Skip to main content

Drug Assays

Lilly’s Virtual Med-Chem Assistant

Here’s an interesting new paper from Lilly (brought to my attention by Ash Jogalekar on Twitter). “Creating a virtual assistant for medicinal chemistry” is the title, but fear not: this is not something that’s come to elbow you aside at the bench. Well, not yet. What they’re talking about is a software agent that is taking on the job of handing around information around the project as it’s generated – these compounds got made this week, these compounds got tested in these assays, these were the most active of the bunch, here are the ones that haven’t been run yet, etc.

That sounds pretty mundane, but it’s quite valuable. This is one of those irritating issues that teams wrestle with, and companies devote a lot of time to figuring out how to share data across large groups in some effective way. Thus you have your Sharepoints and Microsoft Teams and Slacks and Yammers and mailing lists and newsletters and project team updates and meeting minutes and Spotfire files and databases and. . .it goes on. The tricky parts include: (1) the information to be shared is pretty heterogeneous, ranging from high-level “What assay should we run?” and “What compounds should we make next” stuff down to piles of assay data. And since most projects are running several sorts of assays, at different frequencies and in different hands/locations, with different aims and priorities, keeping track of it all is nontrivial. There have been many “Here are the compounds run this week” sorts of system put in place over the years, but the more context these things can be put in, the better.

So the Lilly software (“Kernel”) sends out notices as the numbers hit the database, summarizing what’s going on. But it goes further, also trying to highlight compounds that behaved in unexpected ways by using metrics and models from the project so far (efficiency metrics, QSAR). I can certainly see why that part’s in there, but I’d be interested to hear candidly how valuable the recipients find that part of the output. I can imagine that it works better for some projects (or some SAR series within given projects) than others, and the problem with that situation is that people will tend over time to sort of slide over that part rather than put the effort in to see if it’s worth their time (in this instance) or whether it’s just something not to bother with. There’s a mention of trying to add automated binding mode predictions as well, to which I attach the same concerns.

The software also takes active compounds and runs some matched-molecular-pairs type substitutions on the structures, evaluating those by the same criteria it uses for outlier flagging. The idea here is to put up ideas for further work and to identify what could be particularly interesting analogs to make. All I can say on that is that if the evaluative mode for these models might be problematic (with people finding it useful or not), the predictive mode is surely even more so. I wouldn’t object to seeing what the software came up with, but I would also be quite curious to see how seriously I could take its suggestions and whether it was coming up with anything that I hadn’t thought of myself. It looks like the Lilly team is wondering the same thing, naturally:

. . .As of this writing, 63 compounds have been suggested to a chemist by Kernel and later made by the same chemist (frequently not as a result of the suggestion from Kernel). We also looked for compounds that were predicted by Kernel, but made by a different chemist on the project. These cases most likely correspond to independent compound design (i.e. the chemist came up with the design idea on their own). In these cases, we can look at the time between Kernel’s prediction and when the compound was made independently to see what kind of speedup could be possible if the chemist had seen the prediction and selected those compounds from the much larger number sent to them (typically ~20-times more compounds than those made). On average, Kernel predictions were about 35 days (range of 4-72 days) ahead of the chemist’s. This represents the possibility of accelerating the progress of a discovery project which could be a significant saving in both time and money.

It might. Or it might not. It also depends on how useful those predictions were, and how they compared to the compounds made by the medicinal chemists that were *not* predicted by Kernel. It will do no one much good if people are nudged to make this set of randomly active compounds instead of that set, in other words. There are not data of this sort in the paper, although there is an interesting case from last year, where the team fed the Kernel recommendations back through automated retrosynthesis software, and the easier ones were then submitted for automated synthesis and sent in for testing, which as the paper notes is the first no-human-input SAR cycle tried at Lilly. As you read on, though, you find that “Our implementation is still suboptimal and in this case the synthesized compounds did not drive the project forward. . .

That’s what I would have expected – after all, most human-evaluated and human-synthesized compounds don’t really drive the project forward much, either, on average. So it’s way too early to say how useful this is – I mean, you can picture a future where it’s extremely useful indeed (here’s a vision mostly on the chemistry end of things). But how long it will take to get to that future, well, that’s another thing entirely. I think that the automated-data-distribution is useful, and it’s the sort of thing that other organizations have looked into over the years as well (because it’s not that hard to implement, comparatively). Once you start to bring in modeling and prediction, though, that’s another world – you’ve moved from reporting to prediction/speculation, and honestly, our current systems aren’t that great at prediction (and their usefulness varies widely from situation to situation). That’s the weak link in this whole idea. And it’ll get better – I assume that all modeling will get better. But how much better will it have to get, and how long will that take, and how will we know when it’s there?

I would myself be tempted to split those email alerts in two – one for the facts and one for the predictions/evaluations, because one of those can be argued about (or dismissed, fairly or unfairly) a lot more easily than the other. Mixing them is, I think, a mistake – but clearly the Lilly team doesn’t see it that way, because this whole paper is about how all these things are just naturally intertwined. Thoughts?

13 comments on “Lilly’s Virtual Med-Chem Assistant”

  1. Jeffrey R Weidner1 says:

    As a former Lilly scientist who was deeply embedded in the Assay, IT, and Computational Chemistry areas for many years, versions of these tools have been around for many years. However it’s no secret that the last few rounds of restructuring have been pretty brutal and focused on the more experienced senior scientists that used to mentor younger medicinal chemists. These mentors would not only teach their colleagues about the existing tools but provide insight on to how to interpret and best make use of the data. This looks to me like an attempt to push the data out even easier to new chemists coming into the organization, but can’t replace the perspective and interpretation to make best use of it.

  2. Matt Baumgartner says:

    Hi Derek,
    I’m one of the authors of the paper. Thanks for the commentary, one small typo though. It’s “Kernel” not “Kernal”. It’s meant to be a pun on the machine learning kernel and Colonel (as in Colonel Eli Lilly, founder of Lilly).

    1. Derek Lowe says:

      Thanks! Fixed it.

  3. a. nonymaus says:

    “It looks like you’re synthesizing a pharmaceutical. Would you like help?”

    1. cancer_man says:


    2. John Wayne says:


    3. EternalPostdoc says:

      I was thinking it and you said it. You should get a comment of the week award or something.

  4. Curious guy says:

    For those familiar with this software, is the human-less iterative process more efficient for some target types than others? For example, comparing kinases with GPCRs or agonists vs antagonists at the same target?

  5. Alexa says:

    When this works out without a single chemist and a patent is filed, who’s going to be the inventor?

    1. Nameless says:

      Calliope 7.3

      (For those who arnt up to speed on greek mythology: Calliope is the oldest of nine muses and, among other things, patreon of the science.)

  6. Red Fiona says:

    I’d be tempted to do a test where you have a chemist, a chemist plus kernel who is allowed to use or not use kernel’s suggestions, kernel plus a chemist who has to obey it’s whims and see what comes out.

  7. Geerbox says:

    None of the things the assistant does sound like real problems for science. Here is an example of a real problem for science: the army of researchers that have been trained to do academic research are not able to find jobs doing just that, because of the arrogance and elitism controlling science. Plenty of so called top chem programs have about 3 assistant professor positions working now. It’s laughable to be talking about what great cool things automated systems can do under this environment.

  8. Anonymous says:

    This is when spam filters come in so handy.

Comments are closed.