@article {750, title = {Arabidopsis bioinformatics resources: The current state, challenges, and priorities for the future}, journal = {Plant Direct}, volume = {3}, year = {2019}, month = {01/2019}, url = {https://onlinelibrary.wiley.com/doi/full/10.1002/pld3.109}, author = {Colleen Doherty and Joanna Friesner and Brian Gregory and Ann Loraine and Molly Megraw and Nicholas Provart and R Keith Slotkin and Chris Town and Sarah M Assmann and Michael Axtell and Tanya Berardini and Sixue Chen and Malia Gehan and Eva Huala and Pankaj Jaiswal and Stephen Larson and Song Li and Sean May and Todd Michael and Chris Pires and Chris Topp and Justin Walley and Eve Wurtele} } @article {312, title = {Small Genetic Circuits and MicroRNAs: Big Players in Polymerase II Transcriptional Control in Plants.}, journal = {Plant Cell}, volume = {28}, year = {2016}, month = {2016 Feb}, pages = {286-303}, abstract = {

RNA Polymerase II (Pol II) regulatory cascades involving transcription factors (TFs) and their targets orchestrate the genetic circuitry of every eukaryotic organism. In order to understand how these cascades function, they can be dissected into small genetic networks, each containing just a few Pol II transcribed genes, that generate specific signal-processing outcomes. Small RNA regulatory circuits involve direct regulation of a small RNA by a TF and/or direct regulation of a TF by a small RNA and have been shown to play unique roles in many organisms. Here, we will focus on small RNA regulatory circuits containing Pol II transcribed microRNAs (miRNAs). While the role of miRNA-containing regulatory circuits as modular building blocks for the function of complex networks has long been on the forefront of studies in the animal kingdom, plant studies are poised to take a lead role in this area because of their advantages in probing transcriptional and posttranscriptional control of Pol II genes. The relative simplicity of tissue- and cell-type organization, miRNA targeting, and genomic structure make the Arabidopsis thaliana plant model uniquely amenable for small RNA regulatory circuit studies in a multicellular organism. In this Review, we cover analysis, tools, and validation methods for probing the component interactions in miRNA-containing regulatory circuits. We then review the important roles that plant miRNAs are playing in these circuits and summarize methods for the identification of small genetic circuits that strongly influence plant function. We conclude by noting areas of opportunity where new plant studies are imminently needed.

}, issn = {1532-298X}, doi = {10.1105/tpc.15.00852}, author = {Megraw, Molly and Cumbie, Jason S and Ivanchenko, Maria G and Filichkin, Sergei A} } @article {315, title = {Environmental stresses modulate abundance and timing of alternatively spliced circadian transcripts in Arabidopsis.}, journal = {Mol Plant}, volume = {8}, year = {2015}, month = {2015 Feb}, pages = {207-27}, abstract = {

Environmental stresses profoundly altered accumulation of nonsense mRNAs including intron-retaining (IR) transcripts in Arabidopsis. Temporal patterns of stress-induced IR mRNAs were dissected using both oscillating and non-oscillating transcripts. Broad-range thermal cycles triggered a sharp increase in the long IR CCA1 isoforms and altered their phasing to different times of day. Both abiotic and biotic stresses such as drought or Pseudomonas syringae infection induced a similar increase. Thermal stress induced a time delay in accumulation of CCA1 I4Rb transcripts, whereas functional mRNA showed steady oscillations. Our data favor a hypothesis that stress-induced instabilities of the central oscillator can be in part compensated through fluctuations in abundance and out-of-phase oscillations of CCA1 IR transcripts. Taken together, our results support a concept that mRNA abundance can be modulated through altering ratios between functional and nonsense/IR transcripts. SR45 protein specifically bound to the retained CCA1 intron in\ vitro, suggesting that this splicing factor could be involved in regulation of intron retention. Transcriptomes of nonsense-mediated mRNA decay (NMD)-impaired and heat-stressed plants shared a set of retained introns associated with stress- and defense-inducible transcripts. Constitutive activation of certain stress response networks in an NMD mutant could be linked to disequilibrium between functional and nonsense mRNAs.

