Feature set optimization in biomarker discovery from genome-scale data

2020 ◽  
Vol 36 (11) ◽  
pp. 3393-3400 ◽  
Author(s):  
V Fortino ◽  
G Scala ◽  
D Greco
Keyword(s):  
Dna Methylation ◽  
Classification Accuracy ◽  
Biomarker Discovery ◽  
Classification Systems ◽  
Supplementary Information ◽  
Adaptive Genetic Algorithm ◽  
Omics Data ◽  
Data Types ◽  
Set Size ◽  
New Biomarkers

Abstract Motivation Omics technologies have the potential to facilitate the discovery of new biomarkers. However, only few omics-derived biomarkers have been successfully translated into clinical applications to date. Feature selection is a crucial step in this process that identifies small sets of features with high predictive power. Models consisting of a limited number of features are not only more robust in analytical terms, but also ensure cost effectiveness and clinical translatability of new biomarker panels. Here we introduce GARBO, a novel multi-island adaptive genetic algorithm to simultaneously optimize accuracy and set size in omics-driven biomarker discovery problems. Results Compared to existing methods, GARBO enables the identification of biomarker sets that best optimize the trade-off between classification accuracy and number of biomarkers. We tested GARBO and six alternative selection methods with two high relevant topics in precision medicine: cancer patient stratification and drug sensitivity prediction. We found multivariate biomarker models from different omics data types such as mRNA, miRNA, copy number variation, mutation and DNA methylation. The top performing models were evaluated by using two different strategies: the Pareto-based selection, and the weighted sum between accuracy and set size (w = 0.5). Pareto-based preferences show the ability of the proposed algorithm to search minimal subsets of relevant features that can be used to model accurate random forest-based classification systems. Moreover, GARBO systematically identified, on larger omics data types, such as gene expression and DNA methylation, biomarker panels exhibiting higher classification accuracy or employing a number of features much lower than those discovered with other methods. These results were confirmed on independent datasets. Availability and implementation github.com/Greco-Lab/GARBO. Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Unsupervised discovery of phenotype-specific multi-omics networks

2019 ◽  
Vol 35 (21) ◽  
pp. 4336-4343 ◽  
Author(s):  
W Jenny Shi ◽  
Yonghua Zhuang ◽  
Pamela H Russell ◽  
Brian D Hobbs ◽  
Margaret M Parker ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Wide Spectrum ◽  
Supplementary Information ◽  
Chronic Obstructive ◽  
Phenotypic Traits ◽  
Omics Data ◽  
Data Types ◽  
Obstructive Pulmonary Disease ◽  
Quantitative Phenotype ◽  
Treatment Plans

Abstract Motivation Complex diseases often involve a wide spectrum of phenotypic traits. Better understanding of the biological mechanisms relevant to each trait promotes understanding of the etiology of the disease and the potential for targeted and effective treatment plans. There have been many efforts towards omics data integration and network reconstruction, but limited work has examined the incorporation of relevant (quantitative) phenotypic traits. Results We propose a novel technique, sparse multiple canonical correlation network analysis (SmCCNet), for integrating multiple omics data types along with a quantitative phenotype of interest, and for constructing multi-omics networks that are specific to the phenotype. As a case study, we focus on miRNA–mRNA networks. Through simulations, we demonstrate that SmCCNet has better overall prediction performance compared to popular gene expression network construction and integration approaches under realistic settings. Applying SmCCNet to studies on chronic obstructive pulmonary disease (COPD) and breast cancer, we found enrichment of known relevant pathways (e.g. the Cadherin pathway for COPD and the interferon-gamma signaling pathway for breast cancer) as well as less known omics features that may be important to the diseases. Although those applications focus on miRNA–mRNA co-expression networks, SmCCNet is applicable to a variety of omics and other data types. It can also be easily generalized to incorporate multiple quantitative phenotype simultaneously. The versatility of SmCCNet suggests great potential of the approach in many areas. Availability and implementation The SmCCNet algorithm is written in R, and is freely available on the web at https://cran.r-project.org/web/packages/SmCCNet/index.html. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals DIABLO: an integrative approach for identifying key molecular drivers from multi-omics assays

