Publications

@article{pmid36525587,

title = {Discovery of genomic loci associated with sleep apnea risk through multi-trait GWAS analysis with snoring},

author = {Adrian I Campos and Nathan Ingold and Yunru Huang and Brittany L Mitchell and Pik-Fang Kho and Xikun Han and Luis M García-Marín and Jue-Sheng Ong and  and Matthew H Law and Jennifer S Yokoyama and Nicholas G Martin and Xianjun Dong and Gabriel Cuellar-Partida and Stuart MacGregor and Stella Aslibekyan and Miguel E Rentería},

doi = {10.1093/sleep/zsac308},

issn = {1550-9109},

year  = {2023},

date = {2023-03-01},

journal = {Sleep},

volume = {46},

number = {3},

abstract = {STUDY OBJECTIVES: Despite its association with severe health conditions, the etiology of sleep apnea (SA) remains understudied. This study sought to identify genetic variants robustly associated with SA risk.



METHODS: We performed a genome-wide association study (GWAS) meta-analysis of SA across five cohorts (NTotal = 523 366), followed by a multi-trait analysis of GWAS (multi-trait analysis of genome-wide association summary statistics [MTAG]) to boost power, leveraging the high genetic correlation between SA and snoring. We then adjusted our results for the genetic effects of body mass index (BMI) using multi-trait-based conditional and joint analysis (mtCOJO) and sought replication of lead hits in a large cohort of participants from 23andMe, Inc (NTotal = 1 477 352; Ncases = 175 522). We also explored genetic correlations with other complex traits and performed a phenome-wide screen for causally associated phenotypes using the latent causal variable method.



RESULTS: Our SA meta-analysis identified five independent variants with evidence of association beyond genome-wide significance. After adjustment for BMI, only one genome-wide significant variant was identified. MTAG analyses uncovered 49 significant independent loci associated with SA risk. Twenty-nine variants were replicated in the 23andMe GWAS adjusting for BMI. We observed genetic correlations with several complex traits, including multisite chronic pain, diabetes, eye disorders, high blood pressure, osteoarthritis, chronic obstructive pulmonary disease, and BMI-associated conditions.



CONCLUSION: Our study uncovered multiple genetic loci associated with SA risk, thus increasing our understanding of the etiology of this condition and its relationship with other complex traits.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36343661,

title = {Mitochondrial haplogroups and cognitive progression in Parkinson's disease},

author = {Ganqiang Liu and Chunming Ni and Jiamin Zhan and Weimin Li and Junfeng Luo and Zhixiang Liao and Joseph J Locascio and Wenbiao Xian and Ling Chen and Zhong Pei and Jean-Christophe Corvol and Jodi Maple-Grødem and Meghan C Campbell and Alexis Elbaz and Suzanne Lesage and Alexis Brice and Albert Y Hung and Michael A Schwarzschild and Michael T Hayes and Anne-Marie Wills and Bernard Ravina and Ira Shoulson and Pille Taba and Sulev Kõks and Thomas G Beach and Florence Cormier-Dequaire and Guido Alves and Ole-Bjørn Tysnes and Joel S Perlmutter and Peter Heutink and Jacobus J van Hilten and Roger A Barker and Caroline H Williams-Gray and Clemens R Scherzer and },

doi = {10.1093/brain/awac327},

issn = {1460-2156},

year  = {2023},

date = {2023-01-01},

journal = {Brain},

volume = {146},

number = {1},

pages = {42--49},

abstract = {Mitochondria are a culprit in the onset of Parkinson's disease, but their role during disease progression is unclear. Here we used Cox proportional hazards models to exam the effect of variation in the mitochondrial genome on longitudinal cognitive and motor progression over time in 4064 patients with Parkinson's disease. Mitochondrial macro-haplogroup was associated with reduced risk of cognitive disease progression in the discovery and replication population. In the combined analysis, patients with the super macro-haplogroup J, T, U# had a 41% lower risk of cognitive progression with P = 2.42 × 10-6 compared to those with macro-haplogroup H. Exploratory analysis indicated that the common mitochondrial DNA variant, m.2706A>G, was associated with slower cognitive decline with a hazard ratio of 0.68 (95% confidence interval 0.56-0.81) and P = 2.46 × 10-5. Mitochondrial haplogroups were not appreciably linked to motor progression. This initial genetic survival study of the mitochondrial genome suggests that mitochondrial haplogroups may be associated with the pace of cognitive progression in Parkinson's disease over time.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PPR:PPR647774,

title = {Uncovering Novel Genetic Loci and Biological Pathways Associated with Age-Related Cataracts through GWAS Meta-Analysis},

author = {Santiago Diaz Torres and Samantha Sze-Yee Lee and Luis García-Marín and Adrian Campos and Garreth Lingham and Jue-Sheng Ong and David Mackey and Kathryn Burdon and Michael Hunter and Stuart MacGregor and Xianjun Dong and Puya Gharahkhani and Miguel Renteria},

url = {https://doi.org/10.21203/rs.3.rs-2755149/v1},

doi = {10.21203/rs.3.rs-2755149/v1},

year  = {2023},

date = {2023-01-01},

urldate = {2023-01-01},

journal = {Research Square},

publisher = {Research Square},

abstract = {<h4>Background: </h4> Age-related cataract is a highly prevalent eye disorder that results in the clouding of the crystalline lens and is one of the leading causes of visual impairment and blindness. The disease is influenced by multiple factors including genetics, prolonged exposure to ultraviolet radiation (UVR), and a history of diabetes. However, the extent to which each of these factors contributes to the development of cataracts remains unclear. Further research into the genetic basis of cataracts could provide valuable insights into the disease's etiology and lead to a better understanding of biological mechanisms that are associated with its development. <h4>Methods: </h4> This study presents the largest genome-wide association study of cataracts to date, using data from 127,985 cases and 837,371 controls. We performed gene enrichment analysis to identify genes and biological pathways associated with cataracts. We integrated our results with gene expression reference datasets to identify genetic variants modifying risk for cataracts through changes in the expression of specific genes. We further explored drug-gene interactions to better understand the potential impact of pharmacological interventions on cataract development. Finally, we explored whether a causal relationship underlies the known comorbidity between type 1 diabetes and cataracts using a mendelian randomization framework, and the association between UV exposure and cataract risk in adults using a polygenic risk scoring approach. <h4>Findings: </h4> Our study identified 85 independent genome-wide significant loci, 37 of which are novel. Gene-based association tests identified 126 genes associated with cataracts, hinting at a potential relationship between negative regulation of lipid biosynthesis and the development of cataracts. Four of the genes identified GNL3 , JAG1 , METTL21A , and CREB1 are involved in drug-gene interactions. Moreover, Mendelian Randomisation analysis identified a putative causal relationship between genetic predisposition to type 1 diabetes and an increased risk of cataracts. Lastly, we found evidence indicating that early-life exposure to UVR may have an impact on the later development of cataracts. Interpretation Our findings advance our understanding of the genetic basis of cataract and provide new insights into its etiology. We identified multiple genes and biological pathways associated with the condition, including associations with four genes from which drug repurposing could be proposed. Our results suggest a causal association between type 1 diabetes and cataracts. Also, we highlighted a surrogate measure of UV light exposure as a marker of cataract risk in adults and drug-genes interactions that has the potential of informing novel therapies.},

keywords = {},

pubstate = {forthcoming},

tppubtype = {article}

}

@article{Dong2023.04.01.535194,

title = {Circular RNAs in the human brain are tailored to neuron identity and neuropsychiatric disease},

author = {Xianjun Dong and Yunfei Bai and Zhixiang Liao and David Gritsch and Xiaoli Liu and Tao Wang and Rebeca Borges-Monroy and Alyssa Ehrlich and Geidy E. Serano and Mel B. Feany and Thomas G. Beach and Clemens R. Scherzer},

url = {https://www.biorxiv.org/content/early/2023/04/03/2023.04.01.535194},

doi = {10.1101/2023.04.01.535194},

year  = {2023},

date = {2023-01-01},

urldate = {2023-01-01},

journal = {Nature Communications},

volume = {in press},

publisher = {Cold Spring Harbor Laboratory},

abstract = {Little is known about circular RNAs (circRNAs) in specific brain cells and human neuropsychiatric disease. Here, we systematically identified over 11,039 circRNAs expressed in vulnerable dopamine and pyramidal neurons laser-captured from 190 human brains and non-neuronal cells using ultra-deep, total RNA sequencing. 1,526 and 3,308 circRNAs were custom-tailored to the cell identity of dopamine and pyramidal neurons and enriched in synapse pathways. 88% of Parkinson’s and 80% of Alzheimer’s disease-associated genes produced circRNAs. circDNAJC6, produced from a juvenile-onset Parkinson’s gene, was already dysregulated during prodromal, onset stages of common Parkinson’s disease neuropathology. Globally, addiction-associated genes preferentially produced circRNAs in dopamine neurons, autism-associated genes in pyramidal neurons, and cancers in non-neuronal cells. This study shows that circular RNAs in the human brain are tailored to neuron identity and implicate circRNA- regulated synaptic specialization in neuropsychiatric diseases.Competing Interest StatementBrigham and Women’s Hospital holds US provisional patent applications on biomarkers for PD, on which C.R.S. is named as inventor or co-inventor. Outside this work, C.R.S. has served as consultant, scientific collaborator or on scientific advisory boards for Sanofi, Berg Health, Pfizer, Biogen, and has received grants from NIH, U.S. Department of Defense, APDA, ASAP, and MJFF. X.D. has received funding from NIH, APDA, and ASAP. The other authors declare no competing financial interests.},

