- Centre Eau Terre Environnement, Institut national de la recherche scientifique, Québec, Canada
- Aquatic ecotoxicology, Bioaccumulation/biomagnification, Bioassays, Biomarkers, Biomonitoring, Environmental pollution, Legacy and emerging contaminants, Marine ecotoxicology
- recommender, manager
Identifying pesticide mixtures at country-wide scale
An original approach for the identification of relevant pesticides mixtures at nationwide scaleRecommended by Pierre Labadie based on reviews by Patrice Couture and Clémentine FRITSCH
Over the last decades, pesticides have been massively used in agriculture and their impacts on both the environment and human health are a major growing concern (Humann-Guilleminot et al., 2019; 2019 Boedeker et al., 2020). Improving the prediction of wildlife exposure to pesticides and the associated impacts on ecosystems is therefore crucial. In general, ecotoxicological studies addressing the effects of pesticides include compounds that are selected based on general use over large areas (e.g. regions, country) or specific crop types. Such a selection does not necessarily reflect the mixtures to which species of wildlife are exposed in a particular ecosystem.
In this context, Cairo et al. (2023) present an original approach to identify relevant mixtures of current-use pesticides. Their approach relies on public data concerning pesticide sales and cropping, available at a nationwide scale in France and at a relatively high resolution (i.e. postcode of the buyer). Based on a number of clearly exposed and discussed assumptions (e.g. “pesticides were used in the year of purchase and in the postcode of purchase”), their approach allowed for identifying 18 groups that were discriminated by a reduced number of pesticides. Some compounds were found in most or all groups and were termed “core substances” (e.g. deltamethrin and lambda-cyhalothrin). Other compounds, however, were associated with a limited number of groups and termed “discriminant substances” (e.g. boscalid and epoxiconazole).
The authors identified groups of molecules that are probably associated with the same mixtures, which warrants the investigation of potential synergetic effects. In addition, their approach allowed for the identification of areas where aquatic biota may be exposed to similar mixtures, which is might prove of interest to further investigate in situ the actual impacts of pesticide mixtures on ecosystems. Note that the approach taken by the authors might be applied by others in other countries, provided a database of pesticide sales is available.
Boedeker W, Watts M, Clausing P, Marquez E (2020) The global distribution of acute unintentional pesticide poisoning: estimations based on a systematic review. BMC Public Health, 20, 1875. https://doi.org/10.1186/s12889-020-09939-0
Cairo M, Monnet A-C, Robin S, Porcher E, Fontaine C (2023) Identifying pesticide mixtures at country-wide scale. HAL, ver. 2 peer-reviewed and recommended by Peer Community in Ecotoxicology and Environmental Chemistry. https://hal.science/hal-03815557
Humann-Guilleminot S, Tassin de Montaigu C, Sire J, Grünig S, Gning O, Glauser G, Vallat A, Helfenstein F (2019) A sublethal dose of the neonicotinoid insecticide acetamiprid reduces sperm density in a songbird. Environmental Research, 177, 108589. https://doi.org/10.1016/j.envres.2019.108589
Machine learning models based on molecular descriptors to predict human and environmental toxicological factors in continental freshwater
Predicting characterization factors of chemical substances from a set of molecular descriptors based on machine learning algorithmsRecommended by Sandrine CHARLES based on reviews by Patrice Couture, Sylvain Bart, Dominique Lamonica and 2 anonymous reviewers
Today, thousands of chemical substances are released into the environment because of human activities. It is thus crucial to identify all relevant chemicals that contribute to toxic effects on living organisms, also potentially disturbing the community functioning and the ecosystem services that flow from them. Once identified, chemical substances need to be associated with ecotoxicity factors. Nevertheless, getting such factors usually requires time-, resources- and animal-costly experiments that it should be possible to avoid. In this perspective, modelling approaches may be particularly helpful if they rely on easy-to-obtain information to be used as predictive variables.
Within this context, the paper of Servien et al. (2022) illustrates the use of machine learning algorithms to predict toxicity and ecotoxicity factors that were missing for a collection of compounds. Their modelling approach involve a collection of molecular descriptors as input variables. A total of 40 molecular descriptors were extracted from the TyPol database (Servien et al., 2014) as those describing the best how organic compounds behave within the environment. These molecular descriptors also have the advantage to be easily quantifiable for new chemical substances under evaluation. The performances of the proposed models were systematically checked and compared to the classical linear partial least square method, based on the calculation of the absolute error (namely, the difference between prediction and true value). This finally led to different best models (that is associated to the lowest median absolute error) according to the classification of the 526 compounds comprised in the TyPol database in five clusters. These five clusters of different sizes gather chemical substances with different but specific molecular characteristics, also corresponding to different estimates of the characterization factors both in their median and within-variability.
In a final step, predictions of characterization factors were performed for 102 missing values in the USEtox® database (Rosenbaum et al., 2008) but also referenced in TyPol. This paper highlights that the molecular descriptors that explain the most the toxicity of the chemical substances in each cluster strongly differ. Nevertheless, these predictions, whatever the cluster, appear precise enough to be considered as relevant despite everything.
As a conclusion, this paper is a promising proof-of-concept in using machine learning modelling to go beyond some constraints around the toxicity evaluation of chemical substances, especially handling non-linearities and data-demanding calculations, in in an ever-changing world that is gradually depleting its resources without sufficient concern for the short-term risks to the environment and human health.
Rosenbaum RK, Bachmann TM, Gold LS, Huijbregts MAJ, Jolliet O, Juraske R, Koehler A, Larsen HF, MacLeod M, Margni M, McKone TE, Payet J, Schuhmacher M, van de Meent D, Hauschild MZ (2008) USEtox—the UNEP-SETAC toxicity model: recommended characterisation factors for human toxicity and freshwater ecotoxicity in life cycle impact assessment. The International Journal of Life Cycle Assessment, 13, 532. https://doi.org/10.1007/s11367-008-0038-4
Servien R, Latrille E, Patureau D, Hélias A (2022) Machine learning models based on molecular descriptors to predict human and environmental toxicological factors in continental freshwater. bioRxiv, 2021.07.20.453034, ver. 6 peer-reviewed and recommended by Peer Community in Ecotoxicology and Environmental Chemistry. https://doi.org/10.1101/2021.07.20.453034
Servien R, Mamy L, Li Z, Rossard V, Latrille E, Bessac F, Patureau D, Benoit P (2014) TyPol – A new methodology for organic compounds clustering based on their molecular characteristics and environmental behavior. Chemosphere, 111, 613–622. https://doi.org/10.1016/j.chemosphere.2014.05.020