As an asset pricing model in economics and finance, factor model has been widely used in quantitative investment. Towards building more effective factor models, recent years have witnessed the paradigm shift from linear models to more flexible nonlinear data-driven machine learning models. However, due to low signal-to-noise ratio of the financial data, it is quite challenging to learn effective factor models. In this paper, we propose a novel factor model, FactorVAE, as a probabilistic model with inherent randomness for noise modeling. Essentially, our model integrates the dynamic factor model (DFM) with the variational autoencoder (VAE) in machine learning, and we propose a prior-posterior learning method based on VAE, which can effectively guide the learning of model by approximating an optimal posterior factor model with future information. Particularly, considering that risk modeling is important for the noisy stock data, FactorVAE can estimate the variances from the distribution over the latent space of VAE, in addition to predicting returns. The experiments on the real stock market data demonstrate the effectiveness of FactorVAE, which outperforms various baseline methods. <<<

Eicosapentaenoic acid (EPA), an omega-3 (ω-3) polyunsaturated fatty acid, is an essential nutrient that exhibits antiinflammatory, neuroprotective, and cardiovascular-protective activities. Although EPA is used as a nutrient-based pharmaceutical agent or dietary supplement, its molecular target(s) is debatable. Here, we showed that EPA and its metabolites strongly and reversibly inhibit vesicular nucleotide transporter (VNUT), a key molecule for vesicular storage and release of adenosine triphosphate (ATP) in purinergic chemical transmission. In vitro analysis showed that EPA inhibits human VNUT-mediated ATP uptake at a half-maximal inhibitory concentration (IC) of 67 nM, acting as an allosteric modulator through competition with Cl. EPA impaired vesicular ATP release from neurons without affecting the vesicular release of other neurotransmitters. In vivo, mice showed a delay in the onset of neuropathic pain and resistance to both neuropathic and inflammatory pain. EPA potently attenuated neuropathic and inflammatory pain in wild-type mice but not in mice without affecting the basal nociception. The analgesic effect of EPA was canceled by the intrathecal injection of purinoceptor agonists and was stronger than that of existing drugs used for neuropathic pain treatment, with few side effects. Neuropathic pain impaired insulin sensitivity in previous studies, which was improved by EPA in the wild-type mice but not in the mice. Our results showed that VNUT is a molecular target of EPA that attenuates neuropathic and inflammatory pain and insulin resistance. EPA may represent a unique nutrient-based treatment and prevention strategy for neurological, immunological, and metabolic diseases by targeting purinergic chemical transmission. <<<

Adam Li, Chester Huynh, Zachary Fitzgerald, Iahn Cajigas, Damian Brusko, Jonathan Jagid, Angel O Claudio, Andres M Kanner, Jennifer Hopp, Stephanie Chen, Jennifer Haagensen, Emily Johnson, William Anderson, Nathan Crone, Sara Inati, Kareem A Zaghloul, Juan Bulacio, Jorge Gonzalez-Martinez, Sridevi V Sarma <<<

Over 15 million patients with epilepsy worldwide do not respond to drugs. Successful surgical treatment requires complete removal or disconnection of the seizure onset zone (SOZ), brain region(s) where seizures originate. Unfortunately, surgical success rates vary between 30 and 70% because no clinically validated biological marker of the SOZ exists. We develop and retrospectively validate a new electroencephalogram (EEG) marker-neural fragility-in a retrospective analysis of 91 patients by using neural fragility of the annotated SOZ as a metric to predict surgical outcomes. Fragility predicts 43 out of 47 surgical failures, with an overall prediction accuracy of 76% compared with the accuracy of clinicians at 48% (successful outcomes). In failed outcomes, we identify fragile regions that were untreated. When compared to 20 EEG features proposed as SOZ markers, fragility outperformed in predictive power and interpretability, which suggests neural fragility as an EEG biomarker of the SOZ. <<<

BACKGROUND: For promoting mental health and well-being of individuals, it is important to investigate its association with personal values. However, in Eastern Asian countries, no study has yet investigated the association between personal values in adolescence and mental health and well-being in adulthood. To fill that research gap, we conducted a cross-sectional study based on two online surveys of working populations in Japan and the United States.METHODS: A total of 516 workers from each of the two countries, aged 30-49 years, completed a questionnaire that measured personal values in adolescence, current psychological distress, health-related quality of life, and subjective well-being (satisfaction and happiness). Personal values were measured by items based on Schwartz's theory of basic values and people's commitment to those ten values. Multiple group path analysis was performed to examine the associations between personal values in adolescence and health-related outcomes, grouped by country.RESULTS: Care, graduating from school, and commitment to values were associated with better mental health and well-being in Japanese participants. Belief and challenging were associated with better mental health and well-being in US participants. On the other hand, financial success was associated with poor mental health and well-being in Japanese participants. Avoiding causing trouble and positive evaluation were associated with poor mental health and well-being in the US participants.CONCLUSIONS: Certain personal values and commitment to those values in adolescence may be associated with mental health and well-being in adulthood. To address the limitations of this study, future studies should use a longitudinal design and investigate the interactions among the types of personal values and commitment to the values. <<<

Aspergillus fumigatus is an environmental saprobe and opportunistic human fungal pathogen. Despite an estimated annual occurrence of more than 300,000 cases of invasive disease worldwide, a comprehensive survey of the genomic diversity present in A. fumigatus-including the relationship between clinical and environmental isolates and how this genetic diversity contributes to virulence and antifungal drug resistance-has been lacking. In this study we define the pan-genome of A. fumigatus using a collection of 300 globally sampled genomes (83 clinical and 217 environmental isolates). We found that 7,563 of the 10,907 unique orthogroups (69%) are core and present in all isolates and the remaining 3,344 show presence/absence of variation, representing 16-22% of the genome of each isolate. Using this large genomic dataset of environmental and clinical samples, we found an enrichment for clinical isolates in a genetic cluster whose genomes also contain more accessory genes, including genes coding for transmembrane transporters and proteins with iron-binding activity, and genes involved in both carbohydrate and amino-acid metabolism. Finally, we leverage the power of genome-wide association studies to identify genomic variation associated with clinical isolates and triazole resistance as well as characterize genetic variation in known virulence factors. This characterization of the genomic diversity of A. fumigatus allows us to move away from a single reference genome that does not necessarily represent the species as a whole and better understand its pathogenic versatility, ultimately leading to better management of these infections. <<<

MOTIVATION: Deciphering the language of non-coding DNA is one of the fundamental problems in genome research. Gene regulatory code is highly complex due to the existence of polysemy and distant semantic relationship, which previous informatics methods often fail to capture especially in data-scarce scenarios.RESULTS: To address this challenge, we developed a novel pre-trained bidirectional encoder representation, named DNABERT, to capture global and transferrable understanding of genomic DNA sequences based on up and downstream nucleotide contexts. We compared DNABERT to the most widely used programs for genome-wide regulatory elements prediction and demonstrate its ease of use, accuracy and efficiency. We show that the single pre-trained transformers model can simultaneously achieve state-of-the-art performance on prediction of promoters, splice sites and transcription factor binding sites, after easy fine-tuning using small task-specific labeled data. Further, DNABERT enables direct visualization of nucleotide-level importance and semantic relationship within input sequences for better interpretability and accurate identification of conserved sequence motifs and functional genetic variant candidates. Finally, we demonstrate that pre-trained DNABERT with human genome can even be readily applied to other organisms with exceptional performance. We anticipate that the pre-trained DNABERT model can be fined tuned to many other sequence analyses tasks.AVAILABILITY AND IMPLEMENTATION: The source code, pretrained and finetuned model for DNABERT are available at GitHub (https://github.com/jerryji1993/DNABERT).SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. <<<

Bin Tean Teh, Kevin Lim, Chern Han Yong, Cedric Chuan Young Ng, Sushma Ramesh Rao, Vikneswari Rajasegaran, Weng Khong Lim, Choon Kiat Ong, Ki Chan, Vincent Kin Yuen Cheng, Poh Sheng Soh, Sanjay Swarup, Steven G Rozen, Niranjan Nagarajan, Patrick Tan <<<

Durian (Durio zibethinus) is a Southeast Asian tropical plant known for its hefty, spine-covered fruit and sulfury and onion-like odor. Here we present a draft genome assembly of D. zibethinus, representing the third plant genus in the Malvales order and first in the Helicteroideae subfamily to be sequenced. Single-molecule sequencing and chromosome contact maps enabled assembly of the highly heterozygous durian genome at chromosome-scale resolution. Transcriptomic analysis showed upregulation of sulfur-, ethylene-, and lipid-related pathways in durian fruits. We observed paleopolyploidization events shared by durian and cotton and durian-specific gene expansions in MGL (methionine γ-lyase), associated with production of volatile sulfur compounds (VSCs). MGL and the ethylene-related gene ACS (aminocyclopropane-1-carboxylic acid synthase) were upregulated in fruits concomitantly with their downstream metabolites (VSCs and ethylene), suggesting a potential association between ethylene biosynthesis and methionine regeneration via the Yang cycle. The durian genome provides a resource for tropical fruit biology and agronomy. <<<

Sleep stage classification is essential for sleep assessment and disease diagnosis. Although previous attempts to classify sleep stages have achieved high classification performance, several challenges remain open: 1) How to effectively utilize time-varying spatial and temporal features from multi-channel brain signals remains challenging. Prior works have not been able to fully utilize the spatial topological information among brain regions. 2) Due to the many differences found in individual biological signals, how to overcome the differences of subjects and improve the generalization of deep neural networks is important. 3) Most deep learning methods ignore the interpretability of the model to the brain. To address the above challenges, we propose a multi-view spatial-temporal graph convolutional networks (MSTGCN) with domain generalization for sleep stage classification. Specifically, we construct two brain view graphs for MSTGCN based on the functional connectivity and physical distance proximity of the brain regions. The MSTGCN consists of graph convolutions for extracting spatial features and temporal convolutions for capturing the transition rules among sleep stages. In addition, attention mechanism is employed for capturing the most relevant spatial-temporal information for sleep stage classification. Finally, domain generalization and MSTGCN are integrated into a unified framework to extract subject-invariant sleep features. Experiments on two public datasets demonstrate that the proposed model outperforms the state-of-the-art baselines. <<<

Computation-intensive design problems are becoming increasingly common in manufacturing industries. The computation burden is often caused by expensive analysis and simulation processes in order to reach a comparable level of accuracy as physical testing data. To address such a challenge, approximation or metamodeling techniques are often used. Metamodeling techniques have been developed from many different disciplines including statistics, mathematics, computer science, and various engineering disciplines. These metamodels are initially developed as “surrogates” of the expensive simulation process in order to improve the overall computation efficiency. They are then found to be a valuable tool to support a wide scope of activities in modern engineering design, especially design optimization. This work reviews the state-of-the-art metamodel-based techniques from a practitioner’s perspective according to the role of metamodeling in supporting design optimization, including model approximation, design space exploration, problem formulation, and solving various types of optimization problems. Challenges and future development of metamodeling in support of engineering design is also analyzed and discussed. <<<

Plant volatiles are used not only by herbivorous insects to find their host plants, but also by the natural enemies of the herbivores to find their prey. There is also increasing evidence that plant volatiles, in addition to species-specific pheromones, help these insects to find mating partners. Plant structures such as flowers, fruit, and leaves are frequently rendezvous sites for mate-seeking insects. Here we propose that the combined use of plant volatiles and pheromones can efficiently guide insects to these sites, where they will have access to both mates and food. This notion is supported by the fact that plant volatiles can stimulate the release of sex pheromones and can render various insects more receptive to potential mates. <<<

Jiyoon Lee, Cyrus C Rabbani, Hongyu Gao, Matthew R Steinhart, Benjamin M Woodruff, Zachary E Pflum, Alexander Kim, Stefan Heller, Yunlong Liu, Taha Z Shipchandler, Karl R Koehler <<<

The skin is a multilayered organ, equipped with appendages (that is, follicles and glands), that is critical for regulating body temperature and the retention of bodily fluids, guarding against external stresses and mediating the sensation of touch and pain. Reconstructing appendage-bearing skin in cultures and in bioengineered grafts is a biomedical challenge that has yet to be met. Here we report an organoid culture system that generates complex skin from human pluripotent stem cells. We use stepwise modulation of the transforming growth factor β (TGFβ) and fibroblast growth factor (FGF) signalling pathways to co-induce cranial epithelial cells and neural crest cells within a spherical cell aggregate. During an incubation period of 4-5 months, we observe the emergence of a cyst-like skin organoid composed of stratified epidermis, fat-rich dermis and pigmented hair follicles that are equipped with sebaceous glands. A network of sensory neurons and Schwann cells form nerve-like bundles that target Merkel cells in organoid hair follicles, mimicking the neural circuitry associated with human touch. Single-cell RNA sequencing and direct comparison to fetal specimens suggest that the skin organoids are equivalent to the facial skin of human fetuses in the second trimester of development. Moreover, we show that skin organoids form planar hair-bearing skin when grafted onto nude mice. Together, our results demonstrate that nearly complete skin can self-assemble in vitro and be used to reconstitute skin in vivo. We anticipate that our skin organoids will provide a foundation for future studies of human skin development, disease modelling and reconstructive surgery. <<<