keywords = {},

pubstate = {forthcoming},

tppubtype = {article}

}

@article{pmid35688132,

title = {The Parkinson's disease protein alpha-synuclein is a modulator of processing bodies and mRNA stability},

author = {Erinc Hallacli and Can Kayatekin and Sumaiya Nazeen and Xiou H Wang and Zoe Sheinkopf and Shubhangi Sathyakumar and Souvarish Sarkar and Xin Jiang and Xianjun Dong and Roberto Di Maio and Wen Wang and Matthew T Keeney and Daniel Felsky and Jackson Sandoe and Aazam Vahdatshoar and Namrata D Udeshi and D R Mani and Steven A Carr and Susan Lindquist and Philip L De Jager and David P Bartel and Chad L Myers and J Timothy Greenamyre and Mel B Feany and Shamil R Sunyaev and Chee Yeun Chung and Vikram Khurana},

doi = {10.1016/j.cell.2022.05.008},

issn = {1097-4172},

year  = {2022},

date = {2022-06-01},

journal = {Cell},

volume = {185},

number = {12},

pages = {2035--2056.e33},

abstract = {Alpha-synuclein (αS) is a conformationally plastic protein that reversibly binds to cellular membranes. It aggregates and is genetically linked to Parkinson's disease (PD). Here, we show that αS directly modulates processing bodies (P-bodies), membraneless organelles that function in mRNA turnover and storage. The N terminus of αS, but not other synucleins, dictates mutually exclusive binding either to cellular membranes or to P-bodies in the cytosol. αS associates with multiple decapping proteins in close proximity on the Edc4 scaffold. As αS pathologically accumulates, aberrant interaction with Edc4 occurs at the expense of physiologic decapping-module interactions. mRNA decay kinetics within PD-relevant pathways are correspondingly disrupted in PD patient neurons and brain. Genetic modulation of P-body components alters αS toxicity, and human genetic analysis lends support to the disease-relevance of these interactions. Beyond revealing an unexpected aspect of αS function and pathology, our data highlight the versatility of conformationally plastic proteins with high intrinsic disorder.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid35610053,

title = {WebCSEA: web-based cell-type-specific enrichment analysis of genes},

author = {Yulin Dai and Ruifeng Hu and Andi Liu and Kyung Serk Cho and Astrid Marilyn Manuel and Xiaoyang Li and Xianjun Dong and Peilin Jia and Zhongming Zhao},

doi = {10.1093/nar/gkac392},

issn = {1362-4962},

year  = {2022},

date = {2022-05-01},

journal = {Nucleic Acids Res},

abstract = {Human complex traits and common diseases show tissue- and cell-type- specificity. Recently, single-cell RNA sequencing (scRNA-seq) technology has successfully depicted cellular heterogeneity in human tissue, providing an unprecedented opportunity to understand the context-specific expression of complex trait-associated genes in human tissue-cell types (TCs). Here, we present the first web-based application to quickly assess the cell-type-specificity of genes, named Web-based Cell-type Specific Enrichment Analysis of Genes (WebCSEA, available at https://bioinfo.uth.edu/webcsea/). Specifically, we curated a total of 111 scRNA-seq panels of human tissues and 1,355 TCs from 61 different general tissues across 11 human organ systems. We adapted our previous decoding tissue-specificity (deTS) algorithm to measure the enrichment for each tissue-cell type (TC). To overcome the potential bias from the number of signature genes between different TCs, we further developed a permutation-based method that accurately estimates the TC-specificity of a given inquiry gene list. WebCSEA also provides an interactive heatmap that displays the cell-type specificity across 1355 human TCs, and other interactive and static visualizations of cell-type specificity by human organ system, developmental stage, and top-ranked tissues and cell types. In short, WebCSEA is a one-click application that provides a comprehensive exploration of the TC-specificity of genes among human major TC map.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Mitchell2022,

title = {Genome-wide association meta-analysis identifies 29 new acne susceptibility loci},

author = {Brittany L Mitchell and Jake R Saklatvala and Nick Dand and Fiona A Hagenbeek and Xin Li and Josine L Min and Laurent Thomas and Meike Bartels and Jouke Jan Hottenga and Michelle K Lupton and Dorret I Boomsma and Xianjun Dong and Kristian Hveem and Mari Løset and Nicholas G Martin and Jonathan N Barker and Jiali Han and Catherine H Smith and Miguel E Rentería and Michael A Simpson},

url = {https://doi.org/10.1038/s41467-022-28252-5},

doi = {10.1038/s41467-022-28252-5},

issn = {2041-1723},

year  = {2022},

date = {2022-01-01},

journal = {Nature Communications},

volume = {13},

number = {1},

pages = {702},

abstract = {Acne vulgaris is a highly heritable skin disorder that primarily impacts facial skin. Severely inflamed lesions may leave permanent scars that have been associated with long-term psychosocial consequences. Here, we perform a GWAS meta-analysis comprising 20,165 individuals with acne from nine independent European ancestry cohorts. We identify 29 novel genome-wide significant loci and replicate 14 of the 17 previously identified risk loci, bringing the total number of reported acne risk loci to 46. Using fine-mapping and eQTL colocalisation approaches, we identify putative causal genes at several acne susceptibility loci that have previously been implicated in Mendelian hair and skin disorders, including pustular psoriasis. We identify shared genetic aetiology between acne, hormone levels, hormone-sensitive cancers and psychiatric traits. Finally, we show that a polygenic risk score calculated from our results explains up to 5.6% of the variance in acne liability in an independent cohort.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Zhue2108876118,

title = {The genetic source tracking of human urinary exosomes},

author = {Qingfu Zhu and Liming Cheng and Chunyu Deng and Liu Huang and Jiaoyuan Li and Yong Wang and Meng Li and Qinsi Yang and Xianjun Dong and Jianzhong Su and Luke P. Lee and Fei Liu},

url = {https://www.pnas.org/content/118/43/e2108876118},

doi = {10.1073/pnas.2108876118},

issn = {0027-8424},

year  = {2021},

date = {2021-10-26},

urldate = {2021-10-26},

journal = {PNAS},

volume = {118},

number = {43},

publisher = {National Academy of Sciences},

abstract = {The genetic origins of nanoscale extracellular vesicles in our body fluids remains unclear. Here, we perform a tracking analysis of urinary exosomes via RNA sequencing, revealing that urine exosomes mostly express tissue-specific genes for the bladder and have close cell-genetic relationships to the endothelial cell, basal cell, monocyte, and dendritic cell. Tracking the differentially expressed genes of cancers and corresponding enrichment analysis show urine exosomes are intensively involved in immune activities, indicating that they may be harnessed as reliable biomarkers of noninvasive liquid biopsy in cancer genomic diagnostics and precision medicine.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid34433407,

title = {A pipeline for RNA-seq based eQTL analysis with automated quality control procedures},

author = {T Wang and Y Liu and J Ruan and X Dong and Y Wang and J Peng},

doi = {10.1186/s12859-021-04307-0},

issn = {1471-2105},

year  = {2021},

date = {2021-08-22},

journal = {BMC Bioinformatics},

volume = {22},

number = {Suppl 9},

pages = {403},

abstract = {BACKGROUND: Advances in the expression quantitative trait loci (eQTL) studies have provided valuable insights into the mechanism of diseases and traits-associated genetic variants. However, it remains challenging to evaluate and control the quality of multi-source heterogeneous eQTL raw data for researchers with limited computational background. There is an urgent need to develop a powerful and user-friendly tool to automatically process the raw datasets in various formats and perform the eQTL mapping afterward.



RESULTS: In this work, we present a pipeline for eQTL analysis, termed eQTLQC, featured with automated data preprocessing for both genotype data and gene expression data. Our pipeline provides a set of quality control and normalization approaches, and utilizes automated techniques to reduce manual intervention. We demonstrate the utility and robustness of this pipeline by performing eQTL case studies using multiple independent real-world datasets with RNA-seq data and whole genome sequencing (WGS) based genotype data.



