Last 12 months, Salesforce, the corporate best known for its cloud sales support software (and Slack), spearheaded a project called ProGen to design proteins using generative AI. A research moonshot, ProGen could — if dropped at market — help uncover medical treatments more cheaply than traditional methods, the researchers behind it claimed in a January 2023 blog post.
ProGen culminated in research published within the journal Nature Biotech showing that the AI could successfully create the 3D structures of artificial proteins. But, beyond the paper, the project didn’t amount to much at Salesforce or anywhere else — at the least not within the business sense.
That’s, until recently.
One in every of the researchers liable for ProGen, Ali Madani, has launched an organization, Profluent, that he hopes will bring similar protein-generating tech out of the lab and into the hands of pharmaceutical firms. In an interview with TechCrunch, Madani describes Profluent’s mission as “reversing the drug development paradigm,” starting with patient and therapeutic needs and dealing backwards to create “custom-fit” treatments solution.
“Many drugs — enzymes and antibodies, for instance — consist of proteins,” Madani said. “So ultimately that is for patients who would receive an AI-designed protein as medicine.”
While at Salesforce’s research division, Madani found himself drawn to the parallels between natural language (e.g. English) and the “language” of proteins. Proteins — chains of bonded-together amino acids that the body uses for various purposes, from making hormones to repairing bone and muscle tissue — will be treated like words in a paragraph, Madani discovered. Fed right into a generative AI model, data about proteins will be used to predict entirely latest proteins with novel functions.
With Profluent, Madani and co-founder Alexander Meeske, an assistant professor of microbiology on the University of Washington, aim to take the concept a step further by applying it to gene editing.
“Many genetic diseases can’t be fixed by [proteins or enzymes] lifted directly from nature,” Madani said. “Moreover, gene editing systems mixed and matched for brand new capabilities suffer from functional tradeoffs that significantly limit their reach. In contrast, Profluent can optimize multiple attributes concurrently to realize a custom-designed [gene] editor that’s an ideal fit for every patient.”
It’s not out of left field. Other firms and research groups have demonstrated viable ways by which generative AI will be used to predict proteins.
Nvidia in 2022 released a generative AI model, MegaMolBART, that was trained on a knowledge set of tens of millions of molecules to go looking for potential drug targets and forecast chemical reactions. Meta trained a model called ESM-2 on sequences of proteins, an approach the corporate claimed allowed it to predict sequences for greater than 600 million proteins in only two weeks. And DeepMind, Google’s AI research lab, has a system called AlphaFold that predicts complete protein structures, achieving speed and accuracy far surpassing older, less complex algorithmic methods.
Profluent is training AI models on massive data sets — data sets with over 40 billion protein sequences — to create latest in addition to fine-tune existing gene-editing and protein-producing systems. Fairly than develop treatments itself, the startup plans to collaborate with outside partners to yield “genetic medicines” with probably the most promising paths to approval.
Madani asserts this approach could dramatically cut down on the period of time — and capital — typically required to develop a treatment. In accordance with industry group PhRMA, it takes 10-15 years on average to develop one latest medicine from initial discovery through regulatory approval. Recent estimates peg the associated fee of developing a brand new drug at between several hundred million to $2.8 billion, meanwhile.
“Many impactful medicines were in reality unintentionally discovered, relatively than intentionally designed,” Madani said. “[Profluent’s] capability offers humanity a likelihood to maneuver from accidental discovery to intentional design of our most needed solutions in biology.”
Berkeley-based, 20-employee Profluent is backed by VC heavy hitters including Spark Capital (which led the corporate’s recent $35 million funding round), Insight Partners, Air Street Capital, AIX Ventures and Convergent Ventures. Google chief scientist Jeff Dean has also contributed, lending additional credence to the platform.
Profluent’s focus in the following few months can be upgrading its AI models, partly by expanding the training data sets, Madani says, and customer and partner acquisition. It’ll must move aggressively; rivals, including EvolutionaryScale and Basecamp Research, are fast training their very own protein-generating models and raising vast sums of VC money.
“We’ve developed our initial platform and shown scientific breakthroughs in gene editing,” Madani said. “Now’s the time to scale and begin enabling solutions with partners that match our ambitions for the long run.”
