Biology subjects

Xu, K.

Publications and source records attributed to Xu, K..

At least 235 records · Page 13Linked to original sources

bioRxiv2020

Optimizing Sequencing Resources in Genotyped Livestock Populations Using Linear Programming

BackgroundLow-cost genome-wide single-nucleotide polymorphisms (SNPs) are routinely used in animal breeding programs. Compared to SNP arrays, the use of whole-genome sequence data generated by the next-generation sequencing technologies (NGS) has great potential in livestock populations. However, a large number of animals are required to be sequenced to exploit the full potential of whole-genome sequence data. Thus, novel strategies are desired to allocate sequencing resources in genotyped livestock populations such that the entire population can be sequenced or imputed efficiently. MethodsWe present two applications of linear programming models called LPChoose for sequencing resources allocation. The first application is to identify the minimum number of animals for sequencing while meeting the criteria that each haplotype in the population is contained in at least one of the animals selected for sequencing. The second is to sequence a fixed number of animals whose haplotypes include as large a proportion as possible of the haplotypes present in the population given a limited sequencing budget. ResultsIn both applications LPChoose has similar or better performance than some other methods. The linear programming models we proposed are based on rigorous and well defined optimization techniques and easy and straightforward to implement. LPChoose is available as an open-source package.

genomics↗

bioRxiv2020

Genome-wide CRISPRi/a screens in human neurons link lysosomal failure to ferroptosis

Single-cell transcriptomics provide a systematic map of gene expression in different human cell types. The next challenge is to systematically understand cell-type specific gene function. The integration of CRISPR-based functional genomics and stem cell technology enables the scalable interrogation of gene function in differentiated human cells. Here, we present the first genomewide CRISPR interference and CRISPR activation screens in human neurons. We uncover pathways controlling neuronal response to chronic oxidative stress, which is implicated in neurodegenerative diseases. Unexpectedly, knockdown of the lysosomal protein prosaposin strongly sensitizes neurons, but not other cell types, to oxidative stress by triggering the formation of lipofuscin, a hallmark of aging, which traps iron, generating reactive oxygen species and triggering ferroptosis. We also determine transcriptomic changes in neurons following perturbation of genes linked to neurodegenerative diseases. To enable the systematic comparison of gene function across different human cell types, we establish a data commons named CRISPRbrain.

genomics↗

bioRxiv2020

Combination of favorable gene haplotypes plays an important role in rice hybrid grain quality traits based on genome-wide association analysis

Yield level and grain quality determine the commercial potential of rice (Oryza sativa L.) varieties. Mining and using genes that control important rice grain quality characteristics are major tasks for plant breeders. Here, a genome-wide association study was conducted to determine the genetic bases of 12 rice grain quality traits in 113 varieties and 565 testcross hybrids. A total of 56 significant SNPs were associated with 9 of the traits in variety phenotypic, general combining ability, testcross hybrid phenotypic and mid-parental heterotic datasets, from which 45 novel loci were identified. The cumulative effects of superior alleles or favorable haplotypes of genes closest to significant quality trait-associated loci were found in the four datasets. Additionally, the favorable gene haplotypes performed better than those of superior alleles in the variety and testcross hybrid datasets. Pyramiding the favorable haplotypes of five cloned rice grain quality genes resulted in a very low amylose content and high yield in the latter. These testcross hybrids had rice grain qualities similar to their parental lines but with much higher yields. The amylose content, grain width and grain length predictions for potential hybrids among the 113 varieties using genomic selection based on the BayesB method revealed a performance trend similar to those the testcross hybrids in our study. Thus, the selection of combination of favorable rice quality-related gene haplotypes is recommended to breed hybrids with high yields and elite grain qualities.

genetics↗

bioRxiv2020

Predicting dynamic cellular protein-RNA interactions using deep learning and in vivo RNA structure

