Publications

@article{pmid37481717,

title = {Genetic pathways regulating the longitudinal acquisition of cocaine self-administration in a panel of inbred and recombinant inbred mice},

author = {Arshad H Khan and Jared R Bagley and Nathan LaPierre and Carlos Gonzalez-Figueroa and Tadeo C Spencer and Mudra Choudhury and Xinshu Xiao and Eleazar Eskin and James D Jentsch and Desmond J Smith},

doi = {10.1016/j.celrep.2023.112856},

issn = {2211-1247},

year  = {2023},

date = {2023-07-01},

journal = {Cell Rep},

volume = {42},

number = {8},

pages = {112856},

abstract = {To identify addiction genes, we evaluate intravenous self-administration of cocaine or saline in 84 inbred and recombinant inbred mouse strains over 10 days. We integrate the behavior data with brain RNA-seq data from 41 strains. The self-administration of cocaine and that of saline are genetically distinct. We maximize power to map loci for cocaine intake by using a linear mixed model to account for this longitudinal phenotype while correcting for population structure. A total of 15 unique significant loci are identified in the genome-wide association study. A transcriptome-wide association study highlights the Trpv2 ion channel as a key locus for cocaine self-administration as well as identifying 17 additional genes, including Arhgef26, Slc18b1, and Slco5a1. We find numerous instances where alternate splice site selection or RNA editing altered transcript abundance. Our work emphasizes the importance of Trpv2, an ionotropic cannabinoid receptor, for the response to cocaine.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37474948,

title = {L-GIREMI uncovers RNA editing sites in long-read RNA-seq},

author = {Zhiheng Liu and Giovanni Quinones-Valdez and Ting Fu and Elaine Huang and Mudra Choudhury and Fairlie Reese and Ali Mortazavi and Xinshu Xiao},

doi = {10.1186/s13059-023-03012-w},

issn = {1474-760X},

year  = {2023},

date = {2023-07-01},

journal = {Genome Biol},

volume = {24},

number = {1},

pages = {171},

abstract = {Although long-read RNA-seq is increasingly applied to characterize full-length transcripts it can also enable detection of nucleotide variants, such as genetic mutations or RNA editing sites, which is significantly under-explored. Here, we present an in-depth study to detect and analyze RNA editing sites in long-read RNA-seq. Our new method, L-GIREMI, effectively handles sequencing errors and read biases. Applied to PacBio RNA-seq data, L-GIREMI affords a high accuracy in RNA editing identification. Additionally, our analysis uncovered novel insights about RNA editing occurrences in single molecules and double-stranded RNA structures. L-GIREMI provides a valuable means to study nucleotide variants in long-read RNA-seq.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37027465,

title = {Widespread RNA hypoediting in schizophrenia and its relevance to mitochondrial function},

author = {Mudra Choudhury and Ting Fu and Kofi Amoah and Hyun-Ik Jun and Tracey W Chan and Sungwoo Park and David W Walker and Jae Hoon Bahn and Xinshu Xiao},

doi = {10.1126/sciadv.ade9997},

issn = {2375-2548},

year  = {2023},

date = {2023-04-01},

journal = {Sci Adv},

volume = {9},

number = {14},

pages = {eade9997},

abstract = {RNA editing, the endogenous modification of nucleic acids, is known to be altered in genes with important neurological function in schizophrenia (SCZ). However, the global profile and molecular functions of disease-associated RNA editing remain unclear. Here, we analyzed RNA editing in postmortem brains of four SCZ cohorts and uncovered a significant and reproducible trend of hypoediting in patients of European descent. We report a set of SCZ-associated editing sites via WGCNA analysis, shared across cohorts. Using massively parallel reporter assays and bioinformatic analyses, we observed that differential 3' untranslated region (3'UTR) editing sites affecting host gene expression were enriched for mitochondrial processes. Furthermore, we characterized the impact of two recoding sites in the mitofusin 1 () gene and showed their functional relevance to mitochondrial fusion and cellular apoptosis. Our study reveals a global reduction of editing in SCZ and a compelling link between editing and mitochondrial function in the disease.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36449563,

title = {Single-Cell Analysis in Lung Adenocarcinoma Implicates RNA Editing in Cancer Innate Immunity and Patient Prognosis},

author = {Tracey W Chan and Jack P Dodson and Jaron Arbet and Paul C Boutros and Xinshu Xiao},

doi = {10.1158/0008-5472.CAN-22-1062},

issn = {1538-7445},

year  = {2023},

date = {2023-02-01},

journal = {Cancer Res},

volume = {83},

number = {3},

pages = {374--385},

abstract = {RNA editing modifies single nucleotides of RNAs, regulating primary protein structure and protein abundance. In recent years, the diversity of proteins and complexity of gene regulation associated with RNA editing dysregulation has been increasingly appreciated in oncology. Large-scale shifts in editing have been observed in bulk tumors across various cancer types. However, RNA editing in single cells and individual cell types within tumors has not been explored. By profiling editing in single cells from lung adenocarcinoma biopsies, we found that the increased editing trend of bulk lung tumors was unique to cancer cells. Elevated editing levels were observed in cancer cells resistant to targeted therapy, and editing sites associated with drug response were enriched. Consistent with the regulation of antiviral pathways by RNA editing, higher editing levels in cancer cells were associated with reduced antitumor innate immune response, especially levels of natural killer cell infiltration. In addition, the level of RNA editing in cancer cells was positively associated with somatic point mutation burden. This observation motivated the definition of a new metric, RNA editing load, reflecting the amount of RNA mutations created by RNA editing. Importantly, in lung cancer, RNA editing load was a stronger predictor of patient survival than DNA mutations. This study provides the first single cell dissection of editing in cancer and highlights the significance of RNA editing load in cancer prognosis.



SIGNIFICANCE: RNA editing analysis in single lung adenocarcinoma cells uncovers RNA mutations that correlate with tumor mutation burden and cancer innate immunity and reveals the amount of RNA mutations that strongly predicts patient survival. See related commentary by Luo and Liang, p. 351.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36424375,

title = {Kinetics of mRNA nuclear export regulate innate immune response gene expression},

author = {Diane Lefaudeux and Supriya Sen and Kevin Jiang and Alexander Hoffmann and },

doi = {10.1038/s41467-022-34635-5},

issn = {2041-1723},

year  = {2022},

date = {2022-11-01},

journal = {Nat Commun},

volume = {13},

number = {1},

pages = {7197},

abstract = {The abundance and stimulus-responsiveness of mature mRNA is thought to be determined by nuclear synthesis, processing, and cytoplasmic decay. However, the rate and efficiency of moving mRNA to the cytoplasm almost certainly contributes, but has rarely been measured. Here, we investigated mRNA export rates for innate immune genes. We generated high spatio-temporal resolution RNA-seq data from endotoxin-stimulated macrophages and parameterized a mathematical model to infer kinetic parameters with confidence intervals. We find that the effective chromatin-to-cytoplasm export rate is gene-specific, varying 100-fold: for some genes, less than 5% of synthesized transcripts arrive in the cytoplasm as mature mRNAs, while others show high export efficiency. Interestingly, effective export rates do not determine temporal gene responsiveness, but complement the wide range of mRNA decay rates; this ensures similar abundances of short- and long-lived mRNAs, which form successive innate immune response expression waves.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid35961439,

title = {Improved zebra finch brain transcriptome identifies novel proteins with sex differences},

author = {Jingyan He and Ting Fu and Ling Zhang and Lucy Wanrong Gao and Michelle Rensel and Luke Remage-Healey and Stephanie A White and Gregory Gedman and Julian Whitelegge and Xinshu Xiao and Barney A Schlinger},

doi = {10.1016/j.gene.2022.146803},

issn = {1879-0038},

year  = {2022},

date = {2022-11-01},

journal = {Gene},

volume = {843},

pages = {146803},

abstract = {The zebra finch (Taeniopygia guttata), a representative oscine songbird species, has been widely studied to investigate behavioral neuroscience, most notably the neurobiological basis of vocal learning, a rare trait shared in only a few animal groups including humans. In 2019, an updated zebra finch genome annotation (bTaeGut1_v1.p) was released from the Ensembl database and is substantially more comprehensive than the first version published in 2010. In this study, we utilized the publicly available RNA-seq data generated from Illumina-based short-reads and PacBio single-molecule real-time (SMRT) long-reads to assess the bird transcriptome. To analyze the high-throughput RNA-seq data, we adopted a hybrid bioinformatic approach combining short and long-read pipelines. From our analysis, we added 220 novel genes and 8,134 transcript variants to the Ensembl annotation, and predicted a new proteome based on the refined annotation. We further validated 18 different novel proteins by using mass-spectrometry data generated from zebra finch caudal telencephalon tissue. Our results provide additional resources for future studies of zebra finches utilizing this improved bird genome annotation and proteome.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36054357,

title = {scAllele: A versatile tool for the detection and analysis of variants in scRNA-seq},

author = {Giovanni Quinones-Valdez and Ting Fu and Tracey W Chan and Xinshu Xiao},

doi = {10.1126/sciadv.abn6398},

issn = {2375-2548},

year  = {2022},

date = {2022-09-01},

journal = {Sci Adv},

volume = {8},

number = {35},

pages = {eabn6398},

abstract = {Single-cell RNA sequencing (scRNA-seq) data contain rich information at the gene, transcript, and nucleotide levels. Most analyses of scRNA-seq have focused on gene expression profiles, and it remains challenging to extract nucleotide variants and isoform-specific information. Here, we present scAllele, an integrative approach that detects single-nucleotide variants, insertions, deletions, and their allelic linkage with splicing patterns in scRNA-seq. We demonstrate that scAllele achieves better performance in identifying nucleotide variants than other commonly used tools. In addition, the read-specific variant calls by scAllele enables allele-specific splicing analysis, a unique feature not afforded by other methods. Applied to a lung cancer scRNA-seq dataset, scAllele identified variants with strong allelic linkage to alternative splicing, some of which are cancer specific and enriched in cancer-relevant pathways. scAllele represents a versatile tool to uncover multilayer information and previously unidentified biological insights from scRNA-seq data.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid35992085,

