Large-Scale Automatic Feature Selection for Biomarker Discovery in High-Dimensional OMICs Data.
Ontology highlight
ABSTRACT:
SUBMITTER: Leclercq M
PROVIDER: S-EPMC6532608 | biostudies-literature | 2019
REPOSITORIES: biostudies-literature
Publications
Large-Scale Automatic Feature Selection for Biomarker Discovery in High-Dimensional OMICs Data.
Leclercq Mickael M Vittrant Benjamin B Martin-Magniette Marie Laure ML Scott Boyer Marie Pier MP Perin Olivier O Bergeron Alain A Fradet Yves Y Droit Arnaud A
Frontiers in genetics 20190516
The identification of biomarker signatures in omics molecular profiling is usually performed to predict outcomes in a precision medicine context, such as patient disease susceptibility, diagnosis, prognosis, and treatment response. To identify these signatures, we have developed a biomarker discovery tool, called BioDiscML. From a collection of samples and their associated characteristics, i.e., the biomarkers (e.g., gene expression, protein levels, clinico-pathological data), BioDiscML exploits ...[more]
Similar Datasets
Project description:We are moving into the age of 'Big Data' in biomedical research and bioinformatics. This trend could be encapsulated in this simple formula: D = S * F, where the volume of data generated (D) increases in both dimensions: the number of samples (S) and the number of sample features (F). Frequently, a typical omics classification includes redundant and irrelevant features (e.g. genes or proteins) that can result in long computation times; decrease of the model performance and the selection of suboptimal features (genes and proteins) after the classification/regression step. Multiple algorithms and reviews has been published to describe all the existing methods for feature selection, their strengths and weakness. However, the selection of the correct FS algorithm and strategy constitutes an enormous challenge. Despite the number and diversity of algorithms available, the proper choice of an approach for facing a specific problem often falls in a 'grey zone'. In this study, we select a subset of FS methods to develop an efficient workflow and an R package for bioinformatics machine learning problems. We cover relevant issues concerning FS, ranging from domain's problems to algorithm solutions and computational tools. Finally, we use seven different proteomics and gene expression datasets to evaluate the workflow and guide the FS process.
| S-EPMC5738110 | biostudies-literature
Project description:Untargeted metabolomics is a powerful phenotyping tool for better understanding biological mechanisms involved in human pathology development and identifying early predictive biomarkers. This approach, based on multiple analytical platforms, such as mass spectrometry (MS), chemometrics and bioinformatics, generates massive and complex data that need appropriate analyses to extract the biologically meaningful information. Despite various tools available, it is still a challenge to handle such large and noisy datasets with limited number of individuals without risking overfitting. Moreover, when the objective is focused on the identification of early predictive markers of clinical outcome, few years before occurrence, it becomes essential to use the appropriate algorithms and workflow to be able to discover subtle effects among this large amount of data. In this context, this work consists in studying a workflow describing the general feature selection process, using knowledge discovery and data mining methodologies to propose advanced solutions for predictive biomarker discovery. The strategy was focused on evaluating a combination of numeric-symbolic approaches for feature selection with the objective of obtaining the best combination of metabolites producing an effective and accurate predictive model. Relying first on numerical approaches, and especially on machine learning methods (SVM-RFE, RF, RF-RFE) and on univariate statistical analyses (ANOVA), a comparative study was performed on an original metabolomic dataset and reduced subsets. As resampling method, LOOCV was applied to minimize the risk of overfitting. The best k-features obtained with different scores of importance from the combination of these different approaches were compared and allowed determining the variable stabilities using Formal Concept Analysis. The results revealed the interest of RF-Gini combined with ANOVA for feature selection as these two complementary methods allowed selecting the 48 best candidates for prediction. Using linear logistic regression on this reduced dataset enabled us to obtain the best performances in terms of prediction accuracy and number of false positive with a model including 5 top variables. Therefore, these results highlighted the interest of feature selection methods and the importance of working on reduced datasets for the identification of predictive biomarkers issued from untargeted metabolomics data.
| S-EPMC4937038 | biostudies-literature
Project description:Untargeted mass spectrometry (MS)-based proteomics provides a powerful platform for protein biomarker discovery, but clinical translation depends on the selection of a small number of proteins for downstream verification and validation. Due to the small sample size of typical discovery studies, protein markers identified from discovery data may not be generalizable to independent datasets. In addition, a good protein marker identified using a discovery platform may be difficult to implement in verification and validation platforms. Moreover, although multiomics characterization is being increasingly used in discovery cohort studies, there is no existing method for multiomics-facilitated protein biomarker selection. Here, we present ProMS, a computational algorithm for protein marker selection. The algorithm is based on the hypothesis that a phenotype is characterized by a few underlying biological functions, each manifested by a group of coexpressed proteins. A weighted k-medoids clustering algorithm is applied to all univariately informative proteins to identify both coexpressed protein clusters and a representative protein for each cluster as markers. In two clinically important classification problems, ProMS shows superior performance compared with existing feature selection methods. ProMS can be extended to the multiomics setting (ProMS_mo) through a constrained weighted k-medoids clustering algorithm, and the protein panels selected by ProMS_mo show improved performance on independent test data compared with ProMS. In addition to superior performance, ProMS and ProMS_mo also have two unique strengths. First, the feature clusters enable functional interpretation of the selected protein markers. Second, the feature clusters provide an opportunity to select replacement protein markers, facilitating a robust transition to the verification and validation platforms. In summary, this study provides a unified and effective computational framework for selecting protein biomarkers using proteomics or multiomics data. The software implementation is publicly available at https://github.com/bzhanglab/proms.
