TASA: Temporal Attention with Spatial Autoencoder Network for Odor-induced Emotion Classification Using EEG.

The olfactory system enables humans to smell different odors, which are closely related to emotions. The high temporal resolution and non-invasiveness of Electroencephalogram (EEG) make it suitable to objectively study human preferences for odors. Effectively learning the temporal dynamics and spatial information from EEG is crucial for detecting odor-induced emotional valence. In this paper, we propose a deep learning architecture called Temporal Attention with Spatial Autoencoder Network (TASA) for predicting odor-induced emotions using EEG. TASA consists of a filter-bank layer, a spatial encoder, a time segmentation layer, a Long Short-Term Memory (LSTM) module, a multi-head self-attention (MSA) layer, and a fully connected layer. We improved upon the previous work by utilizing a two-phase learning framework, using the autoencoder module to learn the spatial information among electrodes by reconstructing the given input with a latent representation in the spatial dimension, which aims to minimize information loss compared to spatial filtering with CNN. The second improvement is inspired by the continuous nature of the olfactory process; we propose to use LSTM-MSA in TASA to capture its temporal dynamics by learning the intercorrelation among the time segments of the EEG. TASA is evaluated on an existing olfactory EEG dataset and compared with several existing deep learning architectures to demonstrate its effectiveness in predicting olfactory-triggered emotional responses. Interpretability analyses with DeepLIFT also suggest that TASA learns spatial-spectral features that are relevant to olfactory-induced emotion recognition.

Effect of an Asian-adapted Mediterranean diet and pentadecanoic acid on fatty liver disease: the TANGO randomized controlled trial.

BACKGROUND: Weight loss is the most effective treatment for nonalcoholic fatty liver disease (NAFLD). There is evidence that the Mediterranean diets rich in unsaturated fatty acids and fiber have beneficial effects on weight homeostasis and metabolic risk factors in individuals with NAFLD. Studies have also shown that higher circulating concentrations of pentadecanoic acid (C15:0) are associated with a lower risk for NAFLD. OBJECTIVES: To examine the effects of a Mediterranean-like, culturally contextualized Asian diet rich in fiber and unsaturated fatty acids, with or without C15:0 supplementation, in Chinese females with NAFLD. METHODS: In a double-blinded, parallel-design, randomized controlled trial, 88 Chinese females with NAFLD were randomly assigned to 1 of the 3 groups for 12 wk: diet with C15:0 supplementation (n = 31), diet without C15:0 supplementation (n = 28), or control (habitual diet and no C15:0 supplementation, n = 29). At baseline and after the intervention, body fat percentage, intrahepatic lipid content, muscle and abdominal fat, liver enzymes, cardiometabolic risk factors, and gut microbiome were assessed. RESULTS: In the intention-to-treat analysis, weight reductions of 4.0 ± 0.5 kg (5.3%), 3.4 ± 0.5 kg (4.5%), and 1.5 ± 0.5 kg (2.1%) were achieved in the diet-with-C15:0, diet without-C15:0, and the control groups, respectively. The proton density fat fraction (PDFF) of the liver decreased by 33%, 30%, and 10%, respectively. Both diet groups achieved significantly greater reductions in body weight, liver PDFF, total cholesterol, gamma-glutamyl transferase, and triglyceride concentrations compared with the control group. C15:0 supplementation reduced LDL-cholesterol further, and increased the abundance of Bifidobacterium adolescentis. Fat mass, visceral adipose tissue, subcutaneous abdominal adipose tissue (deep and superficial), insulin, glycated hemoglobin, and blood pressure decreased significantly in all groups, in parallel with weight loss. CONCLUSION: Mild weight loss induced by a Mediterranean-like diet adapted for Asians has multiple beneficial health effects in females with NAFLD. C15:0 supplementation lowers LDL-cholesterol and may cause beneficial shifts in the gut microbiome. TRIAL REGISTRATION NUMBER: This trial was registered at the clinicaltrials.gov as NCT05259475.