title = {Multifaceted role of RNA editing in promoting loss-of-function of PODXL in cancer},

author = {Ting Fu and Tracey W Chan and Jae Hoon Bahn and Tae-Hyung Kim and Amy C Rowat and Xinshu Xiao},

doi = {10.1016/j.isci.2022.104836},

issn = {2589-0042},

year  = {2022},

date = {2022-08-01},

journal = {iScience},

volume = {25},

number = {8},

pages = {104836},

abstract = {PODXL, a protein that is dysregulated in multiple cancers, plays an important role in promoting cancer metastasis. In this study, we report that RNA editing promotes the inclusion of a  alternative exon. The resulting edited PODXL long isoform is more prone to protease digestion and has the strongest effects on reducing cell migration and cisplatin chemoresistance among the three PODXL isoforms (short, unedited long, and edited long isoforms). Importantly, the editing level of the  recoding site and the inclusion level of the  alternative exon are strongly associated with overall patient survival in Kidney Renal Clear Cell Carcinoma (KIRC). Supported by significant enrichment of exonic RNA editing sites in alternatively spliced exons, we hypothesize that exonic RNA editing sites may enhance proteomic diversity through alternative splicing, in addition to amino acid changes, a previously under-appreciated aspect of RNA editing function.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid34494556,

title = {Lipin 1 modulates mRNA splicing during fasting adaptation in liver},

author = {Huan Wang and Tracey W Chan and Ajay A Vashisht and Brian G Drew and Anna C Calkin and Thurl E Harris and James A Wohlschlegel and Xinshu Xiao and Karen Reue},

doi = {10.1172/jci.insight.150114},

issn = {2379-3708},

year  = {2021},

date = {2021-09-01},

journal = {JCI Insight},

volume = {6},

number = {17},

abstract = {Lipin 1 regulates cellular lipid homeostasis through roles in glycerolipid synthesis (through phosphatidic acid phosphatase activity) and transcriptional coactivation. Lipin 1-deficient individuals exhibit episodic disease symptoms that are triggered by metabolic stress, such as stress caused by prolonged fasting. We sought to identify critical lipin 1 activities during fasting. We determined that lipin 1 deficiency induces widespread alternative mRNA splicing in liver during fasting, much of which is normalized by refeeding. The role of lipin 1 in mRNA splicing was largely independent of its enzymatic function. We identified interactions between lipin 1 and spliceosome proteins, as well as a requirement for lipin 1 to maintain homeostatic levels of spliceosome small nuclear RNAs and specific RNA splicing factors. In fasted Lpin1-/- liver, we identified a correspondence between alternative splicing of phospholipid biosynthetic enzymes and dysregulated phospholipid levels; splicing patterns and phospholipid levels were partly normalized by feeding. Thus, lipin 1 influences hepatic lipid metabolism through mRNA splicing, as well as through enzymatic and transcriptional activities, and fasting exacerbates the deleterious effects of lipin 1 deficiency on metabolic homeostasis.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid33092484,

title = {Extracellular microRNA 3' end modification across diverse body fluids},

author = {Kikuye Koyano and Jae Hoon Bahn and Xinshu Xiao},

doi = {10.1080/15592294.2020.1834922},

issn = {1559-2308},

year  = {2021},

date = {2021-09-01},

journal = {Epigenetics},

volume = {16},

number = {9},

pages = {1000--1015},

abstract = {microRNAs (miRNAs) are small non-coding RNAs that play critical roles in gene regulation. The presence of miRNAs in extracellular biofluids is increasingly recognized. However, most previous characterization of extracellular miRNAs focused on their overall expression levels. Alternative sequence isoforms and modifications of miRNAs were rarely considered in the extracellular space. Here, we developed a highly accurate bioinformatic method, called miNTA, to identify 3' non-templated additions (NTAs) of miRNAs using small RNA-sequencing data. Using miNTA, we conducted an in-depth analysis of miRNA 3' NTA profiles in 1047 extracellular RNA-sequencing data sets of 4 types of biofluids. This analysis identified hundreds of miRNAs with 3' uridylation or adenylation, with the former being more prevalent. Among these miRNAs, up to 53% (22%) had an average 3' uridylation (adenylation) level of at least 10% in a specific biofluid. Strikingly, we found that 3' uridylation levels enabled segregation of different types of biofluids, more effectively than overall miRNA expression levels. This observation suggests that 3' NTA levels possess fluid-specific information relatively robust to batch effects. In addition, we observed that extracellular miRNAs with 3' uridylations are enriched in processes related to angiogenesis, apoptosis, and inflammatory response, and this type of modification may stabilize base-pairing between miRNAs and their target genes. Together, our study provides a comprehensive landscape of miRNA NTAs in human biofluids, which paves way for further biomarker discoveries. The insights generated in our work built a foundation for future functional, mechanistic, and translational discoveries.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid34166378,

title = {Genetics of white color and iridophoroma in "Lemon Frost" leopard geckos},

author = {Longhua Guo and Joshua Bloom and Steve Sykes and Elaine Huang and Zain Kashif and Elise Pham and Katarina Ho and Ana Alcaraz and Xinshu Grace Xiao and Sandra Duarte-Vogel and Leonid Kruglyak},

doi = {10.1371/journal.pgen.1009580},

issn = {1553-7404},

year  = {2021},

date = {2021-06-01},

journal = {PLoS Genet},

volume = {17},

number = {6},

pages = {e1009580},

abstract = {The squamates (lizards and snakes) are close relatives of birds and mammals, with more than 10,000 described species that display extensive variation in a number of important biological traits, including coloration, venom production, and regeneration. Due to a lack of genomic tools, few genetic studies in squamates have been carried out. The leopard gecko, Eublepharis macularius, is a popular companion animal, and displays a variety of coloration patterns. We took advantage of a large breeding colony and used linkage analysis, synteny, and homozygosity mapping to investigate a spontaneous semi-dominant mutation, "Lemon Frost", that produces white coloration and causes skin tumors (iridophoroma). We localized the mutation to a single locus which contains a strong candidate gene, SPINT1, a tumor suppressor implicated in human skin cutaneous melanoma (SKCM) and over-proliferation of epithelial cells in mice and zebrafish. Our work establishes the leopard gecko as a tractable genetic system and suggests that a tumor suppressor in melanocytes in humans can also suppress tumor development in iridophores in lizards.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid33452016,

title = {Allele-specific alternative splicing and its functional genetic variants in human tissues},

author = {Kofi Amoah and Yun-Hua Esther Hsiao and Jae Hoon Bahn and Yiwei Sun and Christina Burghard and Boon Xin Tan and Ei-Wen Yang and Xinshu Xiao},

doi = {10.1101/gr.265637.120},

issn = {1549-5469},

year  = {2021},

date = {2021-03-01},

journal = {Genome Res},

volume = {31},

number = {3},

pages = {359--371},

abstract = {Alternative splicing is an RNA processing mechanism that affects most genes in human, contributing to disease mechanisms and phenotypic diversity. The regulation of splicing involves an intricate network of -regulatory elements and -acting factors. Due to their high sequence specificity, -regulation of splicing can be altered by genetic variants, significantly affecting splicing outcomes. Recently, multiple methods have been applied to understanding the regulatory effects of genetic variants on splicing. However, it is still challenging to go beyond apparent association to pinpoint functional variants. To fill in this gap, we utilized large-scale data sets of the Genotype-Tissue Expression (GTEx) project to study genetically modulated alternative splicing (GMAS) via identification of allele-specific splicing events. We demonstrate that GMAS events are shared across tissues and individuals more often than expected by chance, consistent with their genetically driven nature. Moreover, although the allelic bias of GMAS exons varies across samples, the degree of variation is similar across tissues versus individuals. Thus, genetic background drives the GMAS pattern to a similar degree as tissue-specific splicing mechanisms. Leveraging the genetically driven nature of GMAS, we developed a new method to predict functional splicing-altering variants, built upon a genotype-phenotype concordance model across samples. Complemented by experimental validations, this method predicted >1000 functional variants, many of which may alter RNA-protein interactions. Lastly, 72% of GMAS-associated SNPs were in linkage disequilibrium with GWAS-reported SNPs, and such association was enriched in tissues of relevance for specific traits/diseases. Our study enables a comprehensive view of genetically driven splicing variations in human tissues.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid33619405,

title = {Long-term maturation of human cortical organoids matches key early postnatal transitions},

author = {Aaron Gordon and Se-Jin Yoon and Stephen S Tran and Christopher D Makinson and Jin Young Park and Jimena Andersen and Alfredo M Valencia and Steve Horvath and Xinshu Xiao and John R Huguenard and Sergiu P Pașca and Daniel H Geschwind},

