protein sequence

The P450 ApyO crosslinks a 10-residue C-terminal peptide, and substitutions in the YLY motif switch the linkage among C−C, N−C and C−O bonds.

OmegaSwitch estimates dN/dS ratios across sites and evolutionary lineages using Bayesian Markov-modulated codon models, showing well-calibrated posterior intervals in simulations.

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.

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

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.

ProtScape learns context-specific protein interactomes across 200 cell types, improving interaction reconstruction and identifying disease-related mechanisms.

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

Inferring tested-but-undetected pairs from prey lists of 5,530 published interaction screens yields 97 million tested human protein pairs and 18,982,508 non-interactions (≥3 tests) for calibrating screens and predictors.

This study examines how protein language models handle intrinsically disordered proteins, finding they encode structural and functional information despite reduced attention on disordered regions.

HARIBOSS++ is an updated platform for RNA-targeted drug design that includes expanded data and analysis tools for RNA-small molecule interactions.

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

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

TIGRFinder annotated 6,685 TIGR arrays; cryo-EM structures show inactive RuvC domains, and E. coli reporter assays show CsTasR and MbTasA repress transcription in a guide-dependent manner.

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

The paper investigates the evolutionary origins of protein novelty in Saccharomycotina yeasts, identifying two distinct modes of de novo and divergent gene evolution and their structural implications.

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

The paper develops a closed-loop framework for designing receptor-selective cell-penetrating peptides using multi-objective optimization and evaluates its effectiveness through experimental validation.

40S subunit binding to a previously unrecognised RRM in LARP1 activates its TOP-binding HEAT repeats, licensing repression of ribosomal protein mRNA translation in human cells.

This study designs allosterically controlled enzymes using denoising diffusion models, showing that activity can be activated or repressed by designed effectors.

This paper evaluates a self-architecting transformer for protein representation, showing it achieves better performance than existing models with a smaller dataset.

The paper predicts residue-level protein-protein interactions between hepatitis B virus core and envelope proteins using deep learning and coevolution signatures, comparing results with experimental data.

This study reconstructs the evolutionary origin of the GABAergic signaling system across 53 metazoan species, revealing a stepwise assembly from metabolic components into a synaptic inhibitory system.

The paper introduces the GPCR Evolution Database, which provides evolutionary analysis of GPCRs to study their function and conservation across species.

GOlien annotates protein sequences with GO terms using a Shannon-entropy k-mer model, achieving high accuracy on Biological Process, Cellular Component, and Molecular Function.

The paper introduces PlantLRR-PRR, a pipeline for annotating RLP/RLKs in tomato, revealing evolutionary patterns and TE enrichment in defense-related RLPs.

The paper introduces MultiStateFold, a framework that improves prediction of multiple protein conformations by integrating Parallel Tempering into a protein language model, achieving better performance than existing methods.

Odin-Multi is a binder design framework that optimizes sequences against multiple targets simultaneously, improving cross-reactivity and specificity compared to single-target methods.

ProteinSage uses structural constraints during pretraining to improve protein language modeling with less data, achieving competitive performance on structure-aware tasks.

This paper designs novel Rubisco variants using protein language models, identifying active candidates with improved CO2/O2 specificity and structural validity.

This paper introduces a new cyclisation strategy using a bromomethyl picolinaldehyde linker to expand macrocyclic peptide topologies, leading to more potent and diverse inhibitors.