Interactions with RNA-binding proteins (RBPs) are crucial for RNA regulation and function. While both RNA sequence and structure are critical determinants, RNA structure is dependent on cellular environment and especially important in regulating dynamic RBP bindings across various conditions. However, how distinct it contributes to RBP binding in vivo remains poorly understood. To address this issue, we obtained transcriptome-wide RNA secondary structure profiles in multiple cell-types, and established a deep neural network, PrismNet, that uses in vivo RNA structures to accurately predict cellular protein-RNA interactions. With a deep learning "attention" strategy, PrismNet discovers the exact binding nucleotides and their mutational effect. The predicted binding sites are highly conserved and enriched for rare, deleterious genetic variants. Remarkably, dynamic RBP binding sites are enriched for structure-changing variants (riboSNitches), which are often associated with disease, reflecting dysregulated RBP bindings. Our resource enables the analysis of cell-type-specific RNA regulation, with applications in human disease. Highlights1, A big data resource of transcriptome-wide RNA secondary structure profiles in multiple cell types 2, PrismNet, a deep neural network, accurately models the sequence and structural combined patterns of protein-RNA interactions in vivo 3, RNA structural information in vivo is critical for the accurate prediction of dynamic RBP binding in various cellular conditions 4, PrismNet can dissect and predict how mutations affect RBP binding via RNA sequence or structure changes 5, RNA structure-changing RiboSNitches are enriched in dynamic RBP binding sites and often associated with disease, likely disrupting RBP-based regulation

cell biology↗

bioRxiv2020

Rapid development of an inactivated vaccine for SARS-CoV-2

The COVID-19 pandemic caused by SARS-CoV-2 has brought about an unprecedented crisis, taking a heavy toll on human health, lives as well as the global economy. There are no SARS-CoV-2-specific treatments or vaccines available due to the novelty of this virus. Hence, rapid development of effective vaccines against SARS-CoV-2 is urgently needed. Here we developed a pilot-scale production of a purified inactivated SARS-CoV-2 virus vaccine candidate (PiCoVacc), which induced SARS-CoV-2-specific neutralizing antibodies in mice, rats and non-human primates. These antibodies potently neutralized 10 representative SARS-CoV-2 strains, indicative of a possible broader neutralizing ability against SARS-CoV-2 strains circulating worldwide. Immunization with two different doses (3g or 6 g per dose) provided partial or complete protection in macaques against SARS-CoV-2 challenge, respectively, without any antibody-dependent enhancement of infection. Systematic evaluation of PiCoVacc via monitoring clinical signs, hematological and biochemical index, and histophathological analysis in macaques suggests that it is safe. These data support the rapid clinical development of SARS-CoV-2 vaccines for humans. One Sentence SummaryA purified inactivated SARS-CoV-2 virus vaccine candidate (PiCoVacc) confers complete protection in non-human primates against SARS-CoV-2 strains circulating worldwide by eliciting potent humoral responses devoid of immunopathology

microbiology↗

bioRxiv2020

Adaptive actin organization counteracts elevated membrane tension to ensure robust endocytosis

Clathrin-mediated endocytosis (CME) robustness under elevated membrane tension is maintained by actin assembly-mediated force generation. However, whether more actin assembles at endocytic sites in response to increased load, as has been observed in lamellipodia, has not previously been investigated. Here actin network ultrastructure at CME sites was examined under low and high membrane tension. Actin and N-WASP spatial organization indicate that actin polymerization initiates at the base of clathrin-coated pits and that the network then grows away from the plasma membrane. Actin network height at individual CME sites was not coupled to coat shape, raising the possibility that local differences in mechanical load feedback on assembly. By manipulating membrane tension and Arp2/3 complex activity we tested the hypothesis that actin assembly at CME sites increases in response to elevated load. Indeed, in response to elevated membrane tension, actin grew higher, resulting in greater coverage of the clathrin coat, and CME slowed. When membrane tension was elevated and the Arp2/3 complex was inhibited, shallow clathrin-coated pits accumulated, indicating that this adaptive mechanism is especially crucial for coat curvature generation. We propose that actin assembly increases in response to increased load to ensure CME robustness over a range of plasma membrane tensions.

