PMID- 33295759 OWN - NLM STAT- MEDLINE DCOM- 20210923 LR - 20210923 IS - 1520-5010 (Electronic) IS - 0893-228X (Print) IS - 0893-228X (Linking) VI - 34 IP - 2 DP - 2021 Feb 15 TI - Skin Doctor CP: Conformal Prediction of the Skin Sensitization Potential of Small Organic Molecules. PG - 330-344 LID - 10.1021/acs.chemrestox.0c00253 [doi] AB - Skin sensitization potential or potency is an important end point in the safety assessment of new chemicals and new chemical mixtures. Formerly, animal experiments such as the local lymph node assay (LLNA) were the main form of assessment. Today, however, the focus lies on the development of nonanimal testing approaches (i.e., in vitro and in chemico assays) and computational models. In this work, we investigate, based on publicly available LLNA data, the ability of aggregated, Mondrian conformal prediction classifiers to differentiate between non- sensitizing and sensitizing compounds as well as between two levels of skin sensitization potential (weak to moderate sensitizers, and strong to extreme sensitizers). The advantage of the conformal prediction framework over other modeling approaches is that it assigns compounds to activity classes only if a defined minimum level of confidence is reached for the individual predictions. This eliminates the need for applicability domain criteria that often are arbitrary in their nature and less flexible. Our new binary classifier, named Skin Doctor CP, differentiates nonsensitizers from sensitizers with a higher reliability-to-efficiency ratio than the corresponding nonconformal prediction workflow that we presented earlier. When tested on a set of 257 compounds at the significance levels of 0.10 and 0.30, the model reached an efficiency of 0.49 and 0.92, and an accuracy of 0.83 and 0.75, respectively. In addition, we developed a ternary classification workflow to differentiate nonsensitizers, weak to moderate sensitizers, and strong to extreme sensitizers. Although this model achieved satisfactory overall performance (accuracies of 0.90 and 0.73, and efficiencies of 0.42 and 0.90, at significance levels 0.10 and 0.30, respectively), it did not obtain satisfying class-wise results (at a significance level of 0.30, the validities obtained for nonsensitizers, weak to moderate sensitizers, and strong to extreme sensitizers were 0.70, 0.58, and 0.63, respectively). We argue that the model is, in consequence, unable to reliably identify strong to extreme sensitizers and suggest that other ternary models derived from the currently accessible LLNA data might suffer from the same problem. Skin Doctor CP is available via a public web service at https://nerdd.zbh.uni-hamburg.de/skinDoctorII/. FAU - Wilm, Anke AU - Wilm A AUID- ORCID: 0000-0003-2891-1407 AD - Center for Bioinformatics (ZBH), Department of Informatics, Universitat Hamburg, 20146 Hamburg, Germany. AD - HITeC e.V., 22527 Hamburg, Germany. FAU - Norinder, Ulf AU - Norinder U AD - Department of Computer and Systems Sciences, Stockholm University, SE-16407 Kista, Sweden. AD - Department of Pharmaceutical Biosciences, Uppsala University, SE-75124 Uppsala, Sweden. AD - MTM Research Centre, School of Science and Technology, Orebro University, SE-70182 Orebro, Sweden. FAU - Agea, M Isabel AU - Agea MI AUID- ORCID: 0000-0002-3017-7742 AD - Department of Informatics and Chemistry, University of Chemistry and Technology Prague, 16628 Prague, Czech Republic. FAU - de Bruyn Kops, Christina AU - de Bruyn Kops C AUID- ORCID: 0000-0001-8890-2137 AD - Center for Bioinformatics (ZBH), Department of Informatics, Universitat Hamburg, 20146 Hamburg, Germany. FAU - Stork, Conrad AU - Stork C AUID- ORCID: 0000-0002-5499-742X AD - Center for Bioinformatics (ZBH), Department of Informatics, Universitat Hamburg, 20146 Hamburg, Germany. FAU - Kuhnl, Jochen AU - Kuhnl J AD - Front End Innovation, Beiersdorf AG, 22529 Hamburg, Germany. FAU - Kirchmair, Johannes AU - Kirchmair J AUID- ORCID: 0000-0003-2667-5877 AD - Center for Bioinformatics (ZBH), Department of Informatics, Universitat Hamburg, 20146 Hamburg, Germany. AD - Department of Pharmaceutical Chemistry, University of Vienna, 1090 Vienna, Austria. LA - eng PT - Journal Article PT - Research Support, Non-U.S. Gov't DEP - 20201209 PL - United States TA - Chem Res Toxicol JT - Chemical research in toxicology JID - 8807448 RN - 0 (Organic Chemicals) RN - 0 (Small Molecule Libraries) SB - IM MH - Animals MH - Databases, Factual MH - Local Lymph Node Assay MH - Mice MH - Molecular Structure MH - Organic Chemicals/chemistry/*pharmacology MH - Skin/*drug effects MH - *Skin Tests MH - Small Molecule Libraries/chemistry/*pharmacology PMC - PMC7887802 COIS- The authors declare the following competing financial interest(s): A.W. is funded by Beiersdorf AG through HITeC e.V. and J.K. is employed at Beiersdorf AG. A.W. and J.K. were involved in the design of the study, the interpretation of the data, the writing of the manuscript, and the decision to publish the results. EDAT- 2020/12/10 06:00 MHDA- 2021/09/24 06:00 PMCR- 2021/02/17 CRDT- 2020/12/09 12:12 PHST- 2020/12/10 06:00 [pubmed] PHST- 2021/09/24 06:00 [medline] PHST- 2020/12/09 12:12 [entrez] PHST- 2021/02/17 00:00 [pmc-release] AID - 10.1021/acs.chemrestox.0c00253 [doi] PST - ppublish SO - Chem Res Toxicol. 2021 Feb 15;34(2):330-344. doi: 10.1021/acs.chemrestox.0c00253. Epub 2020 Dec 9.