Bioinformatics (Oxford, England)最新文献

{"title":"Seq2Pocket: Augmenting protein language models for spatially consistent binding site prediction.","authors":"Vít Škrhák, Lukáš Polák, Marian Novotný, David Hoksza","doi":"10.1093/bioinformatics/btag778","DOIUrl":"https://doi.org/10.1093/bioinformatics/btag778","url":null,"abstract":"<p><strong>Motivation: </strong>Protein-ligand binding site prediction (LBS) is important for many areas of structural biology and molecular modeling, where, as in other tasks, protein language models (pLMs) have shown great promise. In their application to LBS, the pLM classifies each amino acid as binding or not, but translating these predictions into three-dimensional binding pockets remains challenging; in particular, residue-centric predictions tend to produce spatially fragmented pockets.</p><p><strong>Results: </strong>We present Seq2Pocket, a methodology for pocket-level LBS prediction that combines pLM finetuning, data enhancement, and structure-aware post-processing. First, we introduce sc-PDBenhanced, an extended training dataset that augments an existing sc-PDB dataset with additional small-molecule and ion-binding sites, improving coverage of non-obvious and small pockets. Second, we employ an embedding-supported smoothing classifier to refine residue-level predictions. Third, we define the Pocket Fragmentation Index and use it to select a clustering approach that preserves a consistent mapping between predictions and ground-truth pockets. We evaluate Seq2Pocket on two tasks: general binding site prediction using the LIGYSIS benchmark and cryptic binding site prediction using CryptoBench benchmark. Across both benchmarks, Seq2Pocket achieves state-of-the-art DCCtop-N and DCCtop-(N+2) performance. In particular, for general binding site prediction on the LIGYSIS benchmark, it improves distance-center-to-center recall by up to 13%, outperforming existing predictors. This improvement originates from training data quality rather than model architecture, as demonstrated by an ablation study. We believe that these findings contribute to more reliable evaluation practices in ligand binding site prediction, highlight the importance of training data curation, and provide pocket-level prediction tools that are better suited for downstream applications such as drug discovery.</p><p><strong>Availability: </strong>The Seq2Pocket web interface is available at https://seq2pocket.projekty.ms.mff.cuni.cz, running the ESM-2 650M variant. The sc-PDBenhanced is published using Zenodo platform at https://zenodo.org/records/18271517 [Škrhák and Hoksza 2026]. The models are published at HuggingFace: https://huggingface.co/skrhakv/seq2pocket.</p><p><strong>Supplementary information: </strong>Supplementary data are available at Bioinformatics online.</p>","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149208256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deepweed: Automated Individual Segmentation and Tracking for Duckweed Lineage Analysis.","authors":"Tolulope Oyeniran, Bukola Akindipe, Tasmia Islam, Joshua D Scheel, Eric A Josephs, Samuel M D Oliveira","doi":"10.1093/bioinformatics/btag779","DOIUrl":"https://doi.org/10.1093/bioinformatics/btag779","url":null,"abstract":"<p><strong>Motivation: </strong>Aquatic duckweeds, including Wolffia australiana, are the smallest and fastest growing flowering plants on the planet, with numerous emerging biotechnological applications. Duckweed populations grow through rapid clonal budding, but existing phenotypic characterization and image analysis tools typically operate only at the population level, tracking neither individual plants nor their lineage structure. Deepweed addresses this gap, combining automated individual segmentation, temporal tracking, and clonal lineage reconstruction from time-lapse imaging of duckweed.</p><p><strong>Results: </strong>Deepweed processes time-lapse duckweed imaging datasets using deep-learning-based instance segmentation and multi-object tracking to assign persistent identities to individual fronds and infer mother-daughter relationships. The workflow outputs lineage graphs, individual-level morphological metrics, and population-level growth summaries, supported by lineage-annotated time-lapse visualizations. Applied to dense Wolffia populations, in both freely growing or controlled microfluidic environments, our framework can track hundreds of Wolffia plants simultaneously, resolves overlapping individuals, and reconstructs multi-generation lineage structure, enabling analyses that are inaccessible with population-level phenotyping methods.