cell biology↗

bioRxiv2020

Foundation species across a latitudinal gradient in China

AbstractFoundation species play important roles in structuring forest communities and ecosystems. Foundation species are difficult to identify without long-term observations or experiments and their foundational roles rarely are identified before they are declining or threatened. We used new statistical criteria based on size-frequency distributions, species diversity, and spatial codispersion among woody plants to identify potential ("candidate") foundation species in 12 large forest dynamics plots spanning 26 degrees of latitude in China. We used these data to identify a suite of candidate foundation species in Chinese forests; test the hypothesis that foundation woody plant species are more frequent in the temperate zone than in the tropics; and compare these results with comparable data from the Americas to suggest candidate foundation genera in Northern Hemisphere forests. We identified more candidate foundation species in temperate plots than in subtropical or tropical plots, and this relationship was independent of the latitudinal gradient in overall species richness. Two species of Acer, the canopy tree Acer ukurunduense and the shrubby treelet Acer barbinerve were the only two species that met both criteria in full to be considered as candidate foundation species. When we relaxed the diversity criteria, Acer, Tilia, and Juglans spp., and Corlyus mandshurica were frequently identified as candidate foundation species. In tropical plots, the tree Mezzettiopsis creaghii and the shrubs or treelets Aporusa yunnanensis and Ficus hispida had some characteristics associated with foundation species. Species diversity of co-occurring woody species was negatively associated with basal area of candidate foundation species more frequently at 5- and 10-m spatial grains (scale) than at a 20-m grain. Conversely, Bray-Curtis dissimilarity was positively associated with basal area of candidate foundation species more frequently at 5-m than at 10- or 20-m grains. Our data support the hypothesis that foundation species should be more common in temperate than in tropical or boreal forests, and suggest that in the Northern Hemisphere that Acer be investigated further as a foundation tree genus.

ecology↗

bioRxiv2020

Glycolysis Fuels Phosphoinositide 3-Kinase Signaling to Bolster T Cell Immunity

Infection triggers clonal expansion and effector differentiation of microbial antigen-specific T cells in association with metabolic reprograming. Here, we show that the glycolytic enzyme lactate dehydrogenase A (LDHA) is induced in CD8+ T effector cells via phosphoinositide 3-kinase (PI3K)-dependent mechanisms. In turn, ablation of LDHA inhibits PI3K-dependent phosphorylation of Akt and its transcription factor target Foxo1, causing defective antimicrobial immunity. LDHA deficiency cripples cellular redox control and diminishes glycolytic adenosine triphosphate (ATP) production in effector T cells, resulting in attenuated PI3K signaling. Thus, nutrient metabolism and growth factor signaling are highly integrated processes with glycolytic ATP serving as a rheostat to gauge PI3K/Akt/Foxo1 signaling in T cell immunity control. Such a bioenergetics mechanism of signaling regulation implies a root cause for the century-old phenomenon of Warburg effect, and could guide development of novel therapeutics for infectious diseases and cancer. One Sentence SummaryA PI3K and LDHA circuit enables T cell immunity

immunology↗

bioRxiv2020

Novel and potent inhibitors targeting DHODH, a rate-limiting enzyme in de novo pyrimidine biosynthesis, are broad-spectrum antiviral against RNA viruses including newly emerged coronavirus SARS-CoV-2