doi = {10.1038/s41593-021-00802-y},

issn = {1546-1726},

year  = {2021},

date = {2021-03-01},

journal = {Nat Neurosci},

volume = {24},

number = {3},

pages = {331--342},

abstract = {Human stem-cell-derived models provide the promise of accelerating our understanding of brain disorders, but not knowing whether they possess the ability to mature beyond mid- to late-fetal stages potentially limits their utility. We leveraged a directed differentiation protocol to comprehensively assess maturation in vitro. Based on genome-wide analysis of the epigenetic clock and transcriptomics, as well as RNA editing, we observe that three-dimensional human cortical organoids reach postnatal stages between 250 and 300 days, a timeline paralleling in vivo development. We demonstrate the presence of several known developmental milestones, including switches in the histone deacetylase complex and NMDA receptor subunits, which we confirm at the protein and physiological levels. These results suggest that important components of an intrinsic in vivo developmental program persist in vitro. We further map neurodevelopmental and neurodegenerative disease risk genes onto in vitro gene expression trajectories to provide a resource and webtool (Gene Expression in Cortical Organoids, GECO) to guide disease modeling.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid33106178,

title = {RNA editing in cancer impacts mRNA abundance in immune response pathways},

author = {Tracey W Chan and Ting Fu and Jae Hoon Bahn and Hyun-Ik Jun and Jae-Hyung Lee and Giovanni Quinones-Valdez and Chonghui Cheng and Xinshu Xiao},

doi = {10.1186/s13059-020-02171-4},

issn = {1474-760X},

year  = {2020},

date = {2020-10-01},

journal = {Genome Biol},

volume = {21},

number = {1},

pages = {268},

abstract = {BACKGROUND: RNA editing generates modifications to the RNA sequences, thereby increasing protein diversity and shaping various layers of gene regulation. Recent studies have revealed global shifts in editing levels across many cancer types, as well as a few specific mechanisms implicating individual sites in tumorigenesis or metastasis. However, most tumor-associated sites, predominantly in noncoding regions, have unknown functional relevance.



RESULTS: Here, we carry out integrative analysis of RNA editing profiles between epithelial and mesenchymal tumors, since epithelial-mesenchymal transition is a key paradigm for metastasis. We identify distinct editing patterns between epithelial and mesenchymal tumors in seven cancer types using TCGA data, an observation further supported by single-cell RNA sequencing data and ADAR perturbation experiments in cell culture. Through computational analyses and experimental validations, we show that differential editing sites between epithelial and mesenchymal phenotypes function by regulating mRNA abundance of their respective genes. Our analysis of RNA-binding proteins reveals ILF3 as a potential regulator of this process, supported by experimental validations. Consistent with the known roles of ILF3 in immune response, epithelial-mesenchymal differential editing sites are enriched in genes involved in immune and viral processes. The strongest target of editing-dependent ILF3 regulation is the transcript encoding PKR, a crucial player in immune and viral response.



CONCLUSIONS: Our study reports widespread differences in RNA editing between epithelial and mesenchymal tumors and a novel mechanism of editing-dependent regulation of mRNA abundance. It reveals the broad impact of RNA editing in cancer and its relevance to cancer-related immune pathways.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid32573492,

title = {p38 Mitogen-activated protein kinase regulates chamber-specific perinatal growth in heart},

author = {Tomohiro Yokota and Jin Li and Jijun Huang and Zhaojun Xiong and Qing Zhang and Tracey Chan and Yichen Ding and Christoph Rau and Kevin Sung and Shuxun Ren and Rajan Kulkarni and Tzung Hsiai and Xinshu Xiao and Marlin Touma and Susumu Minamisawa and Yibin Wang},

doi = {10.1172/JCI135859},

issn = {1558-8238},

year  = {2020},

date = {2020-10-01},

journal = {J Clin Invest},

volume = {130},

number = {10},

pages = {5287--5301},

abstract = {In the mammalian heart, the left ventricle (LV) rapidly becomes more dominant in size and function over the right ventricle (RV) after birth. The molecular regulators responsible for this chamber-specific differential growth are largely unknown. We found that cardiomyocytes in the neonatal mouse RV had lower proliferation, more apoptosis, and a smaller average size compared with the LV. This chamber-specific growth pattern was associated with a selective activation of p38 mitogen-activated protein kinase (MAPK) activity in the RV and simultaneous inactivation in the LV. Cardiomyocyte-specific deletion of both the Mapk14 and Mapk11 genes in mice resulted in loss of p38 MAPK expression and activity in the neonatal heart. Inactivation of p38 activity led to a marked increase in cardiomyocyte proliferation and hypertrophy but diminished cardiomyocyte apoptosis, specifically in the RV. Consequently, the p38-inactivated hearts showed RV-specific enlargement postnatally, progressing to pulmonary hypertension and right heart failure at the adult stage. Chamber-specific p38 activity was associated with differential expression of dual-specific phosphatases (DUSPs) in neonatal hearts, including DUSP26. Unbiased transcriptome analysis revealed that IRE1α/XBP1-mediated gene regulation contributed to p38 MAPK-dependent regulation of neonatal cardiomyocyte proliferation and binucleation. These findings establish an obligatory role of DUSP/p38/IRE1α signaling in cardiomyocytes for chamber-specific growth in the postnatal heart.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid32728249,

title = {Expanded encyclopaedias of DNA elements in the human and mouse genomes},

author = { and Jill E Moore and Michael J Purcaro and Henry E Pratt and Charles B Epstein and Noam Shoresh and Jessika Adrian and Trupti Kawli and Carrie A Davis and Alexander Dobin and Rajinder Kaul and Jessica Halow and Eric L Van Nostrand and Peter Freese and David U Gorkin and Yin Shen and Yupeng He and Mark Mackiewicz and Florencia Pauli-Behn and Brian A Williams and Ali Mortazavi and Cheryl A Keller and Xiao-Ou Zhang and Shaimae I Elhajjajy and Jack Huey and Diane E Dickel and Valentina Snetkova and Xintao Wei and Xiaofeng Wang and Juan Carlos Rivera-Mulia and Joel Rozowsky and Jing Zhang and Surya B Chhetri and Jialing Zhang and Alec Victorsen and Kevin P White and Axel Visel and Gene W Yeo and Christopher B Burge and Eric Lécuyer and David M Gilbert and Job Dekker and John Rinn and Eric M Mendenhall and Joseph R Ecker and Manolis Kellis and Robert J Klein and William S Noble and Anshul Kundaje and Roderic Guigó and Peggy J Farnham and J Michael Cherry and Richard M Myers and Bing Ren and Brenton R Graveley and Mark B Gerstein and Len A Pennacchio and Michael P Snyder and Bradley E Bernstein and Barbara Wold and Ross C Hardison and Thomas R Gingeras and John A Stamatoyannopoulos and Zhiping Weng},

doi = {10.1038/s41586-020-2493-4},

issn = {1476-4687},

year  = {2020},

date = {2020-07-01},

journal = {Nature},

volume = {583},

number = {7818},

pages = {699--710},

abstract = {The human and mouse genomes contain instructions that specify RNAs and proteins and govern the timing, magnitude, and cellular context of their production. To better delineate these elements, phase III of the Encyclopedia of DNA Elements (ENCODE) Project has expanded analysis of the cell and tissue repertoires of RNA transcription, chromatin structure and modification, DNA methylation, chromatin looping, and occupancy by transcription factors and RNA-binding proteins. Here we summarize these efforts, which have produced 5,992 new experimental datasets, including systematic determinations across mouse fetal development. All data are available through the ENCODE data portal (https://www.encodeproject.org), including phase II ENCODE and Roadmap Epigenomics data. We have developed a registry of 926,535 human and 339,815 mouse candidate cis-regulatory elements, covering 7.9 and 3.4% of their respective genomes, by integrating selected datatypes associated with gene regulation, and constructed a web-based server (SCREEN; http://screen.encodeproject.org) to provide flexible, user-defined access to this resource. Collectively, the ENCODE data and registry provide an expansive resource for the scientific community to build a better understanding of the organization and function of the human and mouse genomes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid32728248,

title = {Perspectives on ENCODE},

author = { and Michael P Snyder and Thomas R Gingeras and Jill E Moore and Zhiping Weng and Mark B Gerstein and Bing Ren and Ross C Hardison and John A Stamatoyannopoulos and Brenton R Graveley and Elise A Feingold and Michael J Pazin and Michael Pagan and Daniel A Gilchrist and Benjamin C Hitz and J Michael Cherry and Bradley E Bernstein and Eric M Mendenhall and Daniel R Zerbino and Adam Frankish and Paul Flicek and Richard M Myers},

doi = {10.1038/s41586-020-2449-8},

issn = {1476-4687},

year  = {2020},

date = {2020-07-01},

journal = {Nature},

volume = {583},

number = {7818},

pages = {693--698},

abstract = {The Encylopedia of DNA Elements (ENCODE) Project launched in 2003 with the long-term goal of developing a comprehensive map of functional elements in the human genome. These included genes, biochemical regions associated with gene regulation (for example, transcription factor binding sites, open chromatin, and histone marks) and transcript isoforms. The marks serve as sites for candidate cis-regulatory elements (cCREs) that may serve functional roles in regulating gene expression. The project has been extended to model organisms, particularly the mouse. In the third phase of ENCODE, nearly a million and more than 300,000 cCRE annotations have been generated for human and mouse, respectively, and these have provided a valuable resource for the scientific community.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid32003773,

title = {Statistical inference of differential RNA-editing sites from RNA-sequencing data by hierarchical modeling},

author = {Stephen S Tran and Qing Zhou and Xinshu Xiao},

doi = {10.1093/bioinformatics/btaa066},

issn = {1367-4811},

year  = {2020},

date = {2020-05-01},

journal = {Bioinformatics},

volume = {36},

number = {9},

pages = {2796--2804},

abstract = {MOTIVATION: RNA-sequencing (RNA-seq) enables global identification of RNA-editing sites in biological systems and disease. A salient step in many studies is to identify editing sites that statistically associate with treatment (e.g. case versus control) or covary with biological factors, such as age. However, RNA-seq has technical features that incumbent tests (e.g. t-test and linear regression) do not consider, which can lead to false positives and false negatives.



