Data-Driven Metabolic Pathway Compositions Enhance Cancer Survival Prediction

A pan-cancer metabolic atlas of the tumor microenvironment

Tumors are heterogeneous cellular environments with entwined metabolic dependencies. Here, we use a tumor transcriptome deconvolution approach to profile the metabolic states of cancer and non-cancer (stromal) cells in bulk tumors of 20 solid tumor types. We identify metabolic genes and processes recurrently altered in cancer cells across tumor types, highlighting pan-cancer upregulation of deoxythymidine triphosphate (dTTP) production. In contrast, the tryptophan catabolism rate-limiting enzymes IDO1 and TDO2 are highly overexpressed in stroma, raising the hypothesis that kynurenine-mediated suppression of antitumor immunity may be predominantly constrained by the stroma. Oxidative phosphorylation is the most upregulated metabolic process in cancer cells compared to both stromal cells and a large atlas of cancer cell lines, suggesting that the Warburg effect may be less pronounced in cancer cells in vivo. Overall, our analysis highlights fundamental differences in metabolic states of cancer and stromal cells inside tumors and establishes a pan-cancer resource to interrogate tumor metabolism.

Incorporating Machine Learning into Established Bioinformatics Frameworks

The exponential growth of biomedical data in recent years has urged the application of numerous machine learning techniques to address emerging problems in biology and clinical research. By enabling the automatic feature extraction, selection, and generation of predictive models, these methods can be used to efficiently study complex biological systems. Machine learning techniques are frequently integrated with bioinformatic methods, as well as curated databases and biological networks, to enhance training and validation, identify the best interpretable features, and enable feature and model investigation. Here, we review recently developed methods that incorporate machine learning within the same framework with techniques from molecular evolution, protein structure analysis, systems biology, and disease genomics. We outline the challenges posed for machine learning, and, in particular, deep learning in biomedicine, and suggest unique opportunities for machine learning techniques integrated with established bioinformatics approaches to overcome some of these challenges.

Incorporating Pathway Information into Feature Selection towards Better Performed Gene Signatures

To analyze gene expression data with sophisticated grouping structures and to extract hidden patterns from such data, feature selection is of critical importance. It is well known that genes do not function in isolation but rather work together within various metabolic, regulatory, and signaling pathways. If the biological knowledge contained within these pathways is taken into account, the resulting method is a pathway-based algorithm. Studies have demonstrated that a pathway-based method usually outperforms its gene-based counterpart in which no biological knowledge is considered. In this article, a pathway-based feature selection is firstly divided into three major categories, namely, pathway-level selection, bilevel selection, and pathway-guided gene selection. With bilevel selection methods being regarded as a special case of pathway-guided gene selection process, we discuss pathway-guided gene selection methods in detail and the importance of penalization in such methods. Last, we point out the potential utilizations of pathway-guided gene selection in one active research avenue, namely, to analyze longitudinal gene expression data. We believe this article provides valuable insights for computational biologists and biostatisticians so that they can make biology more computable.

Differential metabolic activity and discovery of therapeutic targets using summarized metabolic pathway models

In spite of the increasing availability of genomic and transcriptomic data, there is still a gap between the detection of perturbations in gene expression and the understanding of their contribution to the molecular mechanisms that ultimately account for the phenotype studied. Alterations in the metabolism are behind the initiation and progression of many diseases, including cancer. The wealth of available knowledge on metabolic processes can therefore be used to derive mechanistic models that link gene expression perturbations to changes in metabolic activity that provide relevant clues on molecular mechanisms of disease and drug modes of action (MoA). In particular, pathway modules, which recapitulate the main aspects of metabolism, are especially suitable for this type of modeling. We present Metabolizer, a web-based application that offers an intuitive, easy-to-use interactive interface to analyze differences in pathway metabolic module activities that can also be used for class prediction and in silico prediction of knock-out (KO) effects. Moreover, Metabolizer can automatically predict the optimal KO intervention for restoring a diseased phenotype. We provide different types of validations of some of the predictions made by Metabolizer. Metabolizer is a web tool that allows understanding molecular mechanisms of disease or the MoA of drugs within the context of the metabolism by using gene expression measurements. In addition, this tool automatically suggests potential therapeutic targets for individualized therapeutic interventions.

Classification of early-stage non-small cell lung cancer by weighing gene expression profiles with connectivity information

Pathway-based feature selection algorithms, which utilize biological information contained in pathways to guide which features/genes should be selected, have evolved quickly and become widespread in the field of bioinformatics. Based on how the pathway information is incorporated, we classify pathway-based feature selection algorithms into three major categories-penalty, stepwise forward, and weighting. Compared to the first two categories, the weighting methods have been underutilized even though they are usually the simplest ones. In this article, we constructed three different genes' connectivity information-based weights for each gene and then conducted feature selection upon the resulting weighted gene expression profiles. Using both simulations and a real-world application, we have demonstrated that when the data-driven connectivity information constructed from the data of specific disease under study is considered, the resulting weighted gene expression profiles slightly outperform the original expression profiles. In summary, a big challenge faced by the weighting method is how to estimate pathway knowledge-based weights more accurately and precisely. Only until the issue is conquered successfully will wide utilization of the weighting methods be impossible.