2019 ◽  
Vol 35 (17) ◽  
pp. 3055-3062 ◽  
Author(s):  
Amrit Singh ◽  
Casey P Shannon ◽  
Benoît Gautier ◽  
Florian Rohart ◽  
Michaël Vacher ◽  
...  
Keyword(s):  
Data Integration ◽  
Biomarker Discovery ◽  
Predictive Performance ◽  
Supplementary Information ◽  
Integrative Approach ◽  
Data Types ◽  
Common Information ◽  
Molecular Features ◽  
Study Designs ◽  
Integration Analysis

Abstract Motivation In the continuously expanding omics era, novel computational and statistical strategies are needed for data integration and identification of biomarkers and molecular signatures. We present Data Integration Analysis for Biomarker discovery using Latent cOmponents (DIABLO), a multi-omics integrative method that seeks for common information across different data types through the selection of a subset of molecular features, while discriminating between multiple phenotypic groups. Results Using simulations and benchmark multi-omics studies, we show that DIABLO identifies features with superior biological relevance compared with existing unsupervised integrative methods, while achieving predictive performance comparable to state-of-the-art supervised approaches. DIABLO is versatile, allowing for modular-based analyses and cross-over study designs. In two case studies, DIABLO identified both known and novel multi-omics biomarkers consisting of mRNAs, miRNAs, CpGs, proteins and metabolites. Availability and implementation DIABLO is implemented in the mixOmics R Bioconductor package with functions for parameters’ choice and visualization to assist in the interpretation of the integrative analyses, along with tutorials on http://mixomics.org and in our Bioconductor vignette. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals A latent unknown clustering integrating multi-omics data (LUCID) with phenotypic traits

2019 ◽  
Vol 36 (3) ◽  
pp. 842-850 ◽  
Author(s):  
Cheng Peng ◽  
Jun Wang ◽  
Isaac Asante ◽  
Stan Louie ◽  
Ran Jin ◽  
...  
Keyword(s):  
Real Data ◽  
R Package ◽  
Integrative Model ◽  
Supplementary Information ◽  
Phenotypic Traits ◽  
Omics Data ◽  
Data Types ◽  
Specific Effects ◽  
Metabolomic Data ◽  
Future Prediction

Abstract Motivation Epidemiologic, clinical and translational studies are increasingly generating multiplatform omics data. Methods that can integrate across multiple high-dimensional data types while accounting for differential patterns are critical for uncovering novel associations and underlying relevant subgroups. Results We propose an integrative model to estimate latent unknown clusters (LUCID) aiming to both distinguish unique genomic, exposure and informative biomarkers/omic effects while jointly estimating subgroups relevant to the outcome of interest. Simulation studies indicate that we can obtain consistent estimates reflective of the true simulated values, accurately estimate subgroups and recapitulate subgroup-specific effects. We also demonstrate the use of the integrated model for future prediction of risk subgroups and phenotypes. We apply this approach to two real data applications to highlight the integration of genomic, exposure and metabolomic data. Availability and Implementation The LUCID method is implemented through the LUCIDus R package available on CRAN (https://CRAN.R-project.org/package=LUCIDus). Supplementary information Supplementary materials are available at Bioinformatics online.

scholarly journals Prediction of cancer mutation states using multiple data modalities reveals the utility and consistency of gene expression and DNA methylation

2021 ◽  
Author(s):  
Jake Crawford ◽  
Brock C Christensen ◽  
Maria Chikina ◽  
Casey S Greene
Keyword(s):  
Gene Expression ◽  
Dna Methylation ◽  
Rna Sequencing ◽  
Genetic Alterations ◽  
Cellular Function ◽  
Data Type ◽  
Omics Data ◽  
Data Types ◽  
Cancer Mutation ◽  
Combining Data