Emerging and re-emerging RNA viruses occasionally cause epidemics and pandemics worldwide, such as the on-going outbreak of coronavirus SARS-CoV-2. Existing direct-acting antiviral (DAA) drugs cannot be applied immediately to new viruses because of virus-specificity, and the development of new DAA drugs from the beginning is not timely for outbreaks. Thus, host-targeting antiviral (HTA) drugs have many advantages to fight against a broad spectrum of viruses, by blocking the viral replication and overcoming the potential viral mutagenesis simultaneously. Herein, we identified two potent inhibitors of DHODH, S312 and S416, with favorable drug-like and pharmacokinetic profiles, which all showed broad-spectrum antiviral effects against various RNA viruses, including influenza A virus (H1N1, H3N2, H9N2), Zika virus, Ebola virus, and particularly against the recent novel coronavirus SARS-CoV-2. Our results are the first to validate that DHODH is an attractive host target through high antiviral efficacy in vivo and low virus replication in DHODH knocking-out cells. We also proposed the drug combination of DAA and HTA was a promising strategy for anti-virus treatment and proved that S312 showed more advantageous than Oseltamivir to treat advanced influenza diseases in severely infected animals. Notably, S416 is reported to be the most potent inhibitor with an EC50 of 17nM and SI value >5882 in SARS-CoV-2-infected cells so far. This work demonstrates that both our self-designed candidates and old drugs (Leflunomide/Teriflunomide) with dual actions of antiviral and immuno-repression may have clinical potentials not only to influenza but also to COVID-19 circulating worldwide, no matter such viruses mutate or not.

microbiology↗

bioRxiv2020

Transferrin-dependent crosstalk between the intestinal tract and commensal microbes contributes for immune tolerance

Crosstalks between gastrointestinal tract and commensal microbes regulate immune tolerance and maintain host intestinal homeostasis. However, molecular events that regulate the crosstalks remain poorly understood. Here, we show that microbial products (lipopolysaccharide, lipoteichoic acid and DNA) up-regulate host transferrin, an iron supplier of commensal bacteria, to induce hosts immune tolerance by negatively regulating toll-like receptor (TLR) signaling. Transferrin level in germ-free and broad-spectrum antibiotics-treated mice is much less than that in normal mice. Transferrin is found to silence TLR signaling complex by directly interacting with CD14, a co-receptor of many TLRs. Transferrin knock-down impaired host tolerogenic responses as well as broad-spectrum antibiotics treatment. Our findings reveal that commensal bacteria up-regulate and beneficially use host transferrin as a negative regulator of TLR signaling to shape host immunity and contribute for intestinal tolerance.

immunology↗

bioRxiv2020

The interaction of crossover formation and the dynamic architecture of the synaptonemal complex during meiosis

During meiosis, pairing between homologous chromosomes is stabilized by the assembly of a protein lattice known as the synaptonemal complex (SC). The SC ensures the formation of crossovers between homologous chromosomes and also regulates their distribution. However, how the SC regulates crossover formation remains elusive. We isolated an unusual mutation in C. elegans that disrupts crossover interference but not the assembly of the SC. This mutation alters the unique C-terminal domain of an essential SC protein, SYP-4, a likely ortholog of the vertebrate SC protein SIX6OS1. To characterize the structure of the SC in wild-type and mutant animals, we use three-dimensional STochastic Optical Reconstruction Microscopy (3D-STORM) to interrogate the molecular architecture of the SC in intact germline tissue from C. elegans. The approach enabled us to define positions of protein epitopes with respect to the 3D architecture of this complex. Using a probabilistic mapping approach to analyze super-resolution image data, we detect a marked structural transition in wild-type animals that coincides with crossover designation. We also found that our syp-4 mutant subtly perturbs SC architecture. Our findings add to growing evidence that the SC is an active material whose molecular organization contributes to chromosome-wide crossover regulation.

cell biology↗

bioRxiv2020

Limiting Self-Renewal of the Basal Compartment Induces Differentiation and Alters Evolution of Mammary Tumors