CONCLUSIONS: eQTLQC provides a reliable computational workflow for eQTL analysis. It provides standard quality control and normalization as well as eQTL mapping procedures for eQTL raw data in multiple formats. The source code, demo data, and instructions are freely available at https://github.com/stormlovetao/eQTLQC .},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid33958783,

title = {Genome-wide survival study identifies a novel synaptic locus and polygenic score for cognitive progression in Parkinson's disease},

author = {G Liu and J Peng and Z Liao and JJ Locascio and JC Corvol and F Zhu and X Dong and J Maple-Grødem and MC Campbell and A Elbaz and S Lesage and A Brice and G Mangone and JH Growdon and AY Hung and MA Schwarzschild and MT Hayes and AM Wills and TM Herrington and B Ravina and I Shoulson and P Taba and S Kõks and TG Beach and F Cormier-Dequaire and G Alves and O Tysnes and JS Perlmutter and P Heutink and SS Amr and JJ van Hilten and M Kasten and B Mollenhauer and C Trenkwalder and C Klein and RA Barker and CH Williams-Gray and J Marinus and International Genetics of Parkinson Disease Progression (IGPP) Consortium and CR Scherzer},

doi = {10.1038/s41588-021-00847-6},

issn = {1546-1718},

year  = {2021},

date = {2021-06-01},

urldate = {2021-06-01},

journal = {Nature Genetics},

volume = {53},

number = {6},

pages = {787--793},

abstract = {A key driver of patients' well-being and clinical trials for Parkinson's disease (PD) is the course that the disease takes over time (progression and prognosis). To assess how genetic variation influences the progression of PD over time to dementia, a major determinant for quality of life, we performed a longitudinal genome-wide survival study of 11.2 million variants in 3,821 patients with PD over 31,053 visits. We discover RIMS2 as a progression locus and confirm this in a replicate population (hazard ratio (HR) = 4.77, P = 2.78 × 10), identify suggestive evidence for TMEM108 (HR = 2.86, P = 2.09 × 10) and WWOX (HR = 2.12, P = 2.37 × 10) as progression loci, and confirm associations for GBA (HR = 1.93, P = 0.0002) and APOE (HR = 1.48, P = 0.001). Polygenic progression scores exhibit a substantial aggregate association with dementia risk, while polygenic susceptibility scores are not predictive. This study identifies a novel synaptic locus and polygenic score for cognitive disease progression in PD and proposes diverging genetic architectures of progression and susceptibility.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{10.1093/bioinformatics/btab385b,

title = {powerEQTL: An R package and shiny application for sample size and power calculation of bulk tissue and single-cell eQTL analysis},

author = {X Dong and X Li and TW Chang and CR Scherzer and ST Weiss and W Qiu},

url = {https://bwhbioinfo.shinyapps.io/powerEQTL/},

doi = {10.1093/bioinformatics/btab385},

year  = {2021},

date = {2021-05-17},

journal = {Bioinformatics},

abstract = {Genome-wide association studies (GWAS) have revealed thousands of genetic loci for common diseases. One of the main challenges in the post-GWAS era is to understand the causality of the genetic variants. Expression quantitative trait locus (eQTL) analysis is an effective way to address this question by examining the relationship between gene expression and genetic variation in a sufficiently powered cohort. However, it is frequently a challenge to determine the sample size at which a variant with a specific allele frequency will be detected to associate with gene expression with sufficient power. This is a particularly difficult task for single-cell RNAseq studies. Therefore, a user-friendly tool to estimate statistical power for eQTL analyses in both bulk tissue and single-cell data is needed. Here, we presented an R package called powerEQTL with flexible functions to estimate power, minimal sample size, or detectable minor allele frequency for both bulk tissue and single-cell eQTL analysis. A user-friendly, program-free web application is also provided, allowing users to calculate and visualize the parameters interactively.The powerEQTL R package source code and online tutorial are freely available at CRAN: https://cran.r-project.org/web/packages/powerEQTL/. The R shiny application is publicly hosted at https://bwhbioinfo.shinyapps.io/powerEQTL/.Supplementary data are available at Bioinformatics online.},

note = {btab385},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{iwaki2020accelerating,

title = {Accelerating Medicines Partnership: Parkinson’s Disease. Genetic Resource},

author = {H Iwaki and H Leonard and M Makarious and M Bookman and B Landin and D Vismer and B Casey and R Gibbs and D Hernandez and C Blauwendraat and D Vitale and Y Song and D Kumar and C Dalgard and M Sadeghi and X Dong and L Misquitta and S Scholz and C Scherzer and M Nalls and S Biswas and A Singleton and Uniformed Services University of the Health Sciences Associates and AMP PD Whole Genome Sequencing Working Group and AMP PD consortium},

url = {https://pubmed.ncbi.nlm.nih.gov/33960523/},

doi = {10.1002/mds.28549},

year  = {2021},

date = {2021-05-07},

journal = {Movement Disorders},

publisher = {Cold Spring Harbor Laboratory Press},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid33969380,

title = {Review of multi-omics data resources and integrative analysis for human brain disorders},

author = {X Dong and C Liu and M Dozmorov},

url = {https://bioinformatics.bwh.harvard.edu/wp-content/uploads/2021/05/elab024.pdf},

doi = {10.1093/bfgp/elab024},

year  = {2021},

date = {2021-05-01},

journal = {Briefings of Functional Genomics},

abstract = {In the last decade, massive omics datasets have been generated for human brain research. It is evolving so fast that a timely update is urgently needed. In this review, we summarize the main multi-omics data resources for the human brains of both healthy controls and neuropsychiatric disorders, including schizophrenia, autism, bipolar disorder, Alzheimer's disease, Parkinson's disease, progressive supranuclear palsy, etc. We also review the recent development of single-cell omics in brain research, such as single-nucleus RNA-seq, single-cell ATAC-seq and spatial transcriptomics. We further investigate the integrative multi-omics analysis methods for both tissue and single-cell data. Finally, we discuss the limitations and future directions of the multi-omics study of human brain disorders.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid33884653,

title = {Genetic Modifiers of Age at Onset for Parkinson's Disease in Asians: A Genome-Wide Association Study},

author = {C Li and R Ou and Y Chen and X Gu and Q Wei and B Cao and L Zhang and Y Hou and K Liu and X Chen and W Song and B Zhao and Y Wu and T Li and X Dong and H Shang},

url = {https://pubmed.ncbi.nlm.nih.gov/33884653/},

doi = {10.1002/mds.28621},

year  = {2021},

date = {2021-04-21},

journal = {Movement Disorders},

abstract = {Background: Age at onset (AAO) is an essential feature of Parkinson's disease (PD) and can help predict disease progression and mortality. Identification of genetic variants influencing AAO of PD could lead to a better understanding of the disease's biological mechanism and provide clinical guidance. However, genetic determinants for AAO of PD remain mostly unknown, especially in the Asian population.



Objectives: To identify genetic determinants for AAO of PD in the Asian population.



Methods: We performed a genome-wide association meta-analysis on AAO of PD in 5166 Chinese patients with PD (Ndiscovery = 3628, Nreplication = 1538). We then conducted a further cross-ethnic meta-analysis using our results and summary statistics for the AAO of PD from the European population.



Results: The total heritability of AAO of PD was around 0.10 ~ 0.14, similar to that (~0.11) estimated in populations of European ancestry. One novel significant intergenic locus rs9783733 (NDN; PWRN4) was identified (P = 3.14E-09, beta = 2.30, SE = 0.39). Remarkably, this variant could delay AAO of PD by ~2.43 years, with a more considerable effect on males (~3.18 years) than females (~1.45 years). The variant was suggestively significant in the cross-ethnic meta-analysis and suggested a positive selection in the East Asian population. Additionally, cross-ethnic meta-analysis identified a significant locus rs356203 in SNCA (P = 2.35E-11, beta = -0.71, SE = 0.01).



Conclusions: These findings improve the current understanding of the genetic etiology of AAO of PD in different ethnic groups, and provide a new target for further research on PD pathogenesis and potential therapeutic options. © 2021 International Parkinson and Movement Disorder Society.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{tokarew2020age,

title = {Age-associated insolubility of parkin in human midbrain is linked to redox balance and sequestration of reactive dopamine metabolites},

author = {J Tokarew and D Kodsi and N Lengacher and T Fehr and A Nguyen and B Shutinoski and B O'Nuallain and M Jin and J Khan and A Ng and J Li and Q Jiang and M Zhang and L Wang and R Sengupta and K Barber and A Tran and S Zandee and X Dong and C Scherzer and A Prat and E Tsai and M Takanashi and N Hattori and J Chan and L Zecca and A West and A Holmgren and L Puente and G Shaw and G Toth and J Woulfe and P Taylor and J Tomlinson and M Schlossmacher},

doi = {10.1007/s00401-021-02285-4},

year  = {2021},

date = {2021-03-10},

journal = {Acta Neuropathol.},

publisher = {Cold Spring Harbor Laboratory},

abstract = {The mechanisms by which parkin protects the adult human brain from Parkinson disease remain incompletely understood. We hypothesized that parkin cysteines participate in redox reactions and that these are reflected in its posttranslational modifications. We found that in post mortem human brain, including in the Substantia nigra, parkin is largely insoluble after age 40 years; this transition is linked to its oxidation, such as at residues Cys95 and Cys253. In mice, oxidative stress induces posttranslational modifications of parkin cysteines that lower its solubility in vivo. Similarly, oxidation of recombinant parkin by hydrogen peroxide (H2O2) promotes its insolubility and aggregate formation, and in exchange leads to the reduction of H2O2. This thiol-based redox activity is diminished by parkin point mutants, e.g., p.C431F and p.G328E. In prkn-null mice, H2O2 levels are increased under oxidative stress conditions, such as acutely by 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine toxin exposure or chronically due to a second, genetic hit; H2O2 levels are also significantly increased in parkin-deficient human brain. In dopamine toxicity studies, wild-type parkin, but not disease-linked mutants, protects human dopaminergic cells, in part through lowering H2O2. Parkin also neutralizes reactive, electrophilic dopamine metabolites via adduct formation, which occurs foremost at the primate-specific residue Cys95. Further, wild-type but not p.C95A-mutant parkin augments melanin formation in vitro. By probing sections of adult, human midbrain from control individuals with epitope-mapped, monoclonal antibodies, we found specific and robust parkin reactivity that co-localizes with neuromelanin pigment, frequently within LAMP-3/CD63+ lysosomes. We conclude that oxidative modifications of parkin cysteines are associated with protective outcomes, which include the reduction of H2O2, conjugation of reactive dopamine metabolites, sequestration of radicals within insoluble aggregates, and increased melanin formation. The loss of these complementary redox effects may augment oxidative stress during ageing in dopamine-producing cells of mutant PRKN allele carriers, thereby enhancing the risk of Parkinson's-linked neurodegeneration.