In studies of cellular function in cancer, researchers are increasingly able to choose from many -omics assays as functional readouts. Choosing the correct readout for a given study can be difficult, and which layer of cellular function is most suitable to capture the relevant signal may be unclear. In this study, we consider prediction of cancer mutation status (presence or absence) from functional -omics data as a representative problem. Since functional signatures of cancer mutation have been identified across many data types, this problem presents an opportunity to quantify and compare the ability of different -omics readouts to capture signals of dysregulation in cancer. The TCGA Pan-Cancer Atlas contains genetic alteration data including somatic mutations and copy number variants (CNVs), as well as several -omics data types. From TCGA, we focus on RNA sequencing, DNA methylation arrays, reverse phase protein arrays (RPPA), microRNA, and somatic mutational signatures as -omics readouts. Across a collection of cancer-associated genetic alterations, RNA sequencing and DNA methylation were the most effective predictors of alteration state. Surprisingly, we found that for most alterations, they were approximately equally effective predictors. The target gene was the primary driver of performance, rather than the data type, and there was little difference between the top data types for the majority of genes. We also found that combining data types into a single multi-omics model often provided little or no improvement in predictive ability over the best individual data type. Based on our results, for the design of studies focused on the functional outcomes of cancer mutations, we recommend focusing on gene expression or DNA methylation as first-line readouts.

scholarly journals EPCO-29. EPIGENOMICS OF THE GLIOMA LONGITUDINAL ANALYSIS (GLASS) CONSORTIUM

2020 ◽  
Vol 22 (Supplement_2) ◽  
pp. ii75-ii75
Author(s):  
Thais Sabedot ◽  
Michael Wells ◽  
Indrani Datta ◽  
Tathiane Malta ◽  
Ana Valeria Castro ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Longitudinal Analysis ◽  
Copy Number ◽  
Large Scale ◽  
Molecular Classification ◽  
Tumor Burden ◽  
Copy Number Alterations ◽  
Unsupervised Analysis ◽  
Diffuse Gliomas ◽  
New Biomarkers

Abstract Adult diffuse gliomas are central nervous system (CNS) tumors that arise from the malignant transformation of glial cells. Nearly all gliomas will recur despite standard treatment however, current histopathological grading fails to predict which of them will relapse and/or progress. The Glioma Longitudinal AnalySiS (GLASS) consortium is a large-scale collaboration that aims to investigate the molecular profiling of matched primary and recurrent glioma samples from multiple institutions in order to better understand the dynamic evolution of these tumors. At this time, the cohort comprises 946 samples across 11 institutions and among those, 864 have DNA methylation data available. The current molecular classification based on 7 subtypes published by TCGA in 2016 was applied to the dataset. Among the IDH wildtype tumors, 33% (16/49) of the patients showed a change of subtype upon recurrence, whereas most of them (9/16) were Classic-like at the primary stage but changed to either Mesenchymal-like or PA-like at the recurrent level. Among the IDH mutant tumors, 15% (22/142) showed a change of subtype at recurrent stage, in which 16 out of 22 progressed from G-CIMP-high to G-CIMP-low. Although some tumors progressed to a different subtype upon recurrence, an unsupervised analysis showed that the samples tend to cluster by patient instead of by subtype. By estimating the copy number alterations of these tumors using DNA methylation, the overall copy number profile of the recurrent samples remains similar to their primary counterpart. From this initial analysis using epigenomic data, we were able to characterize some aspects of glioma evolution and how the DNA methylation is associated with the progression of these tumors to different subtypes. These findings corroborate the importance of epigenetics in gliomas and can potentially lead to the identification of new biomarkers that can reflect tumor burden and predict its development.

scholarly journals ASICS: an R package for a whole analysis workflow of 1D 1H NMR spectra

2019 ◽  
Vol 35 (21) ◽  
pp. 4356-4363 ◽  
Author(s):  
Gaëlle Lefort ◽  
Laurence Liaubet ◽  
Cécile Canlet ◽  
Patrick Tardivel ◽  
Marie-Christine Père ◽  
...  
Keyword(s):  
Metabolic Pathways ◽  
Nmr Spectra ◽  
Complex Mixture ◽  
R Package ◽  
Statistical Analyses ◽  
Supplementary Information ◽  
Automatic Identification ◽  
Analysis Workflow ◽  
Expert Analysis ◽  
New Biomarkers

