P&G Experimental Design

  • Which experiment to run to reduce the uncertainty in their parameters the most.
  • From a ping from Eric: Also interested in QSAR (sounded like a different group). TODO Follow up.
  • Eric mentions this paper: https://www.biorxiv.org/content/10.1101/2021.05.02.442325v1
    (actual paper: https://www.mdpi.com/1099-4300/23/6/727)
  • The experimental design is more generic for them. "Is this possible?"
  • Then they ask about QSAR/chemoinformatics: What if your training set is small?
  • Eric talks about local slices of chemoinformatics where you can build targeted models using smaller data.
  • Mentioned BARTs.
  • They ask about number of descriptors to use.
  • Eric talks about Morgan fingerprints by RDKit.
  • They say they're looking forward to reading the paper and get asked about this QSAR more and more. Overall doesn't seem like anything urgent for them.
  • Now Max is taking over.

Future projects

  • A bit more time needed, fall would be when they would have better line of sight.
  • When this particular model is finished,
  • Follow-up: If retainer, what commitment can we get from management (starting July 1). Possibly yes, need to be sure. Keep some amount of hours, reduced to start.
  • Final thing - need to figure out a bias term for the model. They will send newer data, send it to the appropriate repo.
Select a repo