},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid33432243b,

title = {Exosome detection via the ultrafast-isolation system: EXODUS},

author = {Y Chen and Q Zhu and L Cheng and Y Wang and M Li and Q Yang and L Hu and D Lou and J Li and X Dong and L P Lee and F Liu},

url = {https://bioinformatics.bwh.harvard.edu/wp-content/uploads/2021/05/s41592-020-01034-x.pdf},

doi = {10.1038/s41592-020-01034-x},

year  = {2021},

date = {2021-02-01},

journal = {Nature Methods},

volume = {18},

number = {2},

pages = {212--218},

abstract = {Exosomes have shown great potential in disease diagnostics and therapeutics. However, current isolation approaches are burdensome and suffer from low speed, yield and purity, limiting basic research and clinical applications. Here, we describe an efficient exosome detection method via the ultrafast-isolation system (EXODUS) that allows automated label-free purification of exosomes from varied biofluids. We obtained the ultra-efficient purification of exosomes by negative pressure oscillation and double coupled harmonic oscillator-enabled membrane vibration. Our two coupled oscillators generate dual-frequency transverse waves on the membranes, enabling EXODUS to outperform other isolation techniques in speed, purity and yield. We demonstrated EXODUS by purifying exosomes from urine samples of 113 patients and validated the practical relevance in exosomal RNA profiling with the high-resolution capability and high-throughput analysis.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Dominguez-Baleon2021,

title = {Understanding the effect of smoking and drinking behavior on Parkinson's disease risk: a Mendelian randomization study},

author = {C Domínguez-Baleón and J Ong and C Scherzer and M Rentería and X Dong},

url = {https://doi.org/10.1038/s41598-021-93105-y},

doi = {10.1038/s41598-021-93105-y},

issn = {2045-2322},

year  = {2021},

date = {2021-01-01},

journal = {Scientific Reports},

volume = {11},

number = {1},

pages = {13980},

abstract = {Previous observational studies have identified correlations between Parkinson's disease (PD) risk and lifestyle factors. However, whether or not those associations are causal remains unclear. To infer causality between PD risk and smoking or alcohol intake, we conducted a two-sample Mendelian randomization study using genome-wide association study summary statistics from the GWAS & Sequencing Consortium of Alcohol and Nicotine use study (1.2 million participants) and the latest meta-analysis from the International Parkinson's Disease Genomics Consortium (37,688 PD cases and 18,618 proxy-cases). We performed sensitivity analyses, including testing for pleiotropy with MR-Egger and MR-PRESSO, and multivariable MR modeling to account for the genetic effects of competing substance use traits on PD risk. Our results revealed causal associations of alcohol intake (OR 0.79; 95% CI 0.65–0.96; p = 0.021) and smoking continuation (which compares current vs. former smokers) (OR 0.64; 95% CI 0.46–0.89; p = 0.008) with lower PD risk. Multivariable MR analyses showed that the causal association between drinks per week and PD is unlikely due to confounding by smoking behavior. Finally, frailty analyses suggested that the causal effects of both alcohol intake and smoking continuation on PD risk estimated from MR analysis are not explained by the presence of survival bias alone. Our findings support the role of smoking as a protective factor against PD, but only when comparing current vs. former smokers. Similarly, increased alcohol intake had a protective effect over PD risk, with the alcohol dehydrogenase 1B (ADH1B) locus as a potential candidate for further investigation of the mechanisms underlying this association.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{dominguez2020genetic,

title = {Genetic evidence for protective effects of smoking and drinking behavior on Parkinson's disease: A Mendelian Randomization study},

author = {C Domínguez-Baleón and J Ong and C Scherzer and M Rentería and X Dong},

year  = {2020},

date = {2020-01-01},

journal = {medRxiv},

publisher = {Cold Spring Harbor Laboratory Press},

keywords = {},

pubstate = {forthcoming},

tppubtype = {article}

}

@article{bao2020signaling,

title = {Signaling Pathway Analysis Combined With the Strength Variations of Interactions Between Genes Under Different Conditions},

author = {Z Bao and Y Zhu and Q Ge and W Gu and X Dong and Y Bai},

year  = {2020},

date = {2020-01-01},

journal = {IEEE Access},

volume = {8},

pages = {138036--138045},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{campos2020genome,

title = {Genome-wide analyses in 1,987,836 participants identify 39 genetic loci associated with sleep apnoea},

author = {A Campos and N Ingold and Y Huang and P Kho and X Han and J Ong and L Garcia-Marin and M Law and N Martin and X Dong and G Cuellar-Partida and S MacGregor and S Aslibekyan and M Rentería},

year  = {2020},

date = {2020-01-01},

journal = {medRxiv},

publisher = {Cold Spring Harbor Laboratory Press},

keywords = {},

pubstate = {forthcoming},

tppubtype = {article}

}

@article{pmid32926651b,

title = {High-resolution analysis of differential gene expression during skeletal muscle atrophy and programmed cell death},

author = {J Tsuji and T Thomson and E Chan and C K Brown and J Oppenheimer and C Bigelow and X Dong and W E Theurkauf and Z Weng and L M Schwartz},

year  = {2020},

date = {2020-01-01},

journal = {Physiol Genomics},

volume = {52},

number = {10},

pages = {492--511},

abstract = {Skeletal muscles can undergo atrophy and/or programmed cell death (PCD) during development or in response to a wide range of insults, including immobility, cachexia, and spinal cord injury. However, the protracted nature of atrophy and the presence of multiple cell types within the tissue complicate molecular analyses. One model that does not suffer from these limitations is the intersegmental muscle (ISM) of the tobacco hawkmoth Manduca sexta. Three days before the adult eclosion (emergence) at the end of metamorphosis, the ISMs initiate a nonpathological program of atrophy that results in a 40% loss of mass. The ISMs then generate the eclosion behavior and initiate a nonapoptotic PCD during the next 30 h. We have performed a comprehensive transcriptomics analysis of all mRNAs and microRNAs throughout ISM development to better understand the molecular mechanisms that mediate atrophy and death. Atrophy involves enhanced protein catabolism and reduced expression of the genes involved in respiration, adhesion, and the contractile apparatus. In contrast, PCD involves the induction of numerous proteases, DNA methylases, membrane transporters, ribosomes, and anaerobic metabolism. These changes in gene expression are largely repressed when insects are injected with the insect steroid hormone 20-hydroxyecdysone, which delays death. The expression of the death-associated proteins may be greatly enhanced by reductions in specific microRNAs that function to repress translation. This study not only provides fundamental new insights into basic developmental processes, it may also represent a powerful resource for identifying potential diagnostic markers and molecular targets for therapeutic intervention.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{bao2019gwspia,

title = {gwSPIA: Improved Signaling Pathway Impact Analysis With Gene Weights},

author = {Z Bao and Y Zhu and Q Ge and W Gu and X Dong and Y Bai},

year  = {2019},

date = {2019-01-01},

journal = {IEEE Access},

volume = {7},

pages = {69172--69183},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid30224808,

title = {Enhancers active in dopamine neurons are a primary link between genetic variation and neuropsychiatric disease},

author = {X Dong and Z Liao and D Gritsch and Y Hadzhiev and Y Bai and J J Locascio and B Guennewig and G Liu and C Blauwendraat and T Wang and C H Adler and J C Hedreen and R L M Faull and M P Frosch and P T Nelson and P Rizzu and A A Cooper and P Heutink and T G Beach and J S Mattick and F Müller and C R Scherzer},

url = {https://bioinformatics.bwh.harvard.edu/wp-content/uploads/2021/10/s41593-018-0223-0-2.pdf},