| S-EPMC8165452 | biostudies-literature
Project description:High-dimensional clustering analysis is a challenging problem in statistics and machine learning, with broad applications such as the analysis of microarray data and RNA-seq data. In this paper, we propose a new clustering procedure called spectral clustering with feature selection (SC-FS), where we first obtain an initial estimate of labels via spectral clustering, then select a small fraction of features with the largest R-squared with these labels, that is, the proportion of variation explained by group labels, and conduct clustering again using selected features. Under mild conditions, we prove that the proposed method identifies all informative features with high probability and achieves the minimax optimal clustering error rate for the sparse Gaussian mixture model. Applications of SC-FS to four real-world datasets demonstrate its usefulness in clustering high-dimensional data.
| S-EPMC10119907 | biostudies-literature
Project description:BackgroundHepatocellular carcinoma (HCC) is one of the most common cancers. The discovery of specific genes severing as biomarkers is of paramount significance for cancer diagnosis and prognosis. The high-throughput omics data generated by the cancer genome atlas (TCGA) consortium provides a valuable resource for the discovery of HCC biomarker genes. Numerous methods have been proposed to select cancer biomarkers. However, these methods have not investigated the robustness of identification with different feature selection techniques.MethodsWe use six different recursive feature elimination methods to select the gene signiatures of HCC from TCGA liver cancer data. The genes shared in the six selected subsets are proposed as robust biomarkers. Akaike information criterion (AIC) is employed to explain the optimization process of feature selection, which provides a statistical interpretation for the feature selection in machine learning methods. And we use several methods to validate the screened biomarkers.ResultsIn this paper, we propose a robust method for discovering biomarker genes for HCC from gene expression data. Specifically, we implement recursive feature elimination cross-validation (RFE-CV) methods based on six different classication algorithms. The overlaps in the discovered gene sets via different methods are referred as the identified biomarkers. We give an interpretation of the feature selection process based on machine learning using AIC in statistics. Furthermore, the features selected by the backward logistic stepwise regression via AIC minimum theory are completely contained in the identified biomarkers. Through the classification results, the superiority of interpretable robust biomarker discovery method is verified.ConclusionsIt is found that overlaps among gene subsets contain different quantitative features selected by the RFE-CV of 6 classifiers. The AIC values in the model selection provide a theoretical foundation for the feature selection process of biomarker discovery via machine learning. What's more, genes containing in more optimally selected subsets make better biological sense and implication. The quality of feature selection is improved by the intersections of biomarkers selected from different classifiers. This is a general method suitable for screening biomarkers of complex diseases from high-throughput data.
| S-EPMC8386074 | biostudies-literature
Project description:Background In the last few years, multi-omics data, that is, datasets containing different types of high-dimensional molecular variables for the same samples, have become increasingly available. To date, several comparison studies focused on feature selection methods for omics data, but to our knowledge, none compared these methods for the special case of multi-omics data. Given that these data have specific structures that differentiate them from single-omics data, it is unclear whether different feature selection strategies may be optimal for such data. In this paper, using 15 cancer multi-omics datasets we compared four filter methods, two embedded methods, and two wrapper methods with respect to their performance in the prediction of a binary outcome in several situations that may affect the prediction results. As classifiers, we used support vector machines and random forests. The methods were compared using repeated fivefold cross-validation. The accuracy, the AUC, and the Brier score served as performance metrics. Results The results suggested that, first, the chosen number of selected features affects the predictive performance for many feature selection methods but not all. Second, whether the features were selected by data type or from all data types concurrently did not considerably affect the predictive performance, but for some methods, concurrent selection took more time. Third, regardless of which performance measure was considered, the feature selection methods mRMR, the permutation importance of random forests, and the Lasso tended to outperform the other considered methods. Here, mRMR and the permutation importance of random forests already delivered strong predictive performance when considering only a few selected features. Finally, the wrapper methods were computationally much more expensive than the filter and embedded methods. Conclusions We recommend the permutation importance of random forests and the filter method mRMR for feature selection using multi-omics data, where, however, mRMR is considerably more computationally costly. Supplementary Information The online version contains supplementary material available at 10.1186/s12859-022-04962-x.