}, keywords = {Alternative Splicing, Arabidopsis, Arabidopsis Proteins, Circadian Clocks, Gene Expression Regulation, Plant, Introns, Nonsense Mediated mRNA Decay}, issn = {1752-9867}, doi = {10.1016/j.molp.2014.10.011}, author = {Filichkin, Sergei A and Cumbie, Jason S and Dharmawardhana, Palitha and Jaiswal, Pankaj and Chang, Jeff H and Palusa, Saiprasad G and Reddy, A S N and Megraw, Molly and Mockler, Todd C} } @article {310, title = {Improved DNase-seq protocol facilitates high resolution mapping of DNase I hypersensitive sites in roots in Arabidopsis thaliana.}, journal = {Plant Methods}, volume = {11}, year = {2015}, month = {2015}, pages = {42}, abstract = {

BACKGROUND: Identifying cis-regulatory elements is critical in understanding the direct and indirect regulatory mechanisms of gene expression. Current approaches include DNase-seq, a technique that combines sensitivity to the nonspecific endonuclease DNase I with high throughput sequencing to identify regions of regulatory DNA on a genome-wide scale. While this method was originally developed for human cell lines, later adaptations made the processing of plant tissues possible. Challenges still remain in processing recalcitrant tissues that have low DNA content.

RESULTS: By removing steps requiring the use of gel agarose plugs in DNase-seq, we were able to significantly reduce the time required to perform the protocol by at least 2\ days, while also making possible the processing of difficult plant tissues. We refer to this simplified protocol as DNase I SIM (for simplified in-nucleus method). We were able to successfully create DNase-seq libraries for both leaf and root tissues in Arabidopsis using DNase I SIM.

CONCLUSION: This protocol simplifies and facilitates generation of DNase-seq libraries from plant tissues for high resolution mapping of DNase I hypersensitive sites.

[Link to Protocol, Additional Data, and Supplementary Materials]

}, issn = {1746-4811}, doi = {10.1186/s13007-015-0087-1}, author = {Cumbie, Jason S and Filichkin, Sergei A and Megraw, Molly} } @article {311, title = {NanoCAGE-XL and CapFilter: an approach to genome wide identification of high confidence transcription start sites.}, journal = {BMC Genomics}, volume = {16}, year = {2015}, month = {2015}, pages = {597}, abstract = {

BACKGROUND: Identifying the transcription start sites (TSS) of genes is essential for characterizing promoter regions. Several protocols have been developed to capture the 5\&$\#$39; end of transcripts via Cap Analysis of Gene Expression (CAGE) or linker-ligation strategies such as Paired-End Analysis of Transcription Start Sites (PEAT), but often require large amounts of tissue. More recently, nanoCAGE was developed for sequencing on the Illumina GAIIx to overcome these difficulties.

RESULTS: Here we present the first publicly available adaptation of nanoCAGE for sequencing on recent ultra-high throughput platforms such as Illumina HiSeq-2000, and CapFilter, a computational pipeline that greatly increases confidence in TSS identification. We report excellent gene coverage, reproducibility, and precision in transcription start site discovery for samples from Arabidopsis thaliana roots.

CONCLUSION: nanoCAGE-XL together with CapFilter allows for genome wide identification of high confidence transcription start sites in large eukaryotic genomes.

[Link to Protocol, Additional Data, and Supplementary Materials]

[Link to CapFilter Software]

}, keywords = {Arabidopsis, Genes, Plant, Genome, Plant, Nanotechnology, Plant Roots, Promoter Regions, Genetic, Sequence Analysis, DNA, Software, Transcription Initiation Site}, issn = {1471-2164}, doi = {10.1186/s12864-015-1670-6}, author = {Cumbie, Jason S and Ivanchenko, Maria G and Megraw, Molly} } @article {317, title = {Environmental Stresses Modulate Abundance and Timing of Alternatively Spliced Circadian Transcripts in Arabidopsis.}, journal = {Mol Plant}, year = {2014}, month = {2014 Nov 3}, abstract = {

Environmental stresses profoundly altered accumulation of nonsense mRNAs including intron retaining (IR) transcripts in Arabidopsis. Temporal patterns of stress-induced IR mRNAs were dissected using both oscillating and non-oscillating transcripts. Broad range thermal cycles triggered a sharp increase in the long intron retaining CCA1 isoforms and altered their phasing to different times of day. Both abiotic and biotic stresses such as drought or P. syringae infection induced similar increase. Thermal stress induced a time delay in accumulation of CCA1 I4Rb transcripts whereas functional mRNA showed steady oscillations. Our data favor a hypothesis that stress-induced instabilities of the central oscillator can be in part compensated through fluctuations in abundance and out of phase oscillations of CCA1 IR transcripts. Altogether, our results support a concept that mRNA abundance can be modulated through altering ratios between functional and nonsense/IR transcripts. SR45 protein specifically bound to the retained CCA1 intron in vitro, suggesting that this splicing factor could be involved in regulation of intron retention. Transcriptomes of NMD-impaired and heat-stressed plants shared a set of retained introns associated with stress- and defense-inducible transcripts. Constitutive activation of certain stress response networks in an NMD mutant could be linked to disequilibrium between functional and nonsense mRNAs.

