BenchSci uses machine learning and AI to accelerate biomedical discoveries

BenchSci aims to eliminate the frustrating trial-and-error required in determining the right antibody for drug-discovery experiments.

BenchSci, a biomedical startup founded by University of Toronto alumni uses machine learning to scan millions of data points in biomedical research papers, generating searchable results to help shorten the drug discovery process. It has raised USD8 million from a group of investors that includes Montreal's iNovia Capital and Google's Gradient Ventures.

BenchSci, founded in 2015, uses artificial intelligence to scan millions of data points in published research papers in a bid to speed the drug discovery process. BenchSci aims to eliminate the frustrating trial-and-error required in determining the right antibody for drug-discovery experiments.

"We think they're going to have an outsized impact on both the biochemical world and on the Canadian entrepreneur community," Ankit Jain, a founding partner at Gradient and director of engineering at Google, told the Globe and Mail.

"These are drugs that are much needed by the community for some of the most serious ailments out there, they've laid the groundwork for something very impactful across drug discovery and literature in this space," he further added.

The firm's artificial intelligence is designed to help researchers speed up the literature search to find antibodies, potentially shaving months off the process of bringing drugs to market – and in turn, getting patients new kinds of treatments faster.

"Without the use of AI, basic biomedical research is not only challenging, but drug discovery takes much longer and is more expensive. We are applying and developing a number of advanced data science, bioinformatics, and machine learning algorithms to solve this problem and accelerate scientific discovery by ending reagent failure," said Liran Belenzon, CEO, and co-founder of BenchSci.