PMID- 31569429
OWN - NLM
STAT- MEDLINE
DCOM- 20200212
LR  - 20231014
IS  - 1422-0067 (Electronic)
IS  - 1422-0067 (Linking)
VI  - 20
IP  - 19
DP  - 2019 Sep 28
TI  - Skin Doctor: Machine Learning Models for Skin Sensitization Prediction that 
      Provide Estimates and Indicators of Prediction Reliability.
LID - 10.3390/ijms20194833 [doi]
LID - 4833
AB  - The ability to predict the skin sensitization potential of small organic 
      molecules is of high importance to the development and safe application of 
      cosmetics, drugs and pesticides. One of the most widely accepted methods for 
      predicting this hazard is the local lymph node assay (LLNA). The goal of this 
      work was to develop in silico models for the prediction of the skin sensitization 
      potential of small molecules that go beyond the state of the art, with larger 
      LLNA data sets and, most importantly, a robust and intuitive definition of the 
      applicability domain, paired with additional indicators of the reliability of 
      predictions. We explored a large variety of molecular descriptors and 
      fingerprints in combination with random forest and support vector machine 
      classifiers. The most suitable models were tested on holdout data, on which they 
      yielded competitive performance (Matthews correlation coefficients up to 0.52; 
      accuracies up to 0.76; areas under the receiver operating characteristic curves 
      up to 0.83). The most favorable models are available via a public web service 
      that, in addition to predictions, provides assessments of the applicability 
      domain and indicators of the reliability of the individual predictions.
FAU - Wilm, Anke
AU  - Wilm A
AD  - Center for Bioinformatics, Universitat Hamburg, 20146 Hamburg, Germany. 
      wilm@zbh.uni-hamburg.de.
AD  - HITeC e.V, 22527 Hamburg, Germany. wilm@zbh.uni-hamburg.de.
FAU - Stork, Conrad
AU  - Stork C
AD  - Center for Bioinformatics, Universitat Hamburg, 20146 Hamburg, Germany. 
      stork@zbh.uni-hamburg.de.
FAU - Bauer, Christoph
AU  - Bauer C
AUID- ORCID: 0000-0002-6035-6944
AD  - Department of Chemistry, University of Bergen, 5020 Bergen, Norway. 
      christoph.bauer@uib.no.
AD  - Computational Biology Unit (CBU), University of Bergen, 5020 Bergen, Norway. 
      christoph.bauer@uib.no.
FAU - Schepky, Andreas
AU  - Schepky A
AUID- ORCID: 0000-0001-5258-3605
AD  - Front End Innovation, Beiersdorf AG, 20253 Hamburg, Germany. 
      andreas.schepky@beiersdorf.com.
FAU - Kuhnl, Jochen
AU  - Kuhnl J
AUID- ORCID: 0000-0001-8421-9381
AD  - Front End Innovation, Beiersdorf AG, 20253 Hamburg, Germany. 
      jochen.kuehnl@beiersdorf.com.
FAU - Kirchmair, Johannes
AU  - Kirchmair J
AUID- ORCID: 0000-0003-2667-5877
AD  - Center for Bioinformatics, Universitat Hamburg, 20146 Hamburg, Germany. 
      kirchmair@zbh.uni-hamburg.de.
AD  - Department of Chemistry, University of Bergen, 5020 Bergen, Norway. 
      kirchmair@zbh.uni-hamburg.de.
AD  - Computational Biology Unit (CBU), University of Bergen, 5020 Bergen, Norway. 
      kirchmair@zbh.uni-hamburg.de.
LA  - eng
GR  - BFS2017TMT01/Bergens Forskningsstiftelse/
PT  - Journal Article
DEP - 20190928
PL  - Switzerland
TA  - Int J Mol Sci
JT  - International journal of molecular sciences
JID - 101092791
RN  - 0 (Cosmetics)
SB  - IM
MH  - Cosmetics/adverse effects
MH  - Drug-Related Side Effects and Adverse Reactions
MH  - *Immunization
MH  - *Local Lymph Node Assay
MH  - *Machine Learning
MH  - Molecular Mimicry
MH  - Prognosis
MH  - Reproducibility of Results
MH  - Skin/*drug effects/*immunology
PMC - PMC6801714
OTO - NOTNLM
OT  - applicability domain
OT  - chemical space
OT  - cosmetics
OT  - drugs
OT  - in silico models
OT  - local lymph node assay (LLNA)
OT  - machine learning
OT  - pesticides
OT  - prediction
OT  - skin sensitization potential
COIS- J.K. (Jochen Kuhnl) and A.S. are employed at Beiersdorf AG and A.W. is funded by 
      Beiersdorf AG through HITeC e.V. A.W., A.S. and J.K. (Jochen Kuhnl) 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- 2019/10/02 06:00
MHDA- 2020/02/13 06:00
PMCR- 2019/10/01
CRDT- 2019/10/02 06:00
PHST- 2019/08/27 00:00 [received]
PHST- 2019/09/17 00:00 [revised]
PHST- 2019/09/18 00:00 [accepted]
PHST- 2019/10/02 06:00 [entrez]
PHST- 2019/10/02 06:00 [pubmed]
PHST- 2020/02/13 06:00 [medline]
PHST- 2019/10/01 00:00 [pmc-release]
AID - ijms20194833 [pii]
AID - ijms-20-04833 [pii]
AID - 10.3390/ijms20194833 [doi]
PST - epublish
SO  - Int J Mol Sci. 2019 Sep 28;20(19):4833. doi: 10.3390/ijms20194833.