</p><p><strong>Availability: </strong>Deepweed is implemented in Python using PyTorch, scikit-image, OpenCV, and btrack. Source code, trained models, example datasets, and documentation are freely available at https://github.com/SamOliveiraLab/Deepweed. The Deepweed code is archived at https://doi.org/10.5281/zenodo.18844282 and the datasets are archived at https://doi.org/10.5281/zenodo.18843917.</p><p><strong>Supplementary information: </strong>Supplementary data are available at Bioinformatics online.</p>","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149208252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DNAharvester: A Nextflow Pipeline for Analysing Highly Degraded DNA from Ancient and Historical Specimens.","authors":"Bilal Sharif, Verena E Kutschera, Nikolay Oskolkov, Benjamin Guinet, Edana Lord, J Camilo Chacón-Duque, Jonas Oppenheimer, Tom van der Valk, David Díez- Del-Molino, Peter D Heintzman, Love Dalén","doi":"10.1093/bioinformatics/btag782","DOIUrl":"https://doi.org/10.1093/bioinformatics/btag782","url":null,"abstract":"<p><strong>Motivation: </strong>Ancient DNA (aDNA) research has advanced rapidly with the development of high-throughput sequencing, enabling genome-wide analyses of large collections of prehistoric specimens. However, analysing palaeontological and archaeological material with highly degraded DNA constitutes a major bioinformatic challenge. DNA from such samples is characterized by short fragment lengths, low endogenous content, post-mortem damage, and cross-species contamination, which can increase spurious mapping and reference bias, affecting downstream population genetic inferences.</p><p><strong>Results: </strong>We present DNAharvester, a modular and reproducible pipeline designed specifically for processing highly degraded DNA from ancient and historical specimens. DNAharvester integrates metagenomic filtering, competitive mapping, adaptive aligner selection (incorporating BWA-aln, BWA-mem, and Bowtie2), and systematic evaluation of reference bias and spurious mapping. By incorporating flexible mapping and filtering strategies, the pipeline can be adapted to varying sample preservation, focusing on maximizing authentic data recovery. DNAharvester features subworkflows for iterative assembly of mitogenomes, identification of genomic repeats and CpG sites, taxonomic classification, microbial/pathogen screening, genetic sex determination, and variant calling. To accommodate varying sequencing depths, the pipeline supports diploid variant calling, genotype likelihood estimation, and pseudo-haploid random allele calling. We validated the pipeline using simulated and empirical datasets, demonstrating its ability to systematically mitigate complex background contamination while preserving authentic genomic signals. By streamlining complex bioinformatic tasks through simple configuration files, DNAharvester establishes a standardized approach for analysing aDNA datasets and makes genomic analyses of ancient remains accessible to the broader research community.</p><p><strong>Availability and implementation: </strong>Implemented in Nextflow, DNAharvester provides a highly scalable, containerized framework that enhances reproducibility, portability, and robustness in aDNA analyses. DNAharvester is open source under the GNU General Public License v3.0 and freely available at https://github.com/NBISweden/DNAharvester.</p><p><strong>Supplementary information: </strong>Supplementary data are available at Bioinformatics online and Zenodo repository: https://doi.org/10.5281/zenodo.22725211.</p>","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149208226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Motion-corrected Noise2Noise denoising for structural analysis of cells and tissues with (cryo-)FIB/SEM.","authors":"Vicente González-Ruiz, José-Jesús Fernández","doi":"10.1093/bioinformatics/btag765","DOIUrl":"https://doi.org/10.1093/bioinformatics/btag765","url":null,"abstract":"<p><strong>Motivation: </strong>(Cryo-)FIB/SEM enables three-dimensional (3D) ultrastructural analysis of cells and tissues at nanoscale resolution. However, its characteristically low signal-to-noise ratio severely hinders interpretation of the volume data. Noise2Noise has emerged as a state-of-the-art denoising paradigm with outstanding performance in 3D electron microscopy -particularly cryo-ET- but its direct application to (cryo-)FIB/SEM remains unfeasible due to the inherent acquisition workflows.