Dataset Information

Identification of Energy Metabolism-Related Gene Signatures From scRNA-Seq Data to Predict the Prognosis of Liver Cancer Patients.

ABSTRACT: The increasingly common usage of single-cell sequencing in cancer research enables analysis of tumor development mechanisms from a wider range of perspectives. Metabolic disorders are closely associated with liver cancer development. In recent years, liver cancer has been evaluated from different perspectives and classified into different subtypes to improve targeted treatment strategies. Here, we performed an analysis of liver cancer from the perspective of energy metabolism based on single-cell sequencing data. Single-cell and bulk sequencing data of liver cancer patients were obtained from GEO and TCGA/ICGC databases, respectively. Using the Seurat R package and protocols such as consensus clustering analysis, genes associated with energy metabolism in liver cancer were identified and validated. An energy metabolism-related score (EM score) was established based on five identified genes. Finally, the sensitivity of patients in different scoring groups to different chemotherapeutic agents and immune checkpoint inhibitors was analyzed. Tumor cells from liver cancer patients were found to divide into nine clusters, with cluster 4 having the highest energy metabolism score. Based on the marker genes of this cluster and TCGA database data, the five most stable key genes (ADH4, AKR1B10, CEBPZOS, ENO1, and FOXN2) were identified as energy metabolism-related genes in liver cancer. In addition, drug sensitivity analysis showed that patients in the low EM score group were more sensitive to immune checkpoint inhibitors and chemotherapeutic agents AICAR, metformin, and methotrexate.

SUBMITTER: Xu B

PROVIDER: S-EPMC9114438 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundSingle-cell RNA sequencing (scRNA-seq) has emerged has a main strategy to study transcriptional activity at the cellular level. Clustering analysis is routinely performed on scRNA-seq data to explore, recognize or discover underlying cell identities. The high dimensionality of scRNA-seq data and its significant sparsity accentuated by frequent dropout events, introducing false zero count observations, make the clustering analysis computationally challenging. Even though multiple scRNA-seq clustering techniques have been proposed, there is no consensus on the best performing approach. On a parallel research track, self-supervised contrastive learning recently achieved state-of-the-art results on images clustering and, subsequently, image classification.ResultsWe propose contrastive-sc, a new unsupervised learning method for scRNA-seq data that perform cell clustering. The method consists of two consecutive phases: first, an artificial neural network learns an embedding for each cell through a representation training phase. The embedding is then clustered in the second phase with a general clustering algorithm (i.e. KMeans or Leiden community detection). The proposed representation training phase is a new adaptation of the self-supervised contrastive learning framework, initially proposed for image processing, to scRNA-seq data. contrastive-sc has been compared with ten state-of-the-art techniques. A broad experimental study has been conducted on both simulated and real-world datasets, assessing multiple external and internal clustering performance metrics (i.e. ARI, NMI, Silhouette, Calinski scores). Our experimental analysis shows that constastive-sc compares favorably with state-of-the-art methods on both simulated and real-world datasets.ConclusionOn average, our method identifies well-defined clusters in close agreement with ground truth annotations. Our method is computationally efficient, being fast to train and having a limited memory footprint. contrastive-sc maintains good performance when only a fraction of input cells is provided and is robust to changes in hyperparameters or network architecture. The decoupling between the creation of the embedding and the clustering phase allows the flexibility to choose a suitable clustering algorithm (i.e. KMeans when the number of expected clusters is known, Leiden otherwise) or to integrate the embedding with other existing techniques.

Dataset Information

Identification of Energy Metabolism-Related Gene Signatures From scRNA-Seq Data to Predict the Prognosis of Liver Cancer Patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets