Automatic identification of relevant genes from low-dimensional embeddings of single-cell RNA-seq data

The lncRNA Snhg11, a new candidate contributing to neurogenesis, plasticity, and memory deficits in Down syndrome

Down syndrome (DS) stands as the prevalent genetic cause of intellectual disability, yet comprehensive understanding of its cellular and molecular underpinnings remains limited. In this study, we explore the cellular landscape of the hippocampus in a DS mouse model, the Ts65Dn, through single-nuclei transcriptional profiling. Our findings demonstrate that trisomy manifests as a highly specific modification of the transcriptome within distinct cell types. Remarkably, we observed a significant shift in the transcriptomic profile of granule cells in the dentate gyrus (DG) associated with trisomy. We identified the downregulation of a specific small nucleolar RNA host gene, Snhg11, as the primary driver behind this observed shift in the trisomic DG. Notably, reduced levels of Snhg11 in this region were also observed in a distinct DS mouse model, the Dp(16)1Yey, as well as in human postmortem brain tissue, indicating its relevance in Down syndrome. To elucidate the function of this long non-coding RNA (lncRNA), we knocked down Snhg11 in the DG of wild-type mice. Intriguingly, this intervention alone was sufficient to impair synaptic plasticity and adult neurogenesis, resembling the cognitive phenotypes associated with trisomy in the hippocampus. Our study uncovers the functional role of Snhg11 in the DG and underscores the significance of this lncRNA in intellectual disability. Furthermore, our findings highlight the importance of DG in the memory deficits observed in Down syndrome.

Single-Nucleus RNA-Seq Characterizes the Cell Types Along the Neuronal Lineage in the Adult Human Subependymal Zone and Reveals Reduced Oligodendrocyte Progenitor Abundance with Age

The subependymal zone (SEZ), also known as the subventricular zone (SVZ), constitutes a neurogenic niche that persists during postnatal life. In humans, the neurogenic potential of the SEZ declines after the first year of life. However, studies discovering markers of stem and progenitor cells highlight the neurogenic capacity of progenitors in the adult human SEZ, with increased neurogenic activity occurring under pathological conditions. In the present study, the complete cellular niche of the adult human SEZ was characterized by single-nucleus RNA sequencing, and compared between four youth (age 16-22) and four middle-aged adults (age 44-53). We identified 11 cellular clusters including clusters expressing marker genes for neural stem cells (NSCs), neuroblasts, immature neurons, and oligodendrocyte progenitor cells. The relative abundance of NSC and neuroblast clusters did not differ between the two age groups, indicating that the pool of SEZ NSCs does not decline in this age range. The relative abundance of oligodendrocyte progenitors and microglia decreased in middle-age, indicating that the cellular composition of human SEZ is remodeled between youth and adulthood. The expression of genes related to nervous system development was higher across different cell types, including NSCs, in youth as compared with middle-age. These transcriptional changes suggest ongoing central nervous system plasticity in the SEZ in youth, which declined in middle-age.

The lncRNA Snhg11, a new candidate contributing to neurogenesis, plasticity and memory deficits in Down syndrome

Down syndrome (DS) stands as the prevalent genetic cause of intellectual disability, yet comprehensive understanding of its cellular and molecular underpinnings remains limited. In this study, we explore the cellular landscape of the hippocampus in a DS mouse model through single-nuclei transcriptional profiling. Our findings demonstrate that trisomy manifests as a highly specific modification of the transcriptome within distinct cell types. Remarkably, we observed a significant shift in the transcriptomic profile of granule cells in the dentate gyrus (DG) associated with trisomy. We identified the downregulation of a specific small nucleolar RNA host gene, Snhg11, as the primary driver behind this observed shift in the trisomic DG. Notably, reduced levels of Snhg11 in this region were also observed in a distinct DS mouse model, the Dp(16)1Yey, as well as in human postmortem tissue, indicating its relevance in Down syndrome. To elucidate the function of this long non-coding RNA (lncRNA), we knocked down Snhg11 in the DG of wild-type mice. Intriguingly, this intervention alone was sufficient to impair synaptic plasticity and adult neurogenesis, resembling the cognitive phenotypes associated with trisomy in the hippocampus. Our study uncovers the functional role of Snhg11 in the DG and underscores the significance of this lncRNA in intellectual disability. Furthermore, our findings highlight the importance of the DG in the memory deficits observed in Down syndrome.