Differentiation therapy is an approach that utilizes our understanding of the hierarchy of cellular systems to pharmacologically induce a shift towards terminal commitment. While this approach has been a paradigm in treating certain hematological malignancies, efforts to translate this success to solid tumors have proven challenging. In this study we show that activation of PKA drives aberrant mammary differentiation by diminishing the self-renewing potential of the basal compartment. PKA activation results in tumors that are more benign, exhibiting reduced metastatic propensity, loss of tumor-initiating potential and increased sensitivity to chemotherapy. Analysis of tumor histopathology revealed features of overt differentiation with papillary characteristics. Longitudinal single cell profiling at the hyperplasia and tumor stages uncovered an altered path of tumor evolution whereby PKA curtails the emergence of aggressive subpopulations. PKA activation represents a promising approach as an adjuvant to chemotherapy for certain breast cancers, reviving the paradigm of differentiation therapy for solid tumors.

cancer biology↗

bioRxiv2019

Existence and functions of hypothalamic kisspeptin neuropeptide signaling system in a non-chordate deuterostome species

The kisspeptin (Kp) system is a central modulator of the hypothalamic-pituitary-gonadal axis in vertebrates. Its existence outside the vertebrate lineage remains largely unknown. Here we report the identification and characterization of Kp system in the sea cucumber Apostichopus japonicus. The gene encoding the Kp precursor, generates two mature neuropeptides, AjKiss1a and AjKiss1b. The Kp receptors, AjKissR1 and AjKissR2, are strongly activated by synthetic A. japonicus and vertebrate Kps, triggering a rapid intracellular mobilization of Ca2+, followed by receptor internalization. AjKissR1 and AjKissR2 share similar intracellular signaling pathways via Gq/PLC/PKC/MAPK cascade, when activated by C-terminal decapeptide (AjKiss1b-10). The A. japonicus Kp system functions in mutiple tissues which are closely related to reproduction and metabolism. Overall, our findings uncover for the first time, to our knowledge, the existence and function of the Kp system in a non-chordate species and provide new evidence to support the ancient origin of the hypothalamic neurosecretory system.

evolutionary biology↗

bioRxiv2019

DNA Methylation Signature on Phosphatidylethanol, not Self-Reported Alcohol Consumption, Predicts Hazardous Alcohol Consumption in Two Distinct Populations

The process of diagnosing hazardous alcohol drinking (HAD) is based on self-reported data and is thereby vulnerable to bias. There has been an interest in developing epigenetic biomarkers for HAD that might complement clinical assessment. Because alcohol consumption has been previously linked to DNA methylation (DNAm), here, we aimed to select DNAm signatures in blood to predict HAD from two demographically and clinically distinct populations (Ntotal=1,549). We first separately conducted an epigenome-wide association study (EWAS) for phosphatidylethanol (PEth), an objective measure of alcohol consumption, and for self-reported alcohol consumption in Cohort 1. We identified 102 PEth-associated CpGs, including 32 CpGs previously associated with alcohol consumption or alcohol use disorders. In contrast, no CpG reached epigenome-wide significance on self-reported alcohol consumption. Using a machine learning approach, two subsets of CpGs from EWAS on PEth and on self-reported alcohol consumption from Cohort 1 were separately tested for the prediction of HAD in Cohort 2. We found that a subset of 130 CpGs selected from the EWAS on PEth showed an excellent prediction of HAD with area under the ROC curve (AUC) of 91.31% in training set and 70.65% in validation set of Cohort 2. However, CpGs preselected from the EWAS on self-reported alcohol consumption showed a poor prediction of HAD with AUC 75.18% in the training set and 57.60% in the validation set. Our results demonstrate that an objective measure for alcohol consumption is a more informative phenotype than self-reported data for revealing epigenetic mechanism. The PEth-associated DNAm signature in blood is a robust biomarker for alcohol consumption.

bioinformatics↗

bioRxiv2019

Comprehensive molecular characterization of pediatric treatment-induced high-grade glioma: A distinct entity despite disparate etiologies with defining molecular characteristics and potential therapeutic targets

