protein design

Engineering Persistent and Rewritable Genetic Memory in Bacteria through Multiscale Plasmid Competition

This paper engineers a reversible genetic memory system in bacteria that maintains two states for up to two weeks while remaining rewritable.

Molecular Architecture of the Human GCN1-ABCF3 Ribosome Collision Sensor

This study identifies ABCF3 as the mammalian ortholog of yeast Gcn20, which is recruited to ribosomes during amino acid starvation and interacts with GCN1 to activate Gcn2.

idTAG enables programmable and physiologically faithful control of endogenous protein degradation

The paper introduces idTAG, a system for controlled protein degradation that maintains physiological protein levels and allows programmable degradation kinetics.

Random in vitro Protein single-Loop Engineering (RiPLE) by mRNA display

This paper introduces RiPLE, a method for discovering engineered protein binders, and shows it produces high-affinity, selective binders for ROR1 and GS.

ANIMA: predicting protein-protein interactions across species

ANIMA predicts protein-protein interactions across species using an AI model trained on diverse animal species, achieving high accuracy in under-researched species.

Substrate Profiling of RNF216 Uncovers a Translation-Linked OTUD4 Regulatory Axis

The paper identifies RNF216 and OTUD4 as regulators of protein synthesis and degradation, showing their interaction disrupts neurodegeneration in Gordon Holmes syndrome.

Pep-PU-GAN: Positive-Unlabeled Adversarial Learning for Peptide Function Prediction

Pep-PU-GAN improves peptide function prediction using PU learning and GANs with graph neural networks, achieving high F1 and AUROC scores on neuropeptide classification.

Latent generative search unlocks de novo design of untapped biomolecular interactions at scale

Reward-guided inference-time search over the Proteína-Complexa sequence-structure codesign model yields validated binders across 127 targets, kinases and a free carbohydrate, with codesigned sequences outperforming ProteinMPNN redesign.

Virtual experiments bridge sequence and microscopy with generative models

The paper introduces a generative model framework that maps protein sequences to microscopy images and vice versa, enabling virtual mutagenesis and functional motif analysis.

dubTAGs enable on-demand stabilization for tunable and reversible control of endogenous protein levels

The paper introduces dubTAGs, small molecules that stabilize proteins tagged with FKBP12F36V by recruiting deubiquitinases, enabling tunable and reversible control of protein levels.

Programmable DNA Assemblies Reconstitute Supramolecular Protein Function

The paper introduces CASCAD, a DNA nanoplatform that reconstitutes supramolecular protein function, specifically apoptosome activity, through programmable assembly of caspase recruitment domains.

An All-Optical Approach to Probe Chloride Transport with a Bright ChlorON

The paper introduces an improved fluorescent protein indicator, ChlorON-1-PRO, for real-time imaging of chloride transport in cells.

Engineered mRNA nanostructures expand the design space of mRNA therapeutics through programmable protein expression and immune stimulation

This paper introduces mRNA-OG, a programmable mRNA nanostructure that affects protein expression, delivery, and immune response through its architecture.

A complex of MAST1 and 14-3-3 regulates Tau phosphorylation in the developing cortex

This study identifies MAST1 and 14-3-3 as regulators of Tau phosphorylation in the developing cortex through interactions and phosphorylation events.

Calibrated structural homology transfer yields putative molecular functions for domains of unknown function in four model proteomes

The paper evaluates functional annotation reliability from remote homology searches using retrospective DUFs and finds Foldseek performs better than MMseq2 but not significantly better than ESM-2 embeddings.

Targeting Outer Membrane β-barrel Proteins of Burkholderia mallei to design a Multi-epitope Vaccine Against Human Glanders

This study identifies 59 outer membrane β-barrel proteins from B. mallei and constructs a multi-epitope vaccine predicted to induce strong immune responses.

Rapid assay optimization by plug-and-play MAPPIT

This study expands a modular cloning platform to enable rapid, customizable construct assembly for MAPPIT assays, demonstrating its application in studying multiple protein-protein interactions.

Sampling Protein Language Models for Functional Protein Design

This paper evaluates sampling methods for protein language models, showing that multi-mutant strategies outperform single-mutant approaches in capturing epistatic interactions for functional protein design.

Targeting IL-2 to inflamed tissues via oxidation-specific epitopes enables third-generation bispecific IL-2 therapeutics

This paper develops a third-generation IL-2 therapeutic that targets inflamed tissues via oxidation-specific epitopes, showing improved therapeutic benefit in multiple inflammation models.

EvoMut: A Computational Framework for Engineering Oxidative Stability in Proteins

EvoMut identifies oxidation-prone protein residues and evaluates their mutation feasibility to design oxidation-resistant proteins.

MPNN-guided redesign of PET hydrolases with enhanced catalytic activity below the PET glass transition temperature

This paper redesigns PET hydrolase PHL7 using MPNN models to enhance its catalytic activity at lower temperatures, achieving efficiency comparable to its activity at higher temperatures.

An intersectional expression platform for gene complementation using RNA-fragment end joining (REJ)

This paper introduces an RNA-fragment end joining (REJ) platform for gene complementation that enables precise and efficient splicing of RNA units into functional mRNAs.

An interpretable peptide-HLA model emergently learns binding energetics and structure

The paper introduces an interpretable model for predicting peptide-HLA binding that matches state-of-the-art performance using only sequence data.

Multistate Enzyme Design Enables Efficient and Stereoselective Multistep Catalysis

This paper introduces multistate enzyme design to optimize active sites across reaction coordinates, achieving higher catalytic efficiency and enantioselectivity than single-state designs.

Functional alignment of protein language models via reinforcement learning

This paper introduces RLXF, a framework that aligns protein language models with experimental functional goals, improving the generation of high-functioning protein variants.

Reprogramming the Rossmann Fold Signature Motif Creates Orthogonal Redox Biocatalysts

The paper reprograms the Rossmann fold motif to create NMN+-specific enzymes that avoid NAD(P)/H interactions, achieving high specificity and productivity in biotransformation.

Machine learning-based development of Gadolinium binding peptides

This paper uses machine learning to design Gd-binding peptides with improved relaxivity and specificity for MRI contrast agents.

Evolution promotes transition-state-like conformations with enhanced basicity and electric fields in the substrate complex of a designer enzyme

This study shows directed evolution improves a designed enzyme by enhancing its transition-state-like conformation, reducing reaction barriers through desolvation and electric field organization.

Inverse FoldDir: Structure-conditioned Protein Sequence Design by Dirichlet Flow Matching

Inverse FoldDir designs protein sequences compatible with a given backbone structure, achieving high accuracy and experimental validation in nanobody redesign.

Generative Language Modeling for Antibody CDR Grafting and Alignment-driven De Novo Design

GenCDR uses LLaMa-based models to generate antibody CDRs with framework context, achieving high recovery and developable designs through alignment-driven training.