}, issn = {1752-9867}, doi = {10.1093/mp/ssu130}, author = {Filichkin, Sergei A and Cumbie, Jason S and Dharmawadhana, J Palitha and Jaiswal, Pankaj and Chang, Jeff H and Palusa, Saiprasad G and Reddy, A S N and Megraw, Molly and Mockler, Todd C} } @article {319, title = {Paired-end analysis of transcription start sites in Arabidopsis reveals plant-specific promoter signatures.}, journal = {Plant Cell}, volume = {26}, year = {2014}, month = {2014 Jul}, pages = {2746-60}, abstract = {

Understanding plant gene promoter architecture has long been a challenge due to the lack of relevant large-scale data sets and analysis methods. Here, we present a publicly available, large-scale transcription start site (TSS) data set in plants using a high-resolution method for analysis of 5\&$\#$39; ends of mRNA transcripts. Our data set is produced using the paired-end analysis of transcription start sites (PEAT) protocol, providing millions of TSS locations from wild-type Columbia-0 Arabidopsis thaliana whole root samples. Using this data set, we grouped TSS reads into \"TSS tag clusters\" and categorized clusters into three spatial initiation patterns: narrow peak, broad with peak, and weak peak. We then designed a machine learning model that predicts the presence of TSS tag clusters with outstanding sensitivity and specificity for all three initiation patterns. We used this model to analyze the transcription factor binding site content of promoters exhibiting these initiation patterns. In contrast to the canonical notions of TATA-containing and more broad \"TATA-less\" promoters, the model shows that, in plants, the vast majority of transcription start sites are TATA free and are defined by a large compendium of known DNA sequence binding elements. We present results on the usage of these elements and provide our Plant PEAT Peaks (3PEAT) model that predicts the presence of TSSs directly from sequence.

[Link to Additional Data and Supplementary Materials]

}, keywords = {Arabidopsis, Arabidopsis Proteins, Binding Sites, Cluster Analysis, DNA, Plant, Gene Expression Regulation, Plant, Genome, Plant, Models, Genetic, Nucleotide Motifs, Plant Roots, Promoter Regions, Genetic, RNA, Messenger, RNA, Plant, Sequence Analysis, DNA, Species Specificity, TATA Box, Transcription Factors, Transcription Initiation Site}, issn = {1532-298X}, doi = {10.1105/tpc.114.125617}, author = {Morton, Taj and Petricka, Jalean and Corcoran, David L and Li, Song and Winter, Cara M and Carda, Alexa and Benfey, Philip N and Ohler, Uwe and Megraw, Molly} } @article {328, title = {Genomic and epigenetic alterations deregulate microRNA expression in human epithelial ovarian cancer.}, journal = {Proc Natl Acad Sci U S A}, volume = {105}, year = {2008}, month = {2008 May 13}, pages = {7004-9}, abstract = {

MicroRNAs (miRNAs) are an abundant class of small noncoding RNAs that function as negative gene regulators. miRNA deregulation is involved in the initiation and progression of human cancer; however, the underlying mechanism and its contributions to genome-wide transcriptional changes in cancer are still largely unknown. We studied miRNA deregulation in human epithelial ovarian cancer by integrative genomic approach, including miRNA microarray (n = 106), array-based comparative genomic hybridization (n = 109), cDNA microarray (n = 76), and tissue array (n = 504). miRNA expression is markedly down-regulated in malignant transformation and tumor progression. Genomic copy number loss and epigenetic silencing, respectively, may account for the down-regulation of approximately 15\% and at least approximately 36\% of miRNAs in advanced ovarian tumors and miRNA down-regulation contributes to a genome-wide transcriptional deregulation. Last, eight miRNAs located in the chromosome 14 miRNA cluster (Dlk1-Gtl2 domain) were identified as potential tumor suppressor genes. Therefore, our results suggest that miRNAs may offer new biomarkers and therapeutic targets in epithelial ovarian cancer.