siVAE: interpretable deep generative models for single-cell transcriptomes

Neural networks such as variational autoencoders (VAE) perform dimensionality reduction for the visualization and analysis of genomic data, but are limited in their interpretability: it is unknown which data features are represented by each embedding dimension. We present siVAE, a VAE that is interpretable by design, thereby enhancing downstream analysis tasks. Through interpretation, siVAE also identifies gene modules and hubs without explicit gene network inference. We use siVAE to identify gene modules whose connectivity is associated with diverse phenotypes such as iPSC neuronal differentiation efficiency and dementia, showcasing the wide applicability of interpretable generative models for genomic data analysis.

GSEA-SDBE: A gene selection method for breast cancer classification based on GSEA and analyzing differences in performance metrics

MOTIVATION

Selecting the most relevant genes for sample classification is a common process in gene expression studies. Moreover, determining the smallest set of relevant genes that can achieve the required classification performance is particularly important in diagnosing cancer and improving treatment.

RESULTS

In this study, I propose a novel method to eliminate irrelevant and redundant genes, and thus determine the smallest set of relevant genes for breast cancer diagnosis. The method is based on random forest models, gene set enrichment analysis (GSEA), and my developed Sort Difference Backward Elimination (SDBE) algorithm; hence, the method is named GSEA-SDBE. Using this method, genes are filtered according to their importance following random forest training and GSEA is used to select genes by core enrichment of Kyoto Encyclopedia of Genes and Genomes pathways that are strongly related to breast cancer. Subsequently, the SDBE algorithm is applied to eliminate redundant genes and identify the most relevant genes for breast cancer diagnosis. In the SDBE algorithm, the differences in the Matthews correlation coefficients (MCCs) of performing random forest models are computed before and after the deletion of each gene to indicate the degree of redundancy of the corresponding deleted gene on the remaining genes during backward elimination. Next, the obtained MCC difference list is divided into two parts from a set position and each part is respectively sorted. By continuously iterating and changing the set position, the most relevant genes are stably assembled on the left side of the gene list, facilitating their identification, and the redundant genes are gathered on the right side of the gene list for easy elimination. A cross-comparison of the SDBE algorithm was performed by respectively computing differences between MCCs and ROC_AUC_score and then respectively using 10-fold classification models, e.g., random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), extreme gradient boosting (XGBoost), and extremely randomized trees (ExtraTrees). Finally, the classification performance of the proposed method was compared with that of three advanced algorithms for five cancer datasets. Results showed that analyzing MCC differences and using random forest models was the optimal solution for the SDBE algorithm. Accordingly, three consistently relevant genes (i.e., VEGFD, TSLP, and PKMYT1) were selected for the diagnosis of breast cancer. The performance metrics (MCC and ROC_AUC_score, respectively) of the random forest models based on 10-fold verification reached 95.28% and 98.75%. In addition, survival analysis showed that VEGFD and TSLP could be used to predict the prognosis of patients with breast cancer. Moreover, the proposed method significantly outperformed the other methods tested as it allowed selecting a smaller number of genes while maintaining the required classification accuracy.

XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data

The lack of explainability is one of the most prominent disadvantages of deep learning applications in omics. This 'black box' problem can undermine the credibility and limit the practical implementation of biomedical deep learning models. Here we present XOmiVAE, a variational autoencoder (VAE)-based interpretable deep learning model for cancer classification using high-dimensional omics data. XOmiVAE is capable of revealing the contribution of each gene and latent dimension for each classification prediction and the correlation between each gene and each latent dimension. It is also demonstrated that XOmiVAE can explain not only the supervised classification but also the unsupervised clustering results from the deep learning network. To the best of our knowledge, XOmiVAE is one of the first activation level-based interpretable deep learning models explaining novel clusters generated by VAE. The explainable results generated by XOmiVAE were validated by both the performance of downstream tasks and the biomedical knowledge. In our experiments, XOmiVAE explanations of deep learning-based cancer classification and clustering aligned with current domain knowledge including biological annotation and academic literature, which shows great potential for novel biomedical knowledge discovery from deep learning models.