RESULTS: In this study, we demonstrate the limitations of currently used tests and introduce the method, RNA-editing tests (REDITs), a suite of tests that employ beta-binomial models to identify differential RNA editing. The tests in REDITs have higher sensitivity than other tests, while also maintaining the type I error (false positive) rate at the nominal level. Applied to the GTEx dataset, we unveil RNA-editing changes associated with age and gender, and differential recoding profiles between brain regions.



AVAILABILITY AND IMPLEMENTATION: REDITs are implemented as functions in R and freely available for download at https://github.com/gxiaolab/REDITs. The repository also provides a code example for leveraging parallelization using multiple cores.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid33196678,

title = {Molecular consequences of fetal alcohol exposure on amniotic exosomal miRNAs with functional implications for stem cell potency and differentiation},

author = {Honey Tavanasefat and Feng Li and Kikuye Koyano and Bahar Khalilian Gourtani and Vincent Marty and Yatendra Mulpuri and Sung Hee Lee and Ki-Hyuk Shin and David T W Wong and Xinshu Xiao and Igor Spigelman and Yong Kim},

doi = {10.1371/journal.pone.0242276},

issn = {1932-6203},

year  = {2020},

date = {2020-01-01},

journal = {PLoS One},

volume = {15},

number = {11},

pages = {e0242276},

abstract = {Alcohol (ethanol, EtOH) consumption during pregnancy can result in fetal alcohol spectrum disorders (FASDs), which are characterized by prenatal and postnatal growth restriction and craniofacial dysmorphology. Recently, cell-derived extracellular vesicles, including exosomes and microvesicles containing several species of RNAs (exRNAs), have emerged as a mechanism of cell-to-cell communication. However, EtOH's effects on the biogenesis and function of non-coding exRNAs during fetal development have not been explored. Therefore, we studied the effects of maternal EtOH exposure on the composition of exosomal RNAs in the amniotic fluid (AF) using rat fetal alcohol exposure (FAE) model. Through RNA-Seq analysis we identified and verified AF exosomal miRNAs with differential expression levels specifically associated with maternal EtOH exposure. Uptake of purified FAE AF exosomes by rBMSCs resulted in significant alteration of molecular markers associated with osteogenic differentiation of rBMSCs. We also determined putative functional roles for AF exosomal miRNAs (miR-199a-3p, miR-214-3p and let-7g) that are dysregulated by FAE in osteogenic differentiation of rBMSCs. Our results demonstrate that FAE alters AF exosomal miRNAs and that exosomal transfer of dysregulated miRNAs has significant molecular effects on stem cell regulation and differentiation. Our results further suggest the usefulness of assessing molecular alterations in AF exRNAs to study the mechanisms of FAE teratogenesis that should be further investigated by using an in vivo model.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid31081512,

title = {DeepPASTA: deep neural network based polyadenylation site analysis},

author = {Ashraful Arefeen and Xinshu Xiao and Tao Jiang},

doi = {10.1093/bioinformatics/btz283},

issn = {1367-4811},

year  = {2019},

date = {2019-11-01},

journal = {Bioinformatics},

volume = {35},

number = {22},

pages = {4577--4585},

abstract = {MOTIVATION: Alternative polyadenylation (polyA) sites near the 3' end of a pre-mRNA create multiple mRNA transcripts with different 3' untranslated regions (3' UTRs). The sequence elements of a 3' UTR are essential for many biological activities such as mRNA stability, sub-cellular localization, protein translation, protein binding and translation efficiency. Moreover, numerous studies in the literature have reported the correlation between diseases and the shortening (or lengthening) of 3' UTRs. As alternative polyA sites are common in mammalian genes, several machine learning tools have been published for predicting polyA sites from sequence data. These tools either consider limited sequence features or use relatively old algorithms for polyA site prediction. Moreover, none of the previous tools consider RNA secondary structures as a feature to predict polyA sites.



RESULTS: In this paper, we propose a new deep learning model, called DeepPASTA, for predicting polyA sites from both sequence and RNA secondary structure data. The model is then extended to predict tissue-specific polyA sites. Moreover, the tool can predict the most dominant (i.e. frequently used) polyA site of a gene in a specific tissue and relative dominance when two polyA sites of the same gene are given. Our extensive experiments demonstrate that DeepPASTA signisficantly outperforms the existing tools for polyA site prediction and tissue-specific relative and absolute dominant polyA site prediction.



AVAILABILITY AND IMPLEMENTATION: https://github.com/arefeen/DeepPASTA.



SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid31542416,

title = {mountainClimber Identifies Alternative Transcription Start and Polyadenylation Sites in RNA-Seq},

author = {Ashley A Cass and Xinshu Xiao},

doi = {10.1016/j.cels.2019.07.011},

issn = {2405-4720},

year  = {2019},

date = {2019-10-01},

journal = {Cell Syst},

volume = {9},

number = {4},

pages = {393--400.e6},

abstract = {Alternative transcription start (ATS) and alternative polyadenylation (APA) create alternative RNA isoforms and modulate many aspects of RNA expression and protein production. However, ATS and APA remain difficult to detect in RNA sequencing (RNA-seq). Here, we developed mountainClimber, a de novo cumulative-sum-based approach to identify ATS and APA as change points. Unlike many existing methods, mountainClimber runs on a single sample and identifies multiple ATS or APA sites anywhere in the transcript. We analyzed 2,342 GTEx samples (36 tissues, 215 individuals) and found that tissue type is the predominant driver of transcript end variations. 75% and 65% of genes exhibited differential APA and ATS across tissues, respectively. In particular, testis displayed longer 5' untranslated regions (UTRs) and shorter 3' UTRs, often in genes related to testis-specific biology. Overall, we report the largest study of transcript ends across human tissues to our knowledge. mountainClimber is available at github.com/gxiaolab/mountainClimber.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid30951667,

title = {The Extracellular RNA Communication Consortium: Establishing Foundational Knowledge and Technologies for Extracellular RNA Research},

author = {Saumya Das and  and K Mark Ansel and Markus Bitzer and Xandra O Breakefield and Alain Charest and David J Galas and Mark B Gerstein and Mihir Gupta and Aleksandar Milosavljevic and Michael T McManus and Tushar Patel and Robert L Raffai and Joel Rozowsky and Matthew E Roth and Julie A Saugstad and Kendall Van Keuren-Jensen and Alissa M Weaver and Louise C Laurent},

doi = {10.1016/j.cell.2019.03.023},

issn = {1097-4172},

year  = {2019},

date = {2019-04-01},

journal = {Cell},

volume = {177},

number = {2},

pages = {231--242},

abstract = {The Extracellular RNA Communication Consortium (ERCC) was launched to accelerate progress in the new field of extracellular RNA (exRNA) biology and to establish whether exRNAs and their carriers, including extracellular vesicles (EVs), can mediate intercellular communication and be utilized for clinical applications. Phase 1 of the ERCC focused on exRNA/EV biogenesis and function, discovery of exRNA biomarkers, development of exRNA/EV-based therapeutics, and construction of a robust set of reference exRNA profiles for a variety of biofluids. Here, we present progress by ERCC investigators in these areas, and we discuss collaborative projects directed at development of robust methods for EV/exRNA isolation and analysis and tools for sharing and computational analysis of exRNA profiling data.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid30902979,

title = {Allele-specific binding of RNA-binding proteins reveals functional genetic variants in the RNA},

author = {Ei-Wen Yang and Jae Hoon Bahn and Esther Yun-Hua Hsiao and Boon Xin Tan and Yiwei Sun and Ting Fu and Bo Zhou and Eric L Van Nostrand and Gabriel A Pratt and Peter Freese and Xintao Wei and Giovanni Quinones-Valdez and Alexander E Urban and Brenton R Graveley and Christopher B Burge and Gene W Yeo and Xinshu Xiao},

doi = {10.1038/s41467-019-09292-w},

issn = {2041-1723},

year  = {2019},

date = {2019-03-01},

journal = {Nat Commun},

volume = {10},

number = {1},

pages = {1338},

abstract = {Allele-specific protein-RNA binding is an essential aspect that may reveal functional genetic variants (GVs) mediating post-transcriptional regulation. Recently, genome-wide detection of in vivo binding of RNA-binding proteins is greatly facilitated by the enhanced crosslinking and immunoprecipitation (eCLIP) method. We developed a new computational approach, called BEAPR, to identify allele-specific binding (ASB) events in eCLIP-Seq data. BEAPR takes into account crosslinking-induced sequence propensity and variations between replicated experiments. Using simulated and actual data, we show that BEAPR largely outperforms often-used count analysis methods. Importantly, BEAPR overcomes the inherent overdispersion problem of these methods. Complemented by experimental validations, we demonstrate that the application of BEAPR to ENCODE eCLIP-Seq data of 154 proteins helps to predict functional GVs that alter splicing or mRNA abundance. Moreover, many GVs with ASB patterns have known disease relevance. Overall, BEAPR is an effective method that helps to address the outstanding challenge of functional interpretation of GVs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid30652130,

title = {Regulation of RNA editing by RNA-binding proteins in human cells},

author = {Giovanni Quinones-Valdez and Stephen S Tran and Hyun-Ik Jun and Jae Hoon Bahn and Ei-Wen Yang and Lijun Zhan and Anneke Brümmer and Xintao Wei and Eric L Van Nostrand and Gabriel A Pratt and Gene W Yeo and Brenton R Graveley and Xinshu Xiao},

