Towards the Latent Transcriptome

TL;DR

This paper introduces a novel method to generate continuous embeddings of kmers from raw RNA-seq data using an RNN, capturing sequence similarity, abundance, and genomic abnormalities without reference genome alignment.

Contribution

The work presents the Latent Transcriptome, a new embedding space that encodes sequence and abundance information directly from raw RNA-seq data, enabling structural and abnormality detection.

Findings

Embeddings recover exon information from raw data.

Latent space detects genomic translocations.

Model captures both sequence similarity and abundance.

Abstract

In this work we propose a method to compute continuous embeddings for kmers from raw RNA-seq data, without the need for alignment to a reference genome. The approach uses an RNN to transform kmers of the RNA-seq reads into a 2 dimensional representation that is used to predict abundance of each kmer. We report that our model captures information of both DNA sequence similarity as well as DNA sequence abundance in the embedding latent space, that we call the Latent Transcriptome. We confirm the quality of these vectors by comparing them to known gene sub-structures and report that the latent space recovers exon information from raw RNA-Seq data from acute myeloid leukemia patients. Furthermore we show that this latent space allows the detection of genomic abnormalities such as translocations as well as patient-specific mutations, making this representation space both useful for visualization as well as analysis.