@article{hislop_luby_loarca_humann_hummer_bassil_zhao_sheehan_casa_billings_et al._2024, title={A Blueberry (<i> Vaccinium</i> L.) Crop Ontology to Enable Standardized Phenotyping for Blueberry Breeding and Research}, volume={59}, ISSN={["2327-9834"]}, DOI={10.21273/HORTSCI17676-23}, abstractNote={Breeding programs around the world continually collect data on large numbers of individuals. To be able to combine data collected across regions, years, and experiments, research communities develop standard operating procedures for data collection and measurement. One such method is a crop ontology, or a standardized vocabulary for collecting data on commonly measured traits. The ontology is also computer readable to facilitate the use of data management systems such as databases. Blueberry breeders and researchers across the United States have come together to develop the first standardized crop ontology in blueberry ( Vaccinium spp.). We provide an overview and report on the construction of the first blueberry crop ontology and the 178 traits and methods included within. Researchers of Vaccinium species—such as other blueberry species, cranberry, lingonberry, and bilberry—can use the described crop ontology to collect phenotypic data of greater quality and consistency, interoperability, and computer readability. Crop ontologies, as a shared data language, benefit the entire worldwide research community by enabling collaborative meta-analyses that can be used with genomic data for quantitative trait loci, genome-wide association studies, and genomic selection analysis.}, number={10}, journal={HORTSCIENCE}, author={Hislop, Lillian M. and Luby, Claire H. and Loarca, Jenyne and Humann, Jodi and Hummer, Kim E. and Bassil, Nahla and Zhao, Dongyan and Sheehan, Moira J. and Casa, Alexandra M. and Billings, Grant T. and et al.}, year={2024}, month={Oct}, pages={1433–1442} }
 @article{james_manching_mattia_bowman_hulse-kemp_beksi_2024, title={CitDet: A Benchmark Dataset for Citrus Fruit Detection}, url={https://doi.org/10.1109/LRA.2024.3474473}, DOI={10.1109/LRA.2024.3474473}, journal={IEEE Robotics and Automation Letters}, author={James, Jordan A. and Manching, Heather K. and Mattia, Matthew R. and Bowman, Kim D. and Hulse-Kemp, Amanda M. and Beksi, William J.}, year={2024}, month={Dec} }
 @article{islam_corak_mccord_hulse-kemp_lipka_2023, title={A first look at the ability to use genomic prediction for improving the ratooning ability of sugarcane}, volume={14}, ISSN={["1664-462X"]}, DOI={10.3389/fpls.2023.1205999}, abstractNote={The sugarcane ratooning ability (RA) is the most important target trait for breeders seeking to enhance the profitability of sugarcane production by reducing the planting cost. Understanding the genetics governing the RA could help breeders by identifying molecular markers that could be used for genomics-assisted breeding (GAB). A replicated field trial was conducted for three crop cycles (plant cane, first ratoon, and second ratoon) using 432 sugarcane clones and used for conducting genome-wide association and genomic prediction of five sugar and yield component traits of the RA. The RA traits for economic index (EI), stalk population (SP), stalk weight (SW), tonns of cane per hectare (TCH), and tonns of sucrose per hectare (TSH) were estimated from the yield and sugar data. A total of six putative quantitative trait loci and eight nonredundant single-nucleotide polymorphism (SNP) markers were associated with all five tested RA traits and appear to be unique. Seven putative candidate genes were colocated with significant SNPs associated with the five RA traits. The genomic prediction accuracies for those tested traits were moderate and ranged from 0.21 to 0.36. However, the models fitting fixed effects for the most significant associated markers for each respective trait did not give any advantages over the standard models without fixed effects. As a result of this study, more robust markers could be used in the future for clone selection in sugarcane, potentially helping resolve the genetic control of the RA in sugarcane.}, journal={FRONTIERS IN PLANT SCIENCE}, author={Islam, Md. Sariful and Corak, Keo and McCord, Per and Hulse-Kemp, Amanda M. and Lipka, Alexander E.}, year={2023}, month={Aug} }
 @article{schoonmaker_hulse-kemp_youngblood_rahmat_iqbal_rahman_kochan_scheffler_scheffler_2023, title={Detecting Cotton Leaf Curl Virus Resistance Quantitative Trait Loci in Gossypium hirsutum and iCottonQTL a New R/Shiny App to Streamline Genetic Mapping}, volume={12}, ISSN={["2223-7747"]}, url={https://doi.org/10.3390/plants12051153}, DOI={10.3390/plants12051153}, abstractNote={Cotton leaf curl virus (CLCuV) causes devastating losses to fiber production in Central Asia. Viral spread across Asia in the last decade is causing concern that the virus will spread further before resistant varieties can be bred. Current development depends on screening each generation under disease pressure in a country where the disease is endemic. We utilized quantitative trait loci (QTL) mapping in four crosses with different sources of resistance to identify single nucleotide polymorphism (SNP) markers associated with the resistance trait to allow development of varieties without the need for field screening every generation. To assist in the analysis of multiple populations, a new publicly available R/Shiny App was developed to streamline genetic mapping using SNP arrays and to also provide an easy method to convert and deposit genetic data into the CottonGen database. Results identified several QTL from each cross, indicating possible multiple modes of resistance. Multiple sources of resistance would provide several genetic routes to combat the virus as it evolves over time. Kompetitive allele specific PCR (KASP) markers were developed and validated for a subset of QTL, which can be used in further development of CLCuV-resistant cotton lines.}, number={5}, journal={PLANTS-BASEL}, author={Schoonmaker, Ashley N. and Hulse-Kemp, Amanda M. and Youngblood, Ramey C. and Rahmat, Zainab and Iqbal, Muhammad Atif and Rahman, Mehboob-ur and Kochan, Kelli J. and Scheffler, Brian E. and Scheffler, Jodi A.}, year={2023}, month={Mar} }
 @article{newman_andres_youngblood_campbell_simpson_cannon_scheffler_oakley_hulse-kemp_dunne_2023, title={Initiation of genomics-assisted breeding in Virginia-type peanuts through the generation of a de novo reference genome and informative markers}, volume={13}, ISSN={["1664-462X"]}, DOI={10.3389/fpls.2022.1073542}, abstractNote={IntroductionVirginia-type peanut, Arachis hypogaea subsp. hypogaea, is the second largest market class of peanut cultivated in the United States. It is mainly used for large-seeded, in-shell products. Historically, Virginia-type peanut cultivars were developed through long-term recurrent phenotypic selection and wild species introgression projects. Contemporary genomic technologies represent a unique opportunity to revolutionize the traditional breeding pipeline. While there are genomic tools available for wild and cultivated peanuts, none are tailored specifically to applied Virginia-type cultivar development programs.Methods and respective resultsHere, the first Virginia-type peanut reference genome, “Bailey II”, was assembled. It has improved contiguity and reduced instances of manual curation in chromosome arms. Whole-genome sequencing and marker discovery was conducted on 66 peanut lines which resulted in 1.15 million markers. The high marker resolution achieved allowed 34 unique wild species introgression blocks to be cataloged in the A. hypogaea genome, some of which are known to confer resistance to one or more pathogens. To enable marker-assisted selection of the blocks, 111 PCR Allele Competitive Extension assays were designed. Forty thousand high quality markers were selected from the full set that are suitable for mid-density genotyping for genomic selection. Genomic data from representative advanced Virginia-type peanut lines suggests this is an appropriate base population for genomic selection.DiscussionThe findings and tools produced in this research will allow for rapid genetic gain in the Virginia-type peanut population. Genomics-assisted breeding will allow swift response to changing biotic and abiotic threats, and ultimately the development of superior cultivars for public use and consumption.}, journal={FRONTIERS IN PLANT SCIENCE}, author={Newman, Cassondra S. S. and Andres, Ryan J. J. and Youngblood, Ramey C. C. and Campbell, Jacqueline D. D. and Simpson, Sheron A. A. and Cannon, Steven B. B. and Scheffler, Brian E. E. and Oakley, Andrew T. T. and Hulse-Kemp, Amanda M. M. and Dunne, Jeffrey C. C.}, year={2023}, month={Jan} }
 @article{huff_hulse-kemp_scheffler_youngblood_simpson_babiker_staton_2023, title={Long-read, chromosome-scale assembly of Vitis rotundifolia cv. Carlos and its unique resistance to Xylella fastidiosa subsp. fastidiosa}, volume={24}, ISSN={["1471-2164"]}, DOI={10.1186/s12864-023-09514-y}, abstractNote={Abstract
                Background
                Muscadine grape (Vitis rotundifolia) is resistant to many of the pathogens that negatively impact the production of common grape (V. vinifera), including the bacterial pathogen Xylella fastidiosa subsp. fastidiosa (Xfsf), which causes Pierce’s Disease (PD). Previous studies in common grape have indicated Xfsf delays host immune response with a complex O-chain antigen produced by the wzy gene. Muscadine cultivars range from tolerant to completely resistant to Xfsf, but the mechanism is unknown.