MTDN: Learning Multiple Temporal Dynamics Representation for Emotional Valence Classification with EEG.

Emotion recognition from electroencephalogram (EEG) requires computational models to capture the crucial features of the emotional response to external stimulation. Spatial, spectral, and temporal information are relevant features for emotion recognition. However, learning temporal dynamics is a challenging task, and there is a lack of efficient approaches to capture such information. In this work, we present a deep learning framework called MTDN that is designed to capture spectral features with a filterbank module and to learn spatial features with a spatial convolution block. Multiple temporal dynamics are jointly learned with parallel long short-term memory (LSTM) embedding and self-attention modules. The LSTM module is used to embed the time segments, and then the self-attention is utilized to learn the temporal dynamics by intercorrelating every embedded time segment. Multiple temporal dynamics representations are then aggregated to form the final extracted features for classification. We experiment on a publicly available dataset, DEAP, to evaluate the performance of our proposed framework and compare MTDN with existing published results. The results demonstrate improvement over the current state-of-the-art methods on the valence dimension of the DEAP dataset.

Gut microbiome responses to dietary intervention with hypocholesterolemic vegetable oils.

Hypercholesterolemia is becoming a problem with increasing significance. Dietary vegetable oils may help to improve this condition due to presence of phytonutrients with potentially synergistic cholesterol-lowering effects. The objective of this 8-week double-blinded randomized clinical trial was to investigate the effects of consuming 30 g of two different blended cooking oils, rich in omega-3 alpha-linolenic acid and phytonutrients, or refined olive oil on the intestinal microbiota in 126 volunteers with borderline hypercholesterolemia. Multi-factor analysis of relationships between the gut microbiota composition at various taxonomic ranks and the clinical trial parameters revealed the association between beneficial effects of the dietary intervention on the blood lipid profile with abundance of Clostridia class of the gut microbiota. This microbiota feature was upregulated in the course of the dietary intervention and associated with various plasma markers of metabolic health status, such as Triglycerides, Apolipoprotein B and Total Cholesterol to HDL ratio in a beneficial way. The relative abundance of a single species-Clostridium leptum-highly increased during the dietary intervention in all the three study groups. The oil blend with the highest concentration of omega-3 PUFA is associated with faster and more robust responses of the intestinal microbiota, including elevation of alpha-diversity. Butyrate production is being discussed as a plausible process mediating the observed beneficial influence on the plasma lipid profile. Causal mediation analysis suggested that Clostridium genus rather than the higher rank of the phylogeny-Clostridia class-may be involved in the diet-induced improvements of the blood lipid profile.

Genomic and epigenomic EBF1 alterations modulate TERT expression in gastric cancer.

Transcriptional reactivation of telomerase catalytic subunit (TERT) is a frequent hallmark of cancer, occurring in 90% of human malignancies. However, specific mechanisms driving TERT reactivation remain obscure for many tumor types and in particular gastric cancer (GC), a leading cause of global cancer mortality. Here, through comprehensive genomic and epigenomic analysis of primary GCs and GC cell lines, we identified the transcription factor early B cell factor 1 (EBF1) as a TERT transcriptional repressor and inactivation of EBF1 function as a major cause of TERT upregulation. Abolishment of EBF1 function occurs through 3 distinct (epi)genomic mechanisms. First, EBF1 is epigenetically silenced via DNA methyltransferase, polycomb-repressive complex 2 (PRC2), and histone deacetylase activity in GCs. Second, recurrent, somatic, and heterozygous EBF1 DNA-binding domain mutations result in the production of dominant-negative EBF1 isoforms. Third, more rarely, genomic deletions and rearrangements proximal to the TERT promoter remobilize or abolish EBF1-binding sites, derepressing TERT and leading to high TERT expression. EBF1 is also functionally required for various malignant phenotypes in vitro and in vivo, highlighting its importance for GC development. These results indicate that multimodal genomic and epigenomic alterations underpin TERT reactivation in GC, converging on transcriptional repressors such as EBF1.

