Sarah Nexus

Sarah Nexus is a statistical software tool that gives you accurate mutagenicity predictions quickly.

Sarah Nexus logo

Sarah Nexus is a statistical software tool that gives you accurate mutagenicity predictions quickly. Early, accurate in silico toxicity tests using Sarah Nexus is the quick, inexpensive way to identify potentially toxic chemicals, aiding your experts in rejecting unsuitable drug candidates.

Why do you need Sarah Nexus?

The ICH M7 guideline proposes that a computational toxicology assessment should be performed using two complimentary (Q)SAR methodologies that predict the outcome of a bacterial mutagenicity assay. Specifically one methodology should be expert rule-based and the second methodology should be statistical-based. (Q)SAR models utilising these prediction methodologies should also follow the validation principals set forth by the Organisation for Economic Co-operation and Development (OECD).

Sarah Nexus and Derek Nexus (the Lhasa Limited expert toxicity prediction tool), in combination, can provide you with the means to meet the computational toxicological assessment requirements of the ICH M7 guidelines from one intuitive interface. You can assess your potential genotoxic impurities quickly and easily and submit those results to regulators reducing the need for time consuming and expensive in vitro tests.

Both Derek Nexus and Sarah Nexus have been designed independently to meet these validation principles, and both systems can be run from within the same Nexus interface to help simplify your workflow. The models provide completely independent predictions, with the option to consolidate into a single report.


How Sarah Nexus Can Benefit You

  • Clear and easily interpretable results:
    • Sarah Nexus predictions are clearly represented by positive and negative results, including confidence figures for the overall prediction and the the fragments on which it is based.
  • Understand why your chemical is predicted or not predicted to be mutagenic:
    • Transparent predictions facilitate a thorough review by experts; Sarah Nexus provides a confidence score and a structural explanation for each prediction.
  • Confidence in the data used to create the model and in the model itself:
    • Supplied with a pre-built model based upon Lhasa Limited's comprehensive, curated regulatory and public mutagenicity dataset. Vitic users are also able to review detailed experimental data associated with particular fragments.
  • One interface, two predictions:
    • Sarah Nexus sits within the Lhasa Knowledge Suite, providing a single interface from which to generate independent predictions from both Derek Nexus and Sarah Nexus.
  • Confidence in results is increased through the hierarchical approach:
    • By using a hierarchical approach, Sarah Nexus is able to provide results that are not only based on matching fragments, but that also refine the results further by considering structures that are most closely related to the query structure.
  • Reporting results directly to regulators:
    • Creation of customisable reports for one or more compounds in standard file formats (.pdf, .docx, HTML). Supports regulatory submission and sharing of information in-house.


How Sarah Nexus Works

Using Nexus in the Lhasa Knowledge Suite, you submit your structures to Sarah Nexus for processing. The structures are fragmented and these fragments are reviewed for activity versus inactivity. The model then arranges those 'interesting' fragments into a network of hypotheses (or nodes) and relevant hypotheses are used to inform an overall prediction of toxicity.

The Sarah Nexus prediction includes an overall conclusion about the toxicity in a structure, confidence rating in that prediction, as well as supporting examples.

For further information on methodology, confidence and interpretation click here.

Features of Sarah Nexus

Sarah Nexus has the following key features:

  • Fast processing - Sarah Nexus has the ability to run one or multiple predictions quickly, including batch predictions.
  • Easy prediction setup - One setup screen enables you to set up the prediction to suit your needs.
  • Transparent methodology - Predictions are completely transparent and allow an expert to review and explore the prediction with sufficient information to do so efficiently. 
  • Machine learning methodology - Sarah Nexus is a statistical tool that automatically discovers new relationships.
  • Customisable reporting - Choose the content types of interest in the order which suits your workflow. The ability to customise designs with your company's logo also provides a personalised, professional looking report for submission to regulators.
  • Visually interpretable results - Display of results includes an overall prediction of mutagenicity and weighted evidence, enabling users to easily interpret the outcome.
  • Model Builder - Users can duplicate the Lhasa model and supplement it with their own data, or build an entirely new model. These custom models can then be exported and shared with other people.

This is a printable version of