2025
2.
Dost, Katharina; Albrecht, Steffen; MacLean, Paul; Wicker, Jörg; Gupta, Sandeep
Understanding Rumen Methanogen Interactions in Sheep Using Machine Learning Proceedings Article
In: Lecture Notes in Computer Science, pp. 253-269, Springer Nature, 2025, ISSN: 0302-9743.
Abstract | Links | BibTeX | Altmetric | PlumX | Tags: bioinformatics, computational sustainability, machine learning
@inproceedings{Dost2025understanding,
title = {Understanding Rumen Methanogen Interactions in Sheep Using Machine Learning},
author = {Katharina Dost and Steffen Albrecht and Paul MacLean and J\"{o}rg Wicker and Sandeep Gupta},
doi = {10.1007/978-3-662-72243-5_15},
issn = {0302-9743},
year = {2025},
date = {2025-10-04},
booktitle = {Lecture Notes in Computer Science},
volume = {16020},
pages = {253-269},
publisher = {Springer Nature},
abstract = {Methane emissions from livestock pose a significant challenge globally, particularly in countries with a strong farming industry dominated by sheep farming, such as Aotearoa, New Zealand (NZ). Chemical inhibitors such as feed additives or vaccines help to decrease methane emissions. However, their successful development has been hindered by a limited understanding of the complex interactions among the microorganisms in the rumen (forestomach). This study serves as a proof-of-concept to explore the potential of using metatranscriptome data to understand the genetic basis of microbial interactions in the rumen and identify potential inhibitor targets. We analyzed a small but carefully curated dataset of 10 sheep emitting different levels of methane. We employed various statistical and machine learning techniques to uncover new contigs (continuous sequences of DNA) linked to high levels of methane output. Despite the limited sample size, our findings revealed new insights into microbial mechanisms, validated by domain experts. These preliminary results suggest that expanding the dataset and integrating machine learning can enhance our understanding of the complex microbial interactions in the rumen, ultimately contributing to the development of effective strategies to reduce methane emissions in livestock.},
keywords = {bioinformatics, computational sustainability, machine learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Methane emissions from livestock pose a significant challenge globally, particularly in countries with a strong farming industry dominated by sheep farming, such as Aotearoa, New Zealand (NZ). Chemical inhibitors such as feed additives or vaccines help to decrease methane emissions. However, their successful development has been hindered by a limited understanding of the complex interactions among the microorganisms in the rumen (forestomach). This study serves as a proof-of-concept to explore the potential of using metatranscriptome data to understand the genetic basis of microbial interactions in the rumen and identify potential inhibitor targets. We analyzed a small but carefully curated dataset of 10 sheep emitting different levels of methane. We employed various statistical and machine learning techniques to uncover new contigs (continuous sequences of DNA) linked to high levels of methane output. Despite the limited sample size, our findings revealed new insights into microbial mechanisms, validated by domain experts. These preliminary results suggest that expanding the dataset and integrating machine learning can enhance our understanding of the complex microbial interactions in the rumen, ultimately contributing to the development of effective strategies to reduce methane emissions in livestock.
2024
1.
Hafner, Jasmin; Lorsbach, Tim; Schmidt, Sebastian; Brydon, Liam; Dost, Katharina; Zhang, Kunyang; Fenner, Kathrin; Wicker, Jörg
Advancements in Biotransformation Pathway Prediction: Enhancements, Datasets, and Novel Functionalities in enviPath Journal Article
In: Journal of Cheminformatics, vol. 16, no. 1, pp. 93, 2024, ISSN: 1758-2946.
Abstract | Links | BibTeX | Altmetric | PlumX | Tags: applicability domain, biodegradation, bioinformatics, cheminformatics, computational sustainability, enviPath, linked data, machine learning, multi-label classification, Process-based modeling
@article{hafner2023advancements,
title = {Advancements in Biotransformation Pathway Prediction: Enhancements, Datasets, and Novel Functionalities in enviPath},
author = {Jasmin Hafner and Tim Lorsbach and Sebastian Schmidt and Liam Brydon and Katharina Dost and Kunyang Zhang and Kathrin Fenner and J\"{o}rg Wicker},
url = {https://jcheminf.biomedcentral.com/articles/10.1186/s13321-024-00881-6
https://envipath.org},
doi = {10.1186/s13321-024-00881-6},
issn = {1758-2946},
year = {2024},
date = {2024-08-06},
urldate = {2024-08-06},
journal = {Journal of Cheminformatics},
volume = {16},
number = {1},
pages = {93},
abstract = {enviPath is a widely used database and prediction system for microbial biotransformation pathways of primarily xenobiotic compounds. Data and prediction system are freely available both via a web interface and a public REST API. Since its initial release in 2016, we extended the data available in enviPath and improved the performance of the prediction system and usability of the overall system. We now provide three diverse data sets, covering microbial biotransformation in different environments and under different experimental conditions. This also enabled developing a pathway prediction model that is applicable to a more diverse set of chemicals. In the prediction engine, we implemented a new evaluation tailored towards pathway prediction, which returns a more honest and holistic view on the performance. We also implemented a novel applicability domain algorithm, which allows the user to estimate how well the model will perform on their data. Finally, we improved the implementation to speed up the overall system and provide new functionality via a plugin system.
},
keywords = {applicability domain, biodegradation, bioinformatics, cheminformatics, computational sustainability, enviPath, linked data, machine learning, multi-label classification, Process-based modeling},
pubstate = {published},
tppubtype = {article}
}
enviPath is a widely used database and prediction system for microbial biotransformation pathways of primarily xenobiotic compounds. Data and prediction system are freely available both via a web interface and a public REST API. Since its initial release in 2016, we extended the data available in enviPath and improved the performance of the prediction system and usability of the overall system. We now provide three diverse data sets, covering microbial biotransformation in different environments and under different experimental conditions. This also enabled developing a pathway prediction model that is applicable to a more diverse set of chemicals. In the prediction engine, we implemented a new evaluation tailored towards pathway prediction, which returns a more honest and holistic view on the performance. We also implemented a novel applicability domain algorithm, which allows the user to estimate how well the model will perform on their data. Finally, we improved the implementation to speed up the overall system and provide new functionality via a plugin system.