |j 2022 |b 15 |c 09 |h 156211 | ||