Lhasa Limited shared knowledge shared progress

EC3 Predictions for Skin Sensitisation

Derek Nexus contains expert-derived functionality to provide a quantitative EC3 prediction for skin sensitisation.

For further information regarding EC3 predictions and how this has been implemented within Derek Nexus, please take a look at a poster presented by Martyn Chilton at the Society of Toxicology 55th Annual Meeting in New Orleans called: Quantitative Prediction of Skin Sensitisation Potency based on Structural Alert Spaces. In addition, a recorded webinar by Dr. Jeff Plante, highlighting the development of the EC3 prediction engine, can also be viewed.


The Skin Sensitisation Brochure can be found here.  



Derek Nexus already has a well-established skin sensitisation endpoint, but Derek Nexus v5.0.1 gives a quantitative EC3 prediction for query compounds that fire a skin sensitisation alert.

The prediction is built on a Nearest Neighbour model, where the nearest neighbours are taken from a reference set of compounds that exclusively fire the same alert as the query compound. A similarity score is calculated for the nearest neighbours and an EC3 prediction is made.

The nearest neighbour compounds are selected from over 650 compounds in the Lhasa EC3 dataset; the EC3 values for these compounds have been taken from literature and curated by Lhasa scientists. For compounds with multiple literature EC3 values, the median was taken to reduce the interference from outliers (Figures 1-3).




A diagrammatic representation of the Nearest Neighbour model can be seen below  (Figure 1). 

The model involves a three-step process:

  • Firstly, the query compound is processed in Derek to determine whether a skin sensitisation alert is fired
  • Secondly, those compounds from the Lhasa EC3 dataset which fire the same skin sensitisation alert as the query compound are identified. Because they fire the same alert, these compounds are believed to cause skin sensitisation through the same mechanism as the query compound.
  • Thirdly, the compounds in the Lhasa EC3 dataset are assessed using an in-house structural fingerprinting technique. They are then evaluated for their similarity to the query compound using the Tanimoto score. Up to 10 nearest neighbours are highlighted and are used to make the EC3 prediction, based on a weighted average. If less than 3 nearest neighbours are found, no prediction is made. See Figure 1 for a visual representation.

Figure 1: The steps taken in order to predict an EC3 value


Validation Data

Lhasa scientists have assessed the performance of the model in predicting EC3 values for a test set of compounds using several measures of accuracy (Figure 2). The model has been designed not to under-predict, as this may bring about exposure to a chemical that is a sensitiser. The model correctly or over-predicts the EC3 value, to within 10-fold of the experimental value, 93.5% of the time. Furthermore, the model correctly predicts or over-predicts the ECETOC and GHS classification 87.0% and 91.3% of the time.

The ECETOC (European Centre for Ecotoxicology and Toxicology of Chemicals) classifications are split into four different categories depending on the numerical value (Figure 1).

Figure 1

The GHS (Globally Harmonized System of Classification and Labelling of Chemicals) classification has two subcategories: 1A and 1B. If an EC3 value is less than or equal to 2%, it is classified as 1A, if an EC3 value is greater than 2, it is classified as 1B.

Figure 2: Performance Data for Derek EC3 Predictions

Features and Benefits


Visual (Figure 1)

  • A clear, graphical representation of the EC3 prediction is provided, which shows the nearest neighbours, their Tanimoto similarity to the query compound and their EC3 values.
    • Each nearest neighbour is clearly identified as either a sensitiser or a non-sensitiser.
  • There is an option to display the ECETOC classification in addition to the numerical EC3 prediction, these classifications can assist experts in categorising compounds.
  • The structures of the nearest neighbours are shown, and selecting a compound brings up an information box that includes data sources and references.

Expert Fine-Tuning

  • The information that has gone into making the prediction is transparently shown and nearest neighbours can be added to or removed from the prediction based on expert assessment.
  • Users can supplement the Lhasa EC3 dataset with their own data to increase the chemical space covered. However, the compounds added must fire a skin sensitisation alert in Derek, otherwise they cannot be used as a nearest neighbour.


  • Greater understanding of the skin sensitisation risk of compounds:
    • The prediction of skin sensitisation potency allows experts to more fully understand the risk a particular compound poses.
  • Clear and easily interpretable results:
    • The clear visual representation ensures that the expert assessment of potential sensitisers is quick and easy.
  • Understand why chemicals have been predicted as sensitisers:
    • Transparent predictions facilitate a thorough review by experts; for skin sensitisers, Derek Nexus provides the EC3 values and structures of nearest neighbours.
  • Facilitate expert review:
    • Experts can fine-tune the EC3 predictions by adding or removing compounds from the calculation based on their expert knowledge.

Figure 1: The Derek EC3 prediction for 3-(methylamino)phenol

Contact Us

© 2017 Lhasa Limited | Registered office: Granary Wharf House, 2 Canal Wharf, Leeds, LS11 5PS, UK Tel: +44 (0)113 394 6020
VAT number 396 8737 77 | Lhasa Limited is registered as a charity (290866)| Company Registration Number 01765239 (England and Wales).

QuestionPro supports sample survey questions such as multiple choice, drop-down menu, likert-scale, semantic differential, matrix, constant sum, drag-and-drop, slider-scale, net-promoter scale, and many more question types.