              
                Results
                We assembled and annotated a new, long-read genome assembly for ‘Carlos’, a cultivar of muscadine that exhibits tolerance, to build upon the existing genetic resources available for muscadine. We used these resources to construct an initial pan-genome for three cultivars of muscadine and one cultivar of common grape. This pan-genome contains a total of 34,970 synteny-constrained entries containing genes of similar structure. Comparison of resistance gene content between the ‘Carlos’ and common grape genomes indicates an expansion of resistance (R) genes in ‘Carlos.’ We further identified genes involved in Xfsf response by transcriptome sequencing ‘Carlos’ plants inoculated with Xfsf. We observed 234 differentially expressed genes with functions related to lipid catabolism, oxidation-reduction signaling, and abscisic acid (ABA) signaling as well as seven R genes. Leveraging public data from previous experiments of common grape inoculated with Xfsf, we determined that most differentially expressed genes in the muscadine response were not found in common grape, and three of the R genes identified as differentially expressed in muscadine do not have an ortholog in the common grape genome.
              
                Conclusions
                Our results support the utility of a pan-genome approach to identify candidate genes for traits of interest, particularly disease resistance to Xfsf, within and between muscadine and common grape.
              }, number={1}, journal={BMC GENOMICS}, author={Huff, Matthew and Hulse-Kemp, Amanda M. and Scheffler, Brian E. and Youngblood, Ramey C. and Simpson, Sheron A. and Babiker, Ebrahiem and Staton, Margaret}, year={2023}, month={Jul} }
 @article{delorean_youngblood_simpson_schoonmaker_scheffler_rutter_hulse-kemp_2023, title={Representing true plant genomes: haplotype-resolved hybrid pepper genome with trio-binning}, volume={14}, ISSN={["1664-462X"]}, DOI={10.3389/fpls.2023.1184112}, abstractNote={As sequencing costs decrease and availability of high fidelity long-read sequencing increases, generating experiment specific de novo genome assemblies becomes feasible. In many crop species, obtaining the genome of a hybrid or heterozygous individual is necessary for systems that do not tolerate inbreeding or for investigating important biological questions, such as hybrid vigor. However, most genome assembly methods that have been used in plants result in a merged single sequence representation that is not a true biologically accurate representation of either haplotype within a diploid individual. The resulting genome assembly is often fragmented and exhibits a mosaic of the two haplotypes, referred to as haplotype-switching. Important haplotype level information, such as causal mutations and structural variation is therefore lost causing difficulties in interpreting downstream analyses. To overcome this challenge, we have applied a method developed for animal genome assembly called trio-binning to an intra-specific hybrid of chili pepper (Capsicum annuum L. cv. HDA149 x Capsicum annuum L. cv. HDA330). We tested all currently available softwares for performing trio-binning, combined with multiple scaffolding technologies including Bionano to determine the optimal method of producing the best haplotype-resolved assembly. Ultimately, we produced highly contiguous biologically true haplotype-resolved genome assemblies for each parent, with scaffold N50s of 266.0 Mb and 281.3 Mb, with 99.6% and 99.8% positioned into chromosomes respectively. The assemblies captured 3.10 Gb and 3.12 Gb of the estimated 3.5 Gb chili pepper genome size. These assemblies represent the complete genome structure of the intraspecific hybrid, as well as the two parental genomes, and show measurable improvements over the currently available reference genomes. Our manuscript provides a valuable guide on how to apply trio-binning to other plant genomes.}, journal={FRONTIERS IN PLANT SCIENCE}, author={Delorean, Emily E. and Youngblood, Ramey C. and Simpson, Sheron A. and Schoonmaker, Ashley N. and Scheffler, Brian E. and Rutter, William B. and Hulse-Kemp, Amanda M.}, year={2023}, month={Nov} }
 @article{wu_simpson_youngblood_liu_scheffler_rinehart_alexander_hulse-kemp_2023, title={Two haplotype-resolved genomes reveal important flower traits in bigleaf hydrangea (Hydrangea macrophylla) and insights into Asterid evolution}, volume={10}, ISSN={["2052-7276"]}, DOI={10.1093/hr/uhad217}, abstractNote={Abstract
               The Hydrangea genus belongs to the Hydrangeaceae family, in the Cornales order of flowering plants, which early diverged among the Asterids, and includes several species that are commonly used ornamental plants. Of them, Hydrangea macrophylla is one of the most valuable species in the nursery trade, yet few genomic resources are available for this crop or closely related Asterid species. Two high-quality haplotype-resolved reference genomes of hydrangea cultivars ‘Veitchii’ and ‘Endless Summer’ [highest quality at 2.22 gigabase pairs (Gb), 396 contigs, N50 22.8 megabase pairs (Mb)] were assembled and scaffolded into the expected 18 pseudochromosomes. Utilizing the newly developed high-quality reference genomes along with high-quality genomes of other related flowering plants, nuclear data were found to support a single divergence point in the Asterids clade where both the Cornales and Ericales diverged from the euasterids. Genetic mapping with an F1 hybrid population demonstrated the power of linkage mapping combined with the new genomic resources to identify the gene for inflorescence shape, CYP78A5 located on chromosome 4, and a novel gene, BAM3 located on chromosome 17, for causing double flower. Resources developed in this study will not only help to accelerate hydrangea genetic improvement but also contribute to understanding the largest group of flowering plants, the Asterids.}, number={12}, journal={HORTICULTURE RESEARCH}, author={Wu, Xingbo and Simpson, Sheron A. and Youngblood, Ramey C. and Liu, Xiaofen F. and Scheffler, Brian E. and Rinehart, Timothy A. and Alexander, Lisa W. and Hulse-Kemp, Amanda M.}, year={2023}, month={Dec} }
 @article{kloppe_whetten_kim_powell_lück_douchkov_whetten_hulse‐kemp_balint‐kurti_cowger_2023, title={Two pathogen loci determine <i>Blumeria graminis}, volume={238}, ISSN={0028-646X 1469-8137}, url={http://dx.doi.org/10.1111/nph.18809}, DOI={10.1111/nph.18809}, abstractNote={Summary


Blumeria graminis f. sp. tritici (Bgt) is a globally important fungal pathogen of wheat that can rapidly evolve to defeat wheat powdery mildew (Pm) resistance genes. Despite periodic regional deployment of the Pm1a resistance gene in US wheat production, Bgt strains that overcome Pm1a have been notably nonpersistent in the United States, while on other continents, they are more widely established.

