PMID- 27458072
OWN - NLM
STAT- MEDLINE
DCOM- 20170324
LR  - 20220311
IS  - 1879-3177 (Electronic)
IS  - 0887-2333 (Linking)
VI  - 36
DP  - 2016 Oct
TI  - Consensus of classification trees for skin sensitisation hazard prediction.
PG  - 197-209
LID - S0887-2333(16)30143-6 [pii]
LID - 10.1016/j.tiv.2016.07.014 [doi]
AB  - Since March 2013, it is no longer possible to market in the European Union (EU) 
      cosmetics containing new ingredients tested on animals. Although several in 
      silico alternatives are available and achievements have been made in the 
      development and regulatory adoption of skin sensitisation non-animal tests, there 
      is not yet a generally accepted approach for skin sensitisation assessment that 
      would fully substitute the need for animal testing. The aim of this work was to 
      build a defined approach (i.e. a predictive model based on readouts from various 
      information sources that uses a fixed procedure for generating a prediction) for 
      skin sensitisation hazard prediction (sensitiser/non-sensitiser) using Local 
      Lymph Node Assay (LLNA) results as reference classifications. To derive the 
      model, we built a dataset with high quality data from in chemico (DPRA) and in 
      vitro (KeratinoSens and h-CLAT) methods, and it was complemented with 
      predictions from several software packages. The modelling exercise showed that 
      skin sensitisation hazard was better predicted by classification trees based on 
      in silico predictions. The defined approach consists of a consensus of two 
      classification trees that are based on descriptors that account for protein 
      reactivity and structural features. The model showed an accuracy of 0.93, 
      sensitivity of 0.98, and specificity of 0.85 for 269 chemicals. In addition, the 
      defined approach provides a measure of confidence associated to the prediction.
CI  - Copyright (c) 2016 The Authors. Published by Elsevier Ltd.. All rights reserved.
FAU - Asturiol, D
AU  - Asturiol D
AD  - Joint Research Centre, Via Enrico Fermi 2749, Ispra 21027, VA, Italy. Electronic 
      address: david.asturiol-bofill@ec.europa.eu.
FAU - Casati, S
AU  - Casati S
AD  - Joint Research Centre, Via Enrico Fermi 2749, Ispra 21027, VA, Italy.
FAU - Worth, A
AU  - Worth A
AD  - Joint Research Centre, Via Enrico Fermi 2749, Ispra 21027, VA, Italy.
LA  - eng
PT  - Journal Article
DEP - 20160722
PL  - England
TA  - Toxicol In Vitro
JT  - Toxicology in vitro : an international journal published in association with 
      BIBRA
JID - 8712158
RN  - 0 (Haptens)
SB  - IM
MH  - Computer Simulation
MH  - Consensus
MH  - *Dermatitis, Allergic Contact
MH  - Haptens/*classification/*toxicity
MH  - Local Lymph Node Assay
MH  - *Models, Biological
MH  - Sensitivity and Specificity
MH  - Skin
OTO - NOTNLM
OT  - Decision tree
OT  - In silico
OT  - In vitro
OT  - Prediction
OT  - QSAR
OT  - Skin sensitisation
EDAT- 2016/07/28 06:00
MHDA- 2017/03/25 06:00
CRDT- 2016/07/27 06:00
PHST- 2015/12/18 00:00 [received]
PHST- 2016/07/08 00:00 [revised]
PHST- 2016/07/21 00:00 [accepted]
PHST- 2016/07/27 06:00 [entrez]
PHST- 2016/07/28 06:00 [pubmed]
PHST- 2017/03/25 06:00 [medline]
AID - S0887-2333(16)30143-6 [pii]
AID - 10.1016/j.tiv.2016.07.014 [doi]
PST - ppublish
SO  - Toxicol In Vitro. 2016 Oct;36:197-209. doi: 10.1016/j.tiv.2016.07.014. Epub 2016 
      Jul 22.