PURPOSE: Identify mechanism of action (MoA) from animal phenotype models
OVERVIEW: BioSymetrics leverages a proprietary machine learning platform (Augusta™) to generate structure-based activity predictions. This in combination with a vertebrate, in vivo phenotypic profiling framework has allowed us to make phenotype-mechanism association predictions across a range of potential clinical applications.
INPUT: Chemical structures, experimental datasets (public and private)
OUTPUT: Implicated pathways/processes
USE CASE: Phenotype MoA Prediction
1
INPUT: Phenotype Assays
2
Activity prediction model is fit and validated
3
The model ranks a large compound library from most- to least-likely to produce the phenotype
4
Pre-built clusters from experimental assays provide clues as to the target and pathway
5
Enrichment of target; Analysis of most-likely active compounds indicates MoA
6
OUTPUT: Protein targets and affected pathways
Hover on the numbered hot spots above to reveal each stage of progression
USER BENEFITS:
- More certainty of compound effects in vivo
- Fewer off-target effect “surprises”/ reduced toxicity
- leverage multiple experimental and public datasets
- Increased confidence in lead compounds
- Shorter path to market
PREVIOUS APPLICATIONS: Identification of causal pathway in cardiovascular, metabolomic, and neurological models