Joseph M Replogle, Reuben A Saunders, Angela N Pogson, Jeffrey A Hussmann, Alexander Lenail, Alina Guna, Lauren Mascibroda, Eric J Wagner, Karen Adelman, Gila Lithwick-Yanai, Nika Iremadze, Florian Oberstrass, Doron Lipson, Jessica L Bonnar, Marco Jost, Thomas M Norman, Jonathan S Weissman <<<

A central goal of genetics is to define the relationships between genotypes and phenotypes. High-content phenotypic screens such as Perturb-seq (CRISPR-based screens with single-cell RNA-sequencing readouts) enable massively parallel functional genomic mapping but, to date, have been used at limited scales. Here, we perform genome-scale Perturb-seq targeting all expressed genes with CRISPR interference (CRISPRi) across >2.5 million human cells. We use transcriptional phenotypes to predict the function of poorly characterized genes, uncovering new regulators of ribosome biogenesis (including CCDC86, ZNF236, and SPATA5L1), transcription (C7orf26), and mitochondrial respiration (TMEM242). In addition to assigning gene function, single-cell transcriptional phenotypes allow for in-depth dissection of complex cellular phenomena-from RNA processing to differentiation. We leverage this ability to systematically identify genetic drivers and consequences of aneuploidy and to discover an unanticipated layer of stress-specific regulation of the mitochondrial genome. Our information-rich genotype-phenotype map reveals a multidimensional portrait of gene and cellular function. <<<

Yoshitaka Sakamoto, Shuhei Miyake, Miho Oka, Akinori Kanai, Yosuke Kawai, Satoi Nagasawa, Yuichi Shiraishi, Katsushi Tokunaga, Takashi Kohno, Masahide Seki, Yutaka Suzuki, Ayako Suzuki <<<

Chromosomal backgrounds of cancerous mutations still remain elusive. Here, we conduct the phasing analysis of non-small cell lung cancer specimens of 20 Japanese patients. By the combinatory use of short and long read sequencing data, we obtain long phased blocks of 834 kb in N50 length with >99% concordance rate. By analyzing the obtained phasing information, we reveal that several cancer genomes harbor regions in which mutations are unevenly distributed to either of two haplotypes. Large-scale chromosomal rearrangement events, which resemble chromothripsis events but have smaller scales, occur on only one chromosome, and these events account for the observed biased distributions. Interestingly, the events are characteristic of EGFR mutation-positive lung adenocarcinomas. Further integration of long read epigenomic and transcriptomic data reveal that haploid chromosomes are not always at equivalent transcriptomic/epigenomic conditions. Distinct chromosomal backgrounds are responsible for later cancerous aberrations in a haplotype-specific manner. <<<

Myron G Best, Nik Sol, Irsan Kooi, Jihane Tannous, Bart A Westerman, François Rustenburg, Pepijn Schellen, Heleen Verschueren, Edward Post, Jan Koster, Bauke Ylstra, Najim Ameziane, Josephine Dorsman, Egbert F Smit, Henk M Verheul, David P Noske, Jaap C Reijneveld, R Jonas A Nilsson, Bakhos A Tannous, Pieter Wesseling, Thomas Wurdinger <<<

Tumor-educated blood platelets (TEPs) are implicated as central players in the systemic and local responses to tumor growth, thereby altering their RNA profile. We determined the diagnostic potential of TEPs by mRNA sequencing of 283 platelet samples. We distinguished 228 patients with localized and metastasized tumors from 55 healthy individuals with 96% accuracy. Across six different tumor types, the location of the primary tumor was correctly identified with 71% accuracy. Also, MET or HER2-positive, and mutant KRAS, EGFR, or PIK3CA tumors were accurately distinguished using surrogate TEP mRNA profiles. Our results indicate that blood platelets provide a valuable platform for pan-cancer, multiclass cancer, and companion diagnostics, possibly enabling clinical advances in blood-based "liquid biopsies". <<<

Transposable elements (TEs), which make up almost half of the human genome, often display altered expression in cancers. Here, we review recent progress in elucidating the role of TEs as mediators of immune responses in cancer and discuss how novel therapeutic strategies can harness TE immunogenicity for cancer immunotherapy. <<<

