protein design

PepGlider enables precise control over peptide properties through a continuous regularization framework, allowing for de novo generation and targeted optimization of peptides with desired characteristics.

The paper constructs a structure-guided kinase-transcription factor interactome atlas using AlphaFold-Multimer predictions, revealing docking motifs and allosteric hotspots that regulate kinase activity and lipid metabolism.

This paper introduces DiffTopo, a diffusion model for generating novel protein folds, and MirrorTopo, a pipeline to expand known fold space by mirroring native protein topologies.

Protein Hunter uses diffusion models to design proteins de novo by iteratively improving sequence and structure through hallucination and re-design.

This study designs antibody Fc-variants with programmable functional profiles using deep learning and experimental validation.

This paper introduces EMMA, a transformer-based multi-task learning framework for predicting enzyme-small molecule interactions, showing strong performance across different data-splitting regimes.

StabilizeIT is a webserver that enhances protein stability and expression by integrating computational tools and a novel model, demonstrating effectiveness in engineering enzymes for a biosynthetic pathway.

FlexRibbon is a pretrained protein model that jointly learns from sequences and structures, achieving state-of-the-art performance in mutation-rich settings.

This paper introduces UB-PIM, a method for protein identification by mass spectrometry using Core Unique Peptides (CrUPs) to improve specificity and reduce ambiguity in peptide-to-protein mapping.

The paper develops a bioinformatics workflow to identify diverse cellulose-binding domains through in silico prioritisation and high-throughput screening, identifying 5 CBMs with significant binding to cellulose materials.

LOBSTERS provides a modular CRISPR system with diverse Cas nucleases and plasmid markers for efficient multiplex genome editing in yeast.

This paper evolves computationally designed protein binders using in vivo hypermutation and maps their sequence-affinity landscapes to understand affinity improvements and mutation interactions.

ProTrek introduces a tri-modal contrastive learning model for protein sequence, structure, and function, achieving significant improvements in speed and accuracy over existing tools.

This paper introduces split inteins to enable modular NRPS engineering, generating 324 hybrid NRPS and over 200 novel peptides through combinatorial transformation.

The paper identifies how SPRY domains in ubiquitin ligases recognize nucleic acid sensors, using AlphaFold to discover novel interactions and their implications for RNA vaccine design.

PepMimic, an all-atom latent diffusion model guided by a contrastive interface encoder, designs peptides mimicking known binders; 8% of tested peptides across five targets reached 10^-8M KD.

This paper shows that protein language models prioritize sequence novelty over structural diversity, leading to a tradeoff in generating realistic protein structures.

This paper introduces a generative diffusion model for de novo design of RNA and nucleoprotein complexes, validated experimentally with SHAPE-seq and electron microscopy.

This paper introduces Caliby, a sequence design method that conditions on structural ensembles to improve designability while reducing native sequence recovery.

This study uses protein language models and Bayesian optimization to improve protein engineering efficiency by predicting function from sequences and optimizing variant search.

The paper designs and characterizes a random protein walker that diffuses along a designed protein track, finding that walkers with more feet move faster.

This study develops LassoESM, a language model tailored for lasso peptide property prediction, showing improved performance in substrate compatibility and biological activity prediction.

The paper designs proteins with reduced T-cell epitopes using deep generative models and policy optimization to improve immune compatibility across MHC Class I alleles.

The paper introduces mBER, a system for designing antibody-format binders with high experimental success rates, achieving 45% success across 145 targets and 38% binding rates to specific epitopes.

The paper designs a conserved Ty1 LTR sequence for efficient multicopy gene integration in yeast, validated by integrating 15 xylose isomerase copies for ethanol production.

The paper designs proteins using parallel tempering in sequence space to improve structure prediction and globularity.

This study demonstrates genetically encoded RNA strand exchange circuits in living cells, showing that in vitro TMSE design principles apply to E. coli but with cellular-specific caveats.

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.