Collaborations Pharmaceuticals, Inc. Announce A Phase IIB SBIR Award From NIGMS/NIH To Develop Assay Central As A Machine Learning Software Suite

Raleigh – The National Institute of General Medical Sciences (NIGMS) has awarded $1,709,804 to Collaborations Pharmaceuticals, Inc. (CPI) to develop new capabilities in their Assay Central® machine learning software that will be applied to drug discovery research. 

“CPI developed Assay Central® software to enable rapid development and validation of machine learning models which we have applied to many areas of research from predicting endocrine disruption to repurposing molecules for Alzheimer’s disease and discovery of new antivirals for SARS-CoV-2. The last year alone demonstrated the importance of machine learning methods that could be used to learn from existing data to propose compounds for testing. Our own in-house efforts have led to several machine learning models for SARS-CoV-2 which identified molecules for testing in vitro and in vivo as well as demonstrated how quantum computers could be used to accelerate machine learning efforts as our datasets increase dramatically in size. We are excited by this Phase IIB award as it will enable us to continue to create cutting-edge tools that can aid us in our drug discovery projects as well as provide software that can be licensed by other companies so they can benefit from our expertise.” said Sean Ekins, CEO, CPI. 

With previous funding for this project CPI has built software tools and demonstrated  the importance of using multiple machine learning algorithms with over 5000 datasets relevant to drug discovery. This also enabled development of new software to integrate these algorithms available at www.assaycentral.org. This machine learning approach has been used for both common diseases and rare diseases to identify hit compounds as well as repurpose drugs for new uses. Numerous academic collaborations have illustrated how Assay Central® can assist them in their drug discovery projects resulting in many publications in peer reviewed journals. Software was also developed for the automated design of molecules, assessment of their synthesizability and retrosynthetic analysis. Assay Central® has also been used in multiple fee-for service projects with pharmaceutical, consumer product and other companies. 

Phase IIB will focus on further technology developments towards commercialization. These efforts include building out auto-curation software for dealing with complex biological data in unstructured databases, creating machine learning models of disease and toxicity pathways, and the application of multi-objective generative machine learning approaches to design molecules. Assay Central® will have a full suite of integrated capabilities from data curation through to molecule design and retrosynthetic analysis enabling complete end-to end drug discovery aided by machine learning. We will also perform validation of these tools by synthesis and testing of compounds. 

Disclaimer 

“Research reported in this publication was supported by the National Institute Of General Medical Sciences of the National Institutes of Health under Award Number R44GM122196. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.”