}, keywords = {DNA, Neoplasm, Down-Regulation, Epigenesis, Genetic, Epithelial Cells, Female, Gene Expression Profiling, Gene Expression Regulation, Neoplastic, Genome, Human, Humans, MicroRNAs, Neoplasm Staging, Ovarian Neoplasms, Ribonuclease III, RNA, Messenger, Survival Analysis}, issn = {1091-6490}, doi = {10.1073/pnas.0801615105}, author = {Zhang, Lin and Volinia, Stefano and Bonome, Tomas and Calin, George Adrian and Greshock, Joel and Yang, Nuo and Liu, Chang-Gong and Giannakakis, Antonis and Alexiou, Pangiotis and Hasegawa, Kosei and Johnstone, Cameron N and Megraw, Molly S and Adams, Sarah and Lassus, Heini and Huang, Jia and Kaur, Sippy and Liang, Shun and Sethupathy, Praveen and Leminen, Arto and Simossis, Victor A and Sandaltzopoulos, Raphael and Naomoto, Yoshio and Katsaros, Dionyssios and Gimotty, Phyllis A and DeMichele, Angela and Huang, Qihong and B{\"u}tzow, Ralf and Rustgi, Anil K and Weber, Barbara L and Birrer, Michael J and Hatzigeorgiou, Artemis G and Croce, Carlo M and Coukos, George} } @article {329, title = {miRGen: a database for the study of animal microRNA genomic organization and function.}, journal = {Nucleic Acids Res}, volume = {35}, year = {2007}, month = {2007 Jan}, pages = {D149-55}, abstract = {

miRGen is an integrated database of (i) positional relationships between animal miRNAs and genomic annotation sets and (ii) animal miRNA targets according to combinations of widely used target prediction programs. A major goal of the database is the study of the relationship between miRNA genomic organization and miRNA function. This is made possible by three integrated and user friendly interfaces. The Genomics interface allows the user to explore where whole-genome collections of miRNAs are located with respect to UCSC genome browser annotation sets such as Known Genes, Refseq Genes, Genscan predicted genes, CpG islands and pseudogenes. These miRNAs are connected through the Targets interface to their experimentally supported target genes from TarBase, as well as computationally predicted target genes from optimized intersections and unions of several widely used mammalian target prediction programs. Finally, the Clusters interface provides predicted miRNA clusters at any given inter-miRNA distance and provides specific functional information on the targets of miRNAs within each cluster. All of these unique features of miRGen are designed to facilitate investigations into miRNA genomic organization, co-transcription and targeting. miRGen can be freely accessed at http://www.diana.pcbi.upenn.edu/miRGen.

}, keywords = {Animals, Data Interpretation, Statistical, Databases, Nucleic Acid, Genomics, Humans, Internet, Mice, MicroRNAs, Rats, User-Computer Interface}, issn = {1362-4962}, doi = {10.1093/nar/gkl904}, author = {Megraw, Molly and Sethupathy, Praveen and Corda, Benoit and Hatzigeorgiou, Artemis G} } @article {332, title = {microRNAs exhibit high frequency genomic alterations in human cancer.}, journal = {Proc Natl Acad Sci U S A}, volume = {103}, year = {2006}, month = {2006 Jun 13}, pages = {9136-41}, abstract = {

MicroRNAs (miRNAs) are endogenous noncoding RNAs, which negatively regulate gene expression. To determine genomewide miRNA DNA copy number abnormalities in cancer, 283 known human miRNA genes were analyzed by high-resolution array-based comparative genomic hybridization in 227 human ovarian cancer, breast cancer, and melanoma specimens. A high proportion of genomic loci containing miRNA genes exhibited DNA copy number alterations in ovarian cancer (37.1\%), breast cancer (72.8\%), and melanoma (85.9\%), where copy number alterations observed in \>15\% tumors were considered significant for each miRNA gene. We identified 41 miRNA genes with gene copy number changes that were shared among the three cancer types (26 with gains and 15 with losses) as well as miRNA genes with copy number changes that were unique to each tumor type. Importantly, we show that miRNA copy changes correlate with miRNA expression. Finally, we identified high frequency copy number abnormalities of Dicer1, Argonaute2, and other miRNA-associated genes in breast and ovarian cancer as well as melanoma. These findings support the notion that copy number alterations of miRNAs and their regulatory genes are highly prevalent in cancer and may account partly for the frequent miRNA gene deregulation reported in several tumor types.

}, keywords = {Breast Neoplasms, Female, Gene Dosage, Gene Expression Profiling, Humans, MicroRNAs, Neoplasms, Nucleic Acid Hybridization, Oligonucleotide Array Sequence Analysis, Ovarian Neoplasms, Statistics as Topic}, issn = {0027-8424}, doi = {10.1073/pnas.0508889103}, author = {Zhang, Lin and Huang, Jia and Yang, Nuo and Greshock, Joel and Megraw, Molly S and Giannakakis, Antonis and Liang, Shun and Naylor, Tara L and Barchetti, Andrea and Ward, Michelle R and Yao, George and Medina, Angelica and O{\textquoteright}brien-Jenkins, Ann and Katsaros, Dionyssios and Hatzigeorgiou, Artemis and Gimotty, Phyllis A and Weber, Barbara L and Coukos, George} }