</p><p><strong>Results: </strong>A method to enable Noise2Noise denoising in (cryo-)FIB/SEM is introduced. The input volume is split into even and odd slices followed by the application of motion correction methods to estimate and compensate for the structural differences between the two subvolumes. The resulting motion-corrected subvolumes are then used to train the Noise2Noise model, which is ultimately applied to denoise the original volume. Representative (cryo-)FIB/SEM volumes have been used to validate the method and to demonstrate the critical importance of the motion correction stage for volumes with a slice thickness greater than 10 nm.</p><p><strong>Availability and implementation: </strong>Code is available at https://github.com/microscopy-processing/N2N-REO and https://doi.org/10.5281/zenodo.22303478.</p><p><strong>Supplementary information: </strong>Supplementary data are available at Bioinformatics online.</p>","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149198132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PanRes: A database of latent and acquired antimicrobial resistance allowing 3D-based protein homology search.","authors":"Martina Vojtková, Martynas Baltušis, Hannah-Marie Martiny, Amulya Baral, Nikiforos Pyrounakis, Attila Beleon, Rebecca Freitag, Anna Pico-Tomàs, Rolf Sommer Kaas, Thomas N Petersen, Patrick Munk","doi":"10.1093/bioinformatics/btag776","DOIUrl":"https://doi.org/10.1093/bioinformatics/btag776","url":null,"abstract":"<p><strong>Motivation: </strong>Antimicrobial resistance databases are central to genomic surveillance, but resistance determinants remain distributed across resources with different scopes, structures, and annotations.</p><p><strong>Results: </strong>We developed PanRes, a curated resistance database of 11 717 genes integrating acquired and latent determinants of antibiotic, biocide, and metal resistance within a unified ontology. We predicted representative protein structures and clustered them by structural similarity, grouping proteins into 505 high-confidence structurally conserved clusters coherent despite sequence divergence. Their structure-guided alignments were used to build Hidden Markov Models (HMMs) for remote homology search. In seven wastewater metagenomes from five European cities, PanRes 3D-based HMMs expanded detection beyond what was possible with BLAST, with 35.3% of retained hits identified only by the HMMs and generally showing greater divergence from known proteins. For beta-lactamases, several proteins retained beta-lactamase-like folds and catalytic geometry despite weak sequence similarity.</p><p><strong>Availability and implementation: </strong>PanRes is available through an interactive web platform (https://panres.rambio.dk/), a structure-informed resource for exploring the whole resistome. The database, HMM profiles, and ontology are available at Zenodo (10.5281/zenodo.22876216).</p><p><strong>Supplementary information: </strong>Supplementary data are available at Bioinformatics online.</p>","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149198146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Revisiting Batch Effect Correction: A Structured Problem Formulation and Novel Solutions.","authors":"Avraham Harrar, Uri Shaham","doi":"10.1093/bioinformatics/btag735","DOIUrl":"https://doi.org/10.1093/bioinformatics/btag735","url":null,"abstract":"<p><strong>Motivation: </strong>Existing methods for batch effect removal often suffer from an ill-defined problem formulation and rely on unverified assumptions, limiting their robustness and generalizability. This study proposes a principled approach to systematically address these limitations.</p><p><strong>Results: </strong>We present two novel methodologies for removing systematic batch effects: an unsupervised approach based on independent component analysis and a supervised approach using a domain adaptation technique. Both methods are grounded in rigorous mathematical principles. Our approaches outperforms existing methods across multiple datasets.</p><p><strong>Availability and implementation: </strong>The implementation of our methods, including all code, datasets, experimental workflows, and supplementary material, is available in Python and has been made publicly accessible on GitHub: https://github.com/shaham-lab/revisiting-batch-effect-removal, Supplementary Material: https://github.com/shaham-lab/revisiting-batch-effect-removal/blob/main/proofs/suplementery_matirial.pdf.