Publications

@article{pmid41168189,

title = {Long-read RNA-seq demarcates cis- and trans-directed alternative RNA splicing},

author = {Giovanni Quinones-Valdez and Kofi Amoah and Xinshu Xiao},

doi = {10.1038/s41467-025-64605-6},

issn = {2041-1723},

year  = {2025},

date = {2025-10-01},

journal = {Nat Commun},

volume = {16},

number = {1},

pages = {9603},

abstract = {Genetic regulation of alternative splicing constitutes an important link between genetic variation and disease. Nonetheless, RNA splicing is regulated by both cis-acting elements and trans-acting splicing factors. Determining splicing events that are directed primarily by the cis- or trans-acting mechanisms will greatly inform our understanding of the genetic basis of disease. Here, we show that long-read RNA-seq, combined with our new method isoLASER, enables a clear segregation of cis- and trans-directed splicing events for individual samples. The genetic linkage of splicing is largely individual-specific, in stark contrast to the tissue-specific pattern of splicing profiles. Analysis of long-read RNA-seq data from human and mouse revealed thousands of cis-directed splicing events susceptible to genetic regulation. We highlight such events in the HLA genes whose analysis was challenging with short-read data. We also highlight novel cis-directed splicing events in Alzheimer's disease-relevant genes such as MAPT and BIN1. Together, the clear demarcation of cis- and trans-directed splicing paves ways for future studies of the genetic basis of disease.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40913182,

title = {Genetic variants affecting RNA stability influence complex traits and disease risk},

author = {Elaine Huang and Ting Fu and Ling Zhang and Guanao Yan and Ryo Yamamoto and Sari Terrazas and Thuy Linh Nguyen and Carlos Gonzalez-Figueroa and Armen Khanbabaei and Jae Hoon Bahn and Rajagopal Varada and Kofi Amoah and Jonatan Hervoso and Michelle T Paulsen and Brian Magnuson and Mats Ljungman and Jingyi Jessica Li and Xinshu Xiao},

doi = {10.1038/s41588-025-02326-8},

issn = {1546-1718},

year  = {2025},

date = {2025-09-01},

journal = {Nat Genet},

abstract = {Gene expression is modulated jointly by transcriptional regulation and messenger RNA stability, yet the latter is often overlooked in studies on genetic variants. Here, leveraging metabolic labeling data (Bru/BruChase-seq) and a new computational pipeline, RNAtracker, we categorize genes as allele-specific RNA stability (asRS) or allele-specific RNA transcription events. We identify more than 5,000 asRS variants among 665 genes across a panel of 11 human cell lines. These variants directly overlap conserved microRNA target regions and allele-specific RNA-binding protein sites, illuminating mechanisms through which stability is mediated. Furthermore, we identified causal asRS variants using a massively parallel screen (MapUTR) for variants that affect post-transcriptional mRNA abundance, as well as through CRISPR prime editing approaches. Notably, asRS genes were enriched significantly among a multitude of immune-related pathways and contribute to the risk of several immune system diseases. This work highlights RNA stability as a critical, yet understudied mechanism linking genetic variation and disease.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40527326,

title = {Differing Genetics of Saline and Cocaine Self-Administration in the Hybrid Mouse Diversity Panel},

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 = {10.1111/gbb.70029},

issn = {1601-183X},

year  = {2025},

date = {2025-06-01},

journal = {Genes Brain Behav},

volume = {24},

number = {3},

pages = {e70029},

abstract = {To identify genes that regulate the response to the potentially addictive drug cocaine, we performed a control experiment using genome-wide association studies (GWASs) and RNA-Seq of a panel of inbred and recombinant inbred mice undergoing intravenous self-administration of saline. A linear mixed model increased statistical power for the analysis of the longitudinal behavioral data, which was acquired over 10 days. A total of 145 loci were identified for saline compared to 17 for the corresponding cocaine GWAS. Only one locus overlapped. Transcriptome-wide association studies (TWASs) using RNA-Seq data from the nucleus accumbens and medial frontal cortex identified 5031434O11Rik and Zfp60 as significant for saline self-administration. Two other genes, Myh4 and Npc1, were nominated based on proximity to loci for multiple endpoints or a cis locus regulating expression. All four genes have previously been implicated in locomotor activity, despite the absence of a strong relationship between saline taking and distance traveled in the open field. Our results indicate a distinct genetic basis for saline and cocaine self-administration, and suggest some common genes for saline self-administration and locomotor activity.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40315057,

title = {Protocol to perform polysome profiling in primary differentiating murine adipocytes},

author = {Mirian Krystel De Siqueira and Zaynab Nouhi and Yutian Zhao and Siqi Wang and Xinshu Xiao and Xia Yang and Laura Hulea and Claudio J Villanueva},

doi = {10.1016/j.xpro.2025.103799},

issn = {2666-1667},

year  = {2025},

date = {2025-04-01},

journal = {STAR Protoc},

volume = {6},

number = {2},

pages = {103799},

abstract = {Here, we present a protocol for polysome profiling in differentiating adipocytes from the mouse stromal vascular fraction. We describe steps for lysate preparation, ultracentrifugation through sucrose gradients, mRNA isolation, RNA sequencing, and motif enrichment. This protocol enables the analysis of actively translating mRNAs and translational gene regulation by isolating polysome-bound mRNA, revealing insights into protein synthesis during adipogenesis or stimuli responses. Applications include studying translational control in adipocytes, metabolic diseases, and obesity, linking translational regulation to cellular and metabolic phenotypes. For complete details on the use and execution of this protocol, please refer to De Siqueira et al..},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40328247,

title = {DNA methyltransferase 1 modulates mitochondrial function through bridging mC RNA methylation},

author = {Jing Wang and Xiaoqian Deng and Tianshen Jian and Shanshan Yin and Linzhi Chen and Laurent Vergnes and Zhehao Li and Huoyuan Liu and Ryan Lee and Sin Yee Lim and Jae Hoon Bahn and Xinshu Xiao and Xianmin Zhu and Ganlu Hu and Karen Reue and Yizhi Liu and Guoping Fan},

doi = {10.1016/j.molcel.2025.04.019},

issn = {1097-4164},

year  = {2025},

date = {2025-04-01},

journal = {Mol Cell},

abstract = {DNA methyltransferase 1 (DNMT1) is an enzyme known for DNA methylation maintenance. Point mutations in its replication focus targeting sequence (RFTS) domain lead to late-onset neurodegeneration, such as autosomal dominant cerebellar ataxia-deafness and narcolepsy (ADCA-DN) disorder. Here, we demonstrated that DNMT1 has the capability to bind to mRNA transcripts and facilitate 5-methylcytosine (mC) RNA methylation by recruiting NOP2/Sun RNA methyltransferase 2 (NSUN2). RNA mC methylation, in turn, promotes RNA stability for those genes modulating mitochondrial function. When the DNMT1 RFTS domain is mutated in mice, it triggers aberrant DNMT1-RNA interaction and significantly elevated mC RNA methylation and RNA stability for a portion of metabolic genes. Consequently, increased levels of metabolic RNA transcripts contribute to cumulative oxidative stress, mitochondrial dysfunction, and neurological symptoms. Collectively, our results reveal a dual role of DNMT1 in regulating both DNA and RNA methylation, which further modulates mitochondrial function, shedding light on the pathogenic mechanism of DNMT1 mutation-induced neurodegeneration.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Cytosine-to-uracil RNA editing is upregulated by pro-inflammatory stimulation of myeloid cells},

author = {Hyomin Seo and Winston H. Cuddleston and Ting Fu and Elisa Navarro and Madison Parks and Amanda Allan and Anastasia G. Efthymiou and Michael S. Breen and Xinshu Xiao and Towfique Raj and Jack Humphrey},

url = {https://www.biorxiv.org/content/10.1101/2025.03.14.643382v1.abstract?%3Fcollection=},

year  = {2025},

date = {2025-03-17},

urldate = {2025-03-17},

journal = {BioRxiv},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid39656777,

title = {Genetic architecture of RNA editing, splicing and gene expression in schizophrenia},

author = {Mudra Choudhury and Ryo Yamamoto and Xinshu Xiao},

doi = {10.1093/hmg/ddae172},

issn = {1460-2083},

year  = {2024},

date = {2024-12-01},

journal = {Hum Mol Genet},

abstract = {Genome wide association studies (GWAS) have been conducted over the past decades to investigate the underlying genetic origin of neuropsychiatric diseases, such as schizophrenia (SCZ). While these studies demonstrated the significance of disease-phenotype associations, there is a pressing need to fully characterize the functional relevance of disease-associated genetic variants. Functional genetic loci can affect transcriptional and post-transcriptional phenotypes that may contribute to disease pathology. Here, we investigate the associations between genetic variation and RNA editing, splicing, and overall gene expression through identification of quantitative trait loci (QTL) in the CommonMind Consortium SCZ cohort. We find that editing QTL (edQTL), splicing QTL (sQTL) and expression QTL (eQTL) possess both unique and common gene targets, which are involved in many disease-relevant pathways, including brain function and immune response. We identified two QTL that fall into all three QTL categories (seedQTL), one of which, rs146498205, targets the lincRNA gene, RP11-156P1.3. In addition, we observe that the RNA binding protein AKAP1, with known roles in neuronal regulation and mitochondrial function, had enriched binding sites among edQTL, including the seedQTL, rs146498205. We conduct colocalization with various brain disorders and find that all QTL have top colocalizations with SCZ and related neuropsychiatric diseases. Furthermore, we identify QTL within biologically relevant GWAS loci, such as in ELA2, an important tRNA processing gene associated with SCZ risk. This work presents the investigation of multiple QTL types in parallel and demonstrates how they target both distinct and overlapping SCZ-relevant genes and pathways.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid39579770,