A genome‐wide association study (GWAS) was conducted to map sequence variants associated with Pm1a virulence in 216 Bgt isolates from six countries, including the United States. A virulence variant apparently unique to Bgt isolates from the United States was detected in the previously mapped gene AvrPm1a (BgtE‐5612) on Bgt chromosome 6; an in vitro growth assay suggested no fitness reduction associated with this variant.

A gene on Bgt chromosome 8, Bgt‐51526, was shown to function as a second determinant of Pm1a virulence, and despite < 30% amino acid identity, BGT‐51526 and BGTE‐5612 were predicted to share > 85% of their secondary structure. A co‐expression study in Nicotiana benthamiana showed that BGTE‐5612 and BGT‐51526 each produce a PM1A‐dependent hypersensitive response.

More than one member of a B. graminis effector family can be recognized by a single wheat immune receptor, and a two‐gene model is necessary to explain virulence to Pm1a.

}, number={4}, journal={New Phytologist}, publisher={Wiley}, author={Kloppe, Tim and Whetten, Rebecca B. and Kim, Saet‐Byul and Powell, Oliver R. and Lück, Stefanie and Douchkov, Dimitar and Whetten, Ross W. and Hulse‐Kemp, Amanda M. and Balint‐Kurti, Peter and Cowger, Christina}, year={2023}, month={Mar}, pages={1546–1561} }
 @article{chang_marczuk-rojas_waterman_garcia-llanos_chen_ma_hulse-kemp_van deynze_peer_carretero-paulet_2022, title={Chromosome-scale assembly of the Moringa oleifera Lam. genome uncovers polyploid history and evolution of secondary metabolism pathways through tandem duplication}, volume={7}, ISSN={["1940-3372"]}, url={https://doi.org/10.1002/tpg2.20238}, DOI={10.1002/tpg2.20238}, abstractNote={AbstractThe African Orphan Crops Consortium (AOCC) selected the highly nutritious, fast growing and drought tolerant tree crop moringa (Moringa oleifera Lam.) as one of the first of 101 plant species to have its genome sequenced and a first draft assembly was published in 2019. Given the extensive uses and culture of moringa, often referred to as the multipurpose tree, we generated a significantly improved new version of the genome based on long‐read sequencing into 14 pseudochromosomes equivalent to n = 14 haploid chromosomes. We leveraged this nearly complete version of the moringa genome to investigate main drivers of gene family and genome evolution that may be at the origin of relevant biological innovations including agronomical favorable traits. Our results reveal that moringa has not undergone any additional whole‐genome duplication (WGD) or polyploidy event beyond the gamma WGD shared by all core eudicots. Moringa duplicates retained following that ancient gamma events are also enriched for functions commonly considered as dosage balance sensitive. Furthermore, tandem duplications seem to have played a prominent role in the evolution of specific secondary metabolism pathways including those involved in the biosynthesis of bioactive glucosinolate, flavonoid, and alkaloid compounds as well as of defense response pathways and might, at least partially, explain the outstanding phenotypic plasticity attributed to this species. This study provides a genetic roadmap to guide future breeding programs in moringa, especially those aimed at improving secondary metabolism related traits.}, journal={PLANT GENOME}, author={Chang, Jiyang and Marczuk-Rojas, Juan Pablo and Waterman, Carrie and Garcia-Llanos, Armando and Chen, Shiyu and Ma, Xiao and Hulse-Kemp, Amanda and Van Deynze, Allen and Peer, Yves and Carretero-Paulet, Lorenzo}, year={2022}, month={Jul} }
 @article{graham_park_billings_hulse-kemp_haigler_lobaton_2022, title={Efficient imaging and computer vision detection of two cell shapes in young cotton fibers}, volume={11}, ISSN={["2168-0450"]}, url={https://doi.org/10.1002/aps3.11503}, DOI={10.1002/aps3.11503}, abstractNote={AbstractPremiseThe shape of young cotton (Gossypium) fibers varies within and between commercial cotton species, as revealed by previous detailed analyses of one cultivar of G. hirsutum and one of G. barbadense. Both narrow and wide fibers exist in G. hirsutum cv. Deltapine 90, which may impact the quality of our most abundant renewable textile material. More efficient cellular phenotyping methods are needed to empower future research efforts.MethodsWe developed semi‐automated imaging methods for young cotton fibers and a novel machine learning algorithm for the rapid detection of tapered (narrow) or hemisphere (wide) fibers in homogeneous or mixed populations.ResultsThe new methods were accurate for diverse accessions of G. hirsutum and G. barbadense and at least eight times more efficient than manual methods. Narrow fibers dominated in the three G. barbadense accessions analyzed, whereas the three G. hirsutum accessions showed a mixture of tapered and hemisphere fibers in varying proportions.DiscussionThe use or adaptation of these improved methods will facilitate experiments with higher throughput to understand the biological factors controlling the variable shapes of young cotton fibers or other elongating single cells. This research also enables the exploration of links between early cell shape and mature cotton fiber quality in diverse field‐grown cotton accessions.}, journal={APPLICATIONS IN PLANT SCIENCES}, author={Graham, Benjamin P. and Park, Jeremy and Billings, Grant T. and Hulse-Kemp, Amanda M. and Haigler, Candace H. and Lobaton, Edgar}, year={2022}, month={Nov} }
 @article{yu_schoonmaker_yan_hulse-kemp_fontanier_martin_moss_wu_2022, title={Genetic variability and QTL mapping of winter survivability and leaf firing in African bermudagrass}, volume={10}, ISSN={["1435-0653"]}, DOI={10.1002/csc2.20849}, abstractNote={AbstractTurf‐type bermudagrass is susceptible to winterkill when grown in transition zone climates. Minimizing water use in turfgrass management is of societal significance. African bermudagrass (Cynodon transvaalensis Burtt‐Davy) has been extensively used to cross with common bermudagrass (C. dactylon Pers. var. dactylon) in the creation of F1 hybrid cultivars. Little information regarding the molecular basis of winter survivability and drought resistance in African bermudagrass is available. Accordingly, the objectives of this study were to quantify genetic variability and identify quantitative trait loci (QTL) associated with winter survivability traits (spring greenup, SG; spring greenup percent green cover, SGPGC; winterkill, WK), and leaf firing (LF) in African bermudagrass. A total of 109 first‐generation self‐pollinated (S1) progeny of ‘OKC1163’ were evaluated in a field trial in a randomized complete block design with three replications for four seasons. Significant genetic variation existed for all the traits examined, and the broad‐sense heritability estimates ranged from .36 to .54 for the winter survivability traits and .80 for LF. Ten QTL were identified for winter survivability traits and two for LF based on a preexisting high‐density linkage map, which was aligned, reoriented, and renamed as to a recently published reference genome. Seven of 12 QTL were consistently identified at least in 2 yr. The colocation of two QTL, one for winter survivability and another for LF, suggests the possibility of improving both traits together. Findings provide new insights to genetic control of winter survivability traits and LF and contribute genetic resources for marker‐assisted selection in turf‐type bermudagrass improvement.}, journal={CROP SCIENCE}, author={Yu, Shuhao and Schoonmaker, Ashley N. and Yan, Liuling and Hulse-Kemp, Amanda M. and Fontanier, Charles H. and Martin, Dennis L. and Moss, Justin Q. and Wu, Yanqi Q.}, year={2022}, month={Oct} }