</p>","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149198205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ryder: Epigenome normalization using a two-tier model and internal reference regions.","authors":"Yaqiang Cao, Guangzhe Ge, Keji Zhao","doi":"10.1093/bioinformatics/btag753","DOIUrl":"https://doi.org/10.1093/bioinformatics/btag753","url":null,"abstract":"<p><strong>Motivation: </strong>Sequencing-based epigenomic profiling methods are powerful but suffer from technical variability that complicates cross-sample comparisons and can obscure true biological signals. While existing normalization methods using spike-in controls or computational approaches have been proposed, they often rely on assumptions that may not hold across diverse experimental conditions or require additional data types.</p><p><strong>Results: </strong>We present Ryder, a flexible and robust Python package for the normalization of epigenomic signal tracks. Ryder leverages stable internal reference regions, such as invariant CTCF binding sites, to correct for technical artifacts genome-wide. Our results show that it effectively adjusts both background noise and signal intensity, ensuring accurate signal alignment across samples while preserving genuine biological differences. We demonstrate that Ryder performs robustly across diverse assays including DNase-seq, CUT&RUN, ATAC-seq, MNase-seq, and ChIP-seq, with or without spike-in controls. By reducing technical noise, Ryder improves the detection of genuine biological changes, such as quantitative reduction of chromatin accessibility at key enhancer elements by depletion of BRG1, a key subunit of the chromatin remodeling BAF complexes.</p><p><strong>Availability and implementation: </strong>The Ryder source code, documentation and test data are freely available at: https://github.com/YaqiangCao/ryder. The software version used in this study is archived at Zenodo: https://zenodo.org/records/21267457.</p><p><strong>Supplementary information: </strong>Supplementary data are available at Bioinformatics online.</p>","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149198287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"scChronos: Hierarchical Temporal Context Learning for Missing Snapshot Prediction in Single-Cell Time Series.","authors":"Jiongsen Yao, Yunfei Zhang, Yong Xu, Jinjin Ma, Si Wu","doi":"10.1093/bioinformatics/btag772","DOIUrl":"https://doi.org/10.1093/bioinformatics/btag772","url":null,"abstract":"<p><strong>Motivation: </strong>Single-cell time-series atlases provide discrete cross-sectional snapshots of continuous developmental processes, making missing-snapshot prediction essential for reconstructing trajectories and dynamic programs. However, destructive scRNA-seq profiling prevents tracking the same cells across time, yielding unpaired population snapshots and making missing-snapshot prediction challenging. Existing methods typically rely on explicit dynamical propagation or transport-based coupling between snapshots, which may ignore the statistical constraints of the overall population distribution and be sensitive to sampling noise and cell-to-cell variability.</p><p><strong>Results: </strong>We introduce scChronos, a hierarchical temporal context learning framework that formulates missing-snapshot prediction as target-conditioned population distribution prediction rather than individual-cell propagation. Unlike cell-centric propagation approaches, scChronos explicitly captures dual-level dynamics: (i) Within each observed snapshot, scChronos compresses cell populations into cluster-representative cell representations with a transcriptomic encoder, preserving population information while reducing noise; (ii) Across reference snapshots, the dual-branch temporal context integration module fuses information from all available and nearby time points into a temporal representation, which is then decoded with learnable cell-generation seeds to predict the target distribution. Extensive experiments demonstrate that scChronos improves both interpolation-style recovery and extrapolation-style forecasting compared with state-of-the-art methods. Beyond reducing distributional discrepancy, scChronos better preserves developmental topology and maintains cell-type-specific marker and pathway programs.</p><p><strong>Availability: </strong>The code and data are available at https://github.com/yjs193/scChronos and https://doi.org/10.5281/zenodo.20933283.