Enhanced ADME predictions : New and improved models in StarDrop 8
Designing and optimising new drugs involves balancing multiple objectives, including target activity, metabolic stability, absorption, safety, and more. Predictive models…
Counting what counts: Structural descriptors in StarDrop
In medicinal chemistry, it’s often the little things, like the subtle changes in a molecule’s structure, that make the difference.…
Optibrium Delivers Real-Time Collaboration in its Comprehensive Molecular Design Platform with StarDrop 8
Latest release accelerates hit-to-candidate progression by keeping teams aligned, eliminating inefficiencies and enabling better prioritisation decisions CAMBRIDGE, UK, 04 November…
Pushing the limits of QSAR modelling
Probably the most common use of machine learning (ML) in drug discovery is QSAR modelling, where we predict the properties…
Improving predictions of molecular properties with graph featurisation and heterogeneous ensemble models
Abstract We explore a “best-of-both” approach to modelling molecular properties by combining learned molecular descriptors from a graph neural network…
Optibrium partners with TalTech on EU-funded PhD programme to advance sustainable drug discovery
The research will focus on developing faster and more accurate methods for predicting drug metabolism. CAMBRIDGE, UK, 02 July 2025…
How can I predict toxicity in drug discovery?
The importance of predicting toxicity early in drug development Highlighting safety and toxicity early in the drug development process is…
Why don’t my QSAR models work?
Why QSAR models matter in drug discovery Before we start troubleshooting, let’s remember why we build and run these models…
AI is not magic: A scientist’s guide to cutting through the hype
Ground truth matters more than algorithm hype In drug discovery, we deal in imperfect data. Assays are noisy. Endpoints are…
Machine Learning 101: How to optimise hyperparameters
What are parameters in machine learning models? The regular (non-hyper) parameters of an ML model are the numbers that it…
StarDrop vs LiveDesign: Finding the right collaboration platform for your medicinal chemistry team
The launch of StarDrop 8 adds powerful real-time collaboration to our medicinal chemistry toolkit for molecule design, optimisation and data…
How much does 3D molecular modelling software cost?
Introduction 3D molecular modelling plays a vital role in modern drug discovery, offering powerful applications to streamline research, reduce costs,…
How can categorical models provide value in supporting compound prioritisation?
Introduction In early-stage drug discovery, medicinal chemists rely on predictive models to help guide which compounds to synthesise or test…
How to evaluate the performance of QSAR/QSPR classification models?
Introduction After training a classification model, we would like to evaluate its performance by using the trained model on an…
Maximising the ROI of AI – A comprehensive evaluation of Cerella for drug discovery success
When evaluating any new technology, it is important to establish how you will validate whether it will deliver a return…
How is AI transforming drug discovery chemistry?
Imagine you’re trying to find the correct key to unlock a treasure box, but there are billions of keys to…
Derek Nexus for toxicity prediction – What package is right for me?
What is Derek Nexus? Developed by Lhasa Limited, Derek Nexus is an expert-knowledge based system that draws on over 40…
Machine learning 101: How to build your first neural network
What are neural networks? Neural networks (NNs) in various forms are very common nowadays, and specific architectures are used for…
Which ADMET properties are important for me to predict?
How can I predict my compound’s absorption? The first of the ADMET properties relate to absorption. Understanding how a drug…