title = {PPARγ-dependent remodeling of translational machinery in adipose progenitors is impaired in obesity},

author = {Mirian Krystel De Siqueira and Gaoyan Li and Yutian Zhao and Siqi Wang and In Sook Ahn and Mikayla Tamboline and Andrew D Hildreth and Jakeline Larios and Alejandro Schcolnik-Cabrera and Zaynab Nouhi and Zhengyi Zhang and Marcus J Tol and Vijaya Pandey and Shili Xu and Timothy E O'Sullivan and Julia J Mack and Peter Tontonoz and Tamer Sallam and James A Wohlschlegel and Laura Hulea and Xinshu Xiao and Xia Yang and Claudio J Villanueva},

doi = {10.1016/j.celrep.2024.114945},

issn = {2211-1247},

year  = {2024},

date = {2024-11-01},

journal = {Cell Rep},

pages = {114945},

abstract = {Adipose tissue regulates energy homeostasis and metabolic function, but its adaptability is impaired in obesity. In this study, we investigate the impact of acute PPARγ agonist treatment in obese mice and find significant transcriptional remodeling of cells in the stromal vascular fraction (SVF). Using single-cell RNA sequencing, we profile the SVF of inguinal and epididymal adipose tissue of obese mice following rosiglitazone treatment and find an induction of ribosomal factors in both progenitor and preadipocyte populations, while expression of ribosomal factors is reduced with obesity. Notably, the expression of a subset of ribosomal factors is directly regulated by PPARγ. Polysome profiling of the epididymal SVF shows that rosiglitazone promotes translational selectivity of mRNAs that encode pathways involved in adipogenesis and lipid metabolism. Inhibition of translation using a eukaryotic translation initiation factor 4A (eIF4A) inhibitor is sufficient in blocking adipogenesis. Our findings shed light on how PPARγ agonists promote adipose tissue plasticity in obesity.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38925119,

title = {Splicing-specific transcriptome-wide association uncovers genetic mechanisms for schizophrenia},

author = {Jonatan L Hervoso and Kofi Amoah and Jack Dodson and Mudra Choudhury and Arjun Bhattacharya and Giovanni Quinones-Valdez and Bogdan Pasaniuc and Xinshu Xiao},

doi = {10.1016/j.ajhg.2024.06.001},

issn = {1537-6605},

year  = {2024},

date = {2024-06-01},

journal = {Am J Hum Genet},

abstract = {Recent studies have highlighted the essential role of RNA splicing, a key mechanism of alternative RNA processing, in establishing connections between genetic variations and disease. Genetic loci influencing RNA splicing variations show considerable influence on complex traits, possibly surpassing those affecting total gene expression. Dysregulated RNA splicing has emerged as a major potential contributor to neurological and psychiatric disorders, likely due to the exceptionally high prevalence of alternatively spliced genes in the human brain. Nevertheless, establishing direct associations between genetically altered splicing and complex traits has remained an enduring challenge. We introduce Spliced-Transcriptome-Wide Associations (SpliTWAS) to integrate alternative splicing information with genome-wide association studies to pinpoint genes linked to traits through exon splicing events. We applied SpliTWAS to two schizophrenia (SCZ) RNA-sequencing datasets, BrainGVEX and CommonMind, revealing 137 and 88 trait-associated exons (in 84 and 67 genes), respectively. Enriched biological functions in the associated gene sets converged on neuronal function and development, immune cell activation, and cellular transport, which are highly relevant to SCZ. SpliTWAS variants impacted RNA-binding protein binding sites, revealing potential disruption of RNA-protein interactions affecting splicing. We extended the probabilistic fine-mapping method FOCUS to the exon level, identifying 36 genes and 48 exons as putatively causal for SCZ. We highlight VPS45 and APOPT1, where splicing of specific exons was associated with disease risk, eluding detection by conventional gene expression analysis. Collectively, this study supports the substantial role of alternative splicing in shaping the genetic basis of SCZ, providing a valuable approach for future investigations in this area.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38702197,

