After working with biotechs and Big Pharmas to accelerate their research programs, high-tech molecule modeler Schrödinger is taking its first steps as a clinical company itself. It has secured an FDA green light to study its computer-designed therapy for non-Hodgkin lymphomas in an early-phase trial.
The company’s machine-learning-powered platform sorted through 8.2 billion potential compounds over a period of 10 months, identifying 78 that were synthesized and filtered through preclinical experiments to select the most promising candidate.
Dubbed SGR-1505, the potential drug looks to block MALT1, a target that helps drive one of the biological pathways that govern the body’s immune responses but that can also be hijacked to power the out-of-control growth of cancer cells. The approach has shown promise in B-cell-related blood cancers that have relapsed or have not responded to other treatments.
Schrödinger said it plans to launch its phase 1 clinical study in the second half of this year, recruiting patients with relapsed or refractory non-Hodgkin B-cell lymphoma.
The multicenter trial will first test escalating doses of the drug by itself to analyze its safety and therapeutic activity. Once the recommended dose is found, Schrodinger plans to expand the study to additional patients with B-cell malignancies and explore how SGR-1505 performs in combination with other cancer drugs, including BTK and BCL-2 inhibitors.
The FDA’s clearance for the company’s first in-human study “marks an important milestone for our MALT1 program and underscores the impact of incorporating a digital chemistry strategy into research programs,” Schrödinger’s chief computational scientist, Robert Abel, said in a statement.
In the past, Schrödinger has presented preclinical data at the annual meetings of the American Society of Hematology, showing targeting MALT1 could produce benefits in models and samples of B-cell lymphoma and its subtypes. MALT1 has also been studied in chronic lymphocytic leukemia and mantle cell lymphoma.
Before striking off with its own pipeline, New York-based Schrödinger had been known as a major partner with biopharmaceutical companies in computer-driven drug discovery.
Its machine learning platform has been adopted by AstraZeneca with the goal of predicting how strongly a potential drug will bind with a target protein to help optimize its chemical properties and reduce the number of compounds that need to be manufactured and tested in the real world before settling on a lead candidate.
The company has also inked deals with the likes of Takeda, Bayer and Sanofi as well as a $2.7 billion pact that saw Bristol Myers Squibb pick up two programs from Schrödinger's in-house R&D efforts in kidney cancer and KRAS-driven tumors.
However, previous venture funding rounds and a $232 million IPO in early 2020 helped provide enough cash to transition Schrödinger from an AI service provider into a full-fledged clinical biotech company.
In addition to SGR-1505, the company’s wholly owned pipeline includes a CDC7 inhibitor, being lined up for human studies in blood cancers and solid tumors, as well as additional undisclosed programs in oncology and immunology that are currently listed as in the early discovery phase.