\n<\/p>\n
Last year, Salesforce, the company 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 \u2014 if brought to market \u2014 help uncover medical treatments more cost effectively than traditional methods, the researchers behind it claimed<\/a> in a January 2023 blog post.<\/p>\n ProGen culminated in research published in the journal Nature Biotech showing that the AI could successfully create the 3D structures of artificial proteins. But, beyond the paper, the project didn\u2019t amount to much at Salesforce or anywhere else \u2014 at least not in the commercial sense.<\/p>\n That is, until recently.<\/p>\n One of the researchers responsible for ProGen, Ali Madani, has launched a company, Profluent<\/a>, that he hopes will bring similar protein-generating tech out of the lab and into the hands of pharmaceutical companies. In an interview with TechCrunch, Madani describes Profluent\u2019s mission as \u201creversing the drug development paradigm,\u201d starting with patient and therapeutic needs and working backwards to create \u201ccustom-fit\u201d treatments solution.<\/p>\n \u201cMany drugs \u2014 enzymes and antibodies, for example \u2014 consist of proteins,\u201d Madani said. \u201cSo ultimately this is for patients who would receive an AI-designed protein as medicine.\u201d<\/p>\n While at Salesforce\u2019s research division, <\/span>Madani found himself drawn to the parallels between natural language (e.g. English) and the \u201clanguage\u201d of proteins. Proteins \u2014 chains of bonded-together amino acids that the body uses for various purposes, from making hormones to repairing bone and muscle tissue \u2014 can be treated like words in a paragraph, Madani discovered. Fed into a generative AI model, data about proteins can be used to predict entirely new proteins with novel functions.<\/p>\n With Profluent, Madani and co-founder Alexander Meeske, an assistant professor of microbiology at the University of Washington, aim to take the concept a step further by applying it to gene editing.<\/p>\n \u201cMany genetic diseases can\u2019t be fixed by [proteins or enzymes] lifted directly from nature,\u201d Madani said. \u201cFurthermore, gene editing systems mixed and matched for new capabilities suffer from functional tradeoffs that significantly limit their reach. In contrast, Profluent can optimize multiple attributes simultaneously to achieve a custom-designed [gene] editor that\u2019s a perfect fit for each patient.\u201d<\/p>\n It\u2019s not out of left field. Other companies and research groups have demonstrated viable ways in which generative AI can be used to predict proteins.<\/p>\n Nvidia in 2022 released a generative AI model, MegaMolBART<\/a>, that was trained on a data set of millions of molecules to search for potential drug targets and forecast chemical reactions. Meta trained<\/a> a model called ESM-2 on sequences of proteins, an approach the company claimed allowed it to predict sequences for more than 600 million proteins in just two weeks. And DeepMind, Google\u2019s AI research lab, has a system called AlphaFold that predicts complete protein structures, achieving speed and accuracy far surpassing older, less complex algorithmic methods.<\/p>\n Profluent is training AI models on massive data sets \u2014 data sets with over 40 billion protein sequences \u2014 to create new as well as fine-tune existing gene-editing and protein-producing systems. Rather than develop treatments itself, the startup plans to collaborate with outside partners to yield \u201cgenetic medicines\u201d with the most promising paths to approval.<\/p>\n Madani asserts this approach could dramatically cut down on the amount of time \u2014 and capital \u2014 typically required to develop a treatment. According to industry group PhRMA, it takes 10-15 years on average to develop one new medicine from initial discovery through regulatory approval. Recent estimates<\/a> peg the cost of developing a new drug at between several hundred million to $2.8 billion, meanwhile.<\/p>\n \u201cMany impactful medicines were in fact accidentally discovered, rather than intentionally designed,\u201d Madani said. \u201c[Profluent\u2019s] capability offers humanity a chance to move from accidental discovery to intentional design of our most needed solutions in biology.\u201d<\/p>\n Berkeley-based, 20-employee Profluent is backed by VC heavy hitters including Spark Capital (which led the company\u2019s 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.<\/p>\n Profluent\u2019s focus in the next few months will be upgrading its AI models, in part by expanding the training data sets, Madani says, and customer and partner acquisition. It\u2019ll have to move aggressively; rivals, including EvolutionaryScale and Basecamp Research, are fast training their own protein-generating models and raising vast sums of VC cash.<\/p>\n \u201cWe\u2019ve developed our initial platform and shown scientific breakthroughs in gene editing,\u201d Madani said. \u201cNow is the time to scale and start enabling solutions with partners that match our ambitions for the future.\u201d<\/p>\n<\/p><\/div>\n