A Computational Atlas of Tissue-specific Regulatory Networks

The pattern of how gene co-regulation varies across tissues determines human health. However, inferring tissue-specific regulatory networks and associating them with human phenotypes represent a substantial challenge because multi-tissue projects, including the GTEx, typically contain expression data measured only at one time point from highly heterogeneous donors. Here, we implement an interdisciplinary framework for assembling and programming genomic data from multiple tissues into fully informative gene networks, encapsulated by a complete set of bi-directional, signed, and weighted interactions, from static expression data. This framework can monitor how gene networks change simultaneously across tissues and individuals, infer gene-driven inter-tissue wiring networks, compare and test topological alterations of gene/tissue networks between health states, and predict how regulatory networks evolve across spatiotemporal gradients. Our framework provides a tool to catalogue a comprehensive encyclopedia of mechanistic gene networks that walk medical researchers through tissues in each individual and through individuals for each tissue, facilitating the translation of multi-tissue data into clinical practices.

Informative Gene Selection Based on Cost-Sensitive Fast Correlation-Based Feature Selection

Background: Informative gene selection is an essential step in performing tumor classification. However, it is difficult to select informative genes related to tumors from large-scale gene expression profiles because of their characteristics, such as high dimensionality, relatively small samples, and class imbalance, and some genes being superfluous and irrelevant. Objective: Many researchers analyze and process gene expression data to obtain classified gene subsets by using machine learning methods. However, the gene expression profiles of tumors often have massive computational challenges. In addition, when improving feature importance and classification accuracy, cost estimation is often ignored in traditional feature selection algorithms, which makes tumor classification more difficult. Method: In this study, a novel informative gene selection method based on cost-sensitive fast correlation-based feature selection (CS-FCBF) is proposed. Results: First, the symmetric uncertainty index is used to evaluate the correlation between informative genes and class labels, and then a large number of irrelevant and redundant genes are quickly filtered according to importance. Thereby, a candidate gene subset is generated. Second, cost-sensitive learning, which introduces the misclassification cost matrix and support vector machine attribute evaluation, is used to obtain the top-ranked gene subset with minimum misclassification loss. Finally, the candidate gene subset is optimized. Conclusion: This experiment was verified in eight independent tumor datasets. By comparing and analyzing CS-FCBF with another three hybrids of typical gene selection algorithms combined with cost-sensitive learning, we found that the method proposed in this study exhibited a better classification performance with fewer selected genes, which might provide guidance in tumor diagnosis and research.

Incremental Search for Informative Gene Selection in Cancer Classification

Although numerous methods of using microarray data analysis for classification have been reported, there is space in the field of cancer classification for new inventions in terms of informative gene selection. This study introduces a new incremental search-based gene selection approach for cancer classification. The strength of wrappers in determining relevant genes in a gene pool can be increased as they evaluate each possible gene’s subset. Nevertheless, the searching algorithms play a major role in gene’s subset selection. Hence, there is the possibility of finding more informative genes with incremental application. Thus, we introduce an approach which utilizes two searching algorithms in gene’s subset selection. The approach was efficient enough to classify five out of six microarray datasets with 100% accuracy using only a few biomarkers while the rest classified with only one misclassification.

Identifying Informative Gene Modules Across Modalities of Single Cell Genomics

Two fundamental aims that emerge when analyzing single-cell RNA-seq data are that of identifying which genes vary in an informative manner and determining how these genes organize into modules. Here we propose a general approach to these problems that operates directly on a given metric of cell-cell similarity, allowing for its integration with any method (linear or non linear) for identifying the primary axes of transcriptional variation between cells. Additionally, we show that when using multimodal data, our procedure can be used to identify genes whose expression reflects alternative notions of similarity between cells, such as physical proximity in a tissue or clonal relatedness in a cell lineage tree. In this manner, we demonstrate that while our method, called Hotspot, is capable of identifying genes that reflect nuanced transcriptional variability between T helper cells, it can also identify spatially-dependent patterns of gene expression in the cerebellum as well as developmentally-heritable expression signatures during embryogenesis.

Inference of genetic networks using random forests: Assigning different weights for gene expression data

In using gene expression levels for genetic network inference, we believe that two measurements that are similar to each other are less informative than two measurements that differ from each other. Given, for example, that gene expression levels measured at two adjacent time points in a time-series experiment are often similar to each other, we assume that each measurement in the time-series experiment will be less informative than each measurement in a steady-state experiment. Based on this idea, we propose a new inference method that relies heavily on informative gene expression data. Through numerical experiments, we prove that the quality of an inferred genetic network is slightly improved by heavily weighting informative gene expression data. In this study, we develop a new method by modifying the existing random-forest-based inference method to take advantage of its ability to analyze both time-series and static gene expression data. The idea we propose can be similarly applied to many of the other existing inference methods, as well.