Profluent debuts to design proteins with machine learning in bid to move past 'AI sprinkled on top'

26 Jan 2023
endpts.com
While OpenAI’s Microsoft-allied ChatGPT takes the world by storm, a fledgling startup in Berkeley, CA is debuting to take a similar language-learning model approach, but with the goal of designing new proteins. Profluent, founded by a former Salesforce AI research leader, has secured $9 million to kick-start its work, with proceeds going toward building out an integrated wet lab and recruiting machine learning scientists and biologists. Insight Partners led the seed round. The investor base also includes Air Street Capital, AIX Ventures and Phoenix Venture Partners. The startup’s goal is to overcome the laborious process of mining proteins in nature or making adjustments to proteins to reach a desired function. In a Nature Biotechnology paper published Thursday, Profluent CEO Ali Madani said he and others showed they can “generate proteins across multiple families,” tested in vitro and in vivo , using machine learning. “They function as well as exemplar proteins that have had millions of years of evolution, so highly active enzymes, which is a very difficult task to do in a zero shot manner, meaning without doing multiple rounds of optimization, without even feeding any data from the wet lab,” Madani told Endpoints News . “It’s able to generate highly active proteins that normally take millions of years to evolve.” Profluent will design macromolecules like new proteins using its model, Madani said. Still in the very early innings, Madani said the startup is exploring potential collaboration and licensing routes. Madani characterized Profluent’s underlying technologies as “very similar” to that of ChatGPT, which taps into vast troves of data to write text to any question a user feeds it, complete MBA and bar exams, pen college papers and more. “In the same way that ChatGPT learns the language of humans, human languages like English, we learn the language of biology and proteins,” the Profluent executive said. The company will have a “tight coupling” between AI and biology, he said. “We think the future is not going to be wet lab-driven first and AI sprinkled on top,” Madani said. “And while we’re very excited about our AI as well, you need the biology to go hand in hand.” Other early-stage startups are also looking to use AI to design proteins, including Cradle . There’s also Generate Biomedicines , out of biotech incubator Flagship Pioneering, which said last month it used AI to create new proteins. Generate research has yet to be peer reviewed.
For more details,please visit the original website
The content of the article does not represent any opinions of Synapse and its affiliated companies. If there is any copyright infringement or error, please contact us, and we will deal with it within 24 hours.
Organizations
Indications
-
Targets
-
Drugs
-
Get started for free today!
Accelerate Strategic R&D decision making with Synapse, PatSnap’s AI-powered Connected Innovation Intelligence Platform Built for Life Sciences Professionals.
Start your data trial now!
Synapse data is also accessible to external entities via APIs or data packages. Leverages most recent intelligence information, enabling fullest potential.