ACKR3

Protein-making AI models have fueled the launch of a $1 billion startup and a Nobel Prize win in 2024, but are they ready to actually make drugs? Leaders of some of the largest startups working on that question say the technology is promising but not yet ready. But a tiny startup called Nabla Bio is far more bullish, posting a preprint Thursday highlighting its progress in creating antibodies from scratch that look therapeutically viable against some hard-to-drug targets in what it’s calling a first for the field. This isn’t the holy grail of having fully optimized drug candidates at the push of a button. But Nabla’s research is a step forward. The biotech’s leaders say their antibodies showed strong binding affinities and, in general, looked and behaved more like drug candidates than previous de novo efforts. Nabla said these are the first computer-generated antibodies against the family of proteins called GPCRs, which are notoriously hard to drug. The research includes eight examples of de novo antibodies against a range of targets, including proteins found in the membrane of cells like Claudin-4 and CXCR7. “The antibodies are developable, and they could potentially be real drugs,” said Frances Anastassacos, co-founder and president of Nabla. “They will have to go through lead optimization, but unlocking target space is a very exciting space to be. That’s the real promise of de novo design.” Other startups appear to be close behind, if not in lockstep, with Nabla, and that makes its first-ever claims hard to judge. For instance, a California startup called Abalone Bio told Endpoints News it has also generated de novo antibodies targeting GPCRs, the same hard-to-hit protein family cited in Nabla’s preprint. Abalone has not published those results, but presented some of its findings at an antibody engineering conference earlier this month and also framed them as a first for the field. “To our knowledge, these are the first designed GPCR antibody sequences that are functionally active,” its research poster stated. Protein design has arguably become the hottest space when applying AI to biology in 2024. David Baker, a pioneer in the field, won a share of the Nobel Prize in Chemistry last month. He also co-founded Xaira Therapeutics, which launched earlier this year with $1 billion to bring AI into drug R&D, specifically designing antibodies. A year ago, Flagship Pioneering’s Generate:Biomedicines published its own de novo model , called Chroma, and has raised nearly $750 million to build an extensive pipeline of antibody drugs. The leaders of those startups have also acknowledged the limitations of their recent work. Xaira CEO Marc Tessier-Lavigne recently told Endpoints News the AI models can generate initial hit candidates, but those still need to be improved by “old-school methods.” Generate R&D head Alexandra Snyder said earlier this year that designing from scratch isn’t yet ready for prime time, echoing what Baker has acknowledged in his own lab’s research. Despite having a fraction of the resources of Xaira or Generate, Nabla hopes to lead the field. It recently closed a $26 million Series A round and employs 16 people in its 4,500-square-foot lab in Cambridge, MA. CEO Surge Biswas, who co-founded Nabla in 2020 based on his PhD work in Harvard University geneticist George Church’s lab, said technology, rather than capital, is the key limit to progress. “Developing a system like we developed, the scarce commodity is not that you have $100 million to solve this problem,” Biswas said in an interview. “It’s not cheap, but you don’t need to raise giant amounts of capital to unlock some of these technologies.” In an interview, Church called Nabla’s preprint one of “relatively few actual success stories” in applying de novo work for so-called undruggable targets. “My hat is off to them for choosing targets well and not settling for a bunch of academic papers that settle five-decade-old challenges,” Church said. Nabla’s preprint details an AI system called JAM, or Joint Atomic Modeling, in which scientists provide the sequence and structure of a desired drug target. The system then generates antibodies that may fit that target. The most promising creations showed strong binding affinities and looked developable in lab testing, according to the preprint. There are still limitations to Nabla’s findings. They mainly made nanobodies rather than full-sized monoclonal antibodies that are commonplace in the drug industry. The paper included one example of a de novo monoclonal antibody, but that larger size also contributed to a lower binding success rate of 0.0017% for that project. Nabla doesn’t plan to advance these antibodies itself, as the company is focused on partnering with pharma, with ongoing deals with AstraZeneca, Bristol Myers Squibb and Takeda.