doi = {10.1038/s41593-018-0223-0},

year  = {2018},

date = {2018-01-01},

urldate = {2018-01-01},

journal = {Nature Neuroscience},

volume = {21},

number = {10},

pages = {1482--1492},

abstract = {Enhancers function as DNA logic gates and may control specialized functions of billions of neurons. Here we show a tailored program of noncoding genome elements active in situ in physiologically distinct dopamine neurons of the human brain. We found 71,022 transcribed noncoding elements, many of which were consistent with active enhancers and with regulatory mechanisms in zebrafish and mouse brains. Genetic variants associated with schizophrenia, addiction, and Parkinson's disease were enriched in these elements. Expression quantitative trait locus analysis revealed that Parkinson's disease-associated variants on chromosome 17q21 cis-regulate the expression of an enhancer RNA in dopamine neurons. This study shows that enhancers in dopamine neurons link genetic variation to neuropsychiatric traits.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid28860381,

title = {β2-Adrenoreceptor is a regulator of the α-synuclein gene driving risk of Parkinson's disease},

author = {S Mittal and K Bjornevik and D S Im and A Flierl and X Dong and J J Locascio and K M Abo and E Long and M Jin and B Xu and Y K Xiang and J C Rochet and A Engeland and P Rizzu and P Heutink and T Bartels and D J Selkoe and B J Caldarone and M A Glicksman and V Khurana and B Schule and D S Park and T Riise and C R Scherzer},

year  = {2017},

date = {2017-01-01},

journal = {Science},

volume = {357},

number = {6354},

pages = {891--898},

abstract = {Copy number mutations implicate excess production of α-synuclein as a possibly causative factor in Parkinson's disease (PD). Using an unbiased screen targeting endogenous gene expression, we discovered that the β2-adrenoreceptor (β2AR) is a regulator of the α-synuclein gene (SNCA). β2AR ligands modulate SNCA transcription through histone 3 lysine 27 acetylation of its promoter and enhancers. Over 11 years of follow-up in 4 million Norwegians, the β2AR agonist salbutamol, a brain-penetrant asthma medication, was associated with reduced risk of developing PD (rate ratio, 0.66; 95% confidence interval, 0.58 to 0.76). Conversely, a β2AR antagonist correlated with increased risk. β2AR activation protected model mice and patient-derived cells. Thus, β2AR is linked to transcription of α-synuclein and risk of PD in a ligand-specific fashion and constitutes a potential target for therapies.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid27717005,

title = {Specifically neuropathic Gaucher's mutations accelerate cognitive decline in Parkinson's},

author = {G Liu and B Boot and J J Locascio and I E Jansen and S Winder-Rhodes and S Eberly and A Elbaz and A Brice and B Ravina and J J van Hilten and F Cormier-Dequaire and J C Corvol and R A Barker and P Heutink and J Marinus and C H Williams-Gray and C R Scherzer and C Scherzer and B T Hyman and A J Ivinson and A Trisini-Lipsanopoulos and D Franco and K Burke and L R Sudarsky and M T Hayes and C C Umeh and J H Growdon and M A Schwarzschild and A Y Hung and A W Flaherty and A M Wills and N I Mejia and S N Gomperts and V Khurana and D J Selkoe and T Yi and K Page and Z Liao and R Barker and T Foltynie and C H Williams-Gray and S Mason and S Winder-Rhodes and R Barker and C H Williams-Gray and D Breen and G Cummins and J Evans and S Winder-Rhodes and J C Corvol and A Brice and A Elbaz and A Mallet and M Vidailhet and A M Bonnet and C Bonnet and D Grabli and A Hartmann and S Klebe and L Lacomblez and G Mangone and F Bourdain and J P Brandel and P Derkinderen and F Durif and V Mesnage and F Pico and O Rascol and S Forlani and S Lesage and K Tahiri and J J van Hilten and J Marinus and Z Liao and K Page and D Franco and K Duong and T Yi and A Trisini-Lipsanopoulos and X Dong and L R Sudarsky and S J Hutten and S S Amr and I Shoulson and C M Tanner and A E Lang and M A Nalls},

year  = {2016},

date = {2016-11-01},

urldate = {2016-11-01},

journal = {Annals of Neurology},

volume = {80},

number = {5},

pages = {674--685},

abstract = {We hypothesized that specific mutations in the β-glucocerebrosidase gene (GBA) causing neuropathic Gaucher's disease (GD) in homozygotes lead to aggressive cognitive decline in heterozygous Parkinson's disease (PD) patients, whereas non-neuropathic GD mutations confer intermediate progression rates. A total of 2,304 patients with PD and 20,868 longitudinal visits for up to 12.8 years (median, 4.1) from seven cohorts were analyzed. Differential effects of four types of genetic variation in GBA on longitudinal cognitive decline were evaluated using mixed random and fixed effects and Cox proportional hazards models. Overall, 10.3% of patients with PD and GBA sequencing carried a mutation. Carriers of neuropathic GD mutations (1.4% of patients) had hazard ratios (HRs) for global cognitive impairment of 3.17 (95% confidence interval [CI], 1.60-6.25) and a hastened decline in Mini-Mental State Exam scores compared to noncarriers (p = 0.0009). Carriers of complex GBA alleles (0.7%) had an HR of 3.22 (95% CI, 1.18-8.73; p = 0.022). By contrast, the common, non-neuropathic N370S mutation (1.5% of patients; HR, 1.96; 95% CI, 0.92-4.18) or nonpathogenic risk variants (6.6% of patients; HR, 1.36; 95% CI, 0.89-2.05) did not reach significance. Mutations in the GBA gene pathogenic for neuropathic GD and complex alleles shift longitudinal cognitive decline in PD into "high gear." These findings suggest a relationship between specific types of GBA mutations and aggressive cognitive decline and have direct implications for improving the design of clinical trials. Ann Neurol 2016;80:674-685.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid26220939,

title = {Association between α-synuclein blood transcripts and early, neuroimaging-supported Parkinson's disease},

author = {J J Locascio and S Eberly and Z Liao and G Liu and A N Hoesing and K Duong and A Trisini-Lipsanopoulos and K Dhima and A Y Hung and A W Flaherty and M A Schwarzschild and M T Hayes and A M Wills and U Shivraj Sohur and N I Mejia and D J Selkoe and D Oakes and I Shoulson and X Dong and K Marek and B Zheng and A Ivinson and B T Hyman and J H Growdon and L R Sudarsky and M G Schlossmacher and B Ravina and C R Scherzer},

year  = {2015},

date = {2015-09-01},

journal = {Brain},

volume = {138},

number = {Pt 9},

pages = {2659--2671},

abstract = {There are no cures for neurodegenerative diseases and this is partially due to the difficulty of monitoring pathogenic molecules in patients during life. The Parkinson's disease gene α-synuclein (SNCA) is selectively expressed in blood cells and neurons. Here we show that SNCA transcripts in circulating blood cells are paradoxically reduced in early stage, untreated and dopamine transporter neuroimaging-supported Parkinson's disease in three independent regional, national, and international populations representing 500 cases and 363 controls and on three analogue and digital platforms with P < 0.0001 in meta-analysis. Individuals with SNCA transcripts in the lowest quartile of counts had an odds ratio for Parkinson's disease of 2.45 compared to individuals in the highest quartile. Disease-relevant transcript isoforms were low even near disease onset. Importantly, low SNCA transcript abundance predicted cognitive decline in patients with Parkinson's disease during up to 5 years of longitudinal follow-up. This study reveals a consistent association of reduced SNCA transcripts in accessible peripheral blood and early-stage Parkinson's disease in 863 participants and suggests a clinical role as potential predictor of cognitive decline. Moreover, the three independent biobank cohorts provide a generally useful platform for rapidly validating any biological marker of this common disease.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid25480889,

title = {Epigenetic dysregulation of hairy and enhancer of split 4 (HES4) is associated with striatal degeneration in postmortem Huntington brains},

author = {G Bai and I Cheung and H P Shulha and J E Coelho and P Li and X Dong and M Jakovcevski and Y Wang and A Grigorenko and Y Jiang and A Hoss and K Patel and M Zheng and E Rogaev and R H Myers and Z Weng and S Akbarian and J F Chen},

year  = {2015},

date = {2015-03-01},

journal = {Hum Mol Genet},

volume = {24},

number = {5},

pages = {1441--1456},

abstract = {To investigate epigenetic contributions to Huntington's disease (HD) pathogenesis, we carried out genome-wide mapping of the transcriptional mark, trimethyl-histone H3-lysine 4 (H3K4me3) in neuronal nuclei extracted from prefrontal cortex of HD cases and controls using chromatin immunoprecipitation followed by deep-sequencing. Neuron-specific mapping of the genome-wide distribution of H3K4me3 revealed 136 differentially enriched loci associated with genes implicated in neuronal development and neurodegeneration, including GPR3, TMEM106B, PDIA6 and the Notch signaling genes hairy and enhancer of split 4 (HES4) and JAGGED2, supporting the view that the neuronal epigenome is affected in HD. Importantly, loss of H3K4me3 at CpG-rich sequences on the HES4 promoter was associated with excessive DNA methylation, reduced binding of nuclear proteins to the methylated region and altered expression of HES4 and HES4 targeted genes MASH1 and P21 involved in striatal development. Moreover, hypermethylation of HES4 promoter sequences was strikingly correlated with measures of striatal degeneration and age-of-onset in a cohort of 25 HD brains (r = 0.56},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid26636336,

