NCFlow enables the placement of any non-canonical amino acid into proteins, outperforming existing methods in structure prediction for unseen ncAAs.
- 1 cited this week
Oxford University Press · Genomics & Bioinformatics · ISSN 1367-4803, 1460-2059
Rebuilt
NCFlow enables the placement of any non-canonical amino acid into proteins, outperforming existing methods in structure prediction for unseen ncAAs.
ABAG-Rank improves antibody-antigen complex model selection by outperforming AlphaFold3's internal scores, achieving a significant ranking performance boost.
Newest first · last 60 days
met-scDRS effectively integrates single cell methylomes with GWAS data, revealing cell-type-specific epigenetic links to psychiatric disease risk at single-cell resolution.
Integrating large microbiome cohorts with smaller metabolome data reveals robust microbiome-metabolome-disease links using a novel multi-reference framework.
Conditional differential gene expression analysis reveals that only a small fraction of genes have direct effects on traits in RNA sequencing data.
pxGPT achieves 0.572 to 0.712 agreement with human annotators in extracting 38-45 plant traits from Brassica images, matching human consistency levels.
MSCquartets 3.3 enables rapid inference of species networks and trees of blobs under the multispecies coalescent, with improved computational speed and new algorithms.
Open-source Python package ct-validation demonstrates that a single curated open clinical trial source can reproduce the success signal of proprietary data, with RS values of 2.92 versus 2.65.
ARCHER-LD computes biobank-scale linkage disequilibrium matrices with over 120 million variants in under 6 hours using GPU acceleration, representing a significant speedup over traditional methods.
FMCerNet improves cervical cytology screening accuracy by 5.7% in positive detection and enhances subtype classification in gigapixel WSIs using frequency-aware multi-label learning.
DNA Bayesian Flow Networks (DNA-BFN) outperform state-of-the-art models in generating regulatory DNA sequences, consistently across eight diverse datasets, with improved fidelity and efficiency.
MARDy 2.0 offers an enhanced, interactive platform for analyzing antifungal resistance mutations with structural and sequence data from multiple sources.
DNAharvester is a Nextflow pipeline that effectively processes highly degraded ancient and historical DNA, improving authentic data recovery and contamination mitigation.
Motion correction enables Noise2Noise denoising of (cryo-)FIB/SEM volumes with slice thickness over 10 nm, improving 3D ultrastructural analysis.
Deepweed can track hundreds of individual Wolffia australiana plants simultaneously, reconstructing multi-generation lineage structures from dense populations.
Seq2Pocket improves spatially consistent protein-ligand binding site prediction, achieving up to 13% better recall on the LIGYSIS benchmark.
Two novel batch effect removal methods, one unsupervised and one supervised, outperform existing approaches across multiple datasets, based on rigorous mathematical principles.
Ryder effectively normalizes epigenomic signals across diverse assays by using internal reference regions, reducing technical noise and preserving biological differences.
PanRes integrates 11,717 resistance genes into a unified database with 505 structurally conserved clusters, enabling 3D-based homology search that surpasses BLAST in wastewater metagenomes.
scChronos achieves superior missing-snapshot prediction in single-cell time series by explicitly modeling population distributions, outperforming existing methods in both interpolation and extrapolation.
Linguistic features of Gene Ontology term names encode hierarchical depth, with term-name length increasing by approximately 3.2 letters per depth level.
Python implementations of ANCOM-BC and ANCOM-BC2 achieve 380- and 147-fold faster runtimes with over 96% lower memory use on large datasets.
Inverse probability weighting-based mediation analysis reveals a significant microbiome-mediated effect of chemotherapy intensity on infection risk in AML patients.
CryoTriplane achieves 4.6% and 5.5% sequence coverage improvements over SOTA methods on two cryo-EM datasets, enabling higher-resolution 3D reconstructions.
Representation-aware conformal prediction framework RCP-DTA achieves near-nominal coverage with sample-specific intervals in drug-target affinity prediction.
MPA-EC, a generative enzyme function reasoning framework incorporating microenvironment context, improves F1 score by 0.1068 over the state-of-the-art GraphEC model on benchmark data.
CAD-score-LT enables superposition-free comparison of macromolecular structures with over 100-fold faster performance than previous methods.
CMGL achieves improved cancer subtype classification by estimating modality reliability and using consensus neighborhoods in multi-omics data.
DGP-LA enhances generalization in single-cell perturbation response prediction, achieving up to 79.1% improvement in Pearson Delta over existing models for unseen cell types.
PolyTamGen, an autoregressive sequence-based framework, improves joint success rates in multi-target ligand generation for dual- and triple-target benchmarks, using a dataset of 1.6 million ligands.
smiMAD achieves competitive clustering accuracy and spatial coherence in 17 simulated and 15 real paired spatial omics datasets.
FAMUS, a contrastive learning framework, surpasses KEGG's KofamScan and InterProScan for protein annotation on sparse, realistic datasets.
Journals this month
Topics moving, week to 22 Oct 2026