Singapore biotech ‘leading the way’ in machine learning and combinatorial genetics secures $43m in funding
It is reportedly the largest Series A capital raising exercise for a Singapore biotech and was led by Polaris Partners.
The funding round also included new investors, Invus. Existing investors - 6 Dimensions Capital, WuXi AppTec, DHVC, EDBI, Baidu Ventures, Vectr Ventures, Goodman Capital, WI Harper, and Nest.Bio – also participated in the exercise.
Engine has now raised US$53m to date, including US$10m in a 2018 seed round.
Leveraging AI in drug discovery, oncology therapeutics pipeline
The biotech’s technology platform, based on machine learning and next-generation combinatorial genetics, is designed to enable researchers and drug developers to uncover the gene interactions and biological networks underlying diseases orders-of-magnitude faster and more cost-effectively than conventional methods, generating insights for precision medicine applications.
But Engine is not solely a technology developer. It is also advancing a pipeline of targeted therapies for genetically-defined patient populations, which, it said, have shown promise in treating liver, ovarian, colorectal, and breast cancers.
Backing up that claim was Engine Biosciences’ cofounder and CEO, Jeffrey Lu, who told BioPharma-Reporter: "We have generated experimental validation data in a multitude of cell-based and animal-based disease models of the cancers, supporting our potential treatments’ ability to greatly impact tumor viability."
The latest funding will be used in part to help support the biotech’s first clinical programs.
How Engine’s technology platform works
Engine said its NetMAPPR searchable biology platform reveals gene combinations and drug targets integral to diseases. Employing combinatorial CRISPR, a tool called CombiGEM enables experimental confirmation of how genes and gene combinations relate to disease, added the biotech.
CombiGEM can test hundreds of thousands of gene interactions experimentally in diseased cells: “The resulting data from well-controlled experiments improves Engine’s machine learning algorithms, while high-ranking genes are prioritized for drug discovery and development.”
Compared to conventional approaches that are challenged by human limitations and less efficient and less precise experimental systems and hence cover tiny slices of biology, NetMAPPR searches much wider expanses of the complex architecture of biology at greater speeds, unleashing more new therapeutic opportunities, said the developer.