 @article{vaughn_branham_abernathy_hulse-kemp_rivers_levi_wechter_2022, title={Graph-based pangenomics maximizes genotyping density and reveals structural impacts on fungal resistance in melon}, volume={13}, ISSN={["2041-1723"]}, DOI={10.1038/s41467-022-35621-7}, abstractNote={AbstractThe genomic sequences segregating in experimental populations are often highly divergent from the community reference and from one another. Such divergence is problematic under various short-read-based genotyping strategies. In addition, large structural differences are often invisible despite being strong candidates for causal variation. These issues are exacerbated in specialty crop breeding programs with fewer, lower-quality sequence resources. Here, we examine the benefits of complete genomic information, based on long-read assemblies, in a biparental mapping experiment segregating at numerous disease resistance loci in the non-model crop, melon (Cucumis melo). We find that a graph-based approach, which uses both parental genomes, results in 19% more variants callable across the population and raw allele calls with a 2 to 3-fold error-rate reduction, even relative to single reference approaches using a parent genome. We show that structural variation has played a substantial role in shaping two Fusarium wilt resistance loci with known causal genes. We also report on the genetics of powdery mildew resistance, where copy number variation and local recombination suppression are directly interpretable via parental genome alignments. Benefits observed, even in this low-resolution biparental experiment, will inevitably be amplified in more complex populations.}, number={1}, journal={NATURE COMMUNICATIONS}, author={Vaughn, Justin N. and Branham, Sandra E. and Abernathy, Brian and Hulse-Kemp, Amanda M. and Rivers, Adam R. and Levi, Amnon and Wechter, William P.}, year={2022}, month={Dec} }
 @article{restrepo-montoya_hulse-kemp_scheffler_haigler_hinze_love_percy_jones_frelichowski_2022, title={Leveraging National Germplasm Collections to Determine Significantly Associated Categorical Traits in Crops: Upland and Pima Cotton as a Case Study}, volume={13}, ISSN={["1664-462X"]}, url={http://dx.doi.org/10.3389/fpls.2022.837038}, DOI={10.3389/fpls.2022.837038}, abstractNote={Observable qualitative traits are relatively stable across environments and are commonly used to evaluate crop genetic diversity. Recently, molecular markers have largely superseded describing phenotypes in diversity surveys. However, qualitative descriptors are useful in cataloging germplasm collections and for describing new germplasm in patents, publications, and/or the Plant Variety Protection (PVP) system. This research focused on the comparative analysis of standardized cotton traits as represented within the National Cotton Germplasm Collection (NCGC). The cotton traits are named by ‘descriptors’ that have non-numerical sub-categories (descriptor states) reflecting the details of how each trait manifests or is absent in the plant. We statistically assessed selected accessions from three major groups ofGossypiumas defined by the NCGC curator: (1) “Stoneville accessions (SA),” containing mainly Upland cotton (Gossypium hirsutum) cultivars; (2) “Texas accessions (TEX),” containing mainlyG. hirsutumlandraces; and (3)Gossypium barbadense(Gb), containing cultivars or landraces of Pima cotton (Gossypium barbadense). For 33 cotton descriptors we: (a) revealed distributions of character states for each descriptor within each group; (b) analyzed bivariate associations between paired descriptors; and (c) clustered accessions based on their descriptors. The fewest significant associations between descriptors occurred in the SA dataset, likely reflecting extensive breeding for cultivar development. In contrast, the TEX and Gb datasets showed a higher number of significant associations between descriptors, likely correlating with less impact from breeding efforts. Three significant bivariate associations were identified for all three groups,bract nectaries:boll nectaries,leaf hair:stem hair, andlint color:seed fuzz color. Unsupervised clustering analysis recapitulated the species labels for about 97% of the accessions. Unexpected clustering results indicated accessions that may benefit from potential further investigation. In the future, the significant associations between standardized descriptors can be used by curators to determine whether new exotic/unusual accessions most closely resemble Upland or Pima cotton. In addition, the study shows how existing descriptors for large germplasm datasets can be useful to inform downstream goals in breeding and research, such as identifying rare individuals with specific trait combinations and targeting breakdown of remaining trait associations through breeding, thus demonstrating the utility of the analytical methods employed in categorizing germplasm diversity within the collection.}, journal={FRONTIERS IN PLANT SCIENCE}, publisher={Frontiers Media SA}, author={Restrepo-Montoya, Daniel and Hulse-Kemp, Amanda M. and Scheffler, Jodi A. and Haigler, Candace H. and Hinze, Lori L. and Love, Janna and Percy, Richard G. and Jones, Don C. and Frelichowski, James}, year={2022}, month={Apr} }
 @article{redpath_aryal_lynch_spencer_hulse-kemp_ballington_green_bassil_hummer_ranney_et al._2022, title={Nuclear DNA contents and ploidy levels of North American Vaccinium species and interspecific hybrids}, volume={297}, ISSN={["1879-1018"]}, DOI={10.1016/j.scienta.2022.110955}, abstractNote={Breeding strategies for improving blueberry (Vaccinium corymbosum and V. virgatum) cultivars often include introgressing regionally adapted species into the cultivated gene pools through interspecific hybridization. However, these approaches are complicated by variation in ploidy, triploid blocks and infertility, production of unreduced gametes, and aneuploidy. The objective of this study was to use flow cytometry, k-mer distribution analysis, and known pedigree information to evaluate genome sizes (2C nuclear and 1Cx monoploid), and ploidy of diverse accessions from Vaccinium sections and species. A total of 369 accessions, including a diversity panel (DP) of 251 inter- and intra-specific hybrid Vaccinium accessions, as well as 118 non-hybrid Vaccinium species across multiple sections, were sampled from the North Carolina State University blueberry breeding program and the National Clonal Germplasm Repository. The nuclear DNA content was analyzed via flow cytometry. The mean (range) DNA content of diploid, tetraploid, and hexaploid reference species were 1.20 pg (0.99 pg in V. crassifolium 'Well's Delight' to 1.41 pg in V. caesariense NC79–24), 2.37 pg (2.11 pg in V. corymbosum 'Concord' to 3.01 pg in V. corymbosum DE599), and 3.64 pg (3.24 in V. constablaei NC83–21–2 to 3.80 in V. virgatum 'Premier' and NC4790), respectively. Of the 369 unique accessions analyzed for ploidy, 259 were tetraploid, 46 were diploid, one was triploid, 51 were pentaploid or aneuploid with 2C values between tetraploid and hexaploid values, and 12 were hexaploid. Tetraploid hybrid pedigrees, which involved hexaploid crosses within three prior generations, had a 2C value range between 2.22 pg and 2.59 pg. Interspecific pentaploid and aneuploid progeny 2C DNA content ranged from 2.61 pg to 3.15 pg. We speculate some of these progeny to be near tetraploids with extra chromosomes from hexaploid progenitors. Further karyotyping of these individuals is necessary to ascertain aneuploidy anomalies. This research provides an expanded knowledge base of genome sizes, ploidy, and reproductive pathways for diverse species and hybrids to enhance future breeding, improvement, and the genomic study of blueberry.}, journal={SCIENTIA HORTICULTURAE}, author={Redpath, Lauren E. and Aryal, Rishi and Lynch, Nathan and Spencer, Jessica A. and Hulse-Kemp, Amanda M. and Ballington, James R. and Green, Jaimie and Bassil, Nahla and Hummer, Kim and Ranney, Thomas and et al.}, year={2022}, month={Apr} }
