Funding More Work on Deep Learning for Drug Discovery to Treat Aging
Recently Y Combinator announced their intent to fund companies working on treatments for aging. It is one of the many signs of a growing interest in this area of development in the venture community. One of the early results appears to be more funding for computational methods of improving drug discovery, with therapies for aging as the rallying cry, after the established Insilico Medicine model. It makes sense that a primarily software-focused part of the venture community would move into a new area, biotechnology, by funding ventures that apply computational technology to the space. That says nothing about the effectiveness of the approach, of course, just that it is a natural evolution of established knowledge and interests.
There is certainly a lot of room for improvement when it comes to the cost and effort required to find and prove out small molecule and other drugs to treat specific conditions or target specific biological mechanisms with minimal side-effects. It is reasonable to think that established deep learning approaches can be fruitfully applied here, to focus attention on molecules in the standard libraries that might otherwise be overlooked, and to design new therapeutic molecules based on existing data and desired characteristics. There is, however, a sizable difference between, say, applying this technology to the search for senolytics and cross-link breakers, approaches that can in principle produce rejuvenation, or applying it to the search for more geroprotectors like metformin, rapamycin, and so forth. The latter can only marginally slow the progression of aging, and the research community is struggling to produce anything in that part of the field that can do any better than exercise and calorie restriction. It remains to be seen as to the direction taken by this venture.
Over the past few decades, an unignorable amount of evidence has piled up that we are able to slow the biological processes of aging in animals. This evidence has been accumulating along multiple lines of research covering many different therapies. We're left with the same conclusion: by understanding and directly treating the biological damage accumulated while aging, we can find powerful new therapies for fighting disease and living healthier, longer lives.
At Spring Discovery, we're accelerating the discovery of these therapies with our machine learning-based drug discovery platform. And we're proud to announce that we've raised a $4.25M seed round from a team of biotech funders who support our long-term vision. Why do therapies focused on aging present such a profound opportunity? Because aging is the single greatest risk factor for the most detrimental diseases on Earth - cardiovascular disease, neurodegenerative disease, pulmonary disease, cancer, muscle wasting, and more - and drugs that slow the biological damage accumulated while aging have the potential to reduce the incidences of these diseases, possibly simultaneously.
Combined, aging represent A) one of the most important problems facing humanity and B) a problem that looks increasingly possible to tackle. The diseases of old age don't discriminate, but they can be fought. We believe that in the not-too-distant future the discovery of therapies for aging will provide some of the most effective tools in history for reducing our burden of disease and extending our healthy lifespan. Spring Discovery's mission is to dramatically accelerate the realization of that future. And we're bringing a new set of machine learning tools to bear on this challenge.
Interestingly, their two lead scientists worked at Irina Conboy's labo.