Welcome to the Optibrium Community





Forgot login?
Register

Join the

Optibrium Community

Whether you're a StarDrop, Asteris or Ocura user or just want to know more, this community has been set up to provide you with direct access to the Optibrium support team and other users.

Join Today!Login



Publications & Presentations


Imputation of Assay Bioactivity Data using Deep Learning

Thursday, 14 February 2019 10:24
E-mail Print PDF
Matt Segall

This paper was printed in the Journal of Chemical Information and Modeling.

Imputation of Assay Bioactivity Data Using Deep Learning
Whitehead TM*, Irwin BWJ, Hunt P, Segall MD, Conduit GJ** (*Intellegens, **Cavendish Laboratory)
J. Chem. Inf. Model. (2019) 59(3) pp. 1197-1204

Abstract

We describe a novel deep learning neural network method and its application to impute assay pIC50 values. Unlike conventional machine learning approaches, this method is trained on sparse bioactivity data as input, typical of that found in public and commercial databases, enabling it to learn directly from correlations between activities measured in different assays.

In two case studies on public domain data sets we show that the neural network method outperforms traditional quantitative structure-activity relationship (QSAR) models and other leading approaches. Furthermore, by focussing on only the most confident predictions the accuracy is increased to R2 > 0.9 using our method, as compared to R2 = 0.44 when reporting all predictions.

You can download this paper as a PDF


Capturing and Applying Knowledge to Guide Compound Optimisation

Friday, 22 February 2019 13:23
E-mail Print PDF
Matt Segall

This article was published in the online edition of Drug Discovery Today; February 2019

Matthew Segall, Tamsin Mansley, Peter Hunt, Edmund Champness

Abstract

Successful drug discovery requires knowledge and experience across many disciplines and no current ‘artificial intelligence’ method can replace expert scientists. However, computers can recall much more information than any individual or team and facilitate transfer of knowledge across disciplines. We’ll discuss how knowledge relating to chemistry and the biological and physicochemical properties required for a successful compound can be captured. Furthermore, we’ll illustrate how, by combining and applying this knowledge computationally, a much broader range of optimisation strategies can be rigorously explored, and the results presented in an intuitive way for consideration by the experts.

You can download the article as a PDF


Latest Forums


Re:Decimal places in an export?

Friday, 03 August 2018 03:44

Thanks for your question Andre. Unfortunately, as you have noted, the number of significant figures in exported values is fixed at the moment. We've noted the problem and will address this a soon as possible in a future version. Sorry for the inconvenience and thanks again for pointing this out.


Category: General - How Do I...?
Views: 0

Decimal places in an export?

Tuesday, 31 July 2018 07:42

Hi there, I have set the decimal places in the molecular weight column to 2 and they are displayed as two. However, when I export to csv or text, or when I copy and paste into Excel, I only get 1 decimal place in my export. Is there a way to change that? Thank you very much in advance. Best regards Andre


Category: General - How Do I...?
Views: 35275

We're Hiring:C++ Software Engineers

Tuesday, 31 July 2018 01:57

As part of our exciting plans for future product enhancement and growth we are looking to recruit C++ software engineers to work on client- and server-side code development of Optibrium's cheminformatics and computational chemistry software product range. For more information, please visit here. Recruitment agencies need not apply.


Category: Optibrium News & Announcements
Views: 20341

Popular Downloads


ChEMBL Plug-in for StarDrop

Wednesday, 19 June 2019 15:23

ChEMBL is probably the foremost manually curated database of bioactive molecules with drug-like properties. It brings together chemical, bioactivity and genomic data to aid the translation of genomic information into effective new drugs. This script enables you to search ChEMBL directly from StarDrop, returning the data pre-formatted and ready to use for tasks such as:

  • Identifying potential off-target activities for your compounds
  • Understanding SAR around your compounds or targets
  • Building QSAR models to make predictions for new compounds

The installer file and instructions for how to install and use the script are provided in the following pages...

Read more...


Latest Forums

Read more >