Inna Goreshnik

This paper introduces scalable experimental and computational workflows to accelerate protein design by improving throughput, reducing costs, and enabling rapid validation of thousands of protein designs.

This paper designs proteins to reprogram T cell signaling pathways, improving CAR-T and TCR-T performance in solid tumor models.

This paper designs de novo integrated domains using AI tools to enable plant NLR receptors to recognize non-cognate pathogen effectors, demonstrating functional immune responses and structural fidelity.

This paper designs a de novo Tie2 binder that activates the Angiopoietin-Tie2 pathway without integrin engagement, showing improved therapeutic potential in a mouse model of ARDS.

This paper designs sequence-specific DNA binding proteins using deep learning, achieving a 100-fold improvement in success rates over previous methods.

This paper demonstrates that bioPROTACs can reprogram CAR T-cells by targeting DNMT3A, offering a tunable alternative to gene editing for enhancing T-cell function.

Conditioning RFdiffusion on edge beta-strand pairing yields specific binders to polar targets, with in silico success above 9.2% versus 0.98% for hotspot-only conditioning.

This paper designs soluble, miniaturized MHC proteins that enable stable expression in E. coli and retain peptide and TCR binding specificity.

This paper designs antibodies de novo with atomic precision using RFdiffusion and yeast display, validated by cryo-EM and biophysical methods.

The paper designs high-affinity miniprotein binders targeting Flpp3, a virulence factor of Francisella tularensis, using physics-based and deep-learning methods, achieving sub-nanomolar affinities.

The paper designs novel cytokines by fusing computationally generated receptor-binding domains, identifying several that activate signaling pathways and have specific biological effects.

This paper introduces computational methods to design pH-sensitive binders that dissociate under acidic conditions, demonstrating their application in targeting various receptors and proteins.

This paper designs sequence-specific DNA-binding proteins computationally and validates them experimentally, achieving high specificity and affinity for target sequences.

The paper develops RFdiffusion to generate protein binders for IDPs/IDRs, achieving nanomolar affinity and functional applications in amylin and IL2RG.

This study designs miniproteins that inhibit MERS-CoV by targeting the spike protein, showing broad neutralization and protective efficacy in mice.

This paper presents computational methods for designing GPCR-binding miniproteins and validates them through high-throughput screening, producing agonists and antagonists for multiple GPCRs.

The paper develops a method to assess solution properties of designed proteins using mass spectrometry and peptide barcoding, enabling analysis of large protein libraries.

This study uses target-conditioned diffusion to design high-affinity TNFR superfamily antagonists and agonists with switchable specificity.

The paper designs nanomolar binders for diverse small molecules using a pseudocycle-based shape complementarity method, enabling direct conversion into sensing systems.

This paper designs high-affinity proteins that bind to convex protein sites using geometrically matching concave scaffolds, achieving low nanomolar to picomolar affinities.

The paper designs EndoTags to trigger endocytosis and degradation of target proteins, enabling tissue-specific targeting and therapeutic applications.

The paper designs and characterizes trivalent miniprotein binders that neutralize SARS-CoV-2 variants with low pM IC50 values and provide prophylactic and therapeutic protection in mice.

This paper designs small, stable proteins that bind to diverse target proteins using only structural information, achieving nanomolar to picomolar affinities.

The paper designs picomolar SARS-CoV-2 miniprotein inhibitors using computational methods and experimental validation, showing high potency and structural similarity to computational models.