N-of-one differential gene expression without control samples using a deep generative model

Abstract

Differential gene expression analysis of bulk RNA sequencing data plays a major role in the diagnosis, prognosis, and understanding of disease. Such analyses are often challenging due to a lack of good controls and the heterogeneous nature of the samples. Here, we present a deep generative model that can replace control samples. The model is trained on RNA-seq data from healthy tissues and learns a low-dimensional representation that clusters tissues very well without supervision. When applied to cancer samples, the model accurately identifies representations close to the tissue of origin. We interpret these inferred representations as the closest normal to the disease samples and use the resulting count distributions to perform differential expression analysis ofsinglecancer sampleswithoutcontrol samples. In a detailed analysis of breast cancer, we demonstrate how our approach finds subtype-specific cancer driver and marker genes with high specificity and greatly outperforms the state-of-the-art method in detecting differentially expressed genes, DESeq2. We further show that the significant genes found using the model are highly enriched within cancer-specific driver genes across different cancer types. Our results show that thein silicoclosest normal provides a more favorable comparison than control samples.

GeneBag: training a cell foundation model for broad-spectrum cancer diagnosis and prognosis with bulk RNA-seq data

“…Upon closer examination, NT types were found to gravitate towards the upper right, distinctly separated from the TM types clustered at the lower left, with PT samples interspersed in between (Figure 3B). Notably, NT and TM from the same tissue type (in the same color-code, in Figure 3B) were distant in the UMAP, exhibiting a similar diagonal projection, contrasting with previous studies where NT and TM of the same tissue were in closer proximity than those from different tissues (Prada-Luengo et al 2023). It is also insightful to explore the relationships among related tissues.…”

“…Comparing our results with those from prior studies, our model has attained state-of-the-art (SOTA) performance across nearly all commonly studied cancer types. Particularly noteworthy is the model’s performance in classifying Bladder Urothelial Carcinoma (BLAC) and Stomach adenocarcinoma (STAD), which have been challenging to discern with bulk RNA-seq in previous studies (<0.45 for BLAC and <0.35 for STAD) (Prada-Luengo et al 2023; Vivian et al 2020). Our model, however, has demonstrated the capacity to classify these with high precision, attaining accuracies of 0.93 for BLAC and 0.90 for STAD.…”