[adamzk]

I'm a patent holder for a pharmaceutically relevant class of compounds. There are two types of patents typically seen in pharma. One is procedural (how the drug is synthesized, isolated, formulated or administered) and another is composition of matter (the atoms in the molecule, their relative coordinates and the lengths and types of bonds that connect them). This program takes a target compound and does two things. 1) produces a library of similar compounds by structural diversification (making substitutions of atoms or small groups of atoms in the target compound with other atoms or groups which are known to behave similarly) with restrictions based on what has been patented under composition of matter. 2) It then takes each molecule and looks for ways it can be synthesized. It does this by breaking apart the molecule piece by piece until it obtains commercially available building blocks. These piecewise separations correspond to synthetic a steps in the other direction, which the program screens for literature precedence. It does this for every possible combination of piecewise separations until it finds a set of viable pathways from available compounds to the target. This is called retro synthesis. It then filters the potential synthetic routes for those that are covered by procedural patents until it has a list of non patented, commercially viable synthesis plans.

As you can imagine there are thousands of ways a moderately complex molecule could be deconstructed and the bank of known reactions is more than any one person can really grasp. That and the myriad patent literature and how cryptic and dense it can be make the problem particularly suited for algorithmic treatment. This is only being done now because cataloging all the research and patent literature (which goes back to the late 1800s) and digitally formatting in a way that allows it to be computationally analyzed and processed requires manual translation of each report by a human being. Not many people have the expertise required for this and those that do usually prefer less menial work. So it has taken this long to amass a digital library of sufficient size to give one confidence that the answers it provides are comprehensive and that further searching would be pointless.

[yholio]

> The research team hope that their software could help pharmaceutical companies in the protection of their intellectual property, and to hasten research into organic chemistry.

It seems what they are attempting to sell is a IP protection service: let us show you other molecules and synesis routes you should also patent defensively, without actually attempting them in practice. Pretty soon you will have algorithmically defined patents.

It's IP anti-science at it's worst.

[pariahHN]

Depends on how many possible patents there are. Patents do cost money to maintain/file. It's possible that there could be life saving drugs that have so many possible patents that compared to the actual likely financial return it would be uneconomical to patent them.

Which to be fair is probably very unlikely given how healthcare costs and whatnot work in America. Can always bump the price up to compensate for expenses.

BUT - this is still a very useful tool for locating possibly cheaper/simpler methods of producing drugs that have expired protections. There is a project out there that is working on a bioreactor kit that allows the safe home production of several common drugs that are not patent protected. There are also projects that could have been life saving but were already not financially viable that could be rescued by this program.

And if someone is fast enough and has the funds to burn, they could patent some of those processes and then do what Tesla did with their patents.

I think this may open up more opportunities in the long run than it closes.

[anilakar]

A not-so-fun fact: My country used to be on the 301 Special Report (IPR "rogue country" list) until 2015 because American pharmaceutical companies didn't consider procedural patents good enough. The last patents in that category were issued in 1995...

Apparently the income of Big Pharma investors is more important than the affordability of generics.

[michaelcampbell]

> Apparently the income of Big Pharma investors is more important than the affordability of generics.

You say this as if it is surprising.

[jordigh]

One thing I don't get: if you're trying to avoid patents, why go back to the 1800s? Don't you just need to look at recent patents that haven't expired?

[adamzk]

The papers going back that far are to determine which synthetic steps are experimentally viable. You can look at a molecule and think how could I make this? Well if I broke this particular bond it would make A and B, which I can order from a supplier. So let's search the literature to see if anybody has successfully carried out a reaction that connects an A-like molecule and a B-like molecule in a way that would yield the kind of bond(s) that connect them in our target. That's a lot of searching because for a typical drug, there are 10s to 100s of bonds and a total synthesis can take upwards of 20-30 steps. Thankfully, making and breaking most of the bonds is just not possible given the fundamental nature of the compounds (more specifically, it would take a ton of energy to put the molecule together this way, and if that much energy was applied, it would react at more reactive sites long before the desired reactivity occured). For others it is less clear, which is why having a comprehensive literature sure is useful. If your database goes all the way back to the 1800s you can say with some confidence that a certain step has never been done before and therefore assume its not possible (perhaps an incorrect assumption, but pharma isn't interested in developing novel types of reaction methodology for a target screen because if it hasn't been done already, it would probably take several years and the chance of success is low. And besides, that's what graduate students are for ;)

So the literature search is to find out what's possible. Among the possibilités, the only ones of interest are those that are not covered in patents, hence the second screen.

[jordigh]

Thanks so much for your extensive and informative answers.

[vidarh]

Depends what you want: If you want to find new processes and compounds that you can patent, then avoiding older patents is essential, as they're prior art.

On the other hand, if you want to find new processes and compounds that aren't patented, then finding a past expired patent covering a part of the process would mean that part of the process is "safe" (not finding one might mean it is safe, or might mean you've overlooked something)