16S rRNA sequence embeddings: Meaningful numeric feature representations of nucleotide sequences that are convenient for downstream analyses

Abstract

Advances in high-throughput sequencing have increased the availability of microbiome sequencing data that can be exploited to characterize microbiome community structure in situ. We explore using word and sentence embedding approaches for nucleotide sequences since they may be a suitable numerical representation for downstream machine learning applications (especially deep learning). This work involves first encoding ("embedding") each sequence into a dense, low-dimensional, numeric vector space. Here, we use Skip-Gram word2vec to embed k -mers, obtained from 16S rRNA amplicon surveys, and then leverage an existing sentence embedding technique to embed all sequences belonging to specific body sites or samples. We demonstrate that these representations are biologically meaningful, and hence the embedding space can be exploited as a form of feature extraction for exploratory analysis. We show that sequence embeddings preserve relevant information about the sequencing data such as k -mer context, sequence taxonomy, and sample class. Specifically, the sequence embedding space resolved differences among phyla, as well as differences among genera within the same family. Distances between sequence embeddings had similar qualities to distances between alignment identities, and embedding multiple sequences can be thought of as generating a consensus sequence. Using sample embeddings for body site classification resulted in negligible performance loss compared to using OTU abundance data. Lastly, the k -mer embedding space captured distinct k -mer profiles that mapped to specific regions of the 16S rRNA gene and corresponded with particular body sites. Together, our results show that embedding sequences results in meaningful representations that can be used for exploratory analyses or for downstream machine learning applications that require numeric data. Moreover, because the embeddings are trained in an unsupervised manner, unlabeled data can be embedded and used to bolster supervised machine learning tasks. Author summaryImprovements in the way genomes are sequenced have led to an abundance of microbiome data. With the right approaches, researchers use this data to thoroughly characterize how microbes interact with each other and their host, but sequencing data is of a form (sequences of letters) not ideal for many data analysis approaches. We May 3, 2018 1/23 . CC-BY 4.0 International license It is made available under a was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.The copyright holder for this preprint (which . http://dx.doi.org/10.1101/314260 doi: bioRxiv preprint first posted online May. 4, 2018; therefore present an approach to transform sequencing data into arrays of numbers that can capture interesting qualities of the data at the sub-sequence, full-sequence, and sample levels. This allows us to measure the importance of certain microbial sequences with respect to the type of microbe and the condition of the host. Also, representi...

Decoding the Language of Microbiomes: Leveraging Patterns in 16S Public Data using Word-Embedding Techniques and Applications in Inflammatory Bowel Disease

“…Woloszynek et. al represent each 16S sequence by the set of k-length nucleotide sequences (k-mers) it includes, and embed those k-mers to create a vector representation of each sequence (43).…”

Towards end-to-end disease prediction from raw metagenomic data

“…In the work of Woloszynek et al (2018), the objective is to add, in addition to taxonomic profiling, a method to retrieve the source environment of a metagenome (phenotype prediction). A Skip-gram word2vec algorithm ( Mikolov et al 2013) is trained for k-mers embeddings and a SIF algorithm ( Arora et al (2017)) is used to create reads and samples embeddings.…”

“…Moreover, it is difficult to know the location of a read in genomes because the DNA were fragmented prior to sequencing and there is no particular order to the reads after sequencing. To transform the reads onto something similar to words, a possible approach may be to simply split the sequences into k-mers ( Menegaux et al 2019; Woloszynek et al 2018; Min et al 2017; Q. Liang et al 2020). Various size of k can be considered depending on the task.…”

“…Building k-mers, reads and metagenome embeddings Similar to the NLP applications, using vector representations of k-mers can overcome some limitation to treat reads as discrete atomic sequence of nucleotides. Similarly, vector representation of reads and metagenomes can be envisioned to go beyond their simple encoding representations (Woloszynek et al 2018). In this paper we focus on learning metagenome embeddings that have the ability to both reduce the data dimensions and also support computationally-efficient predictive models from embedded raw metagenomes.…”

dom2vec: Unsupervised protein domain embeddings capture domains structure and function providing data-driven insights into collocations in domain architectures

“…Similarly (Woloszynek et al, 2019) computed embeddings for all k-mers using a range of k; they also used doc2vec to find the whole protein embedding. (Bepler and Berger, 2019) learned an embedding of each amino acid position incorporating global structural similarity between a pair of proteins and contact map information for each protein.…”