Self-Supervised Learning Strategies for a Platform to Test the Toxicity of New Chemicals and Materials
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916998274875392 |
|---|---|
| author | Lautenschlager, Thomas Friederich, Nils Sitcheu, Angelo Jovin Yamachui Nau, Katja Hayot, Gaëlle Dickmeis, Thomas Mikut, Ralf |
| author_facet | Lautenschlager, Thomas Friederich, Nils Sitcheu, Angelo Jovin Yamachui Nau, Katja Hayot, Gaëlle Dickmeis, Thomas Mikut, Ralf |
| contents | High-throughput toxicity testing offers a fast and cost-effective way to test large amounts of compounds. A key component for such systems is the automated evaluation via machine learning models. In this paper, we address critical challenges in this domain and demonstrate how representations learned via self-supervised learning can effectively identify toxicant-induced changes. We provide a proof-of-concept that utilizes the publicly available EmbryoNet dataset, which contains ten zebrafish embryo phenotypes elicited by various chemical compounds targeting different processes in early embryonic development. Our analysis shows that the learned representations using self-supervised learning are suitable for effectively distinguishing between the modes-of-action of different compounds. Finally, we discuss the integration of machine learning models in a physical toxicity testing device in the context of the TOXBOX project. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07853 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Learning Strategies for a Platform to Test the Toxicity of New Chemicals and Materials Lautenschlager, Thomas Friederich, Nils Sitcheu, Angelo Jovin Yamachui Nau, Katja Hayot, Gaëlle Dickmeis, Thomas Mikut, Ralf Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning High-throughput toxicity testing offers a fast and cost-effective way to test large amounts of compounds. A key component for such systems is the automated evaluation via machine learning models. In this paper, we address critical challenges in this domain and demonstrate how representations learned via self-supervised learning can effectively identify toxicant-induced changes. We provide a proof-of-concept that utilizes the publicly available EmbryoNet dataset, which contains ten zebrafish embryo phenotypes elicited by various chemical compounds targeting different processes in early embryonic development. Our analysis shows that the learned representations using self-supervised learning are suitable for effectively distinguishing between the modes-of-action of different compounds. Finally, we discuss the integration of machine learning models in a physical toxicity testing device in the context of the TOXBOX project. |
| title | Self-Supervised Learning Strategies for a Platform to Test the Toxicity of New Chemicals and Materials |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.07853 |