Integrating spatial transcriptomics and bulk RNA-seq: predicting gene expression with enhanced resolution through graph attention networks.

Spatial transcriptomics data play a crucial role in cancer research, providing a nuanced understanding of the spatial organization of gene expression within tumor tissues. Unraveling the spatial dynamics of gene expression can unveil key insights into tumor heterogeneity and aid in identifying potential therapeutic targets. However, in many large-scale cancer studies, spatial transcriptomics data are limited, with bulk RNA-seq and corresponding Whole Slide Image (WSI) data being more common (e.g. TCGA project). To address this gap, there is a critical need to develop methodologies that can estimate gene expression at near-cell (spot) level resolution from existing WSI and bulk RNA-seq data. This approach is essential for reanalyzing expansive cohort studies and uncovering novel biomarkers that have been overlooked in the initial assessments. In this study, we present STGAT (Spatial Transcriptomics Graph Attention Network), a novel approach leveraging Graph Attention Networks (GAT) to discern spatial dependencies among spots. Trained on spatial transcriptomics data, STGAT is designed to estimate gene expression profiles at spot-level resolution and predict whether each spot represents tumor or non-tumor tissue, especially in patient samples where only WSI and bulk RNA-seq data are available. Comprehensive tests on two breast cancer spatial transcriptomics datasets demonstrated that STGAT outperformed existing methods in accurately predicting gene expression. Further analyses using the TCGA breast cancer dataset revealed that gene expression estimated from tumor-only spots (predicted by STGAT) provides more accurate molecular signatures for breast cancer sub-type and tumor stage prediction, and also leading to improved patient survival and disease-free analysis. Availability: Code is available at https://github.com/compbiolabucf/STGAT.

CancerCellTracker: a brightfield time-lapse microscopy framework for cancer drug sensitivity estimation.

MOTIVATION: Time-lapse microscopy is a powerful technique that relies on images of live cells cultured ex vivo that are captured at regular intervals of time to describe and quantify their behavior under certain experimental conditions. This imaging method has great potential in advancing the field of precision oncology by quantifying the response of cancer cells to various therapies and identifying the most efficacious treatment for a given patient. Digital image processing algorithms developed so far require high-resolution images involving very few cells originating from homogeneous cell line populations. We propose a novel framework that tracks cancer cells to capture their behavior and quantify cell viability to inform clinical decisions in a high-throughput manner. RESULTS: The brightfield microscopy images a large number of patient-derived cells in an ex vivo reconstruction of the tumor microenvironment treated with 31 drugs for up to 6 days. We developed a robust and user-friendly pipeline CancerCellTracker that detects cells in co-culture, tracks these cells across time and identifies cell death events using changes in cell attributes. We validated our computational pipeline by comparing the timing of cell death estimates by CancerCellTracker from brightfield images and a fluorescent channel featuring ethidium homodimer. We benchmarked our results using a state-of-the-art algorithm implemented in ImageJ and previously published in the literature. We highlighted CancerCellTracker's efficiency in estimating the percentage of live cells in the presence of bone marrow stromal cells. AVAILABILITY AND IMPLEMENTATION: https://github.com/compbiolabucf/CancerCellTracker. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

53BP1-ACLY-SLBP-coordinated activation of replication-dependent histone biogenesis maintains genomic integrity.

p53-binding protein 1 (53BP1) regulates the DNA double-strand break (DSB) repair pathway and maintains genomic integrity. Here we found that 53BP1 functions as a molecular scaffold for the nucleoside diphosphate kinase-mediated phosphorylation of ATP-citrate lyase (ACLY) which enhances the ACLY activity. This functional association is critical for promoting global histone acetylation and subsequent transcriptome-wide alterations in gene expression. Specifically, expression of a replication-dependent histone biogenesis factor, stem-loop binding protein (SLBP), is dependent upon 53BP1-ACLY-controlled acetylation at the SLBP promoter. This chain of regulation events carried out by 53BP1, ACLY, and SLBP is crucial for both quantitative and qualitative histone biogenesis as well as for the preservation of genomic integrity. Collectively, our findings reveal a previously unknown role for 53BP1 in coordinating replication-dependent histone biogenesis and highlight a DNA repair-independent function in the maintenance of genomic stability through a regulatory network that includes ACLY and SLBP.