doi = {10.1038/s42003-018-0271-8},

issn = {2399-3642},

year  = {2019},

date = {2019-01-01},

journal = {Commun Biol},

volume = {2},

pages = {19},

abstract = {Adenosine-to-inosine (A-to-I) editing, mediated by the ADAR enzymes, diversifies the transcriptome by altering RNA sequences. Recent studies reported global changes in RNA editing in disease and development. Such widespread editing variations necessitate an improved understanding of the regulatory mechanisms of RNA editing. Here, we study the roles of >200 RNA-binding proteins (RBPs) in mediating RNA editing in two human cell lines. Using RNA-sequencing and global protein-RNA binding data, we identify a number of RBPs as key regulators of A-to-I editing. These RBPs, such as TDP-43, DROSHA, NF45/90 and Ro60, mediate editing through various mechanisms including regulation of  expression, interaction with ADAR1, and binding to Alu elements. We highlight that editing regulation by Ro60 is consistent with the global up-regulation of RNA editing in systemic lupus erythematosus. Additionally, most key editing regulators act in a cell type-specific manner. Together, our work provides insights for the regulatory mechanisms of RNA editing.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid30503770,

title = {A Multiplexed Assay for Exon Recognition Reveals that an Unappreciated Fraction of Rare Genetic Variants Cause Large-Effect Splicing Disruptions},

author = {Rocky Cheung and Kimberly D Insigne and David Yao and Christina P Burghard and Jeffrey Wang and Yun-Hua E Hsiao and Eric M Jones and Daniel B Goodman and Xinshu Xiao and Sriram Kosuri},

doi = {10.1016/j.molcel.2018.10.037},

issn = {1097-4164},

year  = {2019},

date = {2019-01-01},

journal = {Mol Cell},

volume = {73},

number = {1},

pages = {183--194.e8},

abstract = {Mutations that lead to splicing defects can have severe consequences on gene function and cause disease. Here, we explore how human genetic variation affects exon recognition by developing a multiplexed functional assay of splicing using Sort-seq (MFASS). We assayed 27,733 variants in the Exome Aggregation Consortium (ExAC) within or adjacent to 2,198 human exons in the MFASS minigene reporter and found that 3.8% (1,050) of variants, most of which are extremely rare, led to large-effect splice-disrupting variants (SDVs). Importantly, we find that 83% of SDVs are located outside of canonical splice sites, are distributed evenly across distinct exonic and intronic regions, and are difficult to predict a priori. Our results indicate extant, rare genetic variants can have large functional effects on splicing at appreciable rates, even outside the context of disease, and MFASS enables their empirical assessment at scale.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid30559470,

title = {Widespread RNA editing dysregulation in brains from autistic individuals},

author = {Stephen S Tran and Hyun-Ik Jun and Jae Hoon Bahn and Adel Azghadi and Gokul Ramaswami and Eric L Van Nostrand and Thai B Nguyen and Yun-Hua E Hsiao and Changhoon Lee and Gabriel A Pratt and Verónica Martínez-Cerdeño and Randi J Hagerman and Gene W Yeo and Daniel H Geschwind and Xinshu Xiao},

doi = {10.1038/s41593-018-0287-x},

issn = {1546-1726},

year  = {2019},

date = {2019-01-01},

journal = {Nat Neurosci},

volume = {22},

number = {1},

pages = {25--36},

abstract = {Transcriptomic analyses of postmortem brains have begun to elucidate molecular abnormalities in autism spectrum disorder (ASD). However, a crucial pathway involved in synaptic development, RNA editing, has not yet been studied on a genome-wide scale. Here we profiled global patterns of adenosine-to-inosine (A-to-I) editing in a large cohort of postmortem brains of people with ASD. We observed a global bias for hypoediting in ASD brains, which was shared across brain regions and involved many synaptic genes. We show that the Fragile X proteins FMRP and FXR1P interact with RNA-editing enzymes (ADAR proteins) and modulate A-to-I editing. Furthermore, we observed convergent patterns of RNA-editing alterations in ASD and Fragile X syndrome, establishing this as a molecular link between these related diseases. Our findings, which are corroborated across multiple data sets, including dup15q (genomic duplication of 15q11.2-13.1) cases associated with intellectual disability, highlight RNA-editing dysregulation in ASD and reveal new mechanisms underlying this disorder.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid30042172,

title = {Coregulation of alternative splicing by hnRNPM and ESRP1 during EMT},

author = {Samuel E Harvey and Yilin Xu and Xiaodan Lin and Xin D Gao and Yushan Qiu and Jaegyoon Ahn and Xinshu Xiao and Chonghui Cheng},

doi = {10.1261/rna.066712.118},

issn = {1469-9001},

year  = {2018},

date = {2018-10-01},

journal = {RNA},

volume = {24},

number = {10},

pages = {1326--1338},

abstract = {The epithelial-mesenchymal transition (EMT) is a fundamental developmental process that is abnormally activated in cancer metastasis. Dynamic changes in alternative splicing occur during EMT. ESRP1 and hnRNPM are splicing regulators that promote an epithelial splicing program and a mesenchymal splicing program, respectively. The functional relationships between these splicing factors in the genome scale remain elusive. Comparing alternative splicing targets of hnRNPM and ESRP1 revealed that they coregulate a set of cassette exon events, with the majority showing discordant splicing regulation. Discordant splicing events regulated by hnRNPM show a positive correlation with splicing during EMT; however, concordant events do not, indicating the role of hnRNPM in regulating alternative splicing during EMT is more complex than previously understood. Motif enrichment analysis near hnRNPM-ESRP1 coregulated exons identifies guanine-uridine rich motifs downstream from hnRNPM-repressed and ESRP1-enhanced exons, supporting a general model of competitive binding to these -elements to antagonize alternative splicing. The set of coregulated exons are enriched in genes associated with cell migration and cytoskeletal reorganization, which are pathways associated with EMT. Splicing levels of coregulated exons are associated with breast cancer patient survival and correlate with gene sets involved in EMT and breast cancer subtyping. This study identifies complex modes of interaction between hnRNPM and ESRP1 in regulation of splicing in disease-relevant contexts.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid29702004,

title = {Human tRNA-Derived Small RNAs Modulate Host-Oral Microbial Interactions},

author = {X He and F Li and B Bor and K Koyano and L Cen and X Xiao and W Shi and D T W Wong},

doi = {10.1177/0022034518770605},

issn = {1544-0591},

year  = {2018},

date = {2018-10-01},

journal = {J Dent Res},

volume = {97},

number = {11},

pages = {1236--1243},

abstract = {Coevolution of the human host and its associated microbiota has led to sophisticated interactions to maintain a delicate homeostasis. Emerging evidence suggests that in addition to small molecules, peptides, and proteins, small regulatory noncoding RNAs (sRNAs) might play an important role in cross-domain interactions. In this study, we revealed the presence of diverse host transfer RNA-derived small RNAs (tsRNAs) among human salivary sRNAs. We selected 2 tsRNAs (tsRNA-000794 and tsRNA-020498) for further study based on their high sequence similarity to specific tRNAs from a group of Gram-negative oral bacteria, including Fusobacterium nucleatum, a key oral commensal and opportunistic pathogen. We showed that the presence of F. nucleatum triggers exosome-mediated release of tsRNA-000794 and tsRNA-020498 by human normal oral keratinocyte cells. Furthermore, both tsRNA candidates exerted a growth inhibition effect on F. nucleatum, likely through interference with bacterial protein biosynthesis, but did not affect the growth of Streptococcus mitis, a health-associated oral Gram-positive bacterium whose genome does not carry sequences bearing high similarity to either tsRNA. Our data provide the first line of evidence for the modulatory role of host-derived tsRNAs in the microbial-host interaction.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid30052912,

title = {TAPAS: tool for alternative polyadenylation site analysis},

author = {Ashraful Arefeen and Juntao Liu and Xinshu Xiao and Tao Jiang},

doi = {10.1093/bioinformatics/bty110},

issn = {1367-4811},

year  = {2018},

date = {2018-08-01},

journal = {Bioinformatics},

volume = {34},

number = {15},

pages = {2521--2529},

abstract = {MOTIVATION: The length of the 3' untranslated region (3' UTR) of an mRNA is essential for many biological activities such as mRNA stability, sub-cellular localization, protein translation, protein binding and translation efficiency. Moreover, correlation between diseases and the shortening (or lengthening) of 3' UTRs has been reported in the literature. This length is largely determined by the polyadenylation cleavage site in the mRNA. As alternative polyadenylation (APA) sites are common in mammalian genes, several tools have been published recently for detecting APA sites from RNA-Seq data or performing shortening/lengthening analysis. These tools consider either up to only two APA sites in a gene or only APA sites that occur in the last exon of a gene, although a gene may generally have more than two APA sites and an APA site may sometimes occur before the last exon. Furthermore, the tools are unable to integrate the analysis of shortening/lengthening events with APA site detection.



RESULTS: We propose a new tool, called TAPAS, for detecting novel APA sites from RNA-Seq data. It can deal with more than two APA sites in a gene as well as APA sites that occur before the last exon. The tool is based on an existing method for finding change points in time series data, but some filtration techniques are also adopted to remove change points that are likely false APA sites. It is then extended to identify APA sites that are expressed differently between two biological samples and genes that contain 3' UTRs with shortening/lengthening events. Our extensive experiments on simulated and real RNA-Seq data demonstrate that TAPAS outperforms the existing tools for APA site detection or shortening/lengthening analysis significantly.



AVAILABILITY AND IMPLEMENTATION: https://github.com/arefeen/TAPAS.



SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid29685897,

title = {Characterization of Human Salivary Extracellular RNA by Next-generation Sequencing},

author = {Feng Li and Karolina Elżbieta Kaczor-Urbanowicz and Jie Sun and Blanca Majem and Hsien-Chun Lo and Yong Kim and Kikuye Koyano and Shannon Liu Rao and So Young Kang and Su Mi Kim and Kyoung-Mee Kim and Sung Kim and David Chia and David Elashoff and Tristan R Grogan and Xinshu Xiao and David T W Wong},

doi = {10.1373/clinchem.2017.285072},

issn = {1530-8561},

year  = {2018},

date = {2018-07-01},

journal = {Clin Chem},

volume = {64},

number = {7},

pages = {1085--1095},

abstract = {BACKGROUND: It was recently discovered that abundant and stable extracellular RNA (exRNA) species exist in bodily fluids. Saliva is an emerging biofluid for biomarker development for noninvasive detection and screening of local and systemic diseases. Use of RNA-Sequencing (RNA-Seq) to profile exRNA is rapidly growing; however, no single preparation and analysis protocol can be used for all biofluids. Specifically, RNA-Seq of saliva is particularly challenging owing to high abundance of bacterial contents and low abundance of salivary exRNA. Given the laborious procedures needed for RNA-Seq library construction, sequencing, data storage, and data analysis, saliva-specific and optimized protocols are essential.



METHODS: We compared different RNA isolation methods and library construction kits for long and small RNA sequencing. The role of ribosomal RNA (rRNA) depletion also was evaluated.



RESULTS: The miRNeasy Micro Kit (Qiagen) showed the highest total RNA yield (70.8 ng/mL cell-free saliva) and best small RNA recovery, and the NEBNext library preparation kits resulted in the highest number of detected human genes [5649-6813 at 1 reads per kilobase RNA per million mapped (RPKM)] and small RNAs [482-696 microRNAs (miRNAs) and 190-214 other small RNAs]. The proportion of human RNA-Seq reads was much higher in rRNA-depleted saliva samples (41%) than in samples without rRNA depletion (14%). In addition, the transfer RNA (tRNA)-derived RNA fragments (tRFs), a novel class of small RNAs, were highly abundant in human saliva, specifically tRF-4 (4%) and tRF-5 (15.25%).



CONCLUSIONS: Our results may help in selection of the best adapted methods of RNA isolation and small and long RNA library constructions for salivary exRNA studies.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid29724793,

title = {RNA editing in nascent RNA affects pre-mRNA splicing},

author = {Yun-Hua Esther Hsiao and Jae Hoon Bahn and Yun Yang and Xianzhi Lin and Stephen Tran and Ei-Wen Yang and Giovanni Quinones-Valdez and Xinshu Xiao},

doi = {10.1101/gr.231209.117},

issn = {1549-5469},

year  = {2018},

date = {2018-06-01},

journal = {Genome Res},

volume = {28},

number = {6},

pages = {812--823},

abstract = {In eukaryotes, nascent RNA transcripts undergo an intricate series of RNA processing steps to achieve mRNA maturation. RNA editing and alternative splicing are two major RNA processing steps that can introduce significant modifications to the final gene products. By tackling these processes in isolation, recent studies have enabled substantial progress in understanding their global RNA targets and regulatory pathways. However, the interplay between individual steps of RNA processing, an essential aspect of gene regulation, remains poorly understood. By sequencing the RNA of different subcellular fractions, we examined the timing of adenosine-to-inosine (A-to-I) RNA editing and its impact on alternative splicing. We observed that >95% A-to-I RNA editing events occurred in the chromatin-associated RNA prior to polyadenylation. We report about 500 editing sites in the 3' acceptor sequences that can alter splicing of the associated exons. These exons are highly conserved during evolution and reside in genes with important cellular function. Furthermore, we identified a second class of exons whose splicing is likely modulated by RNA secondary structures that are recognized by the RNA editing machinery. The genome-wide analyses, supported by experimental validations, revealed remarkable interplay between RNA editing and splicing and expanded the repertoire of functional RNA editing sites.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid29742391,

title = {Loss of MECP2 Leads to Activation of P53 and Neuronal Senescence},

author = {Minori Ohashi and Elena Korsakova and Denise Allen and Peiyee Lee and Kai Fu and Benni S Vargas and Jessica Cinkornpumin and Carlos Salas and Jenny C Park and Igal Germanguz and Justin Langerman and Contantinos Chronis and Edward Kuoy and Stephen Tran and Xinshu Xiao and Matteo Pellegrini and Kathrin Plath and William E Lowry},

doi = {10.1016/j.stemcr.2018.04.001},

issn = {2213-6711},

year  = {2018},

date = {2018-05-01},

journal = {Stem Cell Reports},

volume = {10},

number = {5},

pages = {1453--1463},

abstract = {To determine the role for mutations of MECP2 in Rett syndrome, we generated isogenic lines of human induced pluripotent stem cells, neural progenitor cells, and neurons from patient fibroblasts with and without MECP2 expression in an attempt to recapitulate disease phenotypes in vitro. Molecular profiling uncovered neuronal-specific gene expression changes, including induction of a senescence-associated secretory phenotype (SASP) program. Patient-derived neurons made without MECP2 showed signs of stress, including induction of P53, and senescence. The induction of P53 appeared to affect dendritic branching in Rett neurons, as P53 inhibition restored dendritic complexity. The induction of P53 targets was also detectable in analyses of human Rett patient brain, suggesting that this disease-in-a-dish model can provide relevant insights into the human disorder.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid29360038,

title = {FoxP2 isoforms delineate spatiotemporal transcriptional networks for vocal learning in the zebra finch},

author = {Zachary Daniel Burkett and Nancy F Day and Todd Haswell Kimball and Caitlin M Aamodt and Jonathan B Heston and Austin T Hilliard and Xinshu Xiao and Stephanie A White},

doi = {10.7554/eLife.30649},

issn = {2050-084X},

year  = {2018},

date = {2018-01-01},

journal = {Elife},

volume = {7},

abstract = {Human speech is one of the few examples of vocal learning among mammals yet ~half of avian species exhibit this ability. Its neurogenetic basis is largely unknown beyond a shared requirement for FoxP2 in both humans and zebra finches. We manipulated FoxP2 isoforms in Area X, a song-specific region of the avian striatopallidum analogous to human anterior striatum, during a critical period for song development. We delineate, for the first time, unique contributions of each isoform to vocal learning. Weighted gene coexpression network analysis of RNA-seq data revealed gene modules correlated to singing, learning, or vocal variability. Coexpression related to singing was found in juvenile and adult Area X whereas coexpression correlated to learning was unique to juveniles. The confluence of learning and singing coexpression in juvenile Area X may underscore molecular processes that drive vocal learning in young zebra finches and, by analogy, humans.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid28961734,

title = {Novel approaches for bioinformatic analysis of salivary RNA sequencing data for development},

author = {Karolina Elzbieta Kaczor-Urbanowicz and Yong Kim and Feng Li and Timur Galeev and Rob R Kitchen and Mark Gerstein and Kikuye Koyano and Sung-Hee Jeong and Xiaoyan Wang and David Elashoff and So Young Kang and Su Mi Kim and Kyoung Kim and Sung Kim and David Chia and Xinshu Xiao and Joel Rozowsky and David T W Wong},

doi = {10.1093/bioinformatics/btx504},

issn = {1367-4811},

year  = {2018},

date = {2018-01-01},

journal = {Bioinformatics},

volume = {34},

number = {1},

pages = {1--8},

abstract = {MOTIVATION: Analysis of RNA sequencing (RNA-Seq) data in human saliva is challenging. Lack of standardization and unification of the bioinformatic procedures undermines saliva's diagnostic potential. Thus, it motivated us to perform this study.



RESULTS: We applied principal pipelines for bioinformatic analysis of small RNA-Seq data of saliva of 98 healthy Korean volunteers including either direct or indirect mapping of the reads to the human genome using Bowtie1. Analysis of alignments to exogenous genomes by another pipeline revealed that almost all of the reads map to bacterial genomes. Thus, salivary exRNA has fundamental properties that warrant the design of unique additional steps while performing the bioinformatic analysis. Our pipelines can serve as potential guidelines for processing of RNA-Seq data of human saliva.



AVAILABILITY AND IMPLEMENTATION: Processing and analysis results of the experimental data generated by the exceRpt (v4.6.3) small RNA-seq pipeline (github.gersteinlab.org/exceRpt) are available from exRNA atlas (exrna-atlas.org). Alignment to exogenous genomes and their quantification results were used in this paper for the analyses of small RNAs of exogenous origin.



