Ensemble of rankers for efficient gene signature extraction in smoke exposure classification

Netpro2vec: A Graph Embedding Framework for Biomedical Applications

The ever-increasing importance of structured data in different applications, especially in the biomedical field, has driven the need for reducing its complexity through projections into a more manageable space. The latest methods for learning features on graphs focus mainly on the neighborhood of nodes and edges. Methods capable of providing a representation that looks beyond the single node neighborhood are kernel graphs. However, they produce handcrafted features unaccustomed with a generalized model. To reduce this gap, in this work we propose a neural embedding framework, based on probability distribution representations of graphs, named Netpro2vec. The goal is to look at basic node descriptions other than the degree, such as those induced by the Transition Matrix and Node Distance Distribution. Netpro2vec provides embeddings completely independent from the task and nature of the data. The framework is evaluated on synthetic and various real biomedical network datasets through a comprehensive experimental classification phase and is compared to well-known competitors.

Machine learning-based investigation of the cancer protein secretory pathway

Deregulation of the protein secretory pathway (PSP) is linked to many hallmarks of cancer, such as promoting tissue invasion and modulating cell-cell signaling. The collection of secreted proteins processed by the PSP, known as the secretome, is often studied due to its potential as a reservoir of tumor biomarkers. However, there has been less focus on the protein components of the secretory machinery itself. We therefore investigated the expression changes in secretory pathway components across many different cancer types. Specifically, we implemented a dual approach involving differential expression analysis and machine learning to identify PSP genes whose expression was associated with key tumor characteristics: mutation of p53, cancer status, and tumor stage. Eight different machine learning algorithms were included in the analysis to enable comparison between methods and to focus on signals that were robust to algorithm type. The machine learning approach was validated by identifying PSP genes known to be regulated by p53, and even outperformed the differential expression analysis approach. Among the different analysis methods and cancer types, the kinesin family members KIF20A and KIF23 were consistently among the top genes associated with malignant transformation or tumor stage. However, unlike most cancer types which exhibited elevated KIF20A expression that remained relatively constant across tumor stages, renal carcinomas displayed a more gradual increase that continued with increasing disease severity. Collectively, our study demonstrates the complementary nature of a combined differential expression and machine learning approach for analyzing gene expression data, and highlights key PSP components relevant to features of tumor pathophysiology that may constitute potential therapeutic targets.

The secretory pathway is a series of intracellular compartments and enzymes that process and export proteins from the cell to its surrounding environment. Dysfunction of the secretory pathway is associated with many diseases, including cancer, and therefore constitutes a potential target for novel therapeutic strategies. The large number of interacting components that comprise the secretory pathway pose a challenge when attempting to identify where the dysfunction originates or how to restore healthy function. To improve our understanding of how the secretory pathway is changed within tumors, we used gene expression data from normal tissue and tumor samples from thousands of individuals which included many different types of cancers. The data was analyzed using different machine learning algorithms which we trained to predict sample characteristics, such as disease severity. This training quantified the relative degree to which each gene was associated with the tumor characteristic, allowing us to predict which secretory pathway components were important for processes such as tumor progression—both within specific cancer types and across many different cancer types. The machine learning-based approach demonstrated excellent performance compared to traditional gene expression analysis methods and identified several secretory pathway components with strong evidence of involvement in tumor development.

Genome-wide DNA methylation differences in nucleus accumbens of smokers vs. nonsmokers

Numerous DNA methylation (DNAm) biomarkers of cigarette smoking have been identified in peripheral blood studies, but because of tissue specificity, blood-based studies may not detect brain-specific smoking-related DNAm differences that may provide greater insight as neurobiological indicators of smoking and its exposure effects. We report the first epigenome-wide association study (EWAS) of smoking in human postmortem brain, focusing on nucleus accumbens (NAc) as a key brain region in developing and reinforcing addiction. Illumina HumanMethylation EPIC array data from 221 decedents (120 European American [23% current smokers], 101 African American [26% current smokers]) were analyzed. DNAm by smoking (current vs. nonsmoking) was tested within each ancestry group using robust linear regression models adjusted for age, sex, cell-type proportion, DNAm-derived negative control principal components (PCs), and genotype-derived PCs. The resulting ancestry-specific results were combined via meta-analysis. We extended our NAc findings, using published smoking EWAS results in blood, to identify DNAm smoking effects that are unique (tissue-specific) vs. shared between tissues (tissue-shared). We identified seven CpGs (false discovery rate < 0.05), of which three CpGs are located near genes previously indicated with blood-based smoking DNAm biomarkers: ZIC1, ZCCHC24, and PRKDC. The other four CpGs are novel for smoking-related DNAm changes: ABLIM3, APCDD1L, MTMR6, and CTCF. None of the seven smoking-related CpGs in NAc are driven by genetic variants that share association signals with predisposing genetic risk variants for smoking, suggesting that the DNAm changes reflect consequences of smoking. Our results provide the first evidence for smoking-related DNAm changes in human NAc, highlighting CpGs that were undetected as peripheral biomarkers and may reflect brain-specific responses to smoking exposure.

In silico models in drug development: where we are

The use and utility of computational models in drug development has significantly grown in the last decades, fostered by the availability of high throughput datasets and new data analysis strategies. These in silico approaches are demonstrating their ability to generate reliable predictions as well as new knowledge on the mode of action of drugs and the mechanisms underlying their side effects, altogether helping to reduce the costs of drug development. The aim of this review is to provide a panorama of developments in the field in the last two years.