Abstract Motivation In metabolomics, the detection of new biomarkers from Nuclear Magnetic Resonance (NMR) spectra is a promising approach. However, this analysis remains difficult due to the lack of a whole workflow that handles spectra pre-processing, automatic identification and quantification of metabolites and statistical analyses, in a reproducible way. Results We present ASICS, an R package that contains a complete workflow to analyse spectra from NMR experiments. It contains an automatic approach to identify and quantify metabolites in a complex mixture spectrum and uses the results of the quantification in untargeted and targeted statistical analyses. ASICS was shown to improve the precision of quantification in comparison to existing methods on two independent datasets. In addition, ASICS successfully recovered most metabolites that were found important to explain a two level condition describing the samples by a manual and expert analysis based on bucketing. It also found new relevant metabolites involved in metabolic pathways related to risk factors associated with the condition. Availability and implementation ASICS is distributed as an R package, available on Bioconductor. Supplementary information Supplementary data are available at Bioinformatics online.

SMILE: Mutual Information Learning for Integration of Single-cell Omics Data

2021 ◽  
Author(s):  
Yang Xu ◽  
Priyojit Das ◽  
Rachel Patton McCord
Keyword(s):  
Deep Learning ◽  
Mutual Information ◽  
Single Cell ◽  
Learning Algorithm ◽  
Cellular Systems ◽  
Supplementary Information ◽  
Omics Data ◽  
Learning Approaches ◽  
Rna Seq ◽  
Integrate Data

Abstract Motivation Deep learning approaches have empowered single-cell omics data analysis in many ways and generated new insights from complex cellular systems. As there is an increasing need for single cell omics data to be integrated across sources, types, and features of data, the challenges of integrating single-cell omics data are rising. Here, we present an unsupervised deep learning algorithm that learns discriminative representations for single-cell data via maximizing mutual information, SMILE (Single-cell Mutual Information Learning). Results Using a unique cell-pairing design, SMILE successfully integrates multi-source single-cell transcriptome data, removing batch effects and projecting similar cell types, even from different tissues, into the shared space. SMILE can also integrate data from two or more modalities, such as joint profiling technologies using single-cell ATAC-seq, RNA-seq, DNA methylation, Hi-C, and ChIP data. When paired cells are known, SMILE can integrate data with unmatched feature, such as genes for RNA-seq and genome wide peaks for ATAC-seq. Integrated representations learned from joint profiling technologies can then be used as a framework for comparing independent single source data. Supplementary information Supplementary data are available at Bioinformatics online. The source code of SMILE including analyses of key results in the study can be found at: https://github.com/rpmccordlab/SMILE.

PINSPlus: a tool for tumor subtype discovery in integrated genomic data

2018 ◽  
Vol 35 (16) ◽  
pp. 2843-2846 ◽  
Author(s):  
Hung Nguyen ◽  
Sangam Shrestha ◽  
Sorin Draghici ◽  
Tin Nguyen
Keyword(s):  
Personal Computer ◽  
Genomic Data ◽  
Supplementary Information ◽  
Omics Data ◽  
Tumor Subtype ◽  
Supplementary Data ◽  
Significant Survival ◽  
Survival Differences

Abstract Summary Since cancer is a heterogeneous disease, tumor subtyping is crucial for improved treatment and prognosis. We have developed a subtype discovery tool, called PINSPlus, that is: (i) robust against noise and unstable quantitative assays, (ii) able to integrate multiple types of omics data in a single analysis and (iii) dramatically superior to established approaches in identifying known subtypes and novel subgroups with significant survival differences. Our validation on 12,158 samples from 44 datasets shows that PINSPlus vastly outperforms other approaches. The software is easy-to-use and can partition hundreds of patients in a few minutes on a personal computer. Availability and implementation The package is available at https://cran.r-project.org/package=PINSPlus. Data and R script used in this manuscript are available at https://bioinformatics.cse.unr.edu/software/PINSPlus/. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Quickomics: exploring omics data in an intuitive, interactive and informative manner