title = {The Role of H3K4me3 in Transcriptional Regulation Is Altered in Huntington's Disease},

author = {X Dong and J Tsuji and A Labadorf and P Roussos and J F Chen and R H Myers and S Akbarian and Z Weng},

year  = {2015},

date = {2015-01-01},

journal = {PLoS One},

volume = {10},

number = {12},

pages = {e0144398},

abstract = {Huntington's disease (HD) is an autosomal-dominant neurodegenerative disorder resulting from expansion of CAG repeats in the Huntingtin (HTT) gene. Previous studies have shown mutant HTT can alter expression of genes associated with dysregulated epigenetic modifications. One of the most widely studied chromatin modifications is trimethylated lysine 4 of histone 3 (H3K4me3). Here, we conducted the first comprehensive study of H3K4me3 ChIP-sequencing in neuronal chromatin from the prefrontal cortex of six HD cases and six non-neurologic controls, and its association with gene expression measured by RNA-sequencing. We detected 2,830 differentially enriched H3K4me3 peaks between HD and controls, with 55% of them down-regulated in HD. Although H3K4me3 signals are expected to be associated with mRNA levels, we found an unexpected discordance between altered H3K4me3 peaks and mRNA levels. Gene ontology (GO) term enrichment analysis of the genes with differential H3K4me3 peaks, revealed statistically significantly enriched GO terms only in the genes with down-regulated signals in HD. The most frequently implicated biological process terms are organ morphogenesis and positive regulation of gene expression. More than 9,000 H3K4me3 peaks were located not near any recognized transcription start sites and approximately 36% of these "distal" peaks co-localized to known enhancer sites. Six transcription factors and chromatin remodelers are differentially enriched in HD H3K4me3 distal peaks, including EZH2 and SUZ12, two core subunits of the polycomb repressive complex 2 (PRC2). Moreover, PRC2 repressive state was significantly depleted in HD-enriched peaks, suggesting the epigenetic role of PRC2 inhibition associated with up-regulated H3K4me3 in Huntington's disease. In summary, our study provides new insights into transcriptional dysregulation of Huntington's disease by analyzing the differentiation of H3K4me3 enrichment.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid24531765,

title = {Two independent transcription initiation codes overlap on vertebrate core promoters},

author = {V Haberle and N Li and Y Hadzhiev and C Plessy and C Previti and C Nepal and J Gehrig and X Dong and A Akalin and A M Suzuki and W F J van IJcken and O Armant and M Ferg and U Strähle and P Carninci and F Müller and B Lenhard},

year  = {2014},

date = {2014-03-01},

journal = {Nature},

volume = {507},

number = {7492},

pages = {381--385},

abstract = {A core promoter is a stretch of DNA surrounding the transcription start site (TSS) that integrates regulatory inputs and recruits general transcription factors to initiate transcription. The nature and causative relationship of the DNA sequence and chromatin signals that govern the selection of most TSSs by RNA polymerase II remain unresolved. Maternal to zygotic transition represents the most marked change of the transcriptome repertoire in the vertebrate life cycle. Early embryonic development in zebrafish is characterized by a series of transcriptionally silent cell cycles regulated by inherited maternal gene products: zygotic genome activation commences at the tenth cell cycle, marking the mid-blastula transition. This transition provides a unique opportunity to study the rules of TSS selection and the hierarchy of events linking transcription initiation with key chromatin modifications. We analysed TSS usage during zebrafish early embryonic development at high resolution using cap analysis of gene expression, and determined the positions of H3K4me3-marked promoter-associated nucleosomes. Here we show that the transition from the maternal to zygotic transcriptome is characterized by a switch between two fundamentally different modes of defining transcription initiation, which drive the dynamic change of TSS usage and promoter shape. A maternal-specific TSS selection, which requires an A/T-rich (W-box) motif, is replaced with a zygotic TSS selection grammar characterized by broader patterns of dinucleotide enrichments, precisely aligned with the first downstream (+1) nucleosome. The developmental dynamics of the H3K4me3-marked nucleosomes reveal their DNA-sequence-associated positioning at promoters before zygotic transcription and subsequent transcription-independent adjustment to the final position downstream of the zygotic TSS. The two TSS-defining grammars coexist, often physically overlapping, in core promoters of constitutively expressed genes to enable their expression in the two regulatory environments. The dissection of overlapping core promoter determinants represents a framework for future studies of promoter structure and function across different regulatory contexts.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid24586208,

title = {MicroRNAs located in the Hox gene clusters are implicated in huntington's disease pathogenesis},

author = {A G Hoss and V K Kartha and X Dong and J C Latourelle and A Dumitriu and T C Hadzi and M E Macdonald and J F Gusella and S Akbarian and J F Chen and Z Weng and R H Myers},

year  = {2014},

date = {2014-02-01},

journal = {PLoS Genet},

volume = {10},

number = {2},

pages = {e1004188},

abstract = {Transcriptional dysregulation has long been recognized as central to the pathogenesis of Huntington's disease (HD). MicroRNAs (miRNAs) represent a major system of post-transcriptional regulation, by either preventing translational initiation or by targeting transcripts for storage or for degradation. Using next-generation miRNA sequencing in prefrontal cortex (Brodmann Area 9) of twelve HD and nine controls, we identified five miRNAs (miR-10b-5p, miR-196a-5p, miR-196b-5p, miR-615-3p and miR-1247-5p) up-regulated in HD at genome-wide significance (FDR q-value<0.05). Three of these, miR-196a-5p, miR-196b-5p and miR-615-3p, were expressed at near zero levels in control brains. Expression was verified for all five miRNAs using reverse transcription quantitative PCR and all but miR-1247-5p were replicated in an independent sample (8HD/8C). Ectopic miR-10b-5p expression in PC12 HTT-Q73 cells increased survival by MTT assay and cell viability staining suggesting increased expression may be a protective response. All of the miRNAs but miR-1247-5p are located in intergenic regions of Hox clusters. Total mRNA sequencing in the same samples identified fifteen of 55 genes within the Hox cluster gene regions as differentially expressed in HD, and the Hox genes immediately adjacent to the four Hox cluster miRNAs as up-regulated. Pathway analysis of mRNA targets of these miRNAs implicated functions for neuronal differentiation, neurite outgrowth, cell death and survival. In regression models among the HD brains, huntingtin CAG repeat size, onset age and age at death were independently found to be inversely related to miR-10b-5p levels. CAG repeat size and onset age were independently inversely related to miR-196a-5p, onset age was inversely related to miR-196b-5p and age at death was inversely related to miR-615-3p expression. These results suggest these Hox-related miRNAs may be involved in neuroprotective response in HD. Recently, miRNAs have shown promise as biomarkers for human diseases and given their relationship to disease expression, these miRNAs are biomarker candidates in HD.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wang201377,

title = {77 Sequence features and chromatin structure around the genomic regions bound by 119 human transcription factors},

author = {J Wang and J Zhuang and S Iyer and X Lin and T Whitfield and M Greven and B Pierce and X Dong and A Kundaje and Y Cheng and O Rando and E Birney and R Myers and W Noble and M Snyder and Z Weng},

year  = {2013},

date = {2013-01-01},

journal = {Journal of Biomolecular Structure and Dynamics},

volume = {31},

number = {sup1},

pages = {49--50},

publisher = {Routledge},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid23203885,

title = {Factorbook.org: a Wiki-based database for transcription factor-binding data generated by the ENCOĐE consortium},

author = {J Wang and J Zhuang and S Iyer and X Y Lin and M C Greven and B H Kim and J Moore and B G Pierce and X Dong and D Virgil and E Birney and J H Hung and Z Weng},

year  = {2013},

date = {2013-01-01},

journal = {Nucleic Acids Res},

volume = {41},

number = {Database issue},

pages = {D171--176},

abstract = {The Encyclopedia of DNA Elements (ENCODE) consortium aims to identify all functional elements in the human genome including transcripts, transcriptional regulatory regions, along with their chromatin states and DNA methylation patterns. The ENCODE project generates data utilizing a variety of techniques that can enrich for regulatory regions, such as chromatin immunoprecipitation (ChIP), micrococcal nuclease (MNase) digestion and DNase I digestion, followed by deeply sequencing the resulting DNA. As part of the ENCODE project, we have developed a Web-accessible repository accessible at http://factorbook.org. In Wiki format, factorbook is a transcription factor (TF)-centric repository of all ENCODE ChIP-seq datasets on TF-binding regions, as well as the rich analysis results of these data. In the first release, factorbook contains 457 ChIP-seq datasets on 119 TFs in a number of human cell lines, the average profiles of histone modifications and nucleosome positioning around the TF-binding regions, sequence motifs enriched in the regions and the distance and orientation preferences between motif sites.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid23523368,

title = {An ancient transcription factor initiates the burst of piRNA production during early meiosis in mouse testes},

author = {X Z Li and C K Roy and X Dong and E Bolcun-Filas and J Wang and B W Han and J Xu and M J Moore and J C Schimenti and Z Weng and P D Zamore},

