Twist Bioscience Partners With Lilly TuneLab for AI Antibody Data

XtalPi announced that Viva-Thera, a biotechnology company it incubated and backs as a strategic shareholder, has nominated a preclinical candidate targeting the membrane-proximal external region of HIV-1 gp41, completing discovery and optimization in seven months by combining Viva-Thera's atomic-resolution structural research with XtalPi's AI drug design and automation platform. Deploying generative AI from the outset, XtalPi navigated a chemical space of approximately 10 million compounds to isolate five validated hits with desirable drug properties and strong antiviral activity, then continuously optimized the leads to reach PCC nomination. The asset targets gp41-mediated membrane fusion at MPER, a region that retains approximately 90% sequence identity across viral strains, opening a path toward a broad-spectrum antiviral with a binding site distinct from those addressed by reverse-transcriptase, integrase, and protease inhibitors. In its public debut, Viva-Thera also reported that its MPER vaccine immunogens elicited antibody levels in rhesus macaques approximately five times those of the conventional HIV immunogen comparator, with antisera retaining substantial inhibition of HIV pseudovirus infection at a 1:1,000 dilution. The company is pursuing HIV prevention and cure through four modalities—vaccines, long-acting small molecules, gene therapy and cell therapy—and its gene-therapy program has completed vector construction, cell-infection experiments and CD4+ T-cell introduction in humanized mice, with live-virus infection and treatment studies in preparation.

AbbVie announced that the European Commission has approved its immunology drug Rinvoq, also known as upadacitinib, for the treatment of active polyarticular juvenile idiopathic arthritis in patients aged two years and older who have had an inadequate response or intolerance to disease-modifying antirheumatic drugs. The approval marks the 11th indication for Rinvoq in the European Union, where it can be used either as monotherapy or in combination with methotrexate, and follows the drug's existing United States approval for the same condition. The decision was supported by the open-label phase I SELECT-YOUTH study, in which 66.4% of patients achieved an ACR Pediatric 70 response at week 12, rising to 79.5% by week 48, while clinical remission increased from 23% to 43.4% over the same period. Rinvoq is a key growth driver for AbbVie, with sales up 22.2% year over year to $4.64 billion in the first half of 2026 and expected revenues of around $10.2 billion for the full year. Separately, AbbVie announced a multi-year collaboration with Iambic to accelerate discovery of small-molecule therapies in immunology, neuroscience and oncology, using Iambic's AI-powered platform including its next-generation Enchant v3 model, with Iambic receiving an upfront payment plus milestone payments and tiered royalties on net sales.

The AI Structural Biology Network, powered by Apheris, launched AISB Bind, a federated initiative in which AbbVie, AstraZeneca, Bristol Myers Squibb, and Johnson & Johnson will collaboratively train an AI model to predict how small molecules bind to protein targets for virtual screening and lead optimization. The new initiative extends the network's first effort, which focused on protein-ligand structure prediction, where a co-folding model fine-tuned across more than 20,000 proprietary structures from active drug-discovery programs raised the share of high-quality predictions from 36% to 52%, outperforming public models and any model fine-tuned on a single partner's data alone. In AISB Bind, the four founding partners contribute three complementary types of data: experimentally determined structures, quantitative affinity and potency measurements, and high-throughput screening activity data, the last adding a large body of confirmed non-binders that is rarely available at industrial scale. Training runs through federated learning, so each partner's proprietary data stays within its own secure environment, with Apheris hosting the network and running the training and each partner receiving the resulting model to run and further tailor internally. Federated training begins in September 2026, with final models expected in early 2027, powered by the infrastructure of Apheris's technology partner, Amazon Web Services.