Newshot

Medical AI startup Boltz raises $110M to speed up small molecule research

Summary

Boltz PBC, a startup that develops artificial intelligence models for pharmaceutical researchers, has raised $110 million in funding. Bessemer led the Series A investment. Boltz stated on Wednesday that the fund was joined by a large group of new and returning backers. The consortium included Greycroft, Andreessen Horowitz, Amplify Partners, F-Prime Capital, Hummingbird and others. […] The post Medical AI startup Boltz raises $110M to speed up small molecule research appeared first on SiliconANGLE .

Original text(via SiliconANGLE)

Boltz PBC, a startup that develops artificial intelligence models for pharmaceutical researchers, has raised $110 million in funding.

Bessemer led the Series A investment. Boltz stated on Wednesday that the fund was joined by a large group of new and returning backers. The consortium included Greycroft, Andreessen Horowitz, Amplify Partners, F-Prime Capital, Hummingbird and others.

Small molecules, the building blocks of many drugs, can only neutralize a pathogen after binding to it. As a result, researchers start drug discovery projects by looking for molecules that have a high binding affinity with pathogens. They often review hundreds of thousands of candidate molecules per project. The process can take months and often costs millions of dollars.

Boltz offers an AI model called BoltzMol-1 that speeds up the workflow. It generates binding affinity data by reviewing only a few dozen, particularly promising molecules instead of the hundreds of thousands usually needed. The fewer molecules need to be studied, the less time the analysis takes.

Binding affinity evaluations don’t yield drug discoveries right away. Instead, they produce data points called small molecule hits. Those are essentially faint clues that help researchers pinpoint the area where they should focus their efforts.

Boltz staffers asked BoltzMol-1 to look for small molecule hits across 10 “challenging and therapeutically-relevant targets.” Targets are biological building blocks that play a role in disease processes. According to the company, the model found small molecule hits for six of the targets.

Scientists can adapt BoltzMol-1 to project-specific constraints. If a research team has access to a relatively limited number of compounds, it could configure the model to only consider small molecules that can be made from those compounds. When material procurement is not an obstacle, BoltzMol-1 evaluates a much larger number of candidates.

Boltz also offers a second model called BoltzProt-1. It can generate tens of thousands of protein designs based on data gleaned from small molecule hits. Additionally, BoltzProt-1 automatically reviews each protein to determine if it could be used to develop a new drug.

Usually, AI models evaluate protein designs based on rubrics that provide only an indirect view of their effectiveness. According to Boltz, BoltzProt-1 uses more direct metrics. The company says that BoltzProt-1’s protein evaluation mechanism demonstrated “higher success” than several competing models during internal tests.

Boltz sells its algorithms via an application programming interface that is billed based on token usage. According to the company, customers’ token consumption has grown by a factor of 50 since BoltzMol-1 and BoltzProt-1 launched in June. Boltz counts six of the world’s 20 largest pharmaceutical companies as clients.

The company will use its new funding to grow its headcount and procure more computing infrastructure. The extra hardware should make it easier for Boltz to keep up with leading AI labs such as newly public Anthropic PBC and OpenAI Group. Over the past year, both companies have introduced models that are highly adapted at biology research tasks.

Boltz has already started training a new generation of molecule design algorithms. The company says that they are “showing substantial improvements” over its current models.

A message from John Furrier, co-founder of SiliconANGLE:

Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.

  • 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more
  • 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network

Are you an AWS customer? Support SiliconANGLE financially by buying your AWS services from our Marketplace portal page and links: https://siliconangle.com/aws-marketplace/

Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by SiliconANGLE
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