CONTACT: dtww@ucla.edu.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid29093448,

title = {Structure-mediated modulation of mRNA abundance by A-to-I editing},

author = {Anneke Brümmer and Yun Yang and Tracey W Chan and Xinshu Xiao},

doi = {10.1038/s41467-017-01459-7},

issn = {2041-1723},

year  = {2017},

date = {2017-11-01},

journal = {Nat Commun},

volume = {8},

number = {1},

pages = {1255},

abstract = {RNA editing introduces single nucleotide changes to RNA, thus potentially diversifying gene expression. Recent studies have reported significant changes in RNA editing profiles in disease and development. The functional consequences of these widespread alterations remain elusive because of the unknown function of most RNA editing sites. Here, we carry out a comprehensive analysis of A-to-I editomes in human populations. Surprisingly, we observe highly similar editing profiles across populations despite striking differences in the expression levels of ADAR genes. Striving to explain this discrepancy, we uncover a functional mechanism of A-to-I editing in regulating mRNA abundance. We show that A-to-I editing stabilizes RNA secondary structures and reduces the accessibility of AGO2-miRNA to target sites in mRNAs. The editing-dependent stabilization of mRNAs in turn alters the observed editing levels in the stable RNA repertoire. Our study provides valuable insights into the functional impact of RNA editing in human cells.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid28878122,

title = {Wnt11 regulates cardiac chamber development and disease during perinatal maturation},

author = {Marlin Touma and Xuedong Kang and Fuying Gao and Yan Zhao and Ashley A Cass and Reshma Biniwale and Xinshu Xiao and Mansuoreh Eghbali and Giovanni Coppola and Brian Reemtsen and Yibin Wang},

doi = {10.1172/jci.insight.94904},

issn = {2379-3708},

year  = {2017},

date = {2017-09-01},

journal = {JCI Insight},

volume = {2},

number = {17},

abstract = {Ventricular chamber growth and development during perinatal circulatory transition is critical for functional adaptation of the heart. However, the chamber-specific programs of neonatal heart growth are poorly understood. We used integrated systems genomic and functional biology analyses of the perinatal chamber specific transcriptome and we identified Wnt11 as a prominent regulator of chamber-specific proliferation. Importantly, downregulation of Wnt11 expression was associated with cyanotic congenital heart defect (CHD) phenotypes and correlated with O2 saturation levels in hypoxemic infants with Tetralogy of Fallot (TOF). Perinatal hypoxia treatment in mice suppressed Wnt11 expression and induced myocyte proliferation more robustly in the right ventricle, modulating Rb1 protein activity. Wnt11 inactivation was sufficient to induce myocyte proliferation in perinatal mouse hearts and reduced Rb1 protein and phosphorylation in neonatal cardiomyocytes. Finally, downregulated Wnt11 in hypoxemic TOF infantile hearts was associated with Rb1 suppression and induction of proliferation markers. This study revealed a previously uncharacterized function of Wnt11-mediated signaling as an important player in programming the chamber-specific growth of the neonatal heart. This function influences the chamber-specific development and pathogenesis in response to hypoxia and cyanotic CHDs. Defining the underlying regulatory mechanism may yield chamber-specific therapies for infants born with CHDs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid28281539,

title = {Extensive translation of circular RNAs driven by N-methyladenosine},

author = {Yun Yang and Xiaojuan Fan and Miaowei Mao and Xiaowei Song and Ping Wu and Yang Zhang and Yongfeng Jin and Yi Yang and Ling-Ling Chen and Yang Wang and Catherine Cl Wong and Xinshu Xiao and Zefeng Wang},

doi = {10.1038/cr.2017.31},

issn = {1748-7838},

year  = {2017},

date = {2017-05-01},

journal = {Cell Res},

volume = {27},

number = {5},

pages = {626--641},

abstract = {Extensive pre-mRNA back-splicing generates numerous circular RNAs (circRNAs) in human transcriptome. However, the biological functions of these circRNAs remain largely unclear. Here we report that N-methyladenosine (mA), the most abundant base modification of RNA, promotes efficient initiation of protein translation from circRNAs in human cells. We discover that consensus mA motifs are enriched in circRNAs and a single mA site is sufficient to drive translation initiation. This mA-driven translation requires initiation factor eIF4G2 and mA reader YTHDF3, and is enhanced by methyltransferase METTL3/14, inhibited by demethylase FTO, and upregulated upon heat shock. Further analyses through polysome profiling, computational prediction and mass spectrometry reveal that mA-driven translation of circRNAs is widespread, with hundreds of endogenous circRNAs having translation potential. Our study expands the coding landscape of human transcriptome, and suggests a role of circRNA-derived proteins in cellular responses to environmental stress.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid27591185,

title = {Decoding the Long Noncoding RNA During Cardiac Maturation: A Roadmap for Functional Discovery},

author = {Marlin Touma and Xuedong Kang and Yan Zhao and Ashley A Cass and Fuying Gao and Reshma Biniwale and Giovanni Coppola and Xinshu Xiao and Brian Reemtsen and Yibin Wang},

doi = {10.1161/CIRCGENETICS.115.001363},

issn = {1942-3268},

year  = {2016},

date = {2016-10-01},

journal = {Circ Cardiovasc Genet},

volume = {9},

number = {5},

pages = {395--407},

abstract = {BACKGROUND: Cardiac maturation during perinatal transition of heart is critical for functional adaptation to hemodynamic load and nutrient environment. Perturbation in this process has major implications in congenital heart defects. Transcriptome programming during perinatal stages is an important information but incomplete in current literature, particularly, the expression profiles of the long noncoding RNAs (lncRNAs) are not fully elucidated.



METHODS AND RESULTS: From comprehensive analysis of transcriptomes derived from neonatal mouse heart left and right ventricles, a total of 45 167 unique transcripts were identified, including 21 916 known and 2033 novel lncRNAs. Among these lncRNAs, 196 exhibited significant dynamic regulation along maturation process. By implementing parallel weighted gene co-expression network analysis of mRNA and lncRNA data sets, several lncRNA modules coordinately expressed in a developmental manner similar to protein coding genes, while few lncRNAs revealed chamber-specific patterns. Out of 2262 lncRNAs located within 50 kb of protein coding genes, 5% significantly correlate with the expression of their neighboring genes. The impact of Ppp1r1b-lncRNA on the corresponding partner gene Tcap was validated in cultured myoblasts. This concordant regulation was also conserved in human infantile hearts. Furthermore, the Ppp1r1b-lncRNA/Tcap expression ratio was identified as a molecular signature that differentiated congenital heart defect phenotypes.



CONCLUSIONS: The study provides the first high-resolution landscape on neonatal cardiac lncRNAs and reveals their potential interaction with mRNA transcriptome during cardiac maturation. Ppp1r1b-lncRNA was identified as a regulator of Tcap expression, with dynamic interaction in postnatal cardiac development and congenital heart defects.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid27618650,

title = {The long noncoding RNA Chaer defines an epigenetic checkpoint in cardiac hypertrophy},

author = {Zhihua Wang and Xiao-Jing Zhang and Yan-Xiao Ji and Peng Zhang and Ke-Qiong Deng and Jun Gong and Shuxun Ren and Xinghua Wang and Iris Chen and He Wang and Chen Gao and Tomohiro Yokota and Yen Sin Ang and Shen Li and Ashley Cass and Thomas M Vondriska and Guangping Li and Arjun Deb and Deepak Srivastava and Huang-Tian Yang and Xinshu Xiao and Hongliang Li and Yibin Wang},

doi = {10.1038/nm.4179},

issn = {1546-170X},

year  = {2016},

date = {2016-10-01},

journal = {Nat Med},

volume = {22},

number = {10},

pages = {1131--1139},

abstract = {Epigenetic reprogramming is a critical process of pathological gene induction during cardiac hypertrophy and remodeling, but the underlying regulatory mechanisms remain to be elucidated. Here we identified a heart-enriched long noncoding (lnc)RNA, named cardiac-hypertrophy-associated epigenetic regulator (Chaer), which is necessary for the development of cardiac hypertrophy. Mechanistically, Chaer directly interacts with the catalytic subunit of polycomb repressor complex 2 (PRC2). This interaction, which is mediated by a 66-mer motif in Chaer, interferes with PRC2 targeting to genomic loci, thereby inhibiting histone H3 lysine 27 methylation at the promoter regions of genes involved in cardiac hypertrophy. The interaction between Chaer and PRC2 is transiently induced after hormone or stress stimulation in a process involving mammalian target of rapamycin complex 1, and this interaction is a prerequisite for epigenetic reprogramming and induction of genes involved in hypertrophy. Inhibition of Chaer expression in the heart before, but not after, the onset of pressure overload substantially attenuates cardiac hypertrophy and dysfunction. Our study reveals that stress-induced pathological gene activation in the heart requires a previously uncharacterized lncRNA-dependent epigenetic checkpoint.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid27623010,

title = {Hypothalamic transcriptomes of 99 mouse strains reveal trans eQTL hotspots, splicing QTLs and novel non-coding genes},

author = {Yehudit Hasin-Brumshtein and Arshad H Khan and Farhad Hormozdiari and Calvin Pan and Brian W Parks and Vladislav A Petyuk and Paul D Piehowski and Anneke Brümmer and Matteo Pellegrini and Xinshu Xiao and Eleazar Eskin and Richard D Smith and Aldons J Lusis and Desmond J Smith},

doi = {10.7554/eLife.15614},

issn = {2050-084X},

year  = {2016},

date = {2016-09-01},

journal = {Elife},

volume = {5},

abstract = {Previous studies had shown that the integration of genome wide expression profiles, in metabolic tissues, with genetic and phenotypic variance, provided valuable insight into the underlying molecular mechanisms. We used RNA-Seq to characterize hypothalamic transcriptome in 99 inbred strains of mice from the Hybrid Mouse Diversity Panel (HMDP), a reference resource population for cardiovascular and metabolic traits. We report numerous novel transcripts supported by proteomic analyses, as well as novel non coding RNAs. High resolution genetic mapping of transcript levels in HMDP, reveals both  and  expression Quantitative Trait Loci (eQTLs) demonstrating 2  eQTL 'hotspots' associated with expression of hundreds of genes. We also report thousands of alternative splicing events regulated by genetic variants. Finally, comparison with about 150 metabolic and cardiovascular traits revealed many highly significant associations. Our data provide a rich resource for understanding the many physiologic functions mediated by the hypothalamus and their genetic regulation.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid27059949,

title = {Catabolic Defect of Branched-Chain Amino Acids Promotes Heart Failure},

author = {Haipeng Sun and Kristine C Olson and Chen Gao and Domenick A Prosdocimo and Meiyi Zhou and Zhihua Wang and Darwin Jeyaraj and Ji-Youn Youn and Shuxun Ren and Yunxia Liu and Christoph D Rau and Svati Shah and Olga Ilkayeva and Wen-Jun Gui and Noelle S William and R Max Wynn and Christopher B Newgard and Hua Cai and Xinshu Xiao and David T Chuang and Paul Christian Schulze and Christopher Lynch and Mukesh K Jain and Yibin Wang},

doi = {10.1161/CIRCULATIONAHA.115.020226},

issn = {1524-4539},

year  = {2016},

date = {2016-05-01},

journal = {Circulation},

volume = {133},

number = {21},

pages = {2038--2049},

abstract = {BACKGROUND: Although metabolic reprogramming is critical in the pathogenesis of heart failure, studies to date have focused principally on fatty acid and glucose metabolism. Contribution of amino acid metabolic regulation in the disease remains understudied.



