DeepMicro: deep representation learning for disease prediction based on microbiome data

Abstract

<jats:title>Abstract</jats:title><jats:p>Human microbiota plays a key role in human health and growing evidence supports the potential use of microbiome as a predictor of various diseases. However, the high-dimensionality of microbiome data, often in the order of hundreds of thousands, yet low sample sizes, poses great challenge for machine learning-based prediction algorithms. This imbalance induces the data to be highly sparse, preventing from learning a better prediction model. Also, there has been little work on deep learning applications to microbiome data with a rigorous evaluation scheme. To address these challenges, we propose DeepMicro, a deep representation learning framework allowing for an effective representation of microbiome profiles. DeepMicro successfully transforms high-dimensional microbiome data into a robust low-dimensional representation using various autoencoders and applies machine learning classification algorithms on the learned representation. In disease prediction, DeepMicro outperforms the current best approaches based on the strain-level marker profile in five different datasets. In addition, by significantly reducing the dimensionality of the marker profile, DeepMicro accelerates the model training and hyperparameter optimization procedure with 8X-30X speedup over the basic approach. DeepMicro is freely available at <jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/minoh0201/DeepMicro">https://github.com/minoh0201/DeepMicro</jats:ext-link>.</jats:p>

Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey

“…Dony et al [49] found that VAE with a VAMP prior is capable of learning biologically informative embeddings without compromising on generative properties. Oh et al [50] utilized various autoencoders to convert high-dimensional microbiome data into robust low-dimensional representations, and apply machine learning classification algorithms to the learned representations. Way et al [51] compared different methods include VAE to compress data dimensionalities and learn complementary biological representations.…”

“…In addition, a key benefit of VAEs is the ability to control the distribution of the latent representation vector z, which can combine VAEs with representation learning to further improve the downstream tasks [18,22]. Moreover, the generated image quality and diversity are improved by the existing VAE-variants such as β-VAE [23] and InfoVAE [24], which combine VAEs with disentanglement [25], [26], [27], [28], [29], [30], [31] graph representation design [32], [33], [34], [35], [36], [37], [38], [39], [40] sequence datasets analyses sequence engineering [41], [42], [43], [44], [45], [46], [47] dimensionality reduction [48], [49], [50], [51], [52], [53], [54], [55] integrated multi-omics data analyses [56], [57] predict effects of mutations [58], [47] gene expression analyses [56], [59], [54], [60], [61], [57]<...>…”

Predicting microbiomes through a deep latent space

“…relative abundances. This approach is commonly used in DL (Oh and Zhang, 2020), although it brings with several disadvantages, in that it does not remove compositionality (Aitchison, 1982). As such, several standard analyses cannot be applied without bias, such as comparative analysis between groups; however, these problems are distinct from how we use this approach in our study.…”

“…The study most similar to ours is DeepMicro (Oh and Zhang, 2020). Here, we predict a microbiome code from environmental variables and then decode it to obtain the whole microbiome vector using an Au-toencoder.…”

“…Few previous studies have tried to predict microbial composition from environmental features, and those have mainly focused on a few tens of taxa, corresponding to the highest taxonomic levels (Larsen et al, 2012;Ladau et al, 2018;Oh and Zhang, 2020).…”