Biology subjects

Lakiotaki, K.

Publications and source records attributed to Lakiotaki, K..

3 recordsLinked to original sources

bioRxiv2020

Latent Feature Representations for Human Gene Expression Data Improve Phenotypic Predictions

High-throughput technologies such as microarrays and RNA-sequencing (RNA-seq) allow to precisely quantify transcriptomic profiles, generating datasets that are inevitably high-dimensional. In this work, we investigate whether the whole human transcriptome can be represented in a compressed, low dimensional latent space without loosing relevant information. We thus constructed low-dimensional latent feature spaces of the human genome, by utilizing three dimensionality reduction approaches and a diverse set of curated datasets. We applied standard Principal Component Analysis (PCA), kernel PCA and Autoencoder Neural Networks on 1360 datasets from four different measurement technologies. The latent feature spaces are tested for their ability to (a) reconstruct the original data and (b) improve predictive performance on validation datasets not used during the creation of the feature space. While linear techniques show better reconstruction performance, nonlinear approaches, particularly, neural-based models seem to be able to capture non-additive interaction effects, and thus enjoy stronger predictive capabilities. Our results show that low dimensional representations of the human transcriptome can be achieved by integrating hundreds of datasets, despite the limited sample size of each dataset and the biological / technological heterogeneity across studies. The created space is two to three orders of magnitude smaller compared to the raw data, offering the ability of capturing a large portion of the original data variability and eventually reducing computational time for downstream analyses.

bioinformatics↗

bioRxiv2020

Just Add Data: Automated Predictive Modeling and BioSignature Discovery

Fully automated machine learning, statistical modelling, and artificial intelligence for predictive modeling is becoming a reality, giving rise to the field of Automated Machine Learning (AutoML). AutoML systems promise to democratize data analysis to non-experts, drastically increase productivity, improve replicability of the statistical analysis, facilitate the interpretation of results, and shield against common methodological analysis pitfalls. We present the basic ideas and principles of Just Add Data Bio (JADBIO), an AutoML technology applicable to the low-sample, high-dimensional omics data that arise in translational medicine and bioinformatics applications. In addition to predictive and diagnostic models ready for clinical use, JADBIO also returns the corresponding biosignatures, i.e., minimal-size subsets of biomarkers that are jointly predictive of the outcome of interest. A use-case on thymic epithelial tumors is presented, along with an extensive evaluation on 374 public biological datasets. Results show that long-standing challenges with overfitting and overestimation of complex non-linear machine learning pipelines on high-dimensional, low small sample data can be overcome.

bioinformatics↗

bioRxiv2018

Efficient feature selection on gene expression data: Which algorithm to use?

BackgroundFeature selection seeks to identify a minimal-size subset of features that is maximally predictive of the outcome of interest. It is particularly important for biomarker discovery from high-dimensional molecular data, where the features could correspond to gene expressions, Single Nucleotide Polymorphisms (SNPs), proteins concentrations, e.t.c. We evaluate, empirically, three state-of-the-art, feature selection algorithms, scalable to high-dimensional data: a novel generalized variant of OMP (gOMP), LASSO and FBED. All three greedily select the next feature to include; the first two employ the residuals re-sulting from the current selection, while the latter rebuilds a statistical model. The algorithms are compared in terms of predictive performance, number of selected features and computational efficiency, on gene expression data with either survival time (censored time-to-event) or disease status (case-control) as an outcome. This work attempts to answer a) whether gOMP is to be preferred over LASSO and b) whether residual-based algorithms, e.g. gOMP, are to be preferred over algorithms, such as FBED, that rely heavily on regression model fitting.\n\nResultsgOMP is on par, or outperforms LASSO in all metrics, predictive performance, number of features selected and computational efficiency. Contrasting gOMP to FBED, both exhibit similar performance in terms of predictive performance and number of selected features. Overall, gOMP combines the benefits of both LASSO and FBED; it is computationally efficient and produces parsimonious models of high predictive performance.\n\nConclusionsThe use of gOMP is suggested for variable selection with high-dimensional gene expression data, and the target variable need not be restricted to time-to-event or case control, as examined in this paper.

bioinformatics↗