METHODS AND RESULTS: Transcriptomic and metabolomic analyses were performed in mouse failing heart induced by pressure overload. Suppression of branched-chain amino acid (BCAA) catabolic gene expression along with concomitant tissue accumulation of branched-chain α-keto acids was identified as a significant signature of metabolic reprogramming in mouse failing hearts and validated to be shared in human cardiomyopathy hearts. Molecular and genetic evidence identified the transcription factor Krüppel-like factor 15 as a key upstream regulator of the BCAA catabolic regulation in the heart. Studies using a genetic mouse model revealed that BCAA catabolic defect promoted heart failure associated with induced oxidative stress and metabolic disturbance in response to mechanical overload. Mechanistically, elevated branched-chain α-keto acids directly suppressed respiration and induced superoxide production in isolated mitochondria. Finally, pharmacological enhancement of branched-chain α-keto acid dehydrogenase activity significantly blunted cardiac dysfunction after pressure overload.



CONCLUSIONS: BCAA catabolic defect is a metabolic hallmark of failing heart resulting from Krüppel-like factor 15-mediated transcriptional reprogramming. BCAA catabolic defect imposes a previously unappreciated significant contribution to heart failure.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid27322469,

title = {Systems Nutrigenomics Reveals Brain Gene Networks Linking Metabolic and Brain Disorders},

author = {Qingying Meng and Zhe Ying and Emily Noble and Yuqi Zhao and Rahul Agrawal and Andrew Mikhail and Yumei Zhuang and Ethika Tyagi and Qing Zhang and Jae-Hyung Lee and Marco Morselli and Luz Orozco and Weilong Guo and Tina M Kilts and Jun Zhu and Bin Zhang and Matteo Pellegrini and Xinshu Xiao and Marian F Young and Fernando Gomez-Pinilla and Xia Yang},

doi = {10.1016/j.ebiom.2016.04.008},

issn = {2352-3964},

year  = {2016},

date = {2016-05-01},

journal = {EBioMedicine},

volume = {7},

pages = {157--166},

abstract = {Nutrition plays a significant role in the increasing prevalence of metabolic and brain disorders. Here we employ systems nutrigenomics to scrutinize the genomic bases of nutrient-host interaction underlying disease predisposition or therapeutic potential. We conducted transcriptome and epigenome sequencing of hypothalamus (metabolic control) and hippocampus (cognitive processing) from a rodent model of fructose consumption, and identified significant reprogramming of DNA methylation, transcript abundance, alternative splicing, and gene networks governing cell metabolism, cell communication, inflammation, and neuronal signaling. These signals converged with genetic causal risks of metabolic, neurological, and psychiatric disorders revealed in humans. Gene network modeling uncovered the extracellular matrix genes Bgn and Fmod as main orchestrators of the effects of fructose, as validated using two knockout mouse models. We further demonstrate that an omega-3 fatty acid, DHA, reverses the genomic and network perturbations elicited by fructose, providing molecular support for nutritional interventions to counteract diet-induced metabolic and brain disorders. Our integrative approach complementing rodent and human studies supports the applicability of nutrigenomics principles to predict disease susceptibility and to guide personalized medicine.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid26975654,

title = {Global analyses of endonucleolytic cleavage in mammals reveal expanded repertoires of cleavage-inducing small RNAs and their targets},

author = {Ashley A Cass and Jae Hoon Bahn and Jae-Hyung Lee and Christopher Greer and Xianzhi Lin and Yong Kim and Yun-Hua Esther Hsiao and Xinshu Xiao},

doi = {10.1093/nar/gkw164},

issn = {1362-4962},

year  = {2016},

date = {2016-04-01},

journal = {Nucleic Acids Res},

volume = {44},

number = {7},

pages = {3253--3263},

abstract = {In mammals, small RNAs are important players in post-transcriptional gene regulation. While their roles in mRNA destabilization and translational repression are well appreciated, their involvement in endonucleolytic cleavage of target RNAs is poorly understood. Very few microRNAs are known to guide RNA cleavage. Endogenous small interfering RNAs are expected to induce target cleavage, but their target genes remain largely unknown. We report a systematic study of small RNA-mediated endonucleolytic cleavage in mouse through integrative analysis of small RNA and degradome sequencing data without imposing any bias toward known small RNAs. Hundreds of small cleavage-inducing RNAs and their cognate target genes were identified, significantly expanding the repertoire of known small RNA-guided cleavage events. Strikingly, both small RNAs and their target sites demonstrated significant overlap with retrotransposons, providing evidence for the long-standing speculation that retrotransposable elements in mRNAs are leveraged as signals for gene targeting. Furthermore, our analysis showed that the RNA cleavage pathway is also present in human cells but affecting a different repertoire of retrotransposons. These results show that small RNA-guided cleavage is more widespread than previously appreciated. Their impact on retrotransposons in non-coding regions shed light on important aspects of mammalian gene regulation.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid26888265,

title = {Alternative splicing modulated by genetic variants demonstrates accelerated evolution regulated by highly conserved proteins},

author = {Yun-Hua Esther Hsiao and Jae Hoon Bahn and Xianzhi Lin and Tak-Ming Chan and Rena Wang and Xinshu Xiao},

doi = {10.1101/gr.193359.115},

issn = {1549-5469},

year  = {2016},

date = {2016-04-01},

journal = {Genome Res},

volume = {26},

number = {4},

pages = {440--450},

abstract = {Identification of functional genetic variants and elucidation of their regulatory mechanisms represent significant challenges of the post-genomic era. A poorly understood topic is the involvement of genetic variants in mediating post-transcriptional RNA processing, including alternative splicing. Thus far, little is known about the genomic, evolutionary, and regulatory features of genetically modulated alternative splicing (GMAS). Here, we systematically identified intronic tag variants for genetic modulation of alternative splicing using RNA-seq data specific to cellular compartments. Combined with our previous method that identifies exonic tags for GMAS, this study yielded 622 GMAS exons. We observed that GMAS events are highly cell type independent, indicating that splicing-altering genetic variants could have widespread function across cell types. Interestingly, GMAS genes, exons, and single-nucleotide variants (SNVs) all demonstrated positive selection or accelerated evolution in primates. We predicted that GMAS SNVs often alter binding of splicing factors, with SRSF1 affecting the most GMAS events and demonstrating global allelic binding bias. However, in contrast to their GMAS targets, the predicted splicing factors are more conserved than expected, suggesting that cis-regulatory variation is the major driving force of splicing evolution. Moreover, GMAS-related splicing factors had stronger consensus motifs than expected, consistent with their susceptibility to SNV disruption. Intriguingly, GMAS SNVs in general do not alter the strongest consensus position of the splicing factor motif, except the more than 100 GMAS SNVs in linkage disequilibrium with polymorphisms reported by genome-wide association studies. Our study reports many GMAS events and enables a better understanding of the evolutionary and regulatory features of this phenomenon.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid26745669,

title = {Research Resource: Hormones, Genes, and Athleticism: Effect of Androgens on the Avian Muscular Transcriptome},

author = {Matthew J Fuxjager and Jae-Hyung Lee and Tak-Ming Chan and Jae Hoon Bahn and Jenifer G Chew and Xinshu Xiao and Barney A Schlinger},

doi = {10.1210/me.2015-1270},

issn = {1944-9917},

year  = {2016},

date = {2016-02-01},

journal = {Mol Endocrinol},

volume = {30},

number = {2},

pages = {254--271},

abstract = {Male vertebrate social displays vary from physically simple to complex, with the latter involving exquisite motor command of the body and appendages. Studies of these displays have, in turn, provided substantial insight into neuromotor mechanisms. The neotropical golden-collared manakin (Manacus vitellinus) has been used previously as a model to investigate intricate motor skills because adult males of this species perform an acrobatic and androgen-dependent courtship display. To support this behavior, these birds express elevated levels of androgen receptors (AR) in their skeletal muscles. Here we use RNA sequencing to explore how testosterone (T) modulates the muscular transcriptome to support male manakin courtship displays. In addition, we explore how androgens influence gene expression in the muscles of the zebra finch (Taenopygia guttata), a model passerine bird with a limited courtship display and minimal muscle AR. We identify androgen-dependent, muscle-specific gene regulation in both species. In addition, we identify manakin-specific effects that are linked to muscle use during the manakin display, including androgenic regulation of genes associated with muscle fiber contractility, cellular homeostasis, and energetic efficiency. Overall, our results point to numerous genes and gene networks impacted by androgens in male birds, including some that underlie optimal muscle function necessary for performing acrobatic display routines. Manakins are excellent models to explore gene regulation promoting athletic ability.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}