| S-EPMC9533501 | biostudies-literature
Project description:BackgroundMicroRNAs (miRNAs) are noncoding RNA molecules heavily involved in human tumors, in which few of them circulating the human body. Finding a tumor-associated signature of miRNA, that is, the minimum miRNA entities to be measured for discriminating both different types of cancer and normal tissues, is of utmost importance. Feature selection techniques applied in machine learning can help however they often provide naive or biased results.ResultsAn ensemble feature selection strategy for miRNA signatures is proposed. miRNAs are chosen based on consensus on feature relevance from high-accuracy classifiers of different typologies. This methodology aims to identify signatures that are considerably more robust and reliable when used in clinically relevant prediction tasks. Using the proposed method, a 100-miRNA signature is identified in a dataset of 8023 samples, extracted from TCGA. When running eight-state-of-the-art classifiers along with the 100-miRNA signature against the original 1046 features, it could be detected that global accuracy differs only by 1.4%. Importantly, this 100-miRNA signature is sufficient to distinguish between tumor and normal tissues. The approach is then compared against other feature selection methods, such as UFS, RFE, EN, LASSO, Genetic Algorithms, and EFS-CLA. The proposed approach provides better accuracy when tested on a 10-fold cross-validation with different classifiers and it is applied to several GEO datasets across different platforms with some classifiers showing more than 90% classification accuracy, which proves its cross-platform applicability.ConclusionsThe 100-miRNA signature is sufficiently stable to provide almost the same classification accuracy as the complete TCGA dataset, and it is further validated on several GEO datasets, across different types of cancer and platforms. Furthermore, a bibliographic analysis confirms that 77 out of the 100 miRNAs in the signature appear in lists of circulating miRNAs used in cancer studies, in stem-loop or mature-sequence form. The remaining 23 miRNAs offer potentially promising avenues for future research.
| S-EPMC6751684 | biostudies-literature
Project description:Reliable identification of Inflammatory biomarkers from metagenomics data is a promising direction for developing non-invasive, cost-effective, and rapid clinical tests for early diagnosis of IBD. We present an integrative approach to Network-Based Biomarker Discovery (NBBD) which integrates network analyses methods for prioritizing potential biomarkers and machine learning techniques for assessing the discriminative power of the prioritized biomarkers. Using a large dataset of new-onset pediatric IBD metagenomics biopsy samples, we compare the performance of Random Forest (RF) classifiers trained on features selected using a representative set of traditional feature selection methods against NBBD framework, configured using five different tools for inferring networks from metagenomics data, and nine different methods for prioritizing biomarkers as well as a hybrid approach combining best traditional and NBBD based feature selection. We also examine how the performance of the predictive models for IBD diagnosis varies as a function of the size of the data used for biomarker identification. Our results show that (i) NBBD is competitive with some of the state-of-the-art feature selection methods including Random Forest Feature Importance (RFFI) scores; and (ii) NBBD is especially effective in reliably identifying IBD biomarkers when the number of data samples available for biomarker discovery is small.
| S-EPMC6874333 | biostudies-literature
Project description:Fraud is a pervasive problem and can occur as fabrication, falsification, plagiarism, or theft. The scientific community is not exempt from this universal problem and several studies have recently been caught manipulating or fabricating data. Current measures to prevent and deter scientific misconduct come in the form of the peer-review process and on-site clinical trial auditors. As recent advances in high-throughput omics technologies have moved biology into the realm of big-data, fraud detection methods must be updated for sophisticated computational fraud. In the financial sector, machine learning and digit-frequencies are successfully used to detect fraud. Drawing from these sources, we develop methods of fabrication detection in biomedical research and show that machine learning can be used to detect fraud in large-scale omic experiments. Using the gene copy-number data as input, machine learning models correctly predicted fraud with 58-100% accuracy. With digit frequency as input features, the models detected fraud with 82%-100% accuracy. All of the data and analysis scripts used in this project are available at https://github.com/MSBradshaw/FakeData.
| S-EPMC8631639 | biostudies-literature
Project description:Selecting informative features, such as accurate biomarkers for disease diagnosis, prognosis and response to treatment, is an essential task in the field of bioinformatics. Medical data often contain thousands of features and identifying potential biomarkers is challenging due to small number of samples in the data, method dependence and non-reproducibility. This paper proposes a novel ensemble feature selection method, named Filter and Wrapper Stacking Ensemble (FWSE), to identify reproducible biomarkers from high-dimensional omics data. In FWSE, filter feature selection methods are run on numerous subsets of the data to eliminate irrelevant features, and then wrapper feature selection methods are applied to rank the top features. The method was validated on four high-dimensional medical datasets related to mental illnesses and cancer. The results indicate that the features selected by FWSE are stable and statistically more significant than the ones obtained by existing methods while also demonstrating biological relevance. Furthermore, FWSE is a generic method, applicable to various high-dimensional datasets in the fields of machine intelligence and bioinformatics.
| S-EPMC10605029 | biostudies-literature