Abteilung Umwelttoxikologie

array(2 items)
   publications => '33052,33005,32823,32142' (23 chars)
   libraryUrl => '' (0 chars)

array(4 items)
   0 => Snowflake\Publications\Domain\Model\Publicationprototypepersistent entity (uid=33052, pid=124)
      originalId => protected33052 (integer)
      authors => protected'Gasser, L.; Schür, C.; Perez-Cruz, F.; Schirmer, K.; Ba
         ity-Jesi, M.' (93 chars)
      title => protected'Machine learning-based prediction of fish acute mortality: implementation, i
         nterpretation, and regulatory relevance' (115 chars)
      journal => protected'Environmental Science: Advances' (31 chars)
      year => protected2024 (integer)
      volume => protected3 (integer)
      issue => protected'8' (1 chars)
      startpage => protected'1124' (4 chars)
      otherpage => protected'1138' (4 chars)
      categories => protected'' (0 chars)
      description => protected'Regulation of chemicals requires knowledge of their toxicological effects on
          a large number of species, which has traditionally been acquired through in
          vivo testing. The recent effort to find alternatives based on machine learn
         ing, however, has not focused on guaranteeing transparency, comparability an
         d reproducibility, which makes it difficult to assess advantages and disadva
         ntages of these methods. Also, comparable baseline performances are needed. 
         In this study, we trained regression models on the ADORE "t-F2F" challenge p
         roposed in [Schür et al., Nature Scientific data, 2023] to predict acute mo
         rtality, measured as LC50 (lethal concentration 50), of organic compounds on
          fishes. We trained LASSO, random forest (RF), XGBoost, Gaussian process (GP
         ) regression models, and found a series of aspects that are stable across mo
         dels: (i) using mass or molar concentrations does not affect performances; (
         ii) the performances are only weakly dependent on the molecular representati
         ons of the chemicals, but (iii) strongly on how the data is split. Overall, 
         the tree-based models RF and XGBoost performed best and we were able to pred
         ict the log10-transformed LC50 with a root mean square error of 0.90, which 
         corresponds to an order of magnitude on the original LC50 scale. On a local 
         level, on the other hand, the models are not able to consistently predict th
         e toxicity of individual chemicals accurately enough. Predictions for single
          chemicals are mostly influenced by a few chemical properties while taxonomi
         c traits are not captured sufficiently by the models. We discuss technical a
         nd conceptual improvements for these challenges to enhance the suitability o
         f in silico methods to environmental hazard assessment. Accordingly, this wo
         rk showcases state-of-the-art models and contributes to the ongoing discussi
         on on regulatory integration.' (1853 chars)
      serialnumber => protected'' (0 chars)
      doi => protected'10.1039/d4va00072b' (18 chars)
      uid => protected33052 (integer)
      _localizedUid => protected33052 (integer)modified
      _languageUid => protectedNULL
      _versionedUid => protected33052 (integer)modified
      pid => protected124 (integer)
   1 => Snowflake\Publications\Domain\Model\Publicationprototypepersistent entity (uid=33005, pid=124)
      originalId => protected33005 (integer)
      authors => protected'Adamovsky, O.; Groh, K. J.; Białk-Bielińska, A.; Esche
         r, B. I.; Beaudouin, R.; Mora Lagares, L.; Tollefsen,&nb
         sp;K. E.; Fenske, M.; Mulkiewicz, E.; Creusot, N.; Sosno
         wska, A.; Loureiro, S.; Beyer, J.; Repetto, G.; Štern,&
         nbsp;A.; Lopes, I.; Monteiro, M.; Zikova-Kloas, A.; Eleršek,
          T.; Vračko, M.; Zdybel, S.; Puzyn, T.; Koczur, W.
