insitro Bolsters Machine-Learning Platform with Haystack Sciences Acquisition

Bay Area-based insitro snapped up neighboring Haystack Sciences to bolster its machine-learning drug discovery programs with that company’s higher resolution dataset-producing technology.

Bay Area-based insitro snapped up neighboring Haystack Sciences to bolster its machine-learning drug discovery programs with that company’s higher resolution dataset-producing technology.

Financial terms of the deal were not disclosed. insitro intends to leverage South San Francisco-based Haystack’s DNA-sequencing technology, called DNA-encoded libraries (DELs), in order to collect massive small molecule data sets that inform the construction of machine learning models able to predict drug activity from molecular structure. Through this acquisition, insitro said it has taken a significant step towards building in-house capabilities for fully integrated drug discovery and development.

insitro uses predictive models to accelerate target selection, design and develop effective therapeutics, and inform clinical strategy. Daphne Koller, founder and chief executive officer, said the past two years her company has been focused on the creation of predictive cell-based models of disease in order to enable the discovery of novel targets and evaluate the benefits of new or existing molecules in genetically defined patient segments.

“This acquisition enables us to expand our capabilities to the area of therapeutic design and advances us towards our goal of leveraging machine learning across the entire process of designing and developing better medicines for patients,” Koller said in a statement.

insitro did not specify where it might aim this new technology. Last year, the company forged an agreement with Gilead Sciences to discover and develop therapies for patients with nonalcoholic steatohepatitis (NASH). When that deal was announced, Gilead said it intended to harness insitro’s proprietary insitro Human (ISH) platform to create disease models for NASH and discover targets that have an influence on clinical progression and regression of the disease.

The acquisition of Haystack Sciences comes about five months after insitro raised $143 million in a Series B financing round that was expected to be used to continue to build the company’s technology and automation, which enable data generation at a larger scale.

Haystack’s platform uses multiple elements, including the capability to synthetize broad, diverse, small molecule collections, the ability to execute rapid iterative follow-up and a proprietary semi-quantitative screening technology, called nDexer. nDexer generates higher resolution datasets than possible through conventional ‘panning’ approaches, insitro said. These capabilities will greatly enable insitro’s development of multi-dimensional predictive models for small molecule design, the company added.

Richard E. Watts, co-founder and CEO of Haystacks Sciences, said the nDexer capabilities, combined with insitro’s machine learning models, will enable the construction of a platform at the forefront of the industry applying DEL technology to next-generation therapeutics discovery. Following the acquisition, Watts will join insitro as vice president of high-throughput chemistry.

“I am excited by the opportunity to join a company with such a uniquely open and collaborative culture and to work with and learn from colleagues in data science, machine learning, automation and cell biology. The capabilities enabled by joining our efforts are considerably greater than the sum of the parts, and I look forward to helping build core drug discovery efforts at insitro,” Watts said.

insitro’s capabilities in this space are being further developed via a collaboration with DiCE Molecules, a leader in the DEL field. The collaboration, executed earlier this year, is aimed at combining the power of machine learning with high quality DEL datasets to address two difficult protein-protein interface targets that DiCE is pursuing.

MORE ON THIS TOPIC