Comment by morraa | Hacker News Reader

Comment by morraa | Hacker News Reader

Parent Full thread

Yes absolutely, the variance of pricing across different custom synthesis providers can be surprising. This we think though is actually an opportunity to serve our end users (drug hunters) better. Generally the cost of synthesis is a function of raw material costs and the labor time (translates to number of synthetic steps and risk of each step). All these parameters are datapoints we have access to or can model through ML. As such we've found that the ability to search large chemical databases is a huge saving when many clients may often just default to use a single CRO provider who may not be the best provider for their synthesis request. We are aiming to build a good network of reliable CRO providers to address the shortcoming and work with them to improve algorithms to optimize for reaction conditions etc.

Regarding pricing model this is something we are still working on. And yes you've hit the nail on the head -- We could charge the drug hunter (SaaS or IP) or we could charge the CROs that we send the custom synthesis to. Love to hear your thoughts here.

In my experience, cost is not related to materials and labor. For example, CROs know if they're likely the only company that can make a product and will charge accordingly. Often and to me sadly, a bidding processes is needed to determine market value of production. I've seen CROs instantly cut pricing in half if you present another option.

I would be cautious with chemical database (unsure which you are using) as there are companies that post chemicals as lead generation and cannot make them.

If you solve the selection of the best route, helping with sourcing the product may not be worth your resources. In other words, just that piece alone, if done well, is very valuable and hope the market sees it.

Yes I guess I was referring to more robust, standard chemistry for which we would expect the pricing to be a little more formulaic.

And you make a great point. We've been constantly reminded that virtual spaces created by CROs are not always executable. As such we can actually constrain our algorithms to require very high probability of reaction success to remove false positives. We then tell the CRO what building blocks they need and the route design. We're still figuring how much of the lifecycle of making molecules is worth going after or, if indeed as you say, the route itself is the key solution.

Reply on news.ycombinator.com