year  = {2013},

date = {2013-01-01},

journal = {Mol Cell},

volume = {50},

number = {1},

pages = {67--81},

abstract = {Animal germ cells produce PIWI-interacting RNAs (piRNAs), small silencing RNAs that suppress transposons and enable gamete maturation. Mammalian transposon-silencing piRNAs accumulate early in spermatogenesis, whereas pachytene piRNAs are produced later during postnatal spermatogenesis and account for >95% of all piRNAs in the adult mouse testis. Mutants defective for pachytene piRNA pathway proteins fail to produce mature sperm, but neither the piRNA precursor transcripts nor the trigger for pachytene piRNA production is known. Here, we show that the transcription factor A-MYB initiates pachytene piRNA production. A-MYB drives transcription of both pachytene piRNA precursor RNAs and the mRNAs for core piRNA biogenesis factors including MIWI, the protein through which pachytene piRNAs function. A-MYB regulation of piRNA pathway proteins and piRNA genes creates a coherent feedforward loop that ensures the robust accumulation of pachytene piRNAs. This regulatory circuit, which can be detected in rooster testes, likely predates the divergence of birds and mammals.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid23566087,

title = {The correlation between histone modifications and gene expression},

author = {X Dong and Z Weng},

year  = {2013},

date = {2013-01-01},

journal = {Epigenomics},

volume = {5},

number = {2},

pages = {113--116},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid22955990,

title = {Sequence features and chromatin structure around the genomic regions bound by 119 human transcription factors},

author = {J Wang and J Zhuang and S Iyer and X Lin and T W Whitfield and M C Greven and B G Pierce and X Dong and A Kundaje and Y Cheng and O J Rando and E Birney and R M Myers and W S Noble and M Snyder and Z Weng},

year  = {2012},

date = {2012-09-01},

journal = {Genome Res},

volume = {22},

number = {9},

pages = {1798--1812},

abstract = {Chromatin immunoprecipitation coupled with high-throughput sequencing (ChIP-seq) has become the dominant technique for mapping transcription factor (TF) binding regions genome-wide. We performed an integrative analysis centered around 457 ChIP-seq data sets on 119 human TFs generated by the ENCODE Consortium. We identified highly enriched sequence motifs in most data sets, revealing new motifs and validating known ones. The motif sites (TF binding sites) are highly conserved evolutionarily and show distinct footprints upon DNase I digestion. We frequently detected secondary motifs in addition to the canonical motifs of the TFs, indicating tethered binding and cobinding between multiple TFs. We observed significant position and orientation preferences between many cobinding TFs. Genes specifically expressed in a cell line are often associated with a greater occurrence of nearby TF binding in that cell line. We observed cell-line-specific secondary motifs that mediate the binding of the histone deacetylase HDAC2 and the enhancer-binding protein EP300. TF binding sites are located in GC-rich, nucleosome-depleted, and DNase I sensitive regions, flanked by well-positioned nucleosomes, and many of these features show cell type specificity. The GC-richness may be beneficial for regulating TF binding because, when unoccupied by a TF, these regions are occupied by nucleosomes in vivo. We present the results of our analysis in a TF-centric web repository Factorbook (http://factorbook.org) and will continually update this repository as more ENCODE data are generated.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid22955978,

title = {Understanding transcriptional regulation by integrative analysis of transcription factor binding data},

author = {C Cheng and R Alexander and R Min and J Leng and K Y Yip and J Rozowsky and K K Yan and X Dong and S Djebali and Y Ruan and C A Davis and P Carninci and T Lassman and T R Gingeras and R Guigó and E Birney and Z Weng and M Snyder and M Gerstein},

year  = {2012},

date = {2012-09-01},

journal = {Genome Res},

volume = {22},

number = {9},

pages = {1658--1667},

abstract = {Statistical models have been used to quantify the relationship between gene expression and transcription factor (TF) binding signals. Here we apply the models to the large-scale data generated by the ENCODE project to study transcriptional regulation by TFs. Our results reveal a notable difference in the prediction accuracy of expression levels of transcription start sites (TSSs) captured by different technologies and RNA extraction protocols. In general, the expression levels of TSSs with high CpG content are more predictable than those with low CpG content. For genes with alternative TSSs, the expression levels of downstream TSSs are more predictable than those of the upstream ones. Different TF categories and specific TFs vary substantially in their contributions to predicting expression. Between two cell lines, the differential expression of TSS can be precisely reflected by the difference of TF-binding signals in a quantitative manner, arguing against the conventional on-and-off model of TF binding. Finally, we explore the relationships between TF-binding signals and other chromatin features such as histone modifications and DNase hypersensitivity for determining expression. The models imply that these features regulate transcription in a highly coordinated manner.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid22950368,

title = {Modeling gene expression using chromatin features in various cellular contexts},

author = {X Dong and M C Greven and A Kundaje and S Djebali and J B Brown and C Cheng and T R Gingeras and M Gerstein and R Guigó and E Birney and Z Weng},

year  = {2012},

date = {2012-06-01},

journal = {Genome Biol},

volume = {13},

number = {9},

pages = {R53},

abstract = {Previous work has demonstrated that chromatin feature levels correlate with gene expression. The ENCODE project enables us to further explore this relationship using an unprecedented volume of data. Expression levels from more than 100,000 promoters were measured using a variety of high-throughput techniques applied to RNA extracted by different protocols from different cellular compartments of several human cell lines. ENCODE also generated the genome-wide mapping of eleven histone marks, one histone variant, and DNase I hypersensitivity sites in seven cell lines. We built a novel quantitative model to study the relationship between chromatin features and expression levels. Our study not only confirms that the general relationships found in previous studies hold across various cell lines, but also makes new suggestions about the relationship between chromatin features and gene expression levels. We found that expression status and expression levels can be predicted by different groups of chromatin features, both with high accuracy. We also found that expression levels measured by CAGE are better predicted than by RNA-PET or RNA-Seq, and different categories of chromatin features are the most predictive of expression for different RNA measurement methods. Additionally, PolyA+ RNA is overall more predictable than PolyA- RNA among different cell compartments, and PolyA+ cytosolic RNA measured with RNA-Seq is more predictable than PolyA+ nuclear RNA, while the opposite is true for PolyA- RNA. Our study provides new insights into transcriptional regulation by analyzing chromatin features in different cellular contexts.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{encode2012integrated,

title = {An integrated encyclopedia of DNA elements in the human genome},

author = {ENCODE Project Consortium and others},

year  = {2012},

date = {2012-01-01},

journal = {Nature},

abstract = {The human genome encodes the blueprint of life, but the function of the vast majority of its nearly three billion bases is unknown. The Encyclopedia of DNA Elements (ENCODE) project has systematically mapped regions of transcription, transcription factor association, chromatin structure and histone modification. These data enabled us to assign biochemical functions for 80% of the genome, in particular outside of the well-studied protein-coding regions. Many discovered candidate regulatory elements are physically associated with one another and with expressed genes, providing new insights into the mechanisms of gene regulation. The newly identified elements also show a statistical correspondence to sequence variants linked to human disease, and can thereby guide interpretation of this variation. Overall, the project provides new insights into the organization and regulation of our genes and genome, and is an expansive resource of functional annotations for biomedical research.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid22206586,

title = {Making enhancers from spare parts of the genome},

author = {D Fredman and X Dong and B Lenhard},

year  = {2011},

date = {2011-12-01},

journal = {Genome Biol},

volume = {12},

number = {12},

pages = {138},

abstract = {New studies show that novel long-range enhancers of developmental genes can emerge by exaptation of protein-coding sequences with no previous regulatory function.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid22196727,

title = {Mbd3/NURD complex regulates expression of 5-hydroxymethylcytosine marked genes in embryonic stem cells},

author = {O Yildirim and R Li and J H Hung and P B Chen and X Dong and L S Ee and Z Weng and O J Rando and T G Fazzio},

year  = {2011},

date = {2011-12-01},

journal = {Cell},

volume = {147},

number = {7},

pages = {1498--1510},

abstract = {Numerous chromatin regulators are required for embryonic stem (ES) cell self-renewal and pluripotency, but few have been studied in detail. Here, we examine the roles of several chromatin regulators whose loss affects the pluripotent state of ES cells. We find that Mbd3 and Brg1 antagonistically regulate a common set of genes by regulating promoter nucleosome occupancy. Furthermore, both Mbd3 and Brg1 play key roles in the biology of 5-hydroxymethylcytosine (5hmC): Mbd3 colocalizes with Tet1 and 5hmC in vivo, Mbd3 knockdown preferentially affects expression of 5hmC-marked genes, Mbd3 localization is Tet1-dependent, and Mbd3 preferentially binds to 5hmC relative to 5-methylcytosine in vitro. Finally, both Mbd3 and Brg1 are themselves required for normal levels of 5hmC in vivo. Together, our results identify an effector for 5hmC, and reveal that control of gene expression by antagonistic chromatin regulators is a surprisingly common regulatory strategy in ES cells.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{encode2011user,

title = {A user’s guide to the encyclopedia of DNA elements (ENCODE)},

author = {ENCODE Project Consortium and others},

year  = {2011},

date = {2011-01-01},

journal = {PLoS Biol},

volume = {9},

number = {4},

pages = {e1001046},

abstract = {The mission of the Encyclopedia of DNA Elements (ENCODE) Project is to enable the scientific and medical communities to interpret the human genome sequence and apply it to understand human biology and improve health. The ENCODE Consortium is integrating multiple technologies and approaches in a collective effort to discover and define the functional elements encoded in the human genome, including genes, transcripts, and transcriptional regulatory regions, together with their attendant chromatin states and DNA methylation patterns. In the process, standards to ensure high-quality data have been implemented, and novel algorithms have been developed to facilitate analysis. Data and derived results are made available through a freely accessible database. Here we provide an overview of the project and the resources it is generating and illustrate the application of ENCODE data to interpret the human genome.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wang2011genome,

title = {Genome-wide mapping of the binding sites of 119 human transcription factors},

author = {J Wang and J Zhuang and S Iyer and X Lin and T Whitfield and M Greven and S Aldred and N Trinklein and X Dong and A Kundaje and Y Cheng and O Rando and E Birney and R Myers and W Noble and M Snyder and Z Weng