title = {Navigating the landscape of epitranscriptomics and host immunity},

author = {Elaine Huang and Clara Frydman and Xinshu Xiao},

doi = {10.1101/gr.278412.123},

issn = {1549-5469},

year  = {2024},

date = {2024-05-01},

journal = {Genome Res},

volume = {34},

number = {4},

pages = {515--529},

abstract = {RNA modifications, also termed epitranscriptomic marks, encompass chemical alterations to individual nucleotides, including processes such as methylation and editing. These marks contribute to a wide range of biological processes, many of which are related to host immune system defense. The functions of immune-related RNA modifications can be categorized into three main groups: regulation of immunogenic RNAs, control of genes involved in innate immune response, and facilitation of adaptive immunity. Here, we provide an overview of recent research findings that elucidate the contributions of RNA modifications to each of these processes. We also discuss relevant methods for genome-wide identification of RNA modifications and their immunogenic substrates. Finally, we highlight recent advances in cancer immunotherapies that aim to reduce cancer cell viability by targeting the enzymes responsible for RNA modifications. Our presentation of these dynamic research avenues sets the stage for future investigations in this field.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38815579,

title = {hnRNPM protects against the dsRNA-mediated interferon response by repressing LINE-associated cryptic splicing},

author = {Rong Zheng and Mikayla Dunlap and Georg O M Bobkov and Carlos Gonzalez-Figueroa and Khushali J Patel and Jingyi Lyu and Samuel E Harvey and Tracey W Chan and Giovanni Quinones-Valdez and Mudra Choudhury and Charlotte A Le Roux and Mason D Bartels and Amy Vuong and Ryan A Flynn and Howard Y Chang and Eric L Van Nostrand and Xinshu Xiao and Chonghui Cheng},

doi = {10.1016/j.molcel.2024.05.004},

issn = {1097-4164},

year  = {2024},

date = {2024-05-01},

journal = {Mol Cell},

abstract = {RNA splicing is pivotal in post-transcriptional gene regulation, yet the exponential expansion of intron length in humans poses a challenge for accurate splicing. Here, we identify hnRNPM as an essential RNA-binding protein that suppresses cryptic splicing through binding to deep introns, maintaining human transcriptome integrity. Long interspersed nuclear elements (LINEs) in introns harbor numerous pseudo splice sites. hnRNPM preferentially binds at intronic LINEs to repress pseudo splice site usage for cryptic splicing. Remarkably, cryptic exons can generate long dsRNAs through base-pairing of inverted ALU transposable elements interspersed among LINEs and consequently trigger an interferon response, a well-known antiviral defense mechanism. Significantly, hnRNPM-deficient tumors show upregulated interferon-associated pathways and elevated immune cell infiltration. These findings unveil hnRNPM as a guardian of transcriptome integrity by repressing cryptic splicing and suggest that targeting hnRNPM in tumors may be used to trigger an inflammatory immune response, thereby boosting cancer surveillance.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Massively parallel screen uncovers many rare 3′ UTR variants regulating mRNA abundance of cancer driver genes},

author = {Ting Fu and Kofi Amoah and Tracey W. Chan and Jae Hoon Bahn and Jae-Hyung Lee and Sari Terrazas and Rockie Chong and Sriram Kosuri and Xinshu Xiao},

url = {https://www.nature.com/articles/s41467-024-46795-7},

year  = {2024},

date = {2024-04-18},

urldate = {2024-04-18},

journal = {Nature Communications},

volume = {15},

number = {3335},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37871161,

title = {dsRID: in silico identification of dsRNA regions using long-read RNA-seq data},

author = {Ryo Yamamoto and Zhiheng Liu and Mudra Choudhury and Xinshu Xiao},

doi = {10.1093/bioinformatics/btad649},

issn = {1367-4811},

year  = {2023},

date = {2023-11-01},

journal = {Bioinformatics},

volume = {39},

number = {11},

abstract = {MOTIVATION: Double-stranded RNAs (dsRNAs) are potent triggers of innate immune responses upon recognition by cytosolic dsRNA sensor proteins. Identification of endogenous dsRNAs helps to better understand the dsRNAome and its relevance to innate immunity related to human diseases.nnRESULTS: Here, we report dsRID (double-stranded RNA identifier), a machine-learning-based method to predict dsRNA regions in silico, leveraging the power of long-read RNA-sequencing (RNA-seq) and molecular traits of dsRNAs. Using models trained with PacBio long-read RNA-seq data derived from Alzheimer's disease (AD) brain, we show that our approach is highly accurate in predicting dsRNA regions in multiple datasets. Applied to an AD cohort sequenced by the ENCODE consortium, we characterize the global dsRNA profile with potentially distinct expression patterns between AD and controls. Together, we show that dsRID provides an effective approach to capture global dsRNA profiles using long-read RNA-seq data.nnAVAILABILITY AND IMPLEMENTATION: Software implementation of dsRID, and genomic coordinates of regions predicted by dsRID in all samples are available at the GitHub repository: https://github.com/gxiaolab/dsRID.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@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}

}