The Align Foundation, in partnership with NIST, has built a publicly available platform to advance protein sequence-to-function prediction. We are generating standardized functional data for hundreds of thousands of protein variants across diverse functions using our scalable, growth-based quantitative sequencing platform (GROQ-seq). With seven functions onboarded and multiple academic and facility partners, this growing resource is a coordinated field-wide effort to improve functional prediction models and benchmark library design strategies.

Titering of baculovirus stocks is a vital and necessary step in good protein production, though it is often subjective and/or time consuming and tedious. This newly developed cell line, aims to address the issues many of the current day titering techniques and offer a rapid, accurate method for obtaining viral stock titers.

BigHat Biosciences discovery platform couples AI antibody design with a high speed wet lab that enables rapid, iterative screening of thousands of antibodies per week. Powered by a custom cell-free protein synthesis system, our platform enables optimization across multiple axes of antibody properties including affinity, function, and developability. We’ll highlight key developments of our CFPS system, including reagent manufacturing, template construction, and reaction conditions which enable robust antibody characterization of in silico designs in the wet lab. We’ll also share some case studies of how our platform has been used to optimize increasingly complex multi-objective design challenges for next-generation antibody therapeutics.

Novel labware, integrated automation, and optimized workflows now enable efficient, high-throughput production and purification of antibodies at multi-milligram scales. Recent advances remove long-standing bottlenecks in harvesting and purifying harder to express antibody formats from mid-scale cultures, supporting seamless, end-to-end automation. These innovations accelerate discovery and development pipelines, advancing the automated manufacture of complex biologics previously limited by labor-intensive manual processes.

Our deep learning framework analyzes highly expressed transcripts across multiple tissue types to uncover cell-type–specific codon-usage rules. By learning these endogenous patterns, the model generates optimized transgenes—without altering the amino acid sequence—that improve translation efficiency over wild-type and commercial tools. Using EGFP and luciferase benchmarks, we demonstrate enhanced expression across tissues and consistent in vivo AAV validation. This highlights data-driven codon design as a powerful strategy for optimizing protein expression.

Despite recent advances in our understanding of genetic features that promote robust protein expression, transgenes in biotechnology have remained largely unchanged for decades. Natural human genes are rich in intron sequences that can drive these crucial expression benefits, but were previously difficult to replicate in artificial transgenes. At ExpressionEdits, we're changing this by deciphering ‘genetic syntax’ using high-throughput screening and machine learning to design intronized transgenes with improved protein expression.

Leveraging regulatory elements such as re-engineered promoters and optimized terminator polyA sequences can significantly enhance protein yields. By strengthening promoter activity, transcription initiation is increased, while improved polyA terminators ensure efficient mRNA processing and stability. Together, these modifications boost gene expression, leading to higher protein production. This approach is valuable in biotechnology and therapeutic protein manufacturing, where maximizing protein output is essential for cost-effective and scalable production