Integrated paired-end enhancer profiling and whole-genome sequencing reveals recurrent CCNE1 and IGF2 enhancer hijacking in primary gastric adenocarcinoma.

OBJECTIVE: Genomic structural variations (SVs) causing rewiring of cis-regulatory elements remain largely unexplored in gastric cancer (GC). To identify SVs affecting enhancer elements in GC (enhancer-based SVs), we integrated epigenomic enhancer profiles revealed by paired-end H3K27ac ChIP-sequencing from primary GCs with tumour whole-genome sequencing (WGS) data (PeNChIP-seq/WGS). DESIGN: We applied PeNChIP-seq to 11 primary GCs and matched normal tissues combined with WGS profiles of >200 GCs. Epigenome profiles were analysed alongside matched RNA-seq data to identify tumour-associated enhancer-based SVs with altered cancer transcription. Functional validation of candidate enhancer-based SVs was performed using CRISPR/Cas9 genome editing, chromosome conformation capture assays (4C-seq, Capture-C) and Hi-C analysis of primary GCs. RESULTS: PeNChIP-seq/WGS revealed ~150 enhancer-based SVs in GC. The majority (63%) of SVs linked to target gene deregulation were associated with increased tumour expression. Enhancer-based SVs targeting CCNE1, a key driver of therapy resistance, occurred in 8% of patients frequently juxtaposing diverse distal enhancers to CCNE1 proximal regions. CCNE1-rearranged GCs were associated with high CCNE1 expression, disrupted CCNE1 topologically associating domain (TAD) boundaries, and novel TAD interactions in CCNE1-rearranged primary tumours. We also observed IGF2 enhancer-based SVs, previously noted in colorectal cancer, highlighting a common non-coding genetic driver alteration in gastric and colorectal malignancies. CONCLUSION: Integrated paired-end NanoChIP-seq and WGS of gastric tumours reveals tumour-associated regulatory SV in regions associated with both simple and complex genomic rearrangements. Genomic rearrangements may thus exploit enhancer-hijacking as a common mechanism to drive oncogene expression in GC.

VHL Deficiency Drives Enhancer Activation of Oncogenes in Clear Cell Renal Cell Carcinoma.

Protein-coding mutations in clear cell renal cell carcinoma (ccRCC) have been extensively characterized, frequently involving inactivation of the von Hippel-Lindau (VHL) tumor suppressor. Roles for noncoding cis-regulatory aberrations in ccRCC tumorigenesis, however, remain unclear. Analyzing 10 primary tumor/normal pairs and 9 cell lines across 79 chromatin profiles, we observed pervasive enhancer malfunction in ccRCC, with cognate enhancer-target genes associated with tissue-specific aspects of malignancy. Superenhancer profiling identified ZNF395 as a ccRCC-specific and VHL-regulated master regulator whose depletion causes near-complete tumor elimination in vitro and in vivoVHL loss predominantly drives enhancer/superenhancer deregulation more so than promoters, with acquisition of active enhancer marks (H3K27ac, H3K4me1) near ccRCC hallmark genes. Mechanistically, VHL loss stabilizes HIF2α-HIF1ß heterodimer binding at enhancers, subsequently recruiting histone acetyltransferase p300 without overtly affecting preexisting promoter-enhancer interactions. Subtype-specific driver mutations such as VHL may thus propagate unique pathogenic dependencies in ccRCC by modulating epigenomic landscapes and cancer gene expression.Significance: Comprehensive epigenomic profiling of ccRCC establishes a compendium of somatically altered cis-regulatory elements, uncovering new potential targets including ZNF395, a ccRCC master regulator. Loss of VHL, a ccRCC signature event, causes pervasive enhancer malfunction, with binding of enhancer-centric HIF2α and recruitment of histone acetyltransferase p300 at preexisting lineage-specific promoter-enhancer complexes. Cancer Discov; 7(11); 1284-305. ©2017 AACR.See related commentary by Ricketts and Linehan, p. 1221This article is highlighted in the In This Issue feature, p. 1201.