         ; Ebsen Morthorst, J.; Holbech, H.; Carlsson, G.; Örn, 
         S.; Herrero, Ó.; Siddique, A.; Liess, M.; Braun, G.; Sr
         ebny, V.; Žegura, B.; Hinfray, N.; Brion, F.; Knapen,&n
         bsp;D.; Vandeputte, E.; Stinckens, E.; Vergauwen, L.; Behrend
         t, L.; João Silva, M.; Blaha, L.; Kyriakopoulou, K.' (832 chars)
      title => protected'Exploring BPA alternatives - environmental levels and toxicity review' (69 chars)
      journal => protected'Environment International' (25 chars)
      year => protected2024 (integer)
      volume => protected189 (integer)
      issue => protected'' (0 chars)
      startpage => protected'108728 (29 pp.)' (15 chars)
      otherpage => protected'' (0 chars)
      categories => protected'BPA alternatives; biological activity; in silico; invertebrates; vertebrates' (76 chars)
      description => protected'Bisphenol A alternatives are manufactured as potentially less harmful substi
         tutes of bisphenol A (BPA) that offer similar functionality. These alternati
         ves are already in the market, entering the environment and thus raising eco
         logical concerns. However, it can be expected that levels of BPA alternative
         s will dominate in the future, they are limited information on their environ
         mental safety. The EU PARC project highlights BPA alternatives as priority c
         hemicals and consolidates information on BPA alternatives, with a focus on e
         nvironmental relevance and on the identification of the research gaps. The r
         eview highlighted aspects and future perspectives. In brief, an extension of
          environmental monitoring is crucial, extending it to cover BPA alternatives
          to track their levels and facilitate the timely implementation of mitigatio
         n measures. The biological activity has been studied for BPA alternatives, b
         ut in a non-systematic way and prioritized a limited number of chemicals. Fo
         r several BPA alternatives, the data has already provided substantial eviden
         ce regarding their potential harm to the environment. We stress the importan
         ce of conducting more comprehensive assessments that go beyond the tradition
         al reproductive studies and focus on overlooked relevant endpoints. Future r
         esearch should also consider mixture effects, realistic environmental concen
         trations, and the long-term consequences on biota and ecosystems.' (1433 chars)
      serialnumber => protected'0160-4120' (9 chars)
      doi => protected'10.1016/j.envint.2024.108728' (28 chars)
      uid => protected33005 (integer)
      _localizedUid => protected33005 (integer)modified
      _languageUid => protectedNULL
      _versionedUid => protected33005 (integer)modified
      pid => protected124 (integer)
   2 => Snowflake\Publications\Domain\Model\Publicationprototypepersistent entity (uid=32823, pid=124)
      originalId => protected32823 (integer)
      authors => protected'Posthuma, L.; Bloor, M.; Campos, B.; Groh, K.; Leopold,&
         nbsp;A.; Sanderson, H.; Schreiber, H.; Schür, C.; Thomas,&nb
         sp;P.' (157 chars)
      title => protected'Green Swans countering chemical pollution' (41 chars)
      journal => protected'Integrated Environmental Assessment and Management' (50 chars)
      year => protected2024 (integer)
      volume => protected20 (integer)
      issue => protected'3' (1 chars)
      startpage => protected'888' (3 chars)
      otherpage => protected'891' (3 chars)
      categories => protected'' (0 chars)
      description => protected'If a problem has exponential features, its solution asks for counter-exponen
         tial approaches. Chemical pollution appears to be such a problem. Analyses o
         f chemical hazards to human health, biodiversity, and ecosystem services and
          estimates of the cost of inaction suggest the potential for adverse impacts
         , and analyses of trends in the chemical economy appear exponential in kind.
          Here, we argue that we need and can develop an exponential and application-
         focused mindset in thinking about solutions.' (500 chars)
      serialnumber => protected'1551-3777' (9 chars)
      doi => protected'10.1002/ieam.4915' (17 chars)
      uid => protected32823 (integer)
      _localizedUid => protected32823 (integer)modified
      _languageUid => protectedNULL
      _versionedUid => protected32823 (integer)modified
      pid => protected124 (integer)
   3 => Snowflake\Publications\Domain\Model\Publicationprototypepersistent entity (uid=32142, pid=124)
      originalId => protected32142 (integer)
      authors => protected'Schür, C.; Gasser, L.; Perez-Cruz, F.; Schirmer, K.; Ba
         ity-Jesi, M.' (93 chars)
      title => protected'A benchmark dataset for machine learning in ecotoxicology' (57 chars)
      journal => protected'Scientific Data' (15 chars)
      year => protected2023 (integer)
      volume => protected10 (integer)
      issue => protected'1' (1 chars)
      startpage => protected'718 (20 pp.)' (12 chars)
      otherpage => protected'' (0 chars)
      categories => protected'' (0 chars)
      description => protected'The use of machine learning for predicting ecotoxicological outcomes is prom
         ising, but underutilized. The curation of data with informative features req
         uires both expertise in machine learning as well as a strong biological and 
         ecotoxicological background, which we consider a barrier of entry for this k
         ind of research. Additionally, model performances can only be compared acros
         s studies when the same dataset, cleaning, and splittings were used. Therefo
         re, we provide <em>ADORE</em>, an extensive and well-described dataset on ac
         ute aquatic toxicity in three relevant taxonomic groups (fish, crustaceans, 
         and algae). The core dataset describes ecotoxicological experiments and is e
         xpanded with phylogenetic and species-specific data on the species as well a
         s 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 dat
         a and include datasets and splittings corresponding to each of these challen
         ge as well as in-depth characterization and discussion of train-test splitti
         ng approaches.' (1154 chars)
      serialnumber => protected'' (0 chars)
      doi => protected'10.1038/s41597-023-02612-2' (26 chars)
      uid => protected32142 (integer)
      _localizedUid => protected32142 (integer)modified
      _languageUid => protectedNULL
      _versionedUid => protected32142 (integer)modified
      pid => protected124 (integer)