protein sequence

Amino acid clustering and epistasis guide sequence-based prediction of phenotype modulation

The paper develops a method to predict phenotype modulation by analyzing amino acid clustering and epistasis in protein sequences, showing that these factors improve prediction accuracy.

RabbitCD-HIT: Distributed High-Sensitivity Greedy Incremental Clustering for Billion-Scale Protein Sequences in Hours

RabbitCD-HIT clusters billion-scale protein sequences efficiently, achieving faster performance than CD-HIT on large datasets.

Error-Controlled Discovery of Protein Interactions via Conformal Calibration

PPI-Caliper controls false discovery rate in protein interaction prediction using conformal calibration without retraining models.

Mapping and Probing the Substrate Scope of a Ketoamide-Forming Splicease by Computational Design

The paper uses computational methods to design and evaluate splicease variants for generating diverse ketoamide substrates, finding that top-scoring peptides are spliced more efficiently than single-point mutants.

Target Specific Conformational Flexibility and Electrostatic Complementarity Modulate LTNF10 Peptide Binding to Phospholipase A2 Variants from Snake Venoms

This study investigates how charge and conformational changes in a peptide affect its binding to different snake venom PLA2 variants, revealing structural and electrostatic factors influencing affinity.

Minimal requirements and evolution of polar membrane targeting in the land plant SOSEKI protein family

This study identifies a polar targeting peptide in plants and reveals its evolutionary conservation and diversification within the SOSEKI protein family.

Predicted condensation-related signatures localize to two C-terminal regions of the prion protein across cervid PRNP variants associated with chronic wasting disease

De novo design of mini-proteins as specific binders to PACAP-38, a key mediator of migraine

This study designs mini-proteins that bind PACAP-38 with high affinity, showing improved potency and stability compared to earlier versions.

The Quagmire of Immunogenicity-Guided Antibody Design: Labels Limit Progress

The paper evaluates antibody design methods using immunogenicity labels and finds that format-based approaches outperform sequence-based predictors, but label inaccuracies limit progress.

Gene Embedding Hub: a standardized resource for human gene representations

The paper introduces a standardized resource of human gene embeddings derived from diverse biological data sources, enabling comparison and use across modalities.

GLOM TGITO: multiscale protein modelling and multiview landscape-guided sequence discovery

The paper introduces GLOM-TGITO, a method for protein design that combines multiscale modeling with multiview landscape-guided optimization, achieving high accuracy and novel sequence discovery.

Comparative analysis of protease-inhibitor gene family counts under different counting units and genome annotations

The paper compares protease-inhibitor gene family counts across species, showing how annotation methods and counting units affect results.

ESMRank reveals a transferable axis of protein mutational constraint from overlapping variant effect assays

ESMRank is a sequence-based predictor that integrates protein language models and physicochemical features to rank mutational constraint across proteins, outperforming existing methods and capturing disease-relevant variants.

Ground-truth evaluation of sparse autoencoder features on spatial, single-cell and language-model embeddings

The paper evaluates sparse autoencoder features on various embeddings, finding that reproducibility does not guarantee meaningfulness, and proposes reporting features with concept coverage and purity.

OpenAntigens: a structure-aware database for antigen construct design across the human cell-surface and secreted proteome

A static web database proposes 55 305 construct suggestions for 5328 human secreted and cell-surface proteins, using AlphaFold pLDDT and PAE, with ortholog, paralog and BLAST cross-reactivity context.

Iterative Refinement for Structural Optimization of De Novo Protein Sequences

The paper introduces an iterative refinement method to improve de novo protein sequence structural accuracy by substituting amino acids based on structural metrics, achieving significant reductions in RMSD.

Cross-family learning transfers thermal adaptation between enzymes

This paper shows that thermal adaptation can be transferred between unrelated enzymes using a generative framework, improving thermostability without evolutionary homology.

Integrative Biophysical Illumination of the 3D GPCRome Dynamics

The paper develops GPCRmd-NMR, an integrative platform combining MD simulations and NMR spectroscopy to analyze GPCR dynamics at unprecedented scale.

Function-preserving CD8⁺ T Cell Immunogenicity minimization through protein design

The paper develops a computational framework to minimize CD8⁺ T cell immunogenicity in designed proteins while preserving function, using a de novo luciferase as a model.

AltereGO: Prediction of Protein Function by Multimodal Fusion of Protein Language Models.

AltereGO fuses protein language models and structure representations to predict molecular functions, achieving better performance than individual models and some existing methods.

Computational Design and Evaluation of De Novo Protein Minibinders Targeting Specific Sites of STAT3

The paper designs and evaluates de novo protein minibinders targeting specific STAT3 sites using AI and AlphaFold3, identifying high-confidence binders with novel sequences.

Structural and Energetic Determinants of Monobody Recognition of Oncogenic KRAS Variants

This study identifies structural and energetic determinants of monobody 12D4 recognition of KRAS variants using simulations and redesign, revealing key interactions and mutations for improved selectivity.

A New Information Theoretic Approach Shows that Mixture Models Outperform Partition Models for Phylogenetic Analyses of Amino Acid Data

The paper compares mixture and partition models for phylogenetic analyses using the mAIC and finds mixture models consistently outperform partition models.

Design of full-length agonist and antagonist antibodies for hard targets

This paper designs full-length agonist and antagonist antibodies for hard targets using a computational pipeline, achieving nanomolar affinities and functional activity.

Integrated Framework for Probing Multimodal Protein Foundation Models with Structure-Functional Interpretability Analysis in Detection of Allosteric Binding Sites

The paper evaluates multimodal protein foundation models for allosteric binding site detection, finding that dataset properties, not model complexity, primarily determine performance.

Building from the ground up: augmentation strategies to improve protein language model performance on protein sets

This study investigates augmentation strategies to improve protein language model performance by reducing dataset size and enhancing generalization through active learning and generative models.

Mathematical genomics of SRY proteins and their associated HMG-Box domains across mammals

The paper quantifies compositional patterns in SRY proteins and HMG-box domains across mammals, revealing distinct compositional grammars and highlighting the need for alignment-independent analysis.

Projected Gradient Descent for Hallucination-Based Protein Binder Design

This paper evaluates projected gradient descent (PGD) for hallucination-based protein binder design, finding it improves design efficiency and diversity compared to softmax-based methods.

Astrolabe: Programmable all-atom biomolecular design through cross-context coordination and structural intervention

Astrolabe is a programmable framework for biomolecular design that coordinates molecular contexts and structures, achieving high pass rates in binder benchmarks and enabling complex assembly designs.

Cuticulome.org: a centralized database of proteins in arthropod cuticles

Cuticulome.org provides a curated database of arthropod cuticle proteins with standardized nomenclature and tools for sequence analysis and dataset customization.