× Medicines Discovery Catapult

AI says no, but can you trust your model?

Any machine learning algorithm can make predictions about a quantity of interest, whether it be bioactivity, lipophilicity or solubility. But, how much confidence should you have in the model? Several quality indicators for predictive models exist; for example, how well it performs in cross validation. Cross validation is one of the key techniques used to […]

Read more

How blood DNA, as a biomarker, is revolutionising cancer treatment

With the advent of personalised medicine, cancer research is not only a matter of finding drugs that kill cancer, but determining which patients are most likely to benefit from a given type of treatment. The finding that cancer cells release their DNA into the bloodstream revolutionised the way we gain insight into the cancer’s biology. […]

Read more

A patient’s perspective on using samples and data for research

What factors encourage patients to donate clinical samples and data for research? I think there are several factors that encourage patients to donate samples. Data is a slightly separate issue, but together they come down to the three things we already know from surveys about why patients participate in research: Firstly we want to benefit […]

Read more

Stem cells and organoids… what’s all the fuss about?

Just a few years ago the idea of stem cells was seen more as science fiction than science fact. The general public as a whole didn’t really know what stem cells were, or why they were being used. Even today, when speaking to people outside of the life sciences area about my work, they often […]

Read more

Is it AI, or is it good old-fashioned statistics?

The power of Artificial Intelligence to drive cars, accurately diagnose diseases, recognise cats on the internet, and augment human faces with cartoon rabbit ears is driving a huge wave of interest in the field – Including how it can enable drug discovery. Investment inevitably tends to follow, and consequently the tendency to rebrand many techniques […]

Read more

Helping the drug discovery community deliver

Our CEO, Chris Molloy, attended the Delivering novel therapies in the 21st century meeting at The Royal Society from 24th – 25th October 2018. Here, he shares his key learnings from the event – and what they mean for drug discovery. Drug discovery is still failing too often: new treatment types are outdating the ‘white […]

Read more

Building an ecosystem to support data-driven health startups

The UK is in an excellent position to establish a world-leading position in the field of data-driven health. Technologies such as machine learning, computer vision, and neural networks will accelerate drug discovery by measuring and characterising target engagement, validating targets in translatable cell models, improving our understanding of drugs, disease and drug-target interactions within patients. […]

Read more

Writing a winning grant application

Bidding for grants and funding can be a very frustrating, tiresome and demoralising process. Hours can be wasted putting pen to paper, just so your dreams can be shattered months later after “so-called” experts and faceless bureaucrats tear your hard work apart. Of course, this is all part of the democratic process required to justify […]

Read more

On-demand sampling

The majority of biobank samples are collected as surgical excess, diagnostic remnants or post mortem tissue. While all of these sources are extremely valuable, they each have limitations. Surgical excess and diagnostic samples come from diseased patients, often cancer donors, and the closest to a ‘normal’ sample is adjacent tissue – that is, tissue obtained […]

Read more

Science & Technology

Informatics

Virtual R&D

Discovery Syndicates

Samples and Data