Learning curve of adrenal vein sampling. / è‚¾ä¸Šè ºé™è„‰é‡‡è¡€å­¦ä¹ æ›²çº¿çš„åˆ†æž.

OBJECTIVES: Adrenal venous sampling (AVS) is one of the recognized effective methods for the identification of primary aldosteronism, and the success rate is related to the skill level of the operator. This study aims to analyze the learning curve of AVS and to determine the number of staged cases of AVS procedure success rate, and to provide a reference for the standardized use of AVS. METHODS: The age, gender, blood pressure, surgery success rate, operation time, radiation dose, and operation-related complications of 120 patients with primary aldosteronism who underwent continuous AVS in the Second Xiangya Hospital from August 2015 to February 2021 were retrospectively collected. The cumulative sum analysis was used to analyze the learning curve of the operator. The minimum cases who were proficient in the operation was determined according to the learning curve, and the patients were divided into 4 groups a, b, c, and d according to the time sequence of receiving AVS based on the cut-off point. The AVS success rate, radiation dose, operation time, and complications of each group were analyzed. RESULTS: The cumulative sum analysis showed that the learning curves were divided into a learning stage and a mastery stage with 30 cases as the cut-off point, and the operation experience of the surgeon was from raw to mature. The success rates of the a, b, c, and d groups were 66.7%, 86.7%, 93.3%, and 96.7%, respectively. Compared with b, c, and d groups, the success rate in group a was significant decreased (all P<0.05), the operative time in group a was significantly lengthened (all P<0.05), and the radiation dose in group a was significantly increased (all P<0.05). CONCLUSIONS: After accumulating the AVS experience of 30 cases of primary aldosteronism, the operation time is obviously shortened, the radiation dose is significantly decreased, the operative complications are significantly reduced, and the learning curve enters a plateau. In the future, the success rate of AVS procedure may be improved through further standardized training.

Network-based drug sensitivity prediction.

BACKGROUND: Drug sensitivity prediction and drug responsive biomarker selection on high-throughput genomic data is a critical step in drug discovery. Many computational methods have been developed to serve this purpose including several deep neural network models. However, the modular relations among genomic features have been largely ignored in these methods. To overcome this limitation, the role of the gene co-expression network on drug sensitivity prediction is investigated in this study. METHODS: In this paper, we first introduce a network-based method to identify representative features for drug response prediction by using the gene co-expression network. Then, two graph-based neural network models are proposed and both models integrate gene network information directly into neural network for outcome prediction. Next, we present a large-scale comparative study among the proposed network-based methods, canonical prediction algorithms (i.e., Elastic Net, Random Forest, Partial Least Squares Regression, and Support Vector Regression), and deep neural network models for drug sensitivity prediction. All the source code and processed datasets in this study are available at https://github.com/compbiolabucf/drug-sensitivity-prediction . RESULTS: In the comparison of different feature selection methods and prediction methods on a non-small cell lung cancer (NSCLC) cell line RNA-seq gene expression dataset with 50 different drug treatments, we found that (1) the network-based feature selection method improves the prediction performance compared to Pearson correlation coefficients; (2) Random Forest outperforms all the other canonical prediction algorithms and deep neural network models; (3) the proposed graph-based neural network models show better prediction performance compared to deep neural network model; (4) the prediction performance is drug dependent and it may relate to the drug's mechanism of action. CONCLUSIONS: Network-based feature selection method and prediction models improve the performance of the drug response prediction. The relations between the genomic features are more robust and stable compared to the correlation between each individual genomic feature and the drug response in high dimension and low sample size genomic datasets.