DeepGeni: Deep generalized interpretable autoencoder elucidates gut microbiota for better cancer immunotherapy

Oh, Myounghak; Zhang, L

doi:10.1101/2021.05.06.443032

Cited by 4 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leveraging on the multimodal learning capabilities of MVIB, a possible direction for future research consists in using MVIB to combine microbiome-specific, host-specific, treatment-specific and cancer-specific data modalities for the estimation of the probability of success of a given immunotherapy, or for the optimisation of a given cancer treatment. [54,55] are recent microbiome-based machine learning methods which aim at predicting whether melanoma patients treated with immune checkpoint inhibitors will respond to the therapy. These methods represent a first effort in predicting how the microbiome affects the patients' response to cancer treatments.…”

Section: Discussionmentioning

confidence: 99%

Microbiome-based disease prediction with multimodal variational information bottlenecks

Siarheyeu¹,

G²,

A³

2021

Preprint

View full text Add to dashboard Cite

Scientific research is shedding more and more light on the interaction of the gut microbiome with the human body and its role in human health. Empirical evidence shows that the microbiome is strongly interconnected with the host immune system and can contribute to carcinogenesis. Furthermore, studies show that it can be used as a predictor for various diseases. In this work, we propose the Multimodal Variational Information Bottleneck (MVIB), a novel machine learning model capable of learning a joint representation of multiple heterogneous data modalities. Adopting an information theoretic interpretation of deep neural networks, MVIB allows to compute a joint stochastic encoding of the input data modalities, which acts as a minimal sufficient statistics of the inputs for the prediction of a target label. In a supervised learning setting, we use the MVIB to predict whether patients are affected by a certain disease by jointly analising the species-relative abundance and strain-level marker profiles extracted from shotgun metagenomic sequencing of microbial DNA. We propose various pre-processing methods for the marker profiles and validate our model on ten disease datasets. Additionaly, we perform transfer learning experiments by fine-tuning the model on the target disease dataset after a pre-training on all other source diseases. Furthermore, we adopt a saliency technique to interpret the outcome of the model classification and identify which microbial species and strain-level markers mostly contributed to a certain prediction. We show that MVIB achieves competitive results on the microbiome-based disease prediction task. The code for this work is publicly available at https://github.com/nec-research/microbiome-mvib.

show abstract

Section: Discussionmentioning

confidence: 99%

Microbiome-based disease prediction with multimodal variational information bottlenecks

Siarheyeu¹,

G²,

A³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Autoencoders are another form of ML models which have been used for effective representation of microbiome profiles ( Oh and Zhang 2020 , 2021 ). Taking motivation from the capabilities of GANs and autoencoders, in this paper, we use a combination of both these models for effective representation of the augmented microbiome dataset.…”

Section: Introductionmentioning

confidence: 99%

phylaGAN: data augmentation through conditional GANs and autoencoders for improving disease prediction accuracy using microbiome data

Sharma,

Lou,

2024

Bioinformatics

View full text Add to dashboard Cite

Motivation Research is improving our understanding of how the microbiome interacts with the human body and its impact on human health. Existing machine learning methods have shown great potential in discriminating healthy from diseased microbiome states. However, Machine Learning based prediction using microbiome data has challenges such as, small sample size, imbalance between cases and controls and high cost of collecting large number of samples. To address these challenges, we propose a deep learning framework phylaGAN to augment the existing datasets with generated microbiome data using a combination of conditional generative adversarial network (C-GAN) and autoencoder. Conditional generative adversarial networks train two models against each other to compute larger simulated datasets that are representative of the original dataset. Autoencoder maps the original and the generated samples onto a common subspace to make the prediction more accurate. Results Extensive evaluation and predictive analysis was conducted on two datasets, T2D study and Cirrhosis study showing an improvement in mean AUC using data augmentation by 11% and 5% respectively. External validation on a cohort classifying between obese and lean subjects, with a smaller sample size provided an improvement in mean AUC close to 32% when augmented through phylaGAN as compared to using the original cohort. Our findings not only indicate that the generative adversarial networks can create samples that mimic the original data across various diversity metrics, but also highlight the potential of enhancing disease prediction through machine learning models trained on synthetic data. Availability and implementation https://github.com/divya031090/phylaGAN.

show abstract

“…While some machine-learning algorithms perform well on large datasets (Chen et al, 2020;Gou et al, 2021;Carrieri et al, 2021), they are often discriminative in the case/control task without revealing additional information on the underlying reason for the success of their method. Alternatively, the results will highlight specific microbial features that may play a role in the examined clinical manifestation (Oh and Zhang, 2021), which can be further studied from a medical-or a basic-science perspective, as the basis for further studies understanding the mechanisms underlying this association (Aasmets et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

EasyMap - An Interactive Web Tool for Evaluating and Comparing Associations of Clinical Variables and Microbiome Composition

Dahan

Martin

Yassour

2022

Front. Cell. Infect. Microbiol.

View full text Add to dashboard Cite

One of the most common tasks in microbiome studies is comparing microbial profiles across various groups of people (e.g., sick vs. healthy). Routinely, researchers use multivariate linear regression models to address these challenges, such as linear regression packages, MaAsLin2, LEfSe, etc. In many cases, it is unclear which metadata variables should be included in the linear model, as many human-associated variables are correlated with one another. Thus, multiple models are often tested, each including a different set of variables, however the challenge of selecting the metadata variables in the final model remains. Here, we present EasyMap, an interactive online tool allowing for (1) running multiple multivariate linear regression models, on the same features and metadata; (2) visualizing the associations between microbial features and clinical metadata found in each model; and (3) comparing across the various models to identify the critical metadata variables and select the optimal model. EasyMap provides a side-by-side visualization of association results across the various models, each with additional metadata variables, enabling us to evaluate the impact of each metadata variable on the associated feature. EasyMap’s interface enables filtering associations by significance, focusing on specific microbes and finding the robust associations that are found across multiple models. While EasyMap was designed to analyze microbiome data, it can handle any other tabular data with numeric features and metadata variables. EasyMap takes the common task of multivariate linear regression to the next level, with an intuitive and simple user interface, allowing for wide comparisons of multiple models to identify the robust microbial feature associations. EasyMap is available at http://yassour.rcs.huji.ac.il/easymap.

show abstract

DeepGeni: Deep generalized interpretable autoencoder elucidates gut microbiota for better cancer immunotherapy

Cited by 4 publications

References 24 publications

Microbiome-based disease prediction with multimodal variational information bottlenecks

Microbiome-based disease prediction with multimodal variational information bottlenecks

phylaGAN: data augmentation through conditional GANs and autoencoders for improving disease prediction accuracy using microbiome data

EasyMap - An Interactive Web Tool for Evaluating and Comparing Associations of Clinical Variables and Microbiome Composition

Contact Info

Product

Resources

About