Machine Learning And The March Towards Precision Medicine

This post was published on the now-closed HuffPost Contributor platform. Contributors control their own work and posted freely to our site. If you need to flag this entry as abusive, send us an email.

The use of big data in medical research is a topic I've touched on a number of times in the past year. Perhaps the most prominent example of the potential came via a study examining the impact automation could have on the process. It suggested that automation could reduce the cost of drug discovery by approximately 70%.

At the vanguard of this movement has been British startup BenevolentAI, who use AI to identify promising targets for medical research. A good example of their work comes via a recent partnership with the Sheffield Institute for Translational Neuroscience (SITraN), part of the University of Sheffield and one of the world’s leading centres for research into Motor Neurone Disease, Alzheimer’s and Parkinson’s Disease. SITraN announced that they have achieved positive results from early work into a drug candidate recommended by BenevolentAI.

The work conducted by SITraN was into the efficacy of a drug for Moror Neuron Disease (MND), with early signs suggesting the drug could prevent the death of motor neurones in patient cell models, thus delaying the onset of the disease.

The next stage is to assess the suitability and potential of the drug for clinical development, with the research due for publication later this year. It's an approach that would not have been possible without AI first identifying the right compounds to target.

“This is an exciting development in our research for a treatment for ALS. BenevolentAI came to us with some newly identified compounds discovered by their technology - two of which were new to us in the field and, following this research, are now looking very promising. Our plan now is to conduct further detailed testing and continue to quickly progress towards a potential treatment for ALS,” SITraN say.

Big medicine

Of course, there are many fascinating applications of big data in medical research at the moment, with a recent partnership between pharma giant GSK and Regeneron another fine example. They will be working with a huge dataset from the UK Biobank to use the genetic data contained within to look for insights into disease.

The researchers are looking at a specific portion of the genome known as the exome, which researchers believe is where the real action occurs in terms of drug therapies.

The partnership will see 50,000 samples sequenced via the Regeneron technology by the end of 2017, with the full 500,000 database of samples contained in UK Biobank expected to be done within three to five years. The new sequences will then be reincorporated into the Biobank to be accessed and used by fellow researchers, but only after GSK and Regeneron have exclusive access for nine months.

“As a result of the altruism and continued support of our volunteer participants, UK Biobank has amassed an enormous amount of securely-stored health, lifestyle, medical and biological data. Genetics research is already shaping better treatments. This exciting initiative is expected to start producing novel findings rapidly during this year and will make UK Biobank even more useful for health-related research,” Biobank say.

It's clear that medicine is becoming smarter, with fascinating applications of AI on increasingly significant big data sets allowing us to march boldly towards a world of precise and targeted medicine.

Popular in the Community