Drug development is in large part a search problem, looking to find useful compounds within this massive space. A brute-force search is impossible; even if it took only a couple seconds to examine each possible compound you’d see several deaths of our sun (a lifespan of about 10 billion years) before fully exploring that space.
More effective techniques for searching this space include slightly modifying existing drugs for different therapeutic applications (»me-too« compounds) and literally looking at plants and indigenous medical traditions for leads (this general practice is called »bioprospecting« and this particularly colonialist form is called »biopiracy«).
Of course with the proliferation of machine learning there is a big interest in searching this space computationally. Two main categories are virtual screening (looking through known compounds for ones that look promising) and molecular generation (generating completely new compounds that look promising).
Because drug development is so difficult, companies rely on patents to monopolize any promising results. One crucial criteria for a patent is that the invention must be novel; that is, the invention cannot have already been known to the public. An existing publicly-known instance of an invention is called »prior art« and can invalidate a patent claim. However, sufficient variations to an invention may qualify it as original enough to be patentable (this is the idea behind evergreening, described above).
If a drug is discovered and made public prior to a patent claim on it, it would function as prior art and make that compound unpatentable in its current form. If we were able to generate new molecules that could function as useful drugs, and make public those new molecules, then perhaps we can prevent companies from patenting them and maintaining a temporary monopoly on their distribution.
matter.farm is an open-source and public computational drug discovery system. One of our goals was to frame computational drug discovery as a potential mechanism for drug development for public good. Of course, there’s nothing about the current system that can’t become more public good oriented as-is, except for entrenched interests. But our drug discovery system, in combination with patent law, means that any beneficial compounds discovered by our system automatically become unpatentable. The system originally ran continuously, proposing new compounds and estimating their applications every few seconds, and published these compounds to the website matter.farm, thus placing them in the public and making them prior art (in theory, at least). Because the space of possible compounds is so large, it’s unlikely that any useful compound is produced by our system. Our limited resources mean that our training was not comprehensive and the rate of new compound generation is quite low. In theory, a dedicated set of hardware and more fine-tuning would have a better chance of worthwhile discoveries. The project is meant more to put forth a model for how drug discovery might move forward for common benefit. The machine learning component is just a means, the point is public ownership of essentials like medical discoveries.
Other efforts to address the problems with the pharmaceutical industry can be found in initiatives like Medicare for All and the proposed Prescription Drug Price Relief Act, and the organizing happening around those. The issues with the pharmaceutical industry are just one piece of a more general hostility in American healthcare.
There is also a burgeoning DIY medicine movement which aims to build alternatives to industrialized medicine, providing autonomy, access, and reliability where those are normally withheld. For example, the artist Ryan Hammond is working on genetically modifying tobacco plants to produce estrogen and testosterone, and the Four Thieves Vinegar Collective (discussed in the Ashes Ashes »Pill of Sale« episode) provides instructions for a DIY EpiPen and a DIY lab (»MicroLab«) for synthesizing various pharmaceuticals, including Naloxone and Solvadi.
This post was originally written in 2018 and published on space & times, https://spaceandtim.es/projects/matter_farm/ (accessed April 30, 2021).
Francis Tseng is a software engineer and lead independent researcher at the Jain Family Institute. His interests include simulation, games, political ecology, and technology.