HDSI: High dimensional selection with interactions algorithm on feature selection and testing

The impact of Bayesian optimization on feature selection

Feature selection is an indispensable step for the analysis of high-dimensional molecular data. Despite its importance, consensus is lacking on how to choose the most appropriate feature selection methods, especially when the performance of the feature selection methods itself depends on hyper-parameters. Bayesian optimization has demonstrated its advantages in automatically configuring the settings of hyper-parameters for various models. However, it remains unclear whether Bayesian optimization can benefit feature selection methods. In this research, we conducted extensive simulation studies to compare the performance of various feature selection methods, with a particular focus on the impact of Bayesian optimization on those where hyper-parameters tuning is needed. We further utilized the gene expression data obtained from the Alzheimer's Disease Neuroimaging Initiative to predict various brain imaging-related phenotypes, where various feature selection methods were employed to mine the data. We found through simulation studies that feature selection methods with hyper-parameters tuned using Bayesian optimization often yield better recall rates, and the analysis of transcriptomic data further revealed that Bayesian optimization-guided feature selection can improve the accuracy of disease risk prediction models. In conclusion, Bayesian optimization can facilitate feature selection methods when hyper-parameter tuning is needed and has the potential to substantially benefit downstream tasks.

A prognostic prediction model for ovarian cancer using a cross-modal view correlation discovery network

Ovarian cancer is a tumor with different clinicopathological and molecular features, and the vast majority of patients have local or extensive spread at the time of diagnosis. Early diagnosis and prognostic prediction of patients can contribute to the understanding of the underlying pathogenesis of ovarian cancer and the improvement of therapeutic outcomes. The occurrence of ovarian cancer is influenced by multiple complex mechanisms, including the genome, transcriptome and proteome. Different types of omics analysis help predict the survival rate of ovarian cancer patients. Multi-omics data of ovarian cancer exhibit high-dimensional heterogeneity, and existing methods for integrating multi-omics data have not taken into account the variability and inter-correlation between different omics data. In this paper, we propose a deep learning model, MDCADON, which utilizes multi-omics data and cross-modal view correlation discovery network. We introduce random forest into LASSO regression for feature selection on mRNA expression, DNA methylation, miRNA expression and copy number variation (CNV), aiming to select important features highly correlated with ovarian cancer prognosis. A multi-modal deep neural network is used to comprehensively learn feature representations of each omics data and clinical data, and cross-modal view correlation discovery network is employed to construct the multi-omics discovery tensor, exploring the inter-relationships between different omics data. The experimental results demonstrate that MDCADON is superior to the existing methods in predicting ovarian cancer prognosis, which enables survival analysis for patients and facilitates the determination of follow-up treatment plans. Finally, we perform Gene Ontology (GO) term analysis and biological pathway analysis on the genes identified by MDCADON, revealing the underlying mechanisms of ovarian cancer and providing certain support for guiding ovarian cancer treatments.

Toward precision medicine using a "digital twin" approach: modeling the onset of disease-specific brain atrophy in individuals with multiple sclerosis

Digital Twin (DT) is a novel concept that may bring a paradigm shift for precision medicine. In this study we demonstrate a DT application for estimating the age of onset of disease-specific brain atrophy in individuals with multiple sclerosis (MS) using brain MRI. We first augmented longitudinal data from a well-fitted spline model derived from a large cross-sectional normal aging data. Then we compared different mixed spline models through both simulated and real-life data and identified the mixed spline model with the best fit. Using the appropriate covariate structure selected from 52 different candidate structures, we augmented the thalamic atrophy trajectory over the lifespan for each individual MS patient and a corresponding hypothetical twin with normal aging. Theoretically, the age at which the brain atrophy trajectory of an MS patient deviates from the trajectory of their hypothetical healthy twin can be considered as the onset of progressive brain tissue loss. With a tenfold cross validation procedure through 1000 bootstrapping samples, we found the onset age of progressive brain tissue loss was, on average, 5-6 years prior to clinical symptom onset. Our novel approach also discovered two clear patterns of patient clusters: earlier onset versus simultaneous onset of brain atrophy.

LASSO Regression with Multiple Imputations for the Selection of Key Variables Affecting the Fatty Acid Profile of Nannochloropsis oculata

