The machines have already surpassed humans in a number of areas, including chess and bird identification. They can also predict complex protein structures. When it comes to really clever and intuitive things, such as original scientific research or chess, humans still like to believe that they have the edge.
It’s possible that we need to rethink our approach. Daniel Cohen president at the Canadian drug discovery firm Valence Labs, discussed the intriguing, if not a little unnerving possibility of “autonomous science discovery” during the RAAIS Artificial Intelligence conference held in London, earlier this month. AI models that are trained on data from specialists could soon generate hypotheses, run experiments and learn from their results. He said, “Our mission is industrialising scientific discovery.”
It doesn’t take long to see the excitement of people working in computational biology about AI. Google DeepMind, a company that conducts AI research, has spun off Isomorphic Labs to explore this area after its AlphaFold modelled 200mn proteins structures.
Computational biology has the potential to advance scientific research, speed up drug discovery and improve outcomes for patients. The machines have many advantages over their human counterparts, such as researchers and lab assistants. One thing is that they don’t have to deal with colds, hangovers, or messy relationships.
Christina Curtis tells me, “I’m so encouraged by the speed at which this field is progressing.” She is a professor of genetics, biomedical data sciences, and statistics at Stanford University School of Medicine. This is changing the way we perceive disease, detect malignancy, and treat it.
Curtis is the senior author in a paper that was published in Science last week. The article explores the heritability in malignancy of various subsets in cancer. The researchers used machine learning to analyze thousands of genomes of individuals with preinvasive and invasive cancers in order to examine differences in their immune response. The researchers found that the germline genome inherited by individuals at conception “sculpted the way” tumour cells developed in an individual.
This research could lead to an earlier diagnosis and better personalised treatment, increasing the chance of survival. “More that 50% of cancer diagnoses occur at stage 4 or higher. Curtis claims that we are receiving information too late for us to make informed decisions. “Ideally, this could be done more preemptively.”
Two major constraints exist. According to an industry executive, “genetics only provides hints and not answers”. Machines have identified many targets for drug research, but very few have proven successful. Even if technology leads to scientific breakthroughs it can take many years for new drugs to be approved by regulatory agencies.
Thore Graepel was the global leader for computational science at Altos Labs and helped to develop the AlphaGo software at Google DeepMind. AlphaGo’s victory over the world’s best player in the ancient game Go was hailed as a breakthrough in machine learning. Graepel said at the RAAIS Conference that the biological complexity he faces now in cell rejuvenation is “orders-of magnitude” greater. He said, “I’ve never seen such complexity with so few data.”
Second, data is scarce. Curtis says that while patient data is “liquid gold” to researchers, we don’t yet have the tools necessary to collect it regularly. Combining a patient’s genomic information with their longitudinal health data collected throughout their treatment and life would be the most useful.
It will take a massive transformation to reorient healthcare systems away from late diagnosis, treatment and monitoring towards early monitoring and preventative measures. The Labour Party, which is expected to win the general elections next week, has promised to speed up this transformation of the National Health Service. Labour’s manifesto pledges to create a “Fit for the Future” fund to double the amount of CT and MRI scans used to detect cancer in its early stages.
Voters are sceptical about politicians who make big promises. The strain on the public finances of ageing societies could soon force governments to take this path. The Dutch philosopher Desiderius Erasmus is said to have told us, five centuries ago, that “prevention is better than treatment.” AI could be one of our greatest assets.
Post Disclaimer
The following content has been published by Stockmark.IT. All information utilised in the creation of this communication has been gathered from publicly available sources that we consider reliable. Nevertheless, we cannot guarantee the accuracy or completeness of this communication.
This communication is intended solely for informational purposes and should not be construed as an offer, recommendation, solicitation, inducement, or invitation by or on behalf of the Company or any affiliates to engage in any investment activities. The opinions and views expressed by the authors are their own and do not necessarily reflect those of the Company, its affiliates, or any other third party.
The services and products mentioned in this communication may not be suitable for all recipients, by continuing to read this website and its content you agree to the terms of this disclaimer.