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…
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…
Machine Learning 101: How to train your first QSAR model
My hope is that these posts will be of interest to people who want to understand more of the nuts…
What’s the difference between QSAR and imputation predictive models – which method should I use and when?
We’re often asked, “What’s the difference between QSAR and imputation models?”, so I’m going to explain how the methods differ, their advantages and disadvantages, and when each approach is applicable.
How much does drug discovery software cost?
How number of users affect drug discovery software costs The number of people who need access to the platform is…
Aquatic toxicity
Evaluate aquatic toxicity with StarDrop Aquatic Toxicity model.
Can I find rate of metabolism using the Metabolism module?
Quantitative prediction of metabolic rate for diverse chemistry is currently intractable based on structure alone. Local models of metabolic rate…
How can I calculate descriptors using Auto-Modeller?
To calculate descriptors on the current data set, click the Calculate descriptors on the current dataset button within the Auto-Modeller…
Where can I get the list of descriptors calculated by StarDrop?
A list and description of the descriptors used by the Auto-Modeller is available in Appendix 17.2 of the StarDrop Reference…
What papers are available for published by StarDrop users and included the results of Auto-modeller?
We have published several papers using the methods in the Auto-Modeller. They are: In most cases, our users apply the…
Does your model-building workflow detect outliers?
Auto-Modeller doesn’t currently detect outliers when building models, it is dependent on a user’s own judgement. The Gaussian Processes methods…
Is there a way to restart and clear the queue of jobs submitted by the Auto-modeller?
Please check with your internal I.T team with admin access to the server. They can run the followi:ng commands “/etc/init.d/StarDrop_amg…
How do I build a model based on my data?
In addition to the StarDrop Models, it is possible to create your own models from your data with the Auto-Modeller…
What do the Glowing Molecule colours mean?
A Glowing Molecule represents the model result indicating the parts of the molecule that have the greatest influence on the…
Perfecting the use of imperfect QSAR models
In this webinar, we examine the effective use of QSAR modelling in drug discovery and discuss a variety of pain points for medicinal chemists in knowing when a model can be trusted and how to avoid common pitfalls.
Automatic QSAR model building and validation
This example explores the application of the Auto-Modeller module to build a QSAR model of potency against the Muscurinic Acetylcholine M5 receptor, based on public domain Ki data. The resulting model is applied to novel compound to predict their properties and visualise the SAR.
