Department Systems Analysis, Integrated Assessment and Modelling

ML Tox

Photo by Harrison Haines from Pexels


We use machine learning methods to predict the effects of chemicals on aquatic species. Our main goal is to use a combination of data from in-vivo (whole organisms) and in-vitro (cell culture) experiments to infer the effects of chemicals on organisms for which no testing data is available (both for the chemical and for the organism). In the literature, this kind of problem is also known as across-chemical (and across-species) extrapolation. Usually, extrapolation across chemicals is performed using measures of chemical similarity under the assumption that similar chemicals will be similarly toxic to the same species. Extrapolation across species can be performed based on measured chemical effects on some species and the similarity between species, either by phylogenetic distance or sequence/structure similarity of known molecular targets of the chemicals, if at all available, or as well through similarity in physiological traits. Given the enormous number of chemicals and of potentially affected species, extrapolation chemical by chemical or species by species is a daunting task.
Our approach is different. In an interdisciplinary effort by ecotoxicologists and ML experts, we will combine thus far unconnected data to obtain predictions of toxicity across chemicals and species. ML allows the process to be agnostic to previously-determined notions of similarity between species or chemicals. We will use a variety of data sources and types, all available in different publicly available tools and databases, combining chemical structure, data on chemical testing on different organisms, and chemical testing in in-vitro assays.

Team

Dr. Marco Baity Jesi Group Leader (he/him) Tel. +41 58 765 5793 Send Mail
Prof. Dr. Kristin Schirmer Head of department Tel. +41 58 765 5266 Send Mail
Dr. Christoph Schuer Postdoctoral Scientist Tel. +41 58 765 5684 Send Mail

Publications

A benchmark dataset for machine learning in ecotoxicology

The use of machine learning for predicting ecotoxicological outcomes is promising, but underutilized. The curation of data with informative features requires both expertise in machine learning as well as a strong biological and ecotoxicological background, which we consider a barrier of entry for this kind of research. Additionally, model performances can only be compared across studies when the same dataset, cleaning, and splittings were used. Therefore, we provide ADORE, an extensive and well-described dataset on acute aquatic toxicity in three relevant taxonomic groups (fish, crustaceans, and algae). The core dataset describes ecotoxicological experiments and is expanded with phylogenetic and species-specific data on the species as well as chemical properties and molecular representations. Apart from challenging other researchers to try and achieve the best model performances across the whole dataset, we propose specific relevant challenges on subsets of the data and include datasets and splittings corresponding to each of these challenge as well as in-depth characterization and discussion of train-test splitting approaches.
Schür, C.; Gasser, L.; Perez-Cruz, F.; Schirmer, K.; Baity-Jesi, M. (2023) A benchmark dataset for machine learning in ecotoxicology, Scientific Data, 10(1), 718 (20 pp.), doi:10.1038/s41597-023-02612-2, Institutional Repository

Predicting chemical hazard across taxa through machine learning

We applied machine learning methods to predict chemical hazards focusing on fish acute toxicity across taxa. We analyzed the relevance of taxonomy and experimental setup, showing that taking them into account can lead to considerable improvements in the classification performance. We quantified the gain obtained throught the introduction of taxonomic and experimental information, compared to classification based on chemical information alone. We used our approach with standard machine learning models (K-nearest neighbors, random forests and deep neural networks), as well as the recently proposed Read-Across Structure Activity Relationship (RASAR) models, which were very successful in predicting chemical hazards to mammals based on chemical similarity. We were able to obtain accuracies of over 93% on datasets where, due to noise in the data, the maximum achievable accuracy was expected to be below 96%. The best performances were obtained by random forests and RASAR models. We analyzed metrics to compare our results with animal test reproducibility, and despite most of our models "outperform animal test reproducibility" as measured through recently proposed metrics, we showed that the comparison between machine learning performance and animal test reproducibility should be addressed with particular care. While we focused on fish mortality, our approach, provided that the right data is available, is valid for any combination of chemicals, effects and taxa.
Wu, J.; D'Ambrosi, S.; Ammann, L.; Stadnicka-Michalak, J.; Schirmer, K.; Baity-Jesi, M. (2022) Predicting chemical hazard across taxa through machine learning, Environment International, 163, 107184 (15 pp.), doi:10.1016/j.envint.2022.107184, Institutional Repository

Contact

Dr. Marco Baity Jesi Group Leader (he/him) Tel. +41 58 765 5793 Send Mail
Prof. Dr. Kristin Schirmer Head of department Tel. +41 58 765 5266 Send Mail