AI-Driven Drug Design (AIDD)

ADMET property prediction and
QSAR model-building application

Request an Evaluation!

Choose a Module:

What is the AIDD™ Module?

The AIDD Module integrates ADMET Predictor’s top-ranked ADMET property prediction models with multi-objective compound optimization capabilities:

  • Generative chemistry engine
  • Advanced and customizable pruning rules
  • Multi-objective compound selection based on a Pareto front
  • Iterative cycles of optimization based on design criteria

ADMET Predictor AIDD will take one or more starting structures and optimize them against a set of target properties. Activity models can be constructed in ADMET Modeler™ and used as part of the optimization to drive activity against one or multiple targets (e.g., selectivity). All numeric ADMET property prediction models, as well as custom models, can be used as part of the target profile. This includes mechanistic models from the HTPK Simulation module (%Fa and %Fb).

AIDD takes advantage of the recent architectural enhancement to ADMET Predictor, providing multi-threading capabilities for all currently available ADMET property prediction models. Other custom global, local or delta models can also operate in multi-threaded mode. Taking advantage of these capabilities, AIDD can generate and evaluate up to 5 million molecules in the course of an overnight run (8-core laptop computer) exploring a large portion of chemical space around the compound(s) or scaffold(s) of interest.

AIDD empowers chemists to control which part(s) of the molecule may be altered as part of the optimization and which should be maintained. You can also specify positions where substitutions can be applied, and control the chemistry based on synthetic feasibility constraints or a-priori knowledge about the target.

The analysis tools in ADMET Predictor have been enhanced to provide you with the capabilities to sift through and analyze results from AIDD runs. You can analyze intermediate results of each generative cycle (even while the AIDD run is still in progress) as well as examine final results to see which compounds have the best combination of properties.

Robert D. Clark, Ph.D.
Sr. Research Fellow
Simulations Plus, Inc.

Marvin Waldman, Ph.D.
Sr. Research Fellow
Simulations Plus, Inc.


Take the Next Steps

Join your peers around the world and start performing AI-driven compound optimization with ADMET Predictor.

Learn More!