Ningxuan Zhou | Search PubMed

PubMed2026

Toward precision prognosis: Predicting recurrence-free survival in high-grade serous ovarian cancer patients using multi-time point clinical and computed tomography radiomics data.

OBJECTIVE: To evaluate the predictive value of clinical, genomic, and radiomics features in estimating recurrence-free survival (RFS) in patients with high-grade serous ovarian carcinoma (HGSOC) treated with neoadjuvant chemotherapy (NACT). METHODS: This single-center, retrospective study included 91 patients with HGSOC who underwent treatment with NACT followed by surgery, and who had portal venous phase contrast enhanced CT imaging at baseline and after NACT. First-order texture features based on 2D segmentation were extracted from baseline and post-NACT CT images for selected disease sites using commercially available texture software. Multivariate Cox models assessed the prognostic significance of features at baseline, after NACT, and post-surgery time points, and model performance in predicting RFS was evaluated using C-statistics. RESULTS: A model including only baseline clinical data had C-statistic 0.53, while a model including both clinical and radiomics features at baseline had C-statistic 0.63. After NACT, a model including all baseline data plus the change in radiomics features between baseline and post-NACT had C-statistic 0.63. Post-surgery, a model including all baseline data plus surgical outcome had C-statistic 0.69. Incorporating changes in radiomic features between time points did not measurably enhance model performance in the post-surgery data set (C-statistic 0.7). Age, residual disease at surgery, and kurtosis were individually associated with shorter RFS. CONCLUSIONS: Radiomic features extracted from CT imaging may offer additive prognostic value for predicting RFS in HGSOC when integrated with clinical and genetic data. Our results support the potential integration of radiomic analysis with clinical data to improve outcome prediction in HGSOC.

Humans↗

PubMed2026

scATAnno: Automated Cell Type Annotation for Single-cell ATAC-seq Data.

Recent advances in single-cell epigenomic techniques have increased the demand for single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) analysis. One key analytical task is to determine cell type identity based on epigenetic data. Here, we introduce scATAnno, a Python package designed to automatically annotate scATAC-seq data using large-scale scATAC-seq reference atlases. This workflow generates reference atlases from publicly available datasets, enabling accurate cell type annotation by integrating query data with reference atlases without the use of single-cell RNA sequencing (scRNA-seq) data. To enhance annotation accuracy, we incorporated k-nearest neighbors (KNN)-based and weighted distance-based uncertainty scores to effectively detect cell populations within the query data that are distinct from all cell types in the reference data. We compared and benchmarked scATAnno against five other published cell annotation approaches, demonstrating its superior performance across multiple datasets and metrics. We further showcased the utility of scATAnno across multiple datasets, including peripheral blood mononuclear cells (PBMCs), triple-negative breast cancer (TNBC), and basal cell carcinoma (BCC), and demonstrated that scATAnno accurately annotates cell types across diverse biological conditions. Overall, scATAnno is a useful tool for scATAC-seq reference atlas construction and cell type annotation and can facilitate the interpretation of new scATAC-seq datasets in complex biological systems. scATAnno is publicly available at https://scatanno-main.readthedocs.io/.

Single-Cell Analysis↗