},

year  = {2011},

date = {2011-01-01},

journal = {Submitted, NCP010},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid19969543,

title = {Exonic remnants of whole-genome duplication reveal cis-regulatory function of coding exons},

author = {X Dong and P Navratilova and D Fredman and Ø Drivenes and T S Becker and B Lenhard},

url = {https://pubmed.ncbi.nlm.nih.gov/19969543/},

year  = {2010},

date = {2010-03-01},

urldate = {2010-03-01},

journal = {Nucleic Acids Res},

volume = {38},

number = {4},

pages = {1071--1085},

abstract = {Using a comparative genomics approach to reconstruct the fate of genomic regulatory blocks (GRBs) and identify exonic remnants that have survived the disappearance of their host genes after whole-genome duplication (WGD) in teleosts, we discover a set of 38 candidate cis-regulatory coding exons (RCEs) with predicted target genes. These elements demonstrate evolutionary separation of overlapping protein-coding and regulatory information after WGD in teleosts. We present evidence that the corresponding mammalian exons are still under both coding and non-coding selection pressure, are more conserved than other protein coding exons in the host gene and several control sets, and share key characteristics with highly conserved non-coding elements in the same regions. Their dual function is corroborated by existing experimental data. Additionally, we show examples of human exon remnants stemming from the vertebrate 2R WGD. Our findings suggest that long-range cis-regulatory inputs for developmental genes are not limited to non-coding regions, but can also overlap the coding sequence of unrelated genes. Thus, exonic regulatory elements in GRBs might be functionally equivalent to those in non-coding regions, calling for a re-evaluation of the sequence space in which to look for long-range regulatory elements and experimentally test their activity.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid20122234,

title = {Translog, a web browser for studying the expression divergence of homologous genes},

author = {X Dong and A Akalin and Y Sharma and B Lenhard},

url = {https://pubmed.ncbi.nlm.nih.gov/20122234/},

year  = {2010},

date = {2010-01-01},

urldate = {2010-01-01},

journal = {BMC Bioinformatics},

volume = {11 Suppl 1},

pages = {S59},

abstract = {Increasing amount of data from comparative genomics, and newly developed technologies producing accurate gene expression data facilitate the study of the expression divergence of homologous genes. Previous studies have individually highlighted factors that contribute to the expression divergence of duplicate genes, e.g. promoter changes, exon structure heterogeneity, asymmetric histone modifications and genomic neighborhood conservation. However, there is a lack of a tool to integrate multiple factors and visualize their variety among homologous genes in a straightforward way. We introduce Translog (a web-based tool for Transcriptome comparison of homologous genes) that assists in the comparison of homologous genes by displaying the loci in three different views: promoter view for studying the sharing/turnover of transcription initiations, exon structure for displaying the exon-intron structure changes, and genomic neighborhood to show the macro-synteny conservation in a larger scale. CAGE data for transcription initiation are mapped for each transcript and can be used to study transcription turnover and expression changes. Alignment anchors between homologous loci can be used to define the precise homologous transcripts. We demonstrate how these views can be used to visualize the changes of homologous genes during evolution, particularly after the 2R and 3R whole genome duplication. We have developed a web-based tool for assisting in the transcriptome comparison of homologous genes, facilitating the study of expression divergence.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{dong2009brainstorm,

title = {The brainstorm},

author = {X Dong},

url = {https://bioinformatics.bwh.harvard.edu/wp-content/uploads/2021/10/2009.IEEEpotential_brainstorm.pdf},

year  = {2009},

date = {2009-01-01},

urldate = {2009-01-01},

journal = {IEEE Potentials},

volume = {28},

number = {1},

pages = {8--9},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid19698106b,

title = {Synorth: exploring the evolution of synteny and long-range regulatory interactions in vertebrate genomes},

author = {X Dong and D Fredman and B Lenhard},

url = {https://pubmed.ncbi.nlm.nih.gov/19698106/},

year  = {2009},

date = {2009-01-01},

urldate = {2009-01-01},

journal = {Genome Biol},

volume = {10},

number = {8},

pages = {R86},

abstract = {Genomic regulatory blocks are chromosomal regions spanned by long clusters of highly conserved noncoding elements devoted to long-range regulation of developmental genes, often immobilizing other, unrelated genes into long-lasting syntenic arrangements. Synorth http://synorth.genereg.net/ is a web resource for exploring and categorizing the syntenic relationships in genomic regulatory blocks across multiple genomes, tracing their evolutionary fate after teleost whole genome duplication at the level of genomic regulatory block loci, individual genes, and their phylogenetic context.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid19374772b,

title = {Transcriptional features of genomic regulatory blocks},

author = {A Akalin, D Fredman , E Arner, X Dong , JC Bryne, H Suzuki , CO Daub ,Y Hayashizaki, B Lenhard},

url = {https://genomebiology.biomedcentral.com/articles/10.1186/gb-2009-10-4-r38},

year  = {2009},

date = {2009-01-01},

urldate = {2009-01-01},

journal = {Genome Biol},

volume = {10},

number = {4},

pages = {R38},

abstract = {Genomic regulatory blocks (GRBs) are chromosomal regions spanned by highly conserved non-coding elements (HCNEs), most of which serve as regulatory inputs of one target gene in the region. The target genes are most often transcription factors involved in embryonic development and differentiation. GRBs often contain extensive gene deserts, as well as additional 'bystander' genes intertwined with HCNEs but whose expression and function are unrelated to those of the target gene. The tight regulation of target genes, complex arrangement of regulatory inputs, and the differential responsiveness of genes in the region call for the examination of fundamental rules governing transcriptional activity in GRBs. Here we use extensive CAGE tag mapping of transcription start sites across different human tissues and differentiation stages combined with expression data and a number of sequence and epigenetic features to discover these rules and patterns. We show evidence that GRB target genes have properties that set them apart from their bystanders as well as other genes in the genome: longer CpG islands, a higher number and wider spacing of alternative transcription start sites, and a distinct composition of transcription factor binding sites in their core/proximal promoters. Target gene expression correlates with the acetylation state of HCNEs in the region. Additionally, target gene promoters have a distinct combination of activating and repressing histone modifications in mouse embryonic stem cell lines. GRB targets are genes with a number of unique features that are the likely cause of their ability to respond to regulatory inputs from very long distances.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid18424774,

title = {Differential evolution of the 13 Atlantic salmon Hox clusters},

author = {S Mungpakdee and H C Seo and A R Angotzi and X Dong and A Akalin and D Chourrout},

url = {https://pubmed.ncbi.nlm.nih.gov/18424774/},

year  = {2008},

date = {2008-07-01},

urldate = {2008-07-01},

journal = {Mol Biol Evol},

volume = {25},

number = {7},

pages = {1333--1343},

abstract = {Hox cluster organization represents a valuable marker to study the effects of recent genome duplication in salmonid fish (25-100 Mya). Using polymerase chain reaction amplification of cDNAs, BAC library screening, and genome walking, we reconstructed 13 Hox clusters in the Atlantic salmon containing 118 Hox genes including 8 pseudogenes. Hox paralogs resulting from the genome duplication preceding the radiation of ray-finned fish have been much better preserved in salmon than in other model teleosts. The last genome duplication in the salmon lineage has been followed by the loss of 1 of the 4 HoxA clusters. Four rounds of genome duplication after the vertebrate ancestor salmon Hox clusters display the main organizational features of vertebrate Hox clusters, with Hox genes exclusively that are densely packed in the same orientation. Recently, duplicated Hox clusters have engaged a process of divergence, with several cases of pseudogenization or asymmetrical evolution of Hox gene duplicates, and a marked erosion of identity in noncoding sequences. Strikingly, the level of divergence attained strongly depends on the Hox cluster pairs rather than on the Hox genes within each cluster. It is particularly high between both HoxBb clusters and both HoxDa clusters, whereas both HoxBa clusters remained virtually identical. Positive selection on the Hox protein-coding sequences could not be detected.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}