The floodgates for AI-enabled protein design burst open in 2024, with the Institute for Protein Design's David Baker claiming a Nobel Prize in chemistry for his foundational work, and DeepMind's unveiling of AlphaFold 3 to predict protein structures and interactions with  "unprecedented accuracy" (see – ViewPoints: Madrona's Chris Picardo on the AI-biotech convergence and ViewPoints: Expert expounds on potential for AlphaFold 3 to revolutionise research, democratise drug discovery).The year has also seen a slew of startups launch with aspirations to leverage computational technologies for drug design — and now Nabla Bio claims to have accomplished just that. The biotech, which emerged from stealth with a $26-million series A in May, pulled back the curtain on its Joint Atomic Modeling (JAM) platform on Friday. The technology, based on work out of George Church's laboratory at Harvard Medical School, can design lead-quality antibodies based on a target protein sequence or structure, the company said. Announcing the release of its technical paper detailing JAM's capabilities, the Nabla team noted that substantial progress has been made to predict protein structure and design proteins de novo — but noted that in regards to therapeutics, computational protein design tools have made relatively little progress to develop viable drugs. "Antibodies, as the most established drug format, are a great first real-world test for de novo drug design," Nabla said. "However, so far no AI systems have shown they are able to produce high quality lead antibodies from scratch in a way that is robust and generalises across protein targets and antibody formats."According to the company, JAM can design de novo proteins that closely resemble chimeric or humanised antibodies with good affinity, epitope-specificity and function — with no optimisation. With the technology, Nabla theorised that it's possible to replace traditional discovery methods with de novo design, thereby accelerating the development process while also cutting costs. Specificity against intractable targetsTo challenge its JAM platform, Nabla set out to design antibodies that can target several challenging or intractable classes of proteins, including multipass membrane proteins like GPCRs, tight junction proteins, disorder proteins and transiently stable complexes.The company successfully designed de novo, therapeutic-range antibodies against one undisclosed protein target and seven disclosed proteins: SARS-CoV-2 RDB, HER2, IL-13, PD-1, TrkA, CLDN4, CXCR7. Nabla said that its antibodies against the latter two targets, which are multipass membrane proteins, are the first computational designed binders of any kind to engage with CLDN4 and CXCR7.While the generated antibodies are more representative of lead molecules than fully optimised drugs, Nabla said they serve as "a robust starting point… to reach therapeutic-grade performance." The company highlighted that the AI-designed antibodies had high epitope-specificity, as they rarely bound another target. "This boost in specificity increases the likelihood of discovering functional leads and cuts down on wasted effort," Nabla said. Additionally, the firm said the antibodies had expression levels, monomericity and polyreactivity at or better than leading monoclonal products, suggesting they are well suited for manufacturing and formulation.

DONGTAN, KOREA, June 10, 2024 - iLeadBMS, a new drug R&D company under Ildong Pharmaceutical Group, announced on the 10th that it presented in vivo study results on its liver fibrosis treatment candidate 'IL1512' at the European Association for the Study of the Liver (EASL) 2024, held in Milan, Italy, from June 5th to the 8th. IL1512 is an oral CXCR7 agonist and is classified as a first-in-class drug, a type of drug that has never been developed for the same therapeutic indication previously. Last month, iLeadBMS presented the efficacy results of this drug for idiopathic pulmonary fibrosis (IPF) at the American Thoracic Society (ATS 2024), and this time around it announced the anti-fibrotic effects of the drug in the liver. CXCR7 is a G protein-coupled receptor that binds to chemokine ligands CXCL11 and CXCL12, targeting various pathways related to fibrosis such as fibroblast activation, inflammation, tissue repair, and angiogenesis. This makes it an ideal therapeutic target for treating fibrotic diseases. Given that CXCR7 agonists exerts their anti-fibrotic properties through a novel mechanism, iLeadBMS plans to develop anti-fibrotic drugs to treat fibrosis in various organs including but not limited to the lungs, liver, heart, kidneys, and skin, and is also considering utilizing the expedited review and Orphan Drug Designation (ODD) pathways offered by the FDA. Based on the presentation at the conference, iLeadBMS has confirmed the anti-fibrotic effects of IL1512 in the well-established CCl4 (carbon tetrachloride) liver fibrosis model with oral administration of the test article. Significant improvements in various anti-fibrotic indicators (col 1a1, hydroxyproline content, TGF-beta) were observed compared to the placebo. The presentation emphasized that IL1512, with its novel mechanism targeting CXCR7, demonstrated direct anti-inflammatory effects on the liver and improvement in fibrosis. Additionally, it highlighted that IL1512 showed either superior or at minimum, comparable efficacy and safety profiles compared to Elafibranor, the comparator drug. Based on these research results, iLeadBMS has identified preclinical candidate molecules with even greater improvements over IL1512 and, plans to start GLP (Good Laboratory Practice) toxicology studies in the second half of this year. About iLeadBMS Established in 2020, iLeadBMS specializes in the discovery and development of novel drugs, with an R&D pipeline targeting fibrotic diseases, protease inhibitors, solid tumors, and neurodegenerative diseases. For more information on iLeadBMS, please visit: