NONMEM Users Network Archive

Hosted by Cognigen

Webinar: An Integrated Machine Learning Framework for Novel Small Molecule Drug Design

From: Rebecca Baillie <rbaillie>
Date: Mon, 13 Jul 2020 16:24:08 +0000

An Integrated Machine Learning Framework for Novel Small Molecule Drug Desi=
Dr. Jonathan E. Allen, Informatics Thrust Leader, Biosecurity Center at ATO=
M Consortium
Wednesday July 15, 2020, 12:00 to 1:00 pm EDT
Register for free at
The drug discovery process is costly, slow, and failure prone. It takes an =
average of 5.5 years to get to the clinical testing stage, and in this time=
 millions of molecules are tested, thousands are made, and most fail. The A=
TOM Consortium (, comprised of LLNL, GSK, Frederick Nationa=
l Lab, and UCSF, is working to increase efficiencies in the drug discovery =
process through improved integration of machine learning earlier in the dru=
g design and discovery process by evaluating multiple properties needed to =
make a viable drug. A combination of safety, pharmacokinetic and efficacy p=
roperties are considered simultaneously in the early drug design phase with=
 an aim to ultimately show that these molecules will have better success ra=
tes with subsequent pre-clinical and clinical testing.
The purpose of this webinar will be to introduce key components of the ATOM=
 computational framework, highlight ongoing challenges and opportunities fo=
r improvement. The presentation will begin with a description of AMPL, the =
open source framework developed to build machine learning models that gener=
ate key safety and pharmacokinetics parameters, used for molecule evaluatio=
n and as input to anticipated Quantitative System Pharmacology and Toxicolo=
gy models. The end-to-end pipeline handles data curation, feature extractio=
n, model building, prediction generation, and data visualization.
Next, we'll describe how the best-performing models are integrated into an =
active learning loop (with code in the process of being open sourced) to gu=
ide the search for de novo compounds, with plans to integrate an in-house P=
BPK model to predict in-vivo behavior. The active learning loop includes a =
computational search through chemical space for candidate small molecules w=
ith opportunities for proposed molecules to be evaluated experimentally for=
 model validation and re-training. Discussion of the active learning pipeli=
ne will include an examination of the utility of machine learning model unc=
ertainty estimates needed to guide active learning and challenges in design=
ing and bounding the chemical search space. We will conclude with an examin=
ation of an early test of one round of the active learning loop applied to =
the design of a selective kinase inhibitor.

Received on Mon Jul 13 2020 - 12:24:08 EDT

The NONMEM Users Network is maintained by ICON plc. Requests to subscribe to the network should be sent to:

Once subscribed, you may contribute to the discussion by emailing: