Biology subjects

Wei, Z.

Publications and source records attributed to Wei, Z..

At least 181 records · Page 10Linked to original sources

bioRxiv2019

Specialized NADPH diaphorase membrane-related localizations in the brainstem of the pigeons (Columba livia)

NADPH diaphorase (N-d) is used to a histochemical identification of subgroup of neuronal cells. Beside regular intracellular N-d positivity, membrane-related positivity revealed as a specialized staining pattern in the pigeon brain stem. In the investigation of the nervous system of homing pigeons (Columba livia) with N-d staining, we found a specialized structure, which temporally was termed as N-d tubular glomerular body/structure or as T-J body related to the last name of authors. This N-d positive specialization constituted by tubular components bilaterally located in the medial to the lemniscus spinalis in the medulla oblongata. The tubular components were moderate staining. T-J body was a longitudinal oriented structure of 2400 m with N-d staining. N-d positive tubular components were twisted and intermingled together. Beside the young adult pigeons, T-J body s were also consistently detected in the aged pigeons. Membrane-related staining were also detected in the other rostral nuclei in the brain stem. With discussion and review of related scientific literatures, T-J body was considered as a new anatomical structure or a new feature of the existent nucleus. In summary, beside N-d intracellular distribution, there were other three N-d membrane-related localizations: mini-aggregation, patch-aggregation, and arrangement along tubular unit.

neuroscience↗

bioRxiv2019

A comparative assessment of aging-related NADPH diaphorase positivity in the spinal cord and medullary oblongata between pigeon and murine

NADPH diaphorase (N-d) positive neurons has been examined in many animals. N-d neurodegenerative neurites were detected in some animal models. However, detailed information of N-d positivity and aging related changes was still lack in the spinal cord and medulla oblongata of pigeons. In this study, we evaluated the N-d positivity and aging alterations in the spinal cord and medullary oblongata of the pigeon compared with rat and mouse. In pigeons, N-d neurons were more numerous in the dorsal horn, around the central canal and in the column of Terni in the thoracic and lumbar segments and scattered neurons occurred in the ventral horn of spinal segments. N-d neurons also occurred in the white matter of spinal cord. Morphometrical analysis demonstrated in the lumbosacral, cervical and thoracic regions. Compared with young pigeons, the size of N-d soma was significantly altered in aged pigeons. Meanwhile, the dramatic morphological changes occurred in the lumbar to sacral segments. The most important findings of this study were aging-related N-d positive bodies (ANB) in aged pigeons, mainly in the nucleus cuneatus externus (CuE), occasionally in the nuclei gracilis et cuneatus. ANBs were identified in the gracile nuclei in spinal cord in the aged rats and mice. ANBs were also detected in the CuE spinal nucleus in the aged rats. Immunohistochemistry also showed that the aging changes occurred in the cell types and neuropeptides in aged animals. The results suggested the weak inflammation and neuronal dysfunction in the spinal cord in aged pigeons. Our results suggested that the ANB could be considered as aging marker in the central nervous system.

neuroscience↗

bioRxiv2019

OsLUGL involved in floral development through regulating auxin level and OsARFs expression in rice (Oryza sative L.)

Specification of floral organ identity is critical for floral morphology and inflorescence architecture. Floral organ identity in plants is controlled by floral homeotic A/B/C/D/E-class genes. Although multiple genes regulate floral organogenesis our understanding of the regulatory network remains fragmentary. Here, we characterized rice floral organ gene KAIKOUXIAO (KKX), mutation of which produces an uncharacteristic open hull, abnormal seed, and semi-sterility. KKX encodes a putative LEUNIG-like (LUGL) transcriptional co-repressor. OsLUGL is preferentially expressed in young panicles and its protein can interact with OsSEU, which functions were reported as an adaptor for LEUNIG. OsLUGL-OsSEU functions together as a transcriptional regulatory complex to control organ identity specification through regulation of MADS-box genes. During this process, SEP3 (such as OsMADS8) and AP1 (such as OsMADS18) serve as the DNA-binding partner of OsLUGL-OsSEU complex. Further studies indicated that OsMADS8 and OsMADS18 could bind the promoter of OsGH3-8 and regulate its expression. The altered expression of OsGH3-8 caused the increased auxin level and the decreased expression of OsARFs. Overall, our results demonstrate a possible pathway whereby OsLUGL-OsSEU-OsAP1-OsSEP3 complex as a transcriptional regulator by targeting the promoter of OsGH3-8 directly, affecting auxin level, OsARFs expression level and thereby influencing floral development. These findings provide a valuable insight into the molecular functions of OsLUGL in rice floral development. HighlightOsLUGL through forming OsLUGL-OsSEU-OsAP1-OsSEP3 complex regulate OsGH3-8 expression, and regulate auxin level and OsARFs expression indirectly. This work is a new insight to floral development molecular mechanism.

genetics↗

bioRxiv2019

Oxytocin modulation of self-other distinction is replicable and influenced by oxytocin receptor (OXTR) genotype

Intranasal oxytocin (OXT) has been associated with effects on diverse social-emotional domains in humans, however progress in the field is currently hampered by poor replicability. Limited statistical power and individual differences in biological factors, such as oxytocin receptor (OXTR) genetics, may have contributed to these variable findings. To this end, we present a pharmaco-genetic study aiming at (1) replicating previous findings suggesting that intranasal oxytocin (24 IU) blurs self-other distinction in a large sample of n = 170 male subjects, (2) determining whether variations in common receptor polymorphisms (rs237887, rs2268491, rs2254298, rs53576, rs2268498) influence sensitivity to oxytocins behavioral effects. Employing a validated oxytocin-sensitive trait judgment paradigm, we confirmed that it blurred self-other distinction in terms of decision time and subsequent memory. However, oxytocin only influenced decision time in rs53576 G carriers, whereas effects on memory performance were most pronounced in rs2268498 TT homozygotes. In summary, the current study replicates our previous findings showing that oxytocin blurs self-other distinction and suggests that sensitivity to its effects in this domain are receptor genotype dependent.

neuroscience↗

bioRxiv2019

Epistasis Detection using Model-Based Multifactor Dimensionality Reduction in Structured Populations

In genome-wide association studies, the extent and impact of confounding due population structure have been well recognized. Inadequate handling of such confounding is likely to lead to spurious associations, hampering replication and the identification of causal variants. Several strategies have been developed for protecting associations against confounding, the most popular one is based on Principal Component Analysis. In contrast, the extent and impact of confounding due to population structure in gene-gene interaction association epistasis studies are much less investigated and understood. In particular, the role of non-linear genetic population substructure in epistasis detection is largely under-investigated, especially outside a regression framework. In order to identify causal variants in synergy, to improve interpretability and replicability of epistasis results, we introduce three strategies based on model-based multifactor dimensionality reduction (MB-MDR) approach for structured populations. We demonstrate through extensive simulation studies the effect of various degrees of genetic population structure and relatedness on epistasis detection and propose appropriate remedial measures based on linear and non-linear sample genetic similarity. Authors SummaryOne of the biggest challenges in human genetics is to understand the genetic basis of complex diseases such as cancer, diabetes, heart disease, depression, asthma, inflammatory bowel disease and hypertension, for instance via identifying genes, gene-gene and gene-environment interactions in association studies. Over the years, a more prominent role has been given to gene-gene interaction (epistasis) detection, in view of precision medicine and the hunt for novel drug targets and biomarkers. However, the increasing number of consortium-based epistasis studies that are marked by heterogeneous sample collections due to population structure or shared genetic ancestry are likely to be prone to spurious association and low power detection of associated or causal genes. In this work we introduced various strategies in epistasis studies with correction for confounding due to population structure. Based on extensive simulation studies we demonstrated the effect of genetic population structure on epistasis detection and investigated remedial measures to confounding by linear and nonlinear sample genetic similarity.

bioinformatics↗

bioRxiv2019

Dual forms of aging-related NADPH diaphorase neurodegeneration in the sacral spinal cord of aged non-human primates

We discovered two different anomalous NADPH diaphorase (NADPH-d) positive alterations, which were expressed as aging-related NADPH-d positive spheroidal bodies and megaloneurites specially distributed in the superficial dorsal horn, dorsal gray commissure (DGC), lateral collateral pathway (LCP) and sacral parasympathetic nucleus (SPN) in the aged monkeys sacral spinal cord, compared with the cervical, thoracic and lumbar segments. In the gracile nucleus of aged monkeys, only aging-related spheroidal bodies were observed and no megaloneurites occurred. The dense, abnormal NADPH-d positive megaloneurites, extremely different from regular NADPH-d positive fibers, were prominent in the sacral segments and occurred in extending from Lissauers tract (LT) through lamina I along the lateral boundary of the dorsal horn to the region of the SPN. Meanwhile, large diameter punctate NADPH-d activity occurred and scattered in the lateral white matter of the LCP and dorsal root entry zone (DREZ) at the same level of NADPH-d abnormality in the gray matters. Those dot-like NADPH-d alterations were examined by horizontal sectioning and indicated ascending or descending oriental fibers. These NADPH-d megaloneurites had the same composition as the punctate NADPH-d alterations and were co-localized with the VIP immunoreaction, while the ANBs did not coexist with the VIP immunoreaction. Both ANBs and megaloneurites provide consistent evidence that the anomalous neuritic alterations in the aged sacral spinal cord are referred to as a specialized aging marker in the pelvic visceral organs in non-human primates.

neuroscience↗

bioRxiv2018

Maternal Obesity Enhances Oocyte Chromosome Abnormalities Associated With Aging

Obesity is increasing globally and maternal obesity has adverse effects on pregnancy outcomes and the long-term health of offspring. Maternal obesity has been associated with pregnancy failure through impaired oogenesis and embryogenesis. However, whether maternal obesity causes chromosome abnormalities in oocytes has remained unclear. Here we show that chromosome abnormalities are increased in the oocytes of obese mice and identify weakened sister-chromatid cohesion as the likely cause. Numbers of full-grown follicles retrieved from obese mice were the same as controls and the efficiency of in vitro oocyte maturation remained high. However, chromosome abnormalities presenting in both metaphase-I and metaphase-II were elevated, most prominently the premature separation of sister chromatids. Weakened sister-chromatid cohesion in oocytes from obese mice was manifested both as the terminalization of chiasmata in metaphase-I and as increased separation of sister centromeres in metaphase II. Obesity-associated abnormalities were elevated in older mice implying that maternal obesity exacerbates the deterioration of cohesion seen with advancing age.

genetics↗

bioRxiv2018

De novo aging-related meganeurites: alteration of NADPH diaphorase positivity in the sacral spinal cord of the aged dog

The aging-related changes of NADPH-diaphorase (NADPH-d) in the spinal cord were studied in aged dogs. At all levels of the spinal cord examined, NADPH-d activities were present in neurons and fibers in the superficial dorsal horn, dorsal commissure and in neurons around the central canal. In addition, the sympathetic autonomic nucleus in the thoracic and rostral lumbar segments exhibited prominent NADPH-d cellular staining whereas the sacral parasympathetic nucleus (SPN) in the sacral segments was not well stained. Interestingly, we found abundant NADPH-d positive enlarged-diameter fibers termed megaloneurite, which characteristically occurred in the aged sacral segments, distributed in the dorsal gray commissure (DGC), lateral collateral pathway (LCP) the lateral fasciculi and the central canal compared with the cervical, thoracic and lumbar segments. The dense, abnormal NADPH-d megaloneurites occurred in extending from dorsal entry zone through lamina I along with the lateral boundary of the dorsal horn to the region of the SPN. These fibers were prominent in the S1-S3 segments but not in adjacent segments L5-L7 and Cx1 or in thoracolumbar segments and cervical segments. Double staining with GFAP, NeuN, CGRP, MAP2 and Iba1, NADPH-d megaloneurite colocalized with vasoactive intestinal peptide. Presumably, the megaloneurites may represent, in part, visceral afferent projections to the SPN and/or DGC. The NADPH-d megaloneurites in the aged sacral spinal cord indicated some anomalous changes in the neurites, which might account for a disturbance in the aging pathway of the autonomic and sensory nerve in the pelvic visceral organs.

neuroscience↗

bioRxiv2018

The association between weight at birth and breast cancer risk revisited using Mendelian randomisation

Observational studies suggest that higher birth weight (BW) is associated with increased risk of breast cancer in adult life. We conducted a two-sample Mendelian randomisation (MR) study to assess whether this association is causal. Sixty independent single nucleotide polymorphisms (SNPs) known to be associated at P < 5 x 10-8 with BW were used to construct (1) a 41-SNP instrumental variable (IV) for univariable MR after removing SNPs with pleiotropic associations with other breast cancer risk factors and (2) a 49-SNP IV for multivariable MR after filtering SNPs for data availability. BW predicted by the 41-SNP IV was not associated with overall breast cancer risk in inverse-variance weighted (IVW) univariable MR analysis of genetic association data from 122,977 breast cancer cases and 105,974 controls (odds ratio = 0.86 per 500 g higher BW; 95% confidence interval: 0.73--1.01). Sensitivity analyses using four alternative methods and three alternative IVs, including an IV with 59 of the 60 BW-associated SNPs, yielded similar results. Multivariable MR adjusting for the effects of the 49-SNP IV on birth length, adult height, adult body mass index, age at menarche, and age at menopause using IVW and MR-Egger methods provided estimates consistent with univariable analyses. Results were also similar when all analyses were repeated after restricting to estrogen receptor-positive or -negative breast cancer cases. Point estimates of the odds ratios from most analyses performed indicated an inverse relationship between genetically-predicted BW and breast cancer. Thus, there is little evidence from MR to suggest that the previously observed association between higher BW and increased risk of breast cancer in adult life is causal.

epidemiology↗

bioRxiv2018

SIP: An Interchangeable Pipeline for scRNA-seq Data Processing

Multiple steps of bioinformatics processing are needed to convert the raw scRNA-seq data to information that can be used in downstream analyses and in building cell atlases. Dozens of software packages have been developed and different labs tend to have different preferences on choices of the workflow. Such diversity can cause difficulties in future efforts of aggregating data from multiple labs, and also difficulties for new labs to start in this field. A few pipelines have been developed to help integrating multiple steps into a whole, but the fixed software architecture makes it hard for developers to add new features or exchange parts in the pipeline.\n\nWe presented SIP, a Single-cell Interchangeable Pipeline. It is a one-stop platform for the processing of scRNA-seq data from multiple platforms, and will also support for other types of data like scATAC-seq data. SIP utilizes container technology to solve the deployment dilemma when handling multiple packages and provides an easy-to-use interface for users to conduct the complicated multi-step process from raw data to final results with a single command. It also allows advanced users to assemble different versions of the pipeline by interchanging parts or adding new modules. SIP is available at https://github.com/XuegongLab/SIP under the GPL-3.0 license.

bioinformatics↗

bioRxiv2018

Proteomic Profile of TGF-β1 treated Lung Fibroblasts identifies Novel Markers of Activated Fibroblasts in the Silica Exposed Rat Lung

We performed liquid chromatography-tandem mass spectrometry (LC-MS/MS) on control and TGF-{beta}1-exposed rat lung fibroblasts to identify proteins differentially expressed between cell populations. A total of 1648 proteins were found to be differentially expressed in response to TGF-{beta}1 treatment and 196 proteins were expressed at [≥] 1.2 fold relative to control. Guided by these results, we next determined whether similar changes in protein expression were detectable in the rat lung after chronic exposure to silica dust. Of the five proteins selected for further analysis, we found that levels of all proteins were markedly increased in the silica-exposed rat lung, including the proteins for the very low density lipoprotein receptor (VLDLR) and the transmembrane (type I) heparin sulfate proteoglycan called syndecan 2 (SDC2). Because VLDLR and SDC2 have not, to our knowledge, been previously linked to the pathobiology of silicosis, we next examined whether knockdown of either gene altered responses to TGF-{beta}1 in MRC-5 lung fibroblasts. Interestingly, we found knockdown of either VLDLR or SDC2 dramatically reduced collagen production to TGF-{beta}1, suggesting that both proteins might play a novel role in myofibroblast biology and pathogenesis of silica-induced pulmonary fibrosis. In summary, our findings suggest that performing LC-MS/MS on TGF-{beta}1 stimulated lung fibroblasts can uncover novel molecular targets of activated myofibroblasts in silica-exposed lung.\n\nHighlightsWe identified 196 proteins differentially expressed between control and TGF-{beta}1 treated fibroblastsby LC-MS/MS.\n\nSeveral proteins identified by LC-MS/MS were also found to be differentially expressed in whole lung tissues and isolated fibroblasts after chronic exposure to silica dust, including the very low density lipoprotein receptor (VLDLR) and the transmembrane type I heparan sulfate proteoglycan called syndecan 2\n\nKnockdown of SDC2 or VLDLR markedly inhibited collagen production in MRC-5 fibroblasts, suggesting a novel pathogenic role for these proteins in myofibroblast biology.

pharmacology and toxicology↗

bioRxiv2018

An improved high-quality genome assembly and annotation of Qingke, Tibetan hulless barley

BackgroundThe Tibetan hulless barley (Hordeum vulgare L. var. nudum), also called \"Qingke\" in Chinese and \"Ne\" in Tibetan, is the staple food for Tibetans and an important livestock feed in the Tibetan Plateau. The Tibetan hulless barley in China has about 3500 years of cultivation history, mainly produced in Tibet, Qinghai, Sichuan, Yunnan and other areas. In addition, Tibetan hulless barley has rich nutritional value and outstanding health effects, including the beta glucan, dietary fiber, amylopectin, the contents of trace elements, which are higher than any other cereal crops.\n\nFindingsHere, we reported an improved high-quality assembly of Tibetan hulless barley genome with 4.0 Gb in size. We employed the falcon assembly package, scaffolding and error correction tools to finish improvement using PacBio long reads sequencing technology, with contig and scaffold N50 lengths of 1.563Mb and 4.006Mb, respectively, representing more continuous than the original Tibetan hulless barley genome nearly two orders of magnitude. We also re-annotated the new assembly, and reported 61,303 stringent confident putative protein-coding genes, of which 40,457 is HC genes. We have developed a new Tibetan hulless barley genome database (THBGD) to download and use friendly, as well as to better manage the information of the Tibetan hulless barley genetic resources.\n\nConclusionsThe availability of new Tibetan hulless barley genome and annotations will take the genetics of Tibetan hulless barley to a new level and will greatly simplify the breeders effort. It will also enrich the granary of the Tibetan people.

genomics↗

bioRxiv2018

An orderly single-trial organization of population dynamics in premotor cortex predicts behavioral variability

Animals are not simple input-output machines. Their responses to even very similar stimuli are variable. A key, long-standing question in neuroscience is understanding the neural correlates of such behavioral variability. To reveal these correlates, behavior and neural population must be related to one another on single trials. Such analysis is challenging due to the dynamical nature of brain function (e.g. decision making), neuronal heterogeneity and signal to noise difficulties. By analyzing population recordings from mouse frontal cortex in perceptual decision-making tasks, we show that an analysis approach tailored to the coarse grain features of the dynamics was able to reveal previously unrecognized structure in the organization of population activity. This structure was similar on error and correct trials, suggesting what may be the underlying circuit mechanisms, was able to predict multiple aspects of behavioral variability and revealed long time-scale modulation of population activity.

neuroscience↗

bioRxiv2018

Deciphering the metabolic perturbation in hepatic alveolar echinococcosis: a 1H NMR-based metabolomics study

Hepatic alveolar echinococcosis (HAE) is a chronic and potentially lethal parasitic disease. It is caused by growth of Echinococcus multilocularis larvae in liver. To date, early-stage diagnosis for the disease is not mature due to its long asymptomatic incubation period. In this study, a proton nuclear magnetic resonance (1H NMR) -based metabolomics approach was applied in conjunction with multivariate statistical analysis to investigate the altered metabolic profiles in blood serum and urine samples from HAE patients and to identify characteristic metabolic markers associated with HAE. The current results identified 21 distinctive metabolic difference between the HAE patients and healthy individuals, which can be associated with perturbations in energy metabolism, amino acid metabolism, oxidative stress, and neurotransmitter imbalance. In addition, the Fischer ratio, which is the molar ratio of branched-chain amino acids to aromatic amino acids was found significantly lower (p<0.001) in blood serum from HAE patients. The ratio, together with changes in other metabolic pathways may provide new insight into mechanistic understanding of HAE pathogenesis, and may be useful for early-stage HAE diagnosis.\n\nAuthor SummaryHepatic alveolar echinococcosis (HAE) is a life-threatening disease caused by Echinococcus multilocularis infection. The disease has a long asymptomatic early stage (5~15 years), which complicates effective diagnosis of early-stage HAE even with advanced imaging techniques. Metabolomics is an emerging analytical platform that comprises of analysis of all small molecule metabolites that are present within an organism. The applications of metabolomics method on HAE may help to reveal the molecular biology mechanisms of HAE. In the current study, we had used 1H NMR-based metabolomics technique to investigate blood serum and urine samples from HAE patients. Altered metabolic responses and characteristic differential metabolites for HAE were identified. The metabolic profiling of human biofluids provided valuable information for early-stage HAE diagnosis and for therapeutic interventions, without having to extract HAE vesicles from patients. By featuring global and comprehensive metabolic status, the metabolomics approach holds considerable promise as a noninvasive, dynamic, and effective tool for probing the underlying mechanism of HAE.

systems biology↗

bioRxiv2018

Deep learning achieves super-resolution in fluorescence microscopy

AbtsractWe present a deep learning-based method for achieving super-resolution in fluorescence microscopy. This data-driven approach does not require any numerical models of the imaging process or the estimation of a point spread function, and is solely based on training a generative adversarial network, which statistically learns to transform low resolution input images into super-resolved ones. Using this method, we super-resolve wide-field images acquired with low numerical aperture objective lenses, matching the resolution that is acquired using high numerical aperture objectives. We also demonstrate that diffraction-limited confocal microscopy images can be transformed by the same framework into super-resolved fluorescence images, matching the image resolution acquired with a stimulated emission depletion (STED) microscope. The deep network rapidly outputs these super-resolution images, without any iterations or parameter search, and even works for types of samples that it was not trained for.

bioengineering↗

bioRxiv2018

Visual physiology of the Layer 4 cortical circuit in silico

Despite advances in experimental techniques and accumulation of large datasets concerning the composition and properties of the cortex, quantitative modeling of cortical circuits under in-vivo-like conditions remains challenging. Here we report and publicly release a biophysically detailed circuit model of layer 4 in the mouse primary visual cortex, receiving thalamo-cortical visual inputs. The 45,000-neuron model was subjected to a battery of visual stimuli, and results were compared to published work and new in vivo experiments. Simulations reproduced a variety of observations, including effects of optogenetic perturbations. Critical to the agreement between responses in silico and in vivo were the rules of functional synaptic connectivity between neurons. Interestingly, after extreme simplification the model still performed satisfactorily on many measurements, although quantitative agreement with experiments suffered. These results emphasize the importance of functional rules of cortical wiring and enable a next generation of data-driven models of in vivo neural activity and computations.\n\nAUTHOR SUMMARYHow can we capture the incredible complexity of brain circuits in quantitative models, and what can such models teach us about mechanisms underlying brain activity? To answer these questions, we set out to build extensive, bio-realistic models of brain circuitry employing systematic datasets on brain structure and function. Here we report the first modeling results of this project, focusing on the layer 4 of the primary visual cortex (V1) of the mouse. Our simulations reproduced a variety of experimental observations in a large battery of visual stimuli. The results elucidated circuit mechanisms determining patters of neuronal activity in layer 4 - in particular, the roles of feedforward thalamic inputs and specific patterns of intracortical connectivity in producing tuning of neuronal responses to the orientation of motion. Simplification of neuronal models led to specific deficiencies in reproducing experimental data, giving insights into how biological details contribute to various aspects of brain activity. To enable future development of more sophisticated models, we make the software code, the model, and simulation results publicly available.

neuroscience↗

bioRxiv2018

Genome-wide prediction of synthetic rescue mediators of resistance to targeted and immunotherapy

Most patients with advanced cancer eventually acquire resistance to targeted therapies, spurring extensive efforts to identify molecular events mediating therapy resistance. Many of these events involve synthetic rescue (SR) interactions, where the reduction in cancer cell viability caused by targeted gene inactivation is rescued by an adaptive alteration of another gene (the rescuer). Here we perform a genome-wide prediction of SR rescuer genes by analyzing tumor transcriptomics and survival data of 10,000 TCGA cancer patients. Predicted SR interactions are validated in new experimental screens. We show that SR interactions can successfully predict cancer patients response and emerging resistance. Inhibiting predicted rescuer genes sensitizes resistant cancer cells to therapies synergistically, providing initial leads for developing combinatorial approaches to overcome resistance proactively. Finally, we show that the SR analysis of melanoma patients successfully identifies known mediators of resistance to immunotherapy and predicts novel rescuers.

cancer biology↗

bioRxiv2018

A learning-based framework for miRNA-disease association prediction using neural networks

MotivationA microRNA (miRNA) is a type of non-coding RNA, which plays important roles in many bio-logical processes. Lots of studies have shown that miRNAs were implicated in human diseases, indicating that miRNAs might be potential biomarkers for various types of diseases. Therefore, it is important to reveal the relationships between miRNAs and diseases/phenotypes.\n\nResultsWe proposed a novel learning-based framework, MDA-CNN, for miRNA-disease association identification. The model first captures richer interaction features between diseases and miRNAs based on a three-layer network with an additional gene layer. An auto-encoder is then employed to identify the essential feature combination for each pair of miRNA and disease automatically. A final label is given by a convolutional neural network taking the reduced feature representation as input. The evaluation results showed that the proposed framework outperformed some state-of-the-art approaches in a large margin on both tasks of miRNA-disease associations prediction and miRNA-phenotype associations prediction.\n\nAvailabilityThe software will be available after the manuscript is accepted.\n\nContactjiajiepeng@nwpu.edu.cn;zywei@fudan.edu.cn;shang@nwpu.edu.cn\n\nSupplementary informationSupplementary data are available at Bioinformatics online.

bioinformatics↗