 @article{billings_jones_rustgi_bridges_holland_hulse-kemp_campbell_2022, title={Outlook for Implementation of Genomics-Based Selection in Public Cotton Breeding Programs}, volume={11}, ISSN={["2223-7747"]}, url={https://doi.org/10.3390/plants11111446}, DOI={10.3390/plants11111446}, abstractNote={Researchers have used quantitative genetics to map cotton fiber quality and agronomic performance loci, but many alleles may be population or environment-specific, limiting their usefulness in a pedigree selection, inbreeding-based system. Here, we utilized genotypic and phenotypic data on a panel of 80 important historical Upland cotton (Gossypium hirsutum L.) lines to investigate the potential for genomics-based selection within a cotton breeding program’s relatively closed gene pool. We performed a genome-wide association study (GWAS) to identify alleles correlated to 20 fiber quality, seed composition, and yield traits and looked for a consistent detection of GWAS hits across 14 individual field trials. We also explored the potential for genomic prediction to capture genotypic variation for these quantitative traits and tested the incorporation of GWAS hits into the prediction model. Overall, we found that genomic selection programs for fiber quality can begin immediately, and the prediction ability for most other traits is lower but commensurate with heritability. Stably detected GWAS hits can improve prediction accuracy, although a significance threshold must be carefully chosen to include a marker as a fixed effect. We place these results in the context of modern public cotton line-breeding and highlight the need for a community-based approach to amass the data and expertise necessary to launch US public-sector cotton breeders into the genomics-based selection era.}, number={11}, journal={PLANTS-BASEL}, author={Billings, Grant T. and Jones, Michael A. and Rustgi, Sachin and Bridges, William C. and Holland, James B. and Hulse-Kemp, Amanda M. and Campbell, B. Todd}, year={2022}, month={Jun} }
 @article{edger_iorizzo_bassil_benevenuto_ferrao_giongo_hummer_lawas_leisner_li_et al._2022, title={There and back again; historical perspective and future directions for Vaccinium breeding and research studies}, volume={9}, ISSN={["2052-7276"]}, DOI={10.1093/hr/uhac083}, abstractNote={Abstract
               The genus Vaccinium L. (Ericaceae) contains a wide diversity of culturally and economically important berry crop species. Consumer demand and scientific research in blueberry (Vaccinium spp.) and cranberry (Vaccinium macrocarpon) have increased worldwide over the crops’ relatively short domestication history (~100 years). Other species, including bilberry (Vaccinium myrtillus), lingonberry (Vaccinium vitis-idaea), and ohelo berry (Vaccinium reticulatum) are largely still harvested from the wild but with crop improvement efforts underway. Here, we present a review article on these Vaccinium berry crops on topics that span taxonomy to genetics and genomics to breeding. We highlight the accomplishments made thus far for each of these crops, along their journey from the wild, and propose research areas and questions that will require investments by the community over the coming decades to guide future crop improvement efforts. New tools and resources are needed to underpin the development of superior cultivars that are not only more resilient to various environmental stresses and higher yielding, but also produce fruit that continue to meet a variety of consumer preferences, including fruit quality and health related traits.}, journal={HORTICULTURE RESEARCH}, author={Edger, Patrick P. and Iorizzo, Massimo and Bassil, Nahla V and Benevenuto, Juliana and Ferrao, Luis Felipe V and Giongo, Lara and Hummer, Kim and Lawas, Lovely Mae F. and Leisner, Courtney P. and Li, Changying and et al.}, year={2022}, month={Jan} }
 @article{hulse-kemp_bostan_chen_ashrafi_stoffel_sanseverino_li_cheng_schatz_garvin_et al._2021, title={An anchored chromosome-scale genome assembly of spinach improves annotation and reveals extensive gene rearrangements in euasterids}, volume={6}, ISSN={["1940-3372"]}, DOI={10.1002/tpg2.20101}, abstractNote={AbstractSpinach (Spinacia oleracea L.) is a member of the Caryophyllales family, a basal eudicot asterid that consists of sugar beet (Beta vulgaris L. subsp. vulgaris), quinoa (Chenopodium quinoa Willd.), and amaranth (Amaranthus hypochondriacus L.). With the introduction of baby leaf types, spinach has become a staple food in many homes. Production issues focus on yield, nitrogen‐use efficiency and resistance to downy mildew (Peronospora effusa). Although genomes are available for the above species, a chromosome‐level assembly exists only for quinoa, allowing for proper annotation and structural analyses to enhance crop improvement. We independently assembled and annotated genomes of the cultivar Viroflay using short‐read strategy (Illumina) and long‐read strategies (Pacific Biosciences) to develop a chromosome‐level, genetically anchored assembly for spinach. Scaffold N50 for the Illumina assembly was 389 kb, whereas that for Pacific BioSciences was 4.43 Mb, representing 911 Mb (93% of the genome) in 221 scaffolds, 80% of which are anchored and oriented on a sequence‐based genetic map, also described within this work. The two assemblies were 99.5% collinear. Independent annotation of the two assemblies with the same comprehensive transcriptome dataset show that the quality of the assembly directly affects the annotation with significantly more genes predicted (26,862 vs. 34,877) in the long‐read assembly. Analysis of resistance genes confirms a bias in resistant gene motifs more typical of monocots. Evolutionary analysis indicates that Spinacia is a paleohexaploid with a whole‐genome triplication followed by extensive gene rearrangements identified in this work. Diversity analysis of 75 lines indicate that variation in genes is ample for hypothesis‐driven, genomic‐assisted breeding enabled by this work.}, journal={PLANT GENOME}, author={Hulse-Kemp, Amanda M. and Bostan, Hamed and Chen, Shiyu and Ashrafi, Hamid and Stoffel, Kevin and Sanseverino, Walter and Li, Linzhou and Cheng, Shifeng and Schatz, Michael C. and Garvin, Tyler and et al.}, year={2021}, month={Jun} }