2021 ◽  
Author(s):  
Benbo Gao ◽  
Jing Zhu ◽  
Soumya Negi ◽  
Xinmin Zhang ◽  
Stefka Gyoneva ◽  
...  
Keyword(s):  
Modular Design ◽  
Functional Module ◽  
Supplementary Information ◽  
Data Sets ◽  
Omics Data ◽  
Proteomics Data ◽  
Primary Analysis ◽  
Link Type ◽  
R Shiny ◽  
Advanced Analysis

AbstractSummaryWe developed Quickomics, a feature-rich R Shiny-powered tool to enable biologists to fully explore complex omics data and perform advanced analysis in an easy-to-use interactive interface. It covers a broad range of secondary and tertiary analytical tasks after primary analysis of omics data is completed. Each functional module is equipped with customized configurations and generates both interactive and publication-ready high-resolution plots to uncover biological insights from data. The modular design makes the tool extensible with ease.AvailabilityResearchers can experience the functionalities with their own data or demo RNA-Seq and proteomics data sets by using the app hosted at http://quickomics.bxgenomics.com and following the tutorial, https://bit.ly/3rXIyhL. The source code under GPLv3 license is provided at https://github.com/interactivereport/[email protected], [email protected] informationSupplementary materials are available at https://bit.ly/37HP17g.

scholarly journals Biomarker discovery studies for patient stratification using machine learning analysis of omics data: a scoping review

BMJ Open ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. e053674
Author(s):  
Enrico Glaab ◽  
Armin Rauschenberger ◽  
Rita Banzi ◽  
Chiara Gerardi ◽  
Paula Garcia ◽  
...  
Keyword(s):  
Machine Learning ◽  
Scoping Review ◽  
Biomarker Discovery ◽  
Biomedical Literature ◽  
Molecular Signature ◽  
Biological Knowledge ◽  
Measurement Technology ◽  
Omics Data ◽  
Patient Stratification ◽  
Complex Disorders

ObjectiveTo review biomarker discovery studies using omics data for patient stratification which led to clinically validated FDA-cleared tests or laboratory developed tests, in order to identify common characteristics and derive recommendations for future biomarker projects.DesignScoping review.MethodsWe searched PubMed, EMBASE and Web of Science to obtain a comprehensive list of articles from the biomedical literature published between January 2000 and July 2021, describing clinically validated biomarker signatures for patient stratification, derived using statistical learning approaches. All documents were screened to retain only peer-reviewed research articles, review articles or opinion articles, covering supervised and unsupervised machine learning applications for omics-based patient stratification. Two reviewers independently confirmed the eligibility. Disagreements were solved by consensus. We focused the final analysis on omics-based biomarkers which achieved the highest level of validation, that is, clinical approval of the developed molecular signature as a laboratory developed test or FDA approved tests.ResultsOverall, 352 articles fulfilled the eligibility criteria. The analysis of validated biomarker signatures identified multiple common methodological and practical features that may explain the successful test development and guide future biomarker projects. These include study design choices to ensure sufficient statistical power for model building and external testing, suitable combinations of non-targeted and targeted measurement technologies, the integration of prior biological knowledge, strict filtering and inclusion/exclusion criteria, and the adequacy of statistical and machine learning methods for discovery and validation.ConclusionsWhile most clinically validated biomarker models derived from omics data have been developed for personalised oncology, first applications for non-cancer diseases show the potential of multivariate omics biomarker design for other complex disorders. Distinctive characteristics of prior success stories, such as early filtering and robust discovery approaches, continuous improvements in assay design and experimental measurement technology, and rigorous multicohort validation approaches, enable the derivation of specific recommendations for future studies.

Sign in / Sign up

Export Citation Format

Share Document