</p>","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inverse probability weighting-based mediation analysis for microbiome data.","authors":"Yuexia Zhang, Jian Wang, Jiayi Shen, Jessica Galloway-Peña, Samuel Shelburne, Linbo Wang, Jianhua Hu","doi":"10.1093/bioinformatics/btag750","DOIUrl":"https://doi.org/10.1093/bioinformatics/btag750","url":null,"abstract":"<p><strong>Motivation: </strong>Mediation analysis is an important tool for elucidating causal mechanisms in biomedical research and has recently gained increasing attention in microbiome studies. Motivated by a microbiome study of acute myeloid leukemia (AML) patients, we investigate whether the effect of induction chemotherapy intensity on infection status is mediated through gut microbial taxa. This problem poses substantial methodological challenges due to the high dimensionality, zero inflation, and dependence of microbial mediators, as well as the presence of an exposure-induced mediator-outcome confounder, antibiotic use.</p><p><strong>Results: </strong>To address these challenges, we propose a novel nonparametric identification formula for the interventional indirect effect, a causal mediation estimand that remains identifiable in the presence of exposure-induced mediator-outcome confounding. Building on this identification result, we develop an inverse probability weighting estimator and construct standard normal bootstrap confidence intervals for inference. Simulation studies demonstrate that the proposed method achieves accurate effect estimation and maintains appropriate type I error rates and power in finite samples. Application to the AML microbiome study provides evidence of a statistically significant interventional indirect effect of induction chemotherapy intensity on infection risk through alterations in the gut microbiome.</p><p><strong>Availability and implementation: </strong>The R code for the simulation studies is available at https://github.com/YX-ZHANG-1/CausalMediationMicrobiome and archived on Zenodo at https://doi.org/10.5281/zenodo.21960802.</p>","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CryoTriplane: Triplane-based Neural Radiance Field Representation for High-resolution Cryo-EM 3D Homogeneous Reconstruction.","authors":"Yiran Cheng, Bintao He, Qiong Zeng, Fa Zhang, Renmin Han","doi":"10.1093/bioinformatics/btag754","DOIUrl":"https://doi.org/10.1093/bioinformatics/btag754","url":null,"abstract":"<p><strong>Motivation: </strong>Determining the three-dimensional (3D) structure of proteins is a cornerstone of structural biology, providing essential insights into their underlying biological mechanisms and functional roles. Cryogenic electron microscopy (cryo-EM) single-particle analysis allows researchers to investigate biomolecules at near-atomic resolutions, unraveling the structure of biomolecular complexes. However, reconstructing high-fidelity 3D volumes from extremely noisy projections, particularly under the interference of structural heterogeneity, remains a challenging task. Traditional Fourier-domain methods often suffer from frequency-dependent signal attenuation and uneven information distribution. While recent deep-learning-based frameworks attempt to predict high-frequency components directly in frequency space, they are highly susceptible to noise and often introduce artifacts. State-of-the-art (SOTA) real-space method circumvents Fourier-domain defects, yet remains constrained by the inherent spectral bias of multi-layer perceptrons, as fixed positional encoding fails to sufficiently capture intricate high-frequency details.</p><p><strong>Results: </strong>We propose cryoTriplane, a real-space 3D homogeneous reconstruction network that utilizes a hybrid spatial representation to adaptively capture fine structural details. By combining fixed positional encoding for noise-robust structural initialization with structure-aware positional encoding for high-frequency refinement, our method achieves 3D reconstructions that are simultaneously globally consistent and locally fine-grained. Comprehensive qualitative and quantitative evaluations across five simulated and four real-world datasets demonstrate that cryoTriplane significantly outperforms existing methods in resolving fine structural features. Furthermore, validation through downstream atomic modeling underscores cryoTriplane's ability to recover high-quality density maps. Specifically, our method achieves sequence coverage improvements of 4.6% and 5.5% on the EMPIAR-10005 and EMPIAR-10492 datasets over the SOTA approach, respectively.</p><p><strong>Availability and implementation: </strong>Our code is available at  https://github.com/chengyr1999/CryoTriplane. The real datasets used in this study are publicly available from EMPIAR.</p>","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}