 @article{wu_hulse-kemp_wadl_smith_mockaitis_staton_rinehart_alexander_2021, title={Genomic Resource Development for Hydrangea (Hydrangea macrophylla (Thunb.) Ser.)-A Transcriptome Assembly and a High-Density Genetic Linkage Map}, volume={7}, ISSN={["2311-7524"]}, DOI={10.3390/horticulturae7020025}, abstractNote={Hydrangea (Hydrangea macrophylla) is an important ornamental crop that has been cultivated for more than 300 years. Despite the economic importance, genetic studies for hydrangea have been limited by the lack of genetic resources. Genetic linkage maps and subsequent trait mapping are essential tools to identify and make markers available for marker-assisted breeding. A transcriptomic study was performed on two important cultivars, Veitchii and Endless Summer, to discover simple sequence repeat (SSR) markers and an F1 population based on the cross ‘Veitchii’ × ‘Endless Summer’ was established for genetic linkage map construction. Genotyping by sequencing (GBS) was performed on the mapping population along with SSR genotyping. From an analysis of 42,682 putative transcripts, 8780 SSRs were identified and 1535 were validated in the mapping parents. A total of 267 polymorphic SSRs were selected for linkage map construction. The GBS yielded 3923 high quality single nucleotide polymorphisms (SNPs) in the mapping population, resulting in a total of 4190 markers that were used to generate maps for each parent and a consensus map. The consensus linkage map contained 1767 positioned markers (146 SSRs and 1621 SNPs), spanned 1383.4 centiMorgans (cM), and was comprised of 18 linkage groups, with an average mapping interval of 0.8 cM. The transcriptome information and large-scale marker development in this study greatly expanded the genetic resources that are available for hydrangea. The high-density genetic linkage maps presented here will serve as an important foundation for quantitative trait loci mapping, map-based gene cloning, and marker-assisted selection of H. macrophylla.}, number={2}, journal={HORTICULTURAE}, author={Wu, Xingbo and Hulse-Kemp, Amanda M. and Wadl, Phillip A. and Smith, Zach and Mockaitis, Keithanne and Staton, Margaret E. and Rinehart, Timothy A. and Alexander, Lisa W.}, year={2021}, month={Feb} }
 @article{yu_hulse-kemp_babiker_staton_2021, title={High-quality reference genome and annotation aids understanding of berry development for evergreen blueberry (Vaccinium darrowii)}, volume={8}, ISSN={["2052-7276"]}, DOI={10.1038/s41438-021-00641-9}, abstractNote={AbstractVaccinium darrowiiCamp (2n = 2x = 24) is a native North American blueberry species and an important source of traits such as low chill requirement in commercial southern highbush blueberry breeding (Vaccinium corymbosum, 2n = 4x = 48). We present a chromosomal-scale genome ofV. darrowiigenerated by the combination of PacBio sequencing and high throughput chromatin conformation capture (Hi–C) scaffolding technologies, yielding a total length of 1.06 Gigabases (Gb). Over 97.8% of the genome sequences are scaffolded into 24 chromosomes representing the two haplotypes. The primary haplotype assembly ofV. darrowiicontains 34,809 protein-coding genes. Comparison to aV. corymbosumhaplotype assembly reveals high collinearity between the two genomes with small intrachromosomal rearrangements in eight chromosome pairs. With small RNA sequencing, the annotation was further expanded to include more than 200,000 small RNA loci and 638 microRNAs expressed in berry tissues. Transcriptome analysis across fruit development stages indicates that genes involved in photosynthesis are downregulated, while genes involved in flavonoid and anthocyanin biosynthesis are significantly increased at the late stage of berry ripening. A high-quality reference genome and accompanying annotation ofV. darrowiiis a significant new resource for assessing the evergreen blueberry contribution to the breeding of southern highbush blueberries.}, number={1}, journal={HORTICULTURE RESEARCH}, author={Yu, Jiali and Hulse-Kemp, Amanda M. and Babiker, Ebrahiem and Staton, Margaret}, year={2021}, month={Dec} }
 @article{billings_jones_rustgi_hulse-kemp_campbell_2021, title={Population structure and genetic diversity of the Pee Dee cotton breeding program}, volume={11}, ISSN={["2160-1836"]}, url={https://doi.org/10.1093/g3journal/jkab145}, DOI={10.1093/g3journal/jkab145}, abstractNote={Abstract
               Accelerated marker-assisted selection and genomic selection breeding systems require genotyping data to select the best parents for combining beneficial traits. Since 1935, the Pee Dee (PD) cotton germplasm enhancement program has developed an important genetic resource for upland cotton (Gossypium hirsutum L.), contributing alleles for improved fiber quality, agronomic performance, and genetic diversity. To date, a detailed genetic survey of the program’s eight historical breeding cycles has yet to be undertaken. The objectives of this study were to evaluate genetic diversity across and within-breeding groups, examine population structure, and contextualize these findings relative to the global upland cotton gene pool. The CottonSNP63K array was used to identify 17,441 polymorphic markers in a panel of 114 diverse PD genotypes. A subset of 4597 markers was selected to decrease marker density bias. Identity-by-state pairwise distance varied substantially, ranging from 0.55 to 0.97. Pedigree-based estimates of relatedness were not very predictive of observed genetic similarities. Few rare alleles were present, with 99.1% of SNP alleles appearing within the first four breeding cycles. Population structure analysis with principal component analysis, discriminant analysis of principal components, fastSTRUCTURE, and a phylogenetic approach revealed an admixed population with moderate substructure. A small core collection (n < 20) captured 99% of the program’s allelic diversity. Allele frequency analysis indicated potential selection signatures associated with stress resistance and fiber cell growth. The results of this study will steer future utilization of the program’s germplasm resources and aid in combining program-specific beneficial alleles and maintaining genetic diversity.}, number={7}, journal={G3-GENES GENOMES GENETICS}, publisher={Oxford University Press (OUP)}, author={Billings, Grant T. and Jones, Michael A. and Rustgi, Sachin and Hulse-Kemp, Amanda M. and Campbell, B. Todd}, year={2021}, month={Jul} }
 @article{jarret_barboza_costa batista_berke_chou_hulse-kemp_ochoa-alejo_tripodi_veres_garcia_et al._2019, title={Capsicum-An Abbreviated Compendium}, volume={144}, ISSN={["2327-9788"]}, DOI={10.21273/JASHS04446-18}, abstractNote={Pepper (Capsicum L.) is a major vegetable and spice crop worldwide. Global production of both fresh and dried fruit continues to increase steadily in terms of area harvested and yield. Various topics are addressed in this review, including recent additions to and clarification of Capsicum taxonomy, genetic resources of Capsicum, cytogenetic studies, the current status of our understanding of the mechanisms affecting the biosynthesis of capsaicinoids, the use of gene mutations to elucidate carotenoid biosynthetic pathways and their regulation, and recent advances in whole-genome sequencing and assembly.}, number={1}, journal={JOURNAL OF THE AMERICAN SOCIETY FOR HORTICULTURAL SCIENCE}, author={Jarret, Robert L. and Barboza, Gloria E. and Costa Batista, Fabiane Rabelo and Berke, Terry and Chou, Yu-Yu and Hulse-Kemp, Amanda and Ochoa-Alejo, Neftali and Tripodi, Pasquale and Veres, Aniko and Garcia, Carolina Carrizo and et al.}, year={2019}, month={Jan}, pages={3–22} }
