protein structure prediction

The paper audits protein generate-and-screen pipelines by testing steering, confidence, and activation readouts, finding they do not reliably predict foldability.

The paper extends a framework to generate atomic resolution ensembles of intrinsically disordered proteins using six AI structure predictors and compares their performance against experimental data and simulations.

The paper evaluates AlphaFold's predictions of transmembrane protein complexes, finding that while most show plausible membrane geometry, some have inconsistencies and limitations in predicting lipid interactions.

The paper introduces WhatRes, a tool to evaluate AI-predicted protein structures by comparing their geometry to experimental structures across resolution and realism.

This study evaluates AlphaFold 3's accuracy and reliability in predicting RNA structures and protein-RNA interfaces, finding that confidence scores do not always correlate with correct predictions.

Peptorama provides tools for creating and analyzing non-ribosomal peptide structures, enabling efficient comparison of known and predicted peptides to aid in biodiscovery.

Struct-Caliper improves protein structure search reliability by providing accurate p-values, increasing homolog recovery and reducing false discoveries compared to native E-values.

This paper extends a protein structure validation method to RNA, showing it can detect errors in low-resolution structures where map-based methods fail.

FedEpitope uses federated learning with LoRA to predict linear B-cell epitopes without centralizing data, achieving good performance across multiple clients.

EpiRank evaluates epitope prediction by ranking surface patches on single-chain geometry, finding it correctly identifies real epitopes 64% of the time but with significant baseline overlap.

DUET is a sequence-only ensemble model for RNA-small molecule binding-site prediction that outperforms existing methods on benchmark datasets.

The paper identifies limitations in current cryo-EM data deposition practices and proposes an alternative approach to better preserve information and support validation.

PepPr improves peptide sequencing by integrating peptide priors, enhancing reference and variant peptide identification while maintaining discovery flexibility.

ESMfluc predicts local backbone variability in proteins using attention-based evidence decomposition, showing how sequence positions contribute to predictions of single or multi-PB states.

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

TransPepMS verifies peptides not in reference proteomes by resolving ambiguities in mass-spectrometry data to distinguish genuine non-canonical peptides from false positives.

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

This study develops a Cas9-TurboID platform to map dynamic protein assemblies around genome editing sites and identifies factors that enhance editing efficiency in heterochromatic regions.

This paper improves cryo-EM reconstruction of small complexes using 2D template matching and high-resolution structures as priors, enhancing density of ligand-binding sites in a 43 kDa protein kinase.

The paper benchmarks structure prediction models on a new antibody dataset to assess their ability to distinguish binders from decoys, finding moderate success but limitations in epitope localization.

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

This paper evaluates the use of HTA protease in combination with trypsin for proteomic analysis, showing increased protein and modification identifications and improved quantification.

This paper introduces a sample preparation workflow (SP3) that enables nanopore-based protein identification by decoupling proteolysis from interfering components, demonstrating its effectiveness with tryptic digests of myelin basic protein.

MIEN improves glycan pose ranking by distinguishing experimentally observed conformations from non-native ones in protein-carbohydrate interactions.

This study uses machine learning to predict bNAb-HIV-1 Env binding energies across clades, revealing clade-specific binding patterns and affinity trends.

The paper presents DeFluorX, a pipeline using Boltz-2 to identify FAcD variants for PFAS defluorination by analyzing geometric and energetic factors in enzyme-PFAS complexes.

The paper presents a manually curated dataset of protein binding domains, linking them to molecular interactions and genomic variations for benchmarking and disease mechanism studies.

The paper investigates how structural templates affect apparent links between protein stability predictions and longevity in tetrapods, finding that template choice can create spurious associations.

The paper identifies early embryonic gene expression programs in cancer and shows their stage-dependent impact on patient survival.