Treatment-induced high-grade gliomas (TIHGGs) are an incurable late complication of cranial radiation therapy or combined radiation/chemotherapy used to treat pediatric cancer. We assembled a cohort of 33 TIHGGs from multiple institutions. The primary antecedent malignancies were medulloblastoma, acute lymphoblastic leukemia, astrocytoma, and ependymoma. We performed methylation profiling, RNA-seq, and genomic sequencing (whole-genome or whole-exome) on TIHGG samples. Methylation profiling revealed that TIHGGs cluster primarily with the pediatric receptor tyrosine kinase I subtype (26/31 samples). Common TIHGG copy-number alterations include Chromosome (Ch.) 1p loss/1q gain, Ch. 4 loss, Ch. 6q loss, and Ch. 13 and Ch. 14 loss; focal alterations include PDGFRA and CDK4 gain and loss of CDKN2A and BCOR. Relative to de novo pediatric high-grade glioma (pHGG), BCOR loss (p=0.004) and CDKN2A loss (p=0.005) were significantly increased. Transcriptomic analysis identified two distinct TIHGG subgroups, one with a lesser mutation burden (0.12 mut/Mb), Ch. 1p loss/1q gain (5/6 samples), and stem cell characteristics, and one with a greater mutation burden (1.08 mut/Mb, p<0.0002), depletion of DNA repair pathways, and inflammatory characteristics. We observed increased chromothripsis in TIHGG versus pHGG (67% vs. 31%, p=0.036), which was associated with extrachromosomal circular DNA-mediated amplification of PDGFRA and CDK4. In vitro drug screening in one primary, patient-derived TIHGG cell line from each expression subgroup identified microtubule inhibitors/stabilizers, DNA-damaging agents, MEK inhibition, and, in the inflammatory subgroup, proteasome inhibitors as potentially effective therapies. This study provides a comprehensive molecular profile of TIHGG, including mechanistic insights to TIHGG oncogenesis, and identifies potentially effective therapeutic modalities for further investigation.

cancer biology↗

bioRxiv2019

Antigenicity and Potential Use of A Novel Brucella Multiepitope Recombinant Protein in the Diagnosis of Brucellosis

Currently, brucellosis is a reemerged zoonotic infectious disease with an increased incidence in recent years. A simple, rapid and sensitive method for diagnosing brucellosis has important significance for early diagnosis and early treatment, which can help to reduce medical burden and economic loss. Previously, a multiple epitope recombinant protein was constructed based on linear B-cell epitope prediction tools. In this study, the recombinant protein was used as an antigen to study the immune response produced by immunized mice, and goat serum was used to verify its diagnostic accuracy.The production of antibodies was successfully induced in the vaccinated mice. Through analyzing the serum antibody subtypes, the primary antibody was identified as IgG. Flow cytometric analysis revealed that the percentage of CD4+, CD8+ and the CD4+/CD8+ ratios were increased by T cell subsets in mouse splenocytes, indicating that the recombinant protein induced a strong immune response in mice and that it had strong immunoreactivity. Using indirect ELISA, the recombinant protein correctly diagnosed positive and negative brucellosis samples. Compared with the whole bacterial antigen, the recombinant protein had a weaker sensitivity but a stronger specificity.In this study, animal experiments showed that the recombinant protein had good antigenicity, and indirect ELISA indicates that it can be used as an antigen to diagnose brucellosis. Therefore, the recombinant protein is a potential candidate antigen for brucellosis vaccine development and serological diagnosis.

zoology↗

bioRxiv2019

Satellite Imaging of Global Urbanicity relate to Adolescent Brain Development and Behavior