 @article{ulloa_de santiago_hulse-kemp_stelly_burke_2020, title={Enhancing Upland cotton for drought resilience, productivity, and fiber quality: comparative evaluation and genetic dissection}, volume={295}, ISSN={["1617-4623"]}, url={https://doi.org/10.1007/s00438-019-01611-6}, DOI={10.1007/s00438-019-01611-6}, abstractNote={To provision the world sustainably, modern society must increase overall crop production, while conserving and preserving natural resources. Producing more with diminishing water resources is an especially daunting endeavor. Toward the goal of genetically improving drought resilience of cultivated Upland cotton (Gossypium hirsutum L.), this study addresses the genetics of differential yield components referred to as productivity and fiber quality traits under regular-water versus low-water (LW) field conditions. We used ten traits to assess water stress deficit, which included six productivity and four fiber quality traits on two recombinant inbred line (RIL) populations from reciprocally crossed cultivars, Phytogen 72 and Stoneville 474. To facilitate genetic inferences, we genotyped RILs with the CottonSNP63K array, assembled high-density linkage maps of over 7000 SNPs and then analyzed quantitative trait variations. Analysis of variance revealed significant differences for all traits (p < 0.05) in these RIL populations. Although the LW irrigation regime significantly reduced all traits, except lint percent, the RILs exhibited a broad phenotypic spectrum of heritable differences across the water regimes. Transgressive segregation occurred among the RILs, suggesting the possibility of genetic gain through phenotypic selection for drought resilience and perhaps through marker-based selection. Analyses revealed more than 150 quantitative trait loci (QTLs) associated with productivity and fiber quality traits (p < 0.005) on different genomic regions of the cotton genome. The multiple-QTL models analysis with LOD > 3.0 detected 21 QTLs associated with productivity and 22 QTLs associated with fiber quality. For fiber traits, strong clustering and QTL associations occurred in c08 and its homolog c24 as well as c10, c14, and c21. Using contemporary genome sequence assemblies and bioinformatically related information, the identification of genomic regions associated with responses to plant stress/drought elevates the possibility of using marker-assisted and omics-based selection to enhance breeding for drought resilient cultivars and identifying candidate genes and networks. RILs with different responses to drought indicated that it is possible to maintain high fiber quality under LW conditions or reduce the of LW impact on quality. The heritable variation among elite bi-parental RILs for productivity and quality under field drought conditions, and their association of QTLs, and thus specific genomic regions, indicate opportunities for breeding-based gains in water resource conservation, i.e., enhancing cotton's agricultural sustainability.}, number={1}, journal={MOLECULAR GENETICS AND GENOMICS}, publisher={Springer Science and Business Media LLC}, author={Ulloa, Mauricio and De Santiago, Luis M. and Hulse-Kemp, Amanda M. and Stelly, David M. and Burke, John J.}, year={2020}, month={Jan}, pages={155–176} }
 @article{toomer_hulse-kemp_dean_boykin_malheiros_anderson_2019, title={Feeding high-oleic peanuts to layer hens enhances egg yolk color and oleic fatty acid content in shell eggs}, volume={98}, ISSN={0032-5791}, url={http://dx.doi.org/10.3382/ps/pey531}, DOI={10.3382/ps/pey531}, abstractNote={ABSTRACT Previous studies have identified normal‐oleic peanuts as a suitable and economical broiler feed ingredient. However, no studies to date have examined the use of high‐oleic (HO) peanut cultivars as a feed ingredient for laying hens and determined the impact of feeding HO peanuts on performance and egg nutritive qualities. This project aimed to examine the use of HO peanuts as a feed ingredient for layer hens to determine the effect on performance, egg lipid chemistry, and quality of the eggs produced. Forty‐eight 40‐wk‐old layer hens were fed a conventional soybean meal + corn control diet or a HO peanut + corn diet for 10 wk in conventional battery cages. Body and feed weights were collected weekly. Pooled egg samples were analyzed for quality, lipid analysis, and peanut protein allergenicity. There were no significant differences in hen performance or egg quality as measured by USDA grade quality, egg albumen height, or egg Haugh unit between the treatment groups. However, eggs produced from layer hens fed the HO peanut + corn diet had reduced egg weights relative to the controls (P = 0.0001). Eggs produced from layer hens fed the HO peanut diet had greater yolk color scores (P < 0.0001), HO fatty acid (P < 0.0001), and &bgr;‐carotene (P < 0.0001) levels in comparison to the controls. Eggs produced from hens fed the control diet had greater palmitic and stearic saturated fatty acids (P < 0.0001), and trans fat (P < 0.0001) content compared to eggs produced from hens fed the HO peanut diet. All egg protein extracts from all treatments at each time point were non‐reactive with rabbit anti‐peanut agglutinin antibodies. This study identifies HO peanuts as an abundant commodity that could be used to support local agricultural markets of peanuts and poultry within the southeastern United States and be of economic advantage to producers while providing a potential health benefit to the consumer with improved egg nutrition.}, number={4}, journal={Poultry Science}, publisher={Elsevier BV}, author={Toomer, Ondulla T and Hulse-Kemp, Amanda M and Dean, Lisa L and Boykin, Deborah L and Malheiros, Ramon and Anderson, Kenneth E}, year={2019}, month={Apr}, pages={1732–1748} }
 @article{hulse-kemp_maheshwari_stoffel_hill_jaffe_williams_weisenfeld_ramakrishnan_kumar_shah_et al._2018, title={Reference quality assembly of the 3.5-Gb genome of Capsicum annuum from a single linked-read library}, volume={5}, ISSN={["2052-7276"]}, DOI={10.1038/s41438-017-0011-0}, abstractNote={Linked-Read sequencing technology has recently been employed successfully for de novo assembly of human genomes, however, the utility of this technology for complex plant genomes is unproven. We evaluated the technology for this purpose by sequencing the 3.5-gigabase (Gb) diploid pepper (Capsicum annuum) genome with a single Linked-Read library. Plant genomes, including pepper, are characterized by long, highly similar repetitive sequences. Accordingly, significant effort is used to ensure that the sequenced plant is highly homozygous and the resulting assembly is a haploid consensus. With a phased assembly approach, we targeted a heterozygous F1 derived from a wide cross to assess the ability to derive both haplotypes and characterize a pungency gene with a large insertion/deletion. The Supernova software generated a highly ordered, more contiguous sequence assembly than all currently available C. annuum reference genomes. Over 83% of the final assembly was anchored and oriented using four publicly available de novo linkage maps. A comparison of the annotation of conserved eukaryotic genes indicated the completeness of assembly. The validity of the phased assembly is further demonstrated with the complete recovery of both 2.5-Kb insertion/deletion haplotypes of the PUN1 locus in the F1 sample that represents pungent and nonpungent peppers, as well as nearly full recovery of the BUSCO2 gene set within each of the two haplotypes. The most contiguous pepper genome assembly to date has been generated which demonstrates that Linked-Read library technology provides a tool to de novo assemble complex highly repetitive heterozygous plant genomes. This technology can provide an opportunity to cost-effectively develop high-quality genome assemblies for other complex plants and compare structural and gene differences through accurate haplotype reconstruction.}, journal={HORTICULTURE RESEARCH}, author={Hulse-Kemp, Amanda M. and Maheshwari, Shamoni and Stoffel, Kevin and Hill, Theresa A. and Jaffe, David and Williams, Stephen R. and Weisenfeld, Neil and Ramakrishnan, Srividya and Kumar, Vijay and Shah, Preyas and et al.}, year={2018}, month={Jan} }
