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.

MOTIVATION: Common human diseases result from the interplay of genes and their biologically associated pathways. Genetic pathway analyses provide more biological insight as compared to conventional gene-based analysis. In this article, we propose a framework combining genetic data into pathway structure and using an ensemble of convolutional neural networks (CNNs) along with a Canonical Correlation Regularizer layer for comprehensive prediction of disease risk. The novelty of our approach lies in our two-step framework: (i) utilizing the CNN's effectiveness to extract the complex gene associations within individual genetic pathways and (ii) fusing features from ensemble of CNNs through Canonical Correlation Regularization layer to incorporate the interactions between pathways which share common genes. During prediction, we also address the important issues of interpretability of neural network models, and identifying the pathways and genes playing an important role in prediction. RESULTS: Implementation of our methodology into three real cancer genetic datasets for different prediction tasks validates our model's generalizability and robustness. Comparing with conventional models, our methodology provides consistently better performance with AUC improvement of 11% on predicting early/late-stage kidney cancer, 10% on predicting kidney versus liver cancer type and 7% on predicting survival status in ovarian cancer as compared to the next best conventional machine learning model. The robust performance of our deep learning algorithm indicates that disease prediction using neural networks in multiple functionally related genes across different pathways improves genetic data-based prediction and understanding molecular mechanisms of diseases. AVAILABILITY AND IMPLEMENTATION: https://github.com/divya031090/ReGeNNe.

BACKGROUND: Feature selection is important in high dimensional data analysis. The wrapper approach is one of the ways to perform feature selection, but it is computationally intensive as it builds and evaluates models of multiple subsets of features. The existing wrapper algorithm primarily focuses on shortening the path to find an optimal feature set. However, it underutilizes the capability of feature subset models, which impacts feature selection and its predictive performance. METHOD AND RESULTS: This study proposes a novel Artificial Intelligence based Wrapper (AIWrap) algorithm that integrates Artificial Intelligence (AI) with the existing wrapper algorithm. The algorithm develops a Performance Prediction Model using AI which predicts the model performance of any feature set and allows the wrapper algorithm to evaluate the feature subset performance in a model without building the model. The algorithm can make the wrapper algorithm more relevant for high-dimensional data. We evaluate the performance of this algorithm using simulated studies and real research studies. AIWrap shows better or at par feature selection and model prediction performance than standard penalized feature selection algorithms and wrapper algorithms. CONCLUSION: AIWrap approach provides an alternative algorithm to the existing algorithms for feature selection. The current study focuses on AIWrap application in continuous cross-sectional data. However, it could be applied to other datasets like longitudinal, categorical and time-to-event biological data.

MOTIVATION: Research shows that human microbiome is highly dynamic on longitudinal timescales, changing dynamically with diet, or due to medical interventions. In this article, we propose a novel deep learning framework 'phyLoSTM', using a combination of Convolutional Neural Networks and Long Short Term Memory Networks (LSTM) for feature extraction and analysis of temporal dependency in longitudinal microbiome sequencing data along with host's environmental factors for disease prediction. Additional novelty in terms of handling variable timepoints in subjects through LSTMs, as well as, weight balancing between imbalanced cases and controls is proposed. RESULTS: We simulated 100 datasets across multiple time points for model testing. To demonstrate the model's effectiveness, we also implemented this novel method into two real longitudinal human microbiome studies: (i) DIABIMMUNE three country cohort with food allergy outcomes (Milk, Egg, Peanut and Overall) and (ii) DiGiulio study with preterm delivery as outcome. Extensive analysis and comparison of our approach yields encouraging performance with an AUC of 0.897 (increased by 5%) on simulated studies and AUCs of 0.762 (increased by 19%) and 0.713 (increased by 8%) on the two real longitudinal microbiome studies respectively, as compared to the next best performing method, Random Forest. The proposed methodology improves predictive accuracy on longitudinal human microbiome studies containing spatially correlated data, and evaluates the change of microbiome composition contributing to outcome prediction. AVAILABILITY AND IMPLEMENTATION: https://github.com/divya031090/phyLoSTM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Developing statistical and machine learning methods on studies with missing information is a ubiquitous challenge in real-world biological research. The strategy in literature relies on either removing the samples with missing values like complete case analysis (CCA) or imputing the information in the samples with missing values like predictive mean matching (PMM) such as MICE. Some limitations of these strategies are information loss and closeness of the imputed values with the missing values. Further, in scenarios with piecemeal medical data, these strategies have to wait to complete the data collection process to provide a complete dataset for statistical models. METHOD AND RESULTS: This study proposes a dynamic model updating (DMU) approach, a different strategy to develop statistical models with missing data. DMU uses only the information available in the dataset to prepare the statistical models. DMU segments the original dataset into small complete datasets. The study uses hierarchical clustering to segment the original dataset into small complete datasets followed by Bayesian regression on each of the small complete datasets. Predictor estimates are updated using the posterior estimates from each dataset. The performance of DMU is evaluated by using both simulated data and real studies and show better results or at par with other approaches like CCA and PMM. CONCLUSION: DMU approach provides an alternative to the existing approaches of information elimination and imputation in processing the datasets with missing values. While the study applied the approach for continuous cross-sectional data, the approach can be applied to longitudinal, categorical and time-to-event biological data.