Urbanicity, the impact of living in urban areas, is among the greatest environmental challenges for mental health. While urbanicity might be distinct in different sociocultural conditions and geographic locations, there are likely to exist common features shared in different areas of the globe. Understanding these common and specific relations of urbanicity with human brain and behavior will enable to assess the impact of urbanicity on mental disorders, especially in childhood and adolescence, where prevention and early interventions are likely to be most effective.\n\nWe constructed from satellite-based remote sensing data a factor for urbanicity that was highly correlated with population density ground data. This factor, UrbanSat was utilized in the Chinese CHIMGEN sample (N=831) and the longitudinal European IMAGEN cohort (N=810) to investigate if exposure to urbanicity during childhood and adolescence is associated with differences in brain structure and function in young adults, and if these changes are linked to behavior.\n\nUrbanicity was found negatively correlated with medial prefrontal cortex volume and positively correlated with cerebellar vermis volume in young adults from both China and Europe. We found an increased correlation of urbanicity with functional network connectivity within- and between- brain networks in Chinese compared to European participants. Urbanicity was highly correlated with a measure of perceiving a situation from the perspective of others, as well as symptoms of depression in both datasets. These correlations were mediated by the structural and functional brain changes observed. Susceptibility to urbanicity was greatest in two developmental windows during mid-childhood and adolescence.\n\nUsing innovative technology, we were able to probe the relationship between urban upbringing with brain change and behavior in different sociocultural conditions and geographic locations. Our findings help to identify shared and distinct determinants of adolescent brain development and mental health in different regions of the world, thus contributing to targeted prevention and early-intervention programs for young people in their unique environment. Our approach may be relevant for public health, policy and urban planning globally.

neuroscience↗

bioRxiv2019

Developing a dengue forecast model using Long Short Term Memory neural networks method

BackgroundDengue Fever (DF) is a tropical mosquito-borne disease that threatens public health and causes enormous economic burdens worldwide. In China, DF expanded from coastal region to inner land, and the incidence sharply increased in the last few years. In this study, we conduct the analysis of dengue using the Long Short Term Memory (LSTM) recurrent neural networks. This is an artificial intelligence technology, to develop a precise dengue forecast model.\n\nMethodology/Principal FindingsThe model is developed from monthly dengue cases and local meteorological data of 2005-2018 among top 20 Chinese cities with a record of the highest dengue incidence. The first 13 year data were used to construct the LSTM and to predict the dengue outbreaks in 2018. The results are compared with the estimated dengue cases of other previously published models. Model performance and prediction accuracy were assessed using Root Mean Square Error (RMSE). With the LSTM method, the prediction measurements of average RMSE drop by 54.79% and 34.76% as compared with the Susceptible Infected Recovered (SIR) model and Zero Inflated Generalized Additive Model (ZIGAM). Our results showed that if only local data were used to develop forecast models, the LSTM neural networks would fail to capture the transmission characteristics of dengue virus in areas with fewer dengue cases. Contrarily, transfer learning (TL) can improve the accuracy of prediction of the LSTM neural network model in areas with fewer dengue incidences.\n\nConclusion and significanceThe LSTM model is beneficial in predicting dengue incidence as compared with other previously published forecasting models. The findings provide a more precise forecast dengue model, which can help the local government and health-related departments respond early to dengue epidemics.\n\nAuthor summaryIn China, DF is a public health concern that poses a great economic burden on local governments. However, the incidence has sharply increased in recent years with growth in the sub-regions. With this issue, it will be challenging to develop an accurate and timely dengue forecast model. LSTM recurrent neural networks, deep learning methods and virus propagation rules by learning from observational data offer more advantages in predicting the prevalence of infectious disease dynamics than the traditional statistical model. The 2005-2017 data of the top 20 Chinese cities with the highest dengue incidence were used to construct the LSTM model, advantageous in predicting dengue in most cities. Moreover, the model helped to predict the dengue outbreaks in 2018 and used to compare the estimated dengue cases with the RMSE results of other previously published models. A thorough search of the literature shows that this is the first established dengue forecast model using the LSTM method, which is effective in predicting the trend of dengue dynamics.

bioinformatics↗