Blumenstock, K. | bioRxiv Science

bioRxiv2025

Development of AI-designed protein binders for detection and targeting of cancer cell surface proteins

Artificial intelligence (AI)-based protein design opens new avenues for the rapid generation of new research tools and therapeutics, but experimental validation lags behind the computational design throughput. Here, we present a scalable workflow for the discovery and validation of AI-designed protein binders. Leveraging the RFdiffusion protein design pipeline with a custom filter for stable alpha-helical bundle folds, we construct libraries of thousands of AI-binders against cancer-associated surface proteins. Mammalian cell-surface and phage display screening yield multiple high-affinity PD-L1 binders but fewer hits for CD276 (B7-H3) and VTCN1 (B7-H4), reflecting the target-dependent efficiency of RFdiffusion in generating high-quality designs. Using our experimentally validated AI-designed binder libraries, we benchmark freely available structure prediction models. We find that interface predicted template modelling (ipTM) scores by Chai-1 with ESM embedding correlate well with experimental success and even predict deleterious effects of binding interface mutations. To demonstrate the versatility of AI-binders as research tools, we deploy them in CAR-T cells and also assemble them with fluorophore-labeled streptavidin into tetravalent quattrobinders, which achieve antibody-comparable staining of endogenous PD-L1 by flow cytometry. With high production yields and accessible structural models, AI-designed quattrobinders are versatile and cost-effective research tools amenable to community-driven validation and optimization.

bioengineering↗

bioRxiv2024

Sensing endogenous RNA in living human cells using a CRISPR-activated protease

Most techniques used to detect specific mRNAs in eukaryotic cells require to extract nucleic acids and thereby kill the cells. A programmable sensor for monitoring endogenous transcripts in living cells, in contrast, would enable to enrich living cells based on a specific transcription or splicing event, and studying these cells by live microscopy or sequencing methods requiring intact cells. We have engineered CRISPR-READ, a live cell RNA detector based on the CRISPR-associated Lon protease CalpL and a cA4-producing Type III CRISPR system. Upon RNA-programmable RNA sensing, CRISPR-READ produces an orthogonal second messenger, which leads to the cleavage of a dual FRET / localization reporter compatible with FACS sorting and live microscopy. Using this genetically encoded sensing circuit as a readout for a genome-wide CRISPR perturbation screen, we identified an extended Type-I interferon signaling cascade; RNA-Seq on sensor-sorted cells enabled unbiased identification of correlated stochasticity in gene expression across single cells.

bioengineering↗