The marine microalga Nannochloropsis oculata has garnered significant interest as a potential source of lipids, both for biofuel and nutrition, containing significant amounts of C16:0, C16:1, and C20:5, n-3 (EPA) fatty acids (FA). Growth parameters such as temperature, pH, light intensity, and nutrient availability play a crucial role in the fatty acid profile of microalgae, with N. oculata being no exception. This study aims to identify key variables for the FA profile of N. oculata grown autotrophically. To that end, the most relevant literature data were gathered and combined with our previous work as well as with novel experimental data, with 121 observations in total. The examined variables were the percentages of C14:0, C16:0, C16:1, C18:1, C18:2, and C20:5, n-3 in total FAs, their respective ratios to C16:0, and the respective content of biomass in those fatty acids in terms of ash free dry weight. Many potential predictor variables were collected, while dummy variables were introduced to account for bias in the measured variables originating from different authors as well as for other parameters. The method of multiple imputations was chosen to handle missing data, with limits based on the literature and model-based estimation, such as using the software PHREEQC and residual modelling for the estimation of pH. To eliminate unimportant predictor variables, LASSO (Least Absolute Shrinkage and Selection Operator) regression analysis with a novel definition of optimal lambda was employed. LASSO regression identified the most relevant predictors while minimizing the risk of overfitting the model. Subsequently, stepwise linear regression with interaction terms was used to further study the effects of the selected predictors. After two rounds of regression, sparse refined models were acquired, and their coefficients were evaluated based on significance. Our analysis confirms well-known effects, such as that of temperature, and it uncovers novel unreported effects of aeration, calcium, magnesium, and manganese. Of special interest is the negative effect of aeration on polyunsaturated fatty acids (PUFAs), which is possibly related to the enzymatic kinetics of fatty acid desaturation under increased oxygen concentration. These findings contribute to the optimization of the fatty acid profile of N. oculata for different purposes, such as production of, high in PUFAs, food or feed, or production of, high in saturated and monounsaturated FA methyl esters (FAME), biofuels.

Toward Precision Medicine Using a "Digital Twin" Approach: Modeling the Onset of Disease-Specific Brain Atrophy in Individuals with Multiple Sclerosis

Digital Twin (DT) is a novel concept that may bring a paradigm shift for precision medicine. In this study we demonstrate a DT application for estimating the age of onset of disease-specific brain atrophy in individuals with multiple sclerosis (MS) using brain MRI. We first augmented longitudinal data from a well-fitted spline model derived from a large cross-sectional normal aging data. Then we compared different mixed spline models through both simulated and real-life data and identified the mixed spline model with the best fit. Using the appropriate covariate structure selected from 52 different candidate structures, we augmented the thalamic atrophy trajectory over the lifespan for each individual MS patient and a corresponding hypothetical twin with normal aging. Theoretically, the age at which the brain atrophy trajectory of an MS patient deviates from the trajectory of their hypothetical healthy twin can be considered as the onset of progressive brain tissue loss. With a 10-fold cross validation procedure through 1000 bootstrapping samples, we found the onset age of progressive brain tissue loss was, on average, 5-6 years prior to clinical symptom onset. Our novel approach also discovered two clear patterns of patient clusters: earlier onset vs. simultaneous onset of brain atrophy.

Hyperspectral Monitoring Driven by Machine Learning Methods for Grassland Above-Ground Biomass

Above-ground biomass (AGB) is a key indicator for studying grassland productivity and evaluating carbon sequestration capacity; it is also a key area of interest in hyperspectral ecological remote sensing. In this study, we use data from a typical alpine meadow in the Qinghai–Tibet Plateau during the main growing season (July–September), compare the results of various feature selection algorithms to extract an optimal subset of spectral variables, and use machine learning methods and data mining techniques to build an AGB prediction model and realize the optimal inversion of above-ground grassland biomass. The results show that the Lasso and RFE_SVM band filtering machine learning models can effectively select the global optimal feature and improve the prediction effect of the model. The analysis also compares the support vector machine (SVM), least squares regression boosting (LSB), and Gaussian process regression (GPR) AGB inversion models; our findings show that the results of the three models are similar, with the GPR machine learning model achieving the best outcomes. In addition, through the analysis of different data combinations, it is found that the accuracy of AGB inversion can be significantly improved by combining the spectral characteristics with the growing season. Finally, by constructing a machine learning interpretable model to analyze the specific role of features, it was found that the same band plays different roles in different records, and the related results can provide a scientific basis for the research of grassland resource monitoring and estimation.

PIntMF: Penalized Integrative Matrix Factorization method for multi-omics data

MOTIVATION

It is more and more common to perform multi-omics analyses to explore the genome at diverse levels and not only at a single level. Through integrative statistical methods, multi-omics data have the power to reveal new biological processes, potential biomarkers and subgroups in a cohort. Matrix factorization (MF) is an unsupervised statistical method that allows a clustering of individuals, but also reveals relevant omics variables from the various blocks.

RESULTS

Here, we present PIntMF (Penalized Integrative Matrix Factorization), an MF model with sparsity, positivity and equality constraints. To induce sparsity in the model, we used a classical Lasso penalization on variable and individual matrices. For the matrix of samples, sparsity helps in the clustering, while normalization (matching an equality constraint) of inferred coefficients is added to improve interpretation. Moreover, we added an automatic tuning of the sparsity parameters using the famous glmnet package. We also proposed three criteria to help the user to choose the number of latent variables. PIntMF was compared with other state-of-the-art integrative methods including feature selection techniques in both synthetic and real data. PIntMF succeeds in finding relevant clusters as well as variables in two types of simulated data (correlated and uncorrelated). Next, PIntMF was applied to two real datasets (Diet and cancer), and it revealed interpretable clusters linked to available clinical data. Our method outperforms the existing ones on two criteria (clustering and variable selection). We show that PIntMF is an easy, fast and powerful tool to extract patterns and cluster samples from multi-omics data.

AVAILABILITY AND IMPLEMENTATION

An R package is available at https://github.com/mpierrejean/pintmf.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.