Vector Embeddings by Sequence Similarity and Context for Improved Compression, Similarity Search, Clustering, Organization, and Manipulation of cDNA Libraries

TL;DR

This paper introduces a vector embedding approach for cDNA sequences that enhances clustering, compression, and similarity search efficiency by transforming raw sequences into context-aware numerical representations.

Contribution

It presents a novel method for encoding gene sequences into vector embeddings based on sequence similarity and context, improving clustering, compression, and search tasks.

Findings

Enhanced clustering of gene sequences using vector embeddings.

Improved compression performance for cDNA libraries.

Faster similarity searches through Euclidean space proximity algorithms.

Abstract

This paper demonstrates the utility of organized numerical representations of genes in research involving flat string gene formats (i.e., FASTA/FASTQ5). FASTA/FASTQ files have several current limitations, such as their large file sizes, slow processing speeds for mapping and alignment, and contextual dependencies. These challenges significantly hinder investigations and tasks that involve finding similar sequences. The solution lies in transforming sequences into an alternative representation that facilitates easier clustering into similar groups compared to the raw sequences themselves. By assigning a unique vector embedding to each short sequence, it is possible to more efficiently cluster and improve upon compression performance for the string representations of cDNA libraries. Furthermore, through learning alternative coordinate vector embeddings based on the contexts of codon triplets, we can demonstrate clustering based on amino acid properties. Finally, using this sequence embedding method to encode barcodes and cDNA sequences, we can improve the time complexity of the similarity search by coupling vector embeddings with an algorithm that determines the proximity of vectors in Euclidean space; this allows us to perform sequence similarity searches in a quicker and more modular fashion.