Discovery Accelerated

BioSymetrics combines Artificial Intelligence and in vivo experimental research to improve drug discovery.

Our biomedical specific machine learning framework uses a patent pending Contingent-AI™ process to iterate feature engineering in the pre-processing stages. When paired with experimental methods using a multi-dimensional “barcode” of in vivo phenotypic characteristics, BioSymetrics can enrich target-based drug discovery and shorten timelines for phenotype-based MoA prediction.

BioSymetrics is impacting every stage of drug discovery. Roll-over the hot spots below to see how.

TARGET-BASED DRUG DISCOVERY

Applying our ContingentAI framework to clinical data allows for novel gene-disease associations
Our in vivo experimental platform allows us to work in specific genetic contexts, allowing scalable complementation assays
Drug screening leverages our phenotypic barcoding platform, allowing automated lead identification for multi-dimensional phenotype rescue
Predicted off-target effects and toxicity models are used to optimize lead structures

Our target-based approach leverages computational and experimental processes to better predict in vivo efficacy and off-target effects.

PHENOTYPE-BASED DRUG DISCOVERY

Applying our Contingent-AI™ framework to clinical data allows for novel gene-disease associations
Our in vivo experimental platform allows us to work in specific genetic contexts, allowing scalable complementation assays
Drug screening leverages our phenotypic barcoding platform, allowing automated lead identification for multi-dimensional phenotype rescue
Predicted off-target effects and toxicity models are used to optimize lead structures

The Contingent-AI™ computational framework begins with phenotypic screens as input, and predicts molecular mechanism, shortening timelines for target/mechanism identification.

COMPUTATIONAL

Contingent A.I.™

  • Dynamically reduces bias from experimental datasets, including from high-content screening
  • Automated preprocessing of disparate data types (e.g. HCS, proteomics, genomics / transcriptomics) and data sources for faster discovery

EXPERIMENTAL

In Vivo Phenotypic Barcoding

  • We leverage a multi-dimensional “barcode” of in vivo phenotypic characteristics predictive of potential clinical applications and toxicity

BioSymetrics Combines Experimental and Machine Learning Methods to Enrich Target-Based Drug Discovery and Shorten Timelines for Phenotype-Based Drug Discovery

MoA PREDICTION

Life science companies tend focus on machine learning, ignoring the impact of the decisions they made in collecting and processing their data.

BioSymetrics has built AugustaTM , a fundamentally different approach to Data Science, optimizing every step of the process

Pre-processing Artificial Intelligence

The result: less time spent in data processing, easier data integration, more accurate results for diagnostics and drug discovery, as well as truly autonomous capabilities for precision medicine

Products

AugustaTM  is a biomedical Machine Learning (ML) framework designed to integrate data pre-processing into model building and interrogation.

Services

We offer turnkey services to our clients and corporate partners, with the aim of assisting organizations and teams in getting the greatest benefit from their data science initiatives. Our track record in massive data analytics including machine learning has been recognized with industry awards and conference speaking opportunities, and ties to our insight and knowledge base about the complexities in biomedical AI.

BioSymetrics services are available in several different ways, from our comprehensive technology solution implementations formalized in licensing agreements, to CRO consulting engagements and ad hoc projects.

Case Studies

“Augusta Architect is unique in its focus on efficient pre-processing, enabling more transparent model building in biomedicine. We’re excited to be users of the platform.”

Dr. Eric SchadtFounder and CEO, Sema4

“Augusta has supported us in a variety of projects in different settings. In health insurance, BioSymetrics saved us months of man hours and approximately $6.4 million (£5-million) annually … the use of Augusta enabled the company to drive faster, more accurate and meaningful innovation.”

Matt HickeyFounder and CEO, Intacare
Recent Blog Posts
March 30, 2020 in Drug Discovery, Industry News

Uniting Against COVID-19

Already working with clinicians, leveraging international collaborations to put prediction platforms in place, and re-investigating our drug lead pipeline, BioSymetrics will pursue any collaboration to have a positive impact against…
Read More
March 23, 2020 in Blog Post, Case Study, Drug Discovery

Mitigating Batch Effects in Cell Painting Data

With the advent of high content screening methodologies (e.g. cellular imaging, transcriptomics, etc.), it becomes more challenging to tease apart and visualize batch effects. This is further compounded when building…
Read More
February 12, 2020 in Blog Post, Case Study, Drug Discovery

De-noising CMap L1000 Data

As with any assay, L1000 data is noisy. Experimental replicates (the same compound tested on the same cell line under the same conditions) often result in different levels of expression…
Read More
January 28, 2020 in Blog Post, Case Study, Drug Discovery

When are Two Compounds the Same?

When are two compounds the same? The effect of Simplified Molecular Input Line Entry System (SMILES) format on chemical database overlap including best practice for canonicalization and harmonization to understand…
Read More