protein design

This paper introduces salad, a sparse denoising model for efficient protein backbone generation, and demonstrates its effectiveness for various protein design tasks.

The paper introduces a universal single-copy knock-in system for C. elegans that allows transgene insertion at specific loci using CRISPR/Cas9.

An all-atom diffusion model using a 14-atom residue representation and sparse U-Net architecture accelerates biomolecular design 10-fold, enabling experimentally validated DNA-binding proteins and multi-turnover cysteine hydrolases.

This study shows that rabbit kappa light chain allotypes affect chimeric antibody expression and function, with K1-b9 maintaining robust performance due to a stable disulfide bond.

This study identifies and engineers novel Cas12j orthologues into efficient genome editors with enhanced editing activity and specific sequence requirements.

This paper designs beta barrels and transmembrane nanopores using deep learning and parametric methods, achieving high success rates with experimental validation.

This study shows that protein language models capture both structural and functional dependencies from sequence data alone through epistasis analysis.

This paper develops a Cas12a-based toolkit for efficient genomic editing and CRISPRi in Group B Streptococcus, enabling targeted gene modifications and inducible gene silencing with minimal off-target effects.

PlasmoFP uses deep learning to predict protein function in Plasmodium species, reducing unannotated proteins from 15-59% to 3-28% and increasing fully annotated proteins from 7-42% to 36-68%.

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

IgGM is a generative model for antibody design that produces high-affinity antibodies through tasks like structure prediction and affinity maturation, validated on multiple antigens.

The paper identifies new protein interactions of FANCA, revealing its roles in mRNA processes beyond DNA repair, and suggests potential therapeutic targets for Fanconi anemia.

This paper introduces BinderFlow, a modular pipeline for protein binder design, and BFmonitor, a dashboard for campaign monitoring, making generative protein design more accessible.

This paper designs phosphorylation-induced protein switches that control transcription in cells, demonstrating their functionality in synthetic signaling.

IRIS predicts protein-RNA binding affinities and motifs using sequence, structural, and AI-predicted data without requiring large-scale affinity measurements.

The paper introduces miniCARbids, small human-derived CAR binding domains that show high anti-tumor potency in CAR T cells, outperforming traditional scFvs in some cases.

This paper designs de novo proteins to modify nanopore complexes, creating customized structural and functional properties for enhanced sequencing applications.

The paper introduces {micro}Protein, a framework combining deep learning and reinforcement learning to predict and discover high-gain protein mutants using single mutation data.

Structure providers for 18 CASP16 nucleic acid targets find blind predictions capture secondary structure but miss non-canonical interactions, backbone kinks, ligand sites, and intermolecular interfaces.

This study maps the proximity interactome of NR2E3 and its G56R variant using TurboID, revealing interactions with retinal development complexes and identifying BCOR as enriched in the mutant network.

This study identifies Jlp2 as a non-canonical release factor that facilitates peptide release from tRNA and prevents excessive CAT tailing during ribosome stalling.

This paper introduces SLiPP, a machine learning model that predicts lipid-binding pockets in proteins with high accuracy, identifying novel lipid-binding proteins and potential therapeutic targets.

This paper introduces ProDiT, a multimodal diffusion model for generating functional proteins with multiple states, demonstrating its ability to design proteins with specific molecular functions and allosteric regulation.

This paper improves the computational efficiency of protein language models, achieving faster inference, reduced memory usage, and efficient fine-tuning for better accessibility.

APEX automates recombinant protein production in E. coli, enabling high-throughput and reproducible expression with minimal setup.

The paper introduces EiRA, a generative model for designing proteins that bind biomolecules, achieving state-of-the-art performance across multiple metrics and demonstrating DNA-conditioned binder design.

This paper introduces METL, a protein language model that integrates biophysical modeling with machine learning to predict protein properties and design functional variants.

This paper shows that the Spt6 N-terminal domain binds histones and controls chromatin structure, with its function conserved between yeast and humans.

The paper validates target proteins of heterobifunctional molecules using AirID, showing different interactome profiles based on E3 ligase binders.

This paper uses a generative AI model to design novel tryptophan synthase variants with enhanced catalytic activity and substrate promiscuity, outperforming natural and optimized versions.