Knowledge distillation has been applied to various tasks successfully. The current distillation algorithm usually improves students' performance by imitating the output of the teacher. This paper shows that teachers can also improve students' representation power by guiding students' feature recovery. From this point of view, we propose Masked Generative Distillation (MGD), which is simple: we mask random pixels of the student's feature and force it to generate the teacher's full feature through a simple block. MGD is a truly general feature-based distillation method, which can be utilized on various tasks, including image classification, object detection, semantic segmentation and instance segmentation. We experiment on different models with extensive datasets and the results show that all the students achieve excellent improvements. Notably, we boost ResNet-18 from 69.90% to 71.69% ImageNet top-1 accuracy, RetinaNet with ResNet-50 backbone from 37.4 to 41.0 Boundingbox mAP, SOLO based on ResNet-50 from 33.1 to 36.2 Mask mAP and DeepLabV3 based on ResNet-18 from 73.20 to 76.02 mIoU. Our codes are available at this https URL. <<<

Flowering plants alternate between multicellular haploid (gametophyte) and diploid (sporophyte) generations. Pollen actively transcribes its haploid genome, providing phenotypic diversity even among pollen grains from a single plant. In this study, we used allele-specific RNA sequencing of single pollen precursors to follow the shift to haploid expression in maize pollen. We observed widespread biallelic expression for 11 days after meiosis, indicating that transcripts synthesized by the diploid sporophyte persist long into the haploid phase. Subsequently, there was a rapid and global conversion to monoallelic expression at pollen mitosis I, driven by active new transcription from the haploid genome. Genes showed evidence of increased purifying selection if they were expressed after (but not before) pollen mitosis I. This work establishes the timing during which haploid selection may act in pollen. <<<

Because of the accessibility of big data collections from consumers, products, and stores, advanced sales forecasting capabilities have drawn great attention from many businesses, especially those in retail, because of the importance of forecasting in decision making. Improvement of forecasting accuracy, even by a small percentage, may have a substantial impact on companies’ production and financial planning, marketing strategies, inventory controls, and supply chain management. Specifically, our research goal is to forecast the sales of each product in each store in the near future. Motivated by tensor factorization methodologies for context-aware recommender systems, we propose a novel approach called the advanced temporal latent factor approach to sales forecasting, or ATLAS for short, which achieves accurate and individualized predictions for sales by building a single tensor factorization model across multiple stores and products. Our contribution is a combination of a tensor framework (to leverage information across stores and products), a new regularization function (to incorporate demand dynamics), and extrapolation of the tensor into future time periods using state-of-the-art statistical (seasonal autoregressive integrated moving-average models) and machine-learning (recurrent neural networks) models. The advantages of ATLAS are demonstrated on eight product category data sets collected by Information Resources, Inc., where we analyze a total of 165 million weekly sales transactions of over 15,560 products from more than 1,500 grocery stores. Summary of Contribution: Sales forecasting has been a task of long-standing importance. Accurate sales forecasting provides critical managerial implications for companies’ decision making and operations. Improvement of forecasting accuracy may have a substantial impact on companies’ production planning, marketing strategies, inventory controls, and supply chain management, among other things. This paper proposes a novel computational (machine-learning-based) approach to sales forecasting and thus is positioned directly at the intersection of computing and business/operations research. <<<

Immortal cancer cell lines (CCLs) are the most widely used system for investigating cancer biology and for the preclinical development of oncology therapies. Pharmacogenomic and genome-wide editing screenings have facilitated the discovery of clinically relevant gene-drug interactions and novel therapeutic targets via large panels of extensively characterised CCLs. However, tailoring pharmacological strategies in a precision medicine context requires bridging the existing gaps between tumours and in vitro models. Indeed, intrinsic limitations of CCLs such as misidentification, the absence of tumour microenvironment and genetic drift have highlighted the need to identify the most faithful CCLs for each primary tumour while addressing their heterogeneity, with the development of new models where necessary. Here, we discuss the most significant limitations of CCLs in representing patient features, and we review computational methods aiming at systematically evaluating the suitability of CCLs as tumour proxies and identifying the best patient representative in vitro models. Additionally, we provide an overview of the applications of these methods to more complex models and discuss future machine-learning-based directions that could resolve some of the arising discrepancies. <<<

Identification of somatic mutations in tumor samples is commonly based on statistical methods in combination with heuristic filters. Here we develop VarNet, an end-to-end deep learning approach for identification of somatic variants from aligned tumor and matched normal DNA reads. VarNet is trained using image representations of 4.6 million high-confidence somatic variants annotated in 356 tumor whole genomes. We benchmark VarNet across a range of publicly available datasets, demonstrating performance often exceeding current state-of-the-art methods. Overall, our results demonstrate how a scalable deep learning approach could augment and potentially supplant human engineered features and heuristic filters in somatic variant calling. <<<