Classical statistical learning techniques struggle to perform feature selection in high-dimensional data that includes interaction effects i.e., when independent feature/s influence the effect of another feature on study outcome. Methods like penalized regression and sparse partial least squares regression can help, but penalization restricts the handling of interaction terms. This study proposes a novel Dimensionality Reduction based algorithm on High Dimensional feature Selection with Interactions (RHDSI), a new feature selection method that integrates dimensionality reduction and machine learning. The method can handle high-dimensional data, incorporate interaction terms and perform statistically-interpretable feature selection; and enables existing classical statistical techniques to work on high-dimensional data. RHDSI performs feature selection in three steps. The first step is a coarse feature selection through dimensionality reduction and statistical modeling on multiple resampled datasets and features, along with their interaction terms. The second step uses pooled results for unsupervised statistical learning-based feature refinement. Finally, supervised statistical learning-based feature selection is performed on the refined feature set to identify the final features with interactions. We evaluate the performance of this algorithm on simulated data and real studies. RHDSI shows better or par performance compared to standard feature selection algorithms like LASSO, subset selection, and sparse PLS.

MOTIVATION: Research supports the potential use of microbiome as a predictor of some diseases. Motivated by the findings that microbiome data is complex in nature, and there is an inherent correlation due to hierarchical taxonomy of microbial Operational Taxonomic Units (OTUs), we propose a novel machine learning method incorporating a stratified approach to group OTUs into phylum clusters. Convolutional Neural Networks (CNNs) were used to train within each of the clusters individually. Further, through an ensemble learning approach, features obtained from each cluster were then concatenated to improve prediction accuracy. Our two-step approach comprising stratification prior to combining multiple CNNs, aided in capturing the relationships between OTUs sharing a phylum efficiently, as compared to using a single CNN ignoring OTU correlations. RESULTS: We used simulated datasets containing 168 OTUs in 200 cases and 200 controls for model testing. Thirty-two OTUs, potentially associated with risk of disease were randomly selected and interactions between three OTUs were used to introduce non-linearity. We also implemented this novel method in two human microbiome studies: (i) Cirrhosis with 118 cases, 114 controls; (ii) type 2 diabetes (T2D) with 170 cases, 174 controls; to demonstrate the model's effectiveness. Extensive experimentation and comparison against conventional machine learning techniques yielded encouraging results. We obtained mean AUC values of 0.88, 0.92, 0.75, showing a consistent increment (5%, 3%, 7%) in simulations, Cirrhosis and T2D data, respectively, against the next best performing method, Random Forest. AVAILABILITY AND IMPLEMENTATION: https://github.com/divya031090/TaxoNN_OTU. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.