 @article{gonda_ashrafi_lyon_strickler_hulse-kemp_ma_sun_stoffel_powell_futrell_et al._2019, title={Sequencing-Based Bin Map Construction of a Tomato Mapping Population, Facilitating High-Resolution Quantitative Trait Loci Detection}, volume={12}, ISSN={["1940-3372"]}, DOI={10.3835/plantgenome2018.02.0010}, abstractNote={Genotyping‐by‐sequencing (GBS) was employed to construct a highly saturated genetic linkage map of a tomato (Solanum lycopersicum L.) recombinant inbred line (RIL) population, derived from a cross between cultivar NC EBR‐1 and the wild tomato S. pimpinellifolium L. accession LA2093. A pipeline was developed to convert single nucleotide polymorphism (SNP) data into genomic bins, which could be used for fine mapping of quantitative trait loci (QTL) and identification of candidate genes. The pipeline, implemented in a python script named SNPbinner, adopts a hidden Markov model approach for calculation of recombination breakpoints followed by genomic bins construction. The total length of the newly developed high‐resolution genetic map was 1.2‐fold larger than previously estimated based on restriction fragment length polymorphism (RFLP) and polymerase chain reaction (PCR)–based markers. The map was used to verify and refine QTL previously identified for two fruit quality traits in the RIL population, fruit weight (FW) and fruit lycopene content (LYC). Two well‐described FW QTL (fw2.2 and fw3.2) were localized precisely at their known underlying causative genes, and the QTL intervals were decreased by two‐ to tenfold. A major QTL for LYC content (Lyc12.1) was verified at high resolution and its underlying causative gene was determined to be ζ‐carotene isomerase (SlZISO). The RIL population, the high resolution genetic map, and the easy‐to‐use genotyping pipeline, SNPbinner, are made publicly available.}, number={1}, journal={PLANT GENOME}, author={Gonda, Itay and Ashrafi, Hamid and Lyon, David A. and Strickler, Susan R. and Hulse-Kemp, Amanda M. and Ma, Qiyue and Sun, Honghe and Stoffel, Kevin and Powell, Adrian F. and Futrell, Stephanie and et al.}, year={2019}, month={Mar} }
 @article{hinze_hulse-kemp_wilson_zhu_llewellyn_taylor_spriggs_fang_ulloa_burke_et al._2017, title={Diversity analysis of cotton (Gossypium hirsutum L.) germplasm using the CottonSNP63K Array.}, volume={17}, url={http://europepmc.org/abstract/med/28158969}, DOI={10.1186/s12870-017-0981-y}, abstractNote={Cotton germplasm resources contain beneficial alleles that can be exploited to develop germplasm adapted to emerging environmental and climate conditions. Accessions and lines have traditionally been characterized based on phenotypes, but phenotypic profiles are limited by the cost, time, and space required to make visual observations and measurements. With advances in molecular genetic methods, genotypic profiles are increasingly able to identify differences among accessions due to the larger number of genetic markers that can be measured. A combination of both methods would greatly enhance our ability to characterize germplasm resources. Recent efforts have culminated in the identification of sufficient SNP markers to establish high-throughput genotyping systems, such as the CottonSNP63K array, which enables a researcher to efficiently analyze large numbers of SNP markers and obtain highly repeatable results. In the current investigation, we have utilized the SNP array for analyzing genetic diversity primarily among cotton cultivars, making comparisons to SSR-based phylogenetic analyses, and identifying loci associated with seed nutritional traits. The SNP markers distinctly separated G. hirsutum from other Gossypium species and distinguished the wild from cultivated types of G. hirsutum. The markers also efficiently discerned differences among cultivars, which was the primary goal when designing the CottonSNP63K array. Population structure within the genus compared favorably with previous results obtained using SSR markers, and an association study identified loci linked to factors that affect cottonseed protein content. Our results provide a large genome-wide variation data set for primarily cultivated cotton. Thousands of SNPs in representative cotton genotypes provide an opportunity to finely discriminate among cultivated cotton from around the world. The SNPs will be relevant as dense markers of genome variation for association mapping approaches aimed at correlating molecular polymorphisms with variation in phenotypic traits, as well as for molecular breeding approaches in cotton.}, number={1}, journal={BMC plant biology}, author={Hinze, LL and Hulse-Kemp, AM and Wilson, IW and Zhu, QH and Llewellyn, DJ and Taylor, JM and Spriggs, A and Fang, DD and Ulloa, M and Burke, JJ and et al.}, year={2017}, month={Feb}, pages={37,} }
 @article{hulse-kemp_maheshwari_stoffel_hill_jaffe_williams_weisenfeld_ramakrishnan_kumar_shah_et al._2017, title={Reference Quality Assembly of the 3.5 Gb genome ofCapsicum annuumfrom a Single Linked-Read Library}, url={https://doi.org/10.1101/152777}, DOI={10.1101/152777}, abstractNote={AbstractBackgroundLinked-Read sequencing technology has recently been employed successfully for de novo assembly of multiple human genomes, however the utility of this technology for complex plant genomes is unproven. We evaluated the technology for this purpose by sequencing the 3.5 gigabase (Gb) diploid pepper (Capsicum annuum) genome with a single Linked-Read library. Plant genomes, including pepper, are characterized by long, highly similar repetitive sequences. Accordingly, significant effort is used to ensure the sequenced plant is highly homozygous and the resulting assembly is a haploid consensus. With a phased assembly approach, we targeted a heterozygous F1 derived from a wide cross to assess the ability to derive both haplotypes for a pungency gene characterized by a large insertion/deletion.ResultsThe Supernova software generated a highly ordered, more contiguous sequence assembly than all currently available C. annuum reference genomes. Eighty-four percent of the final assembly was anchored and oriented using four de novo linkage maps. A comparison of the annotation of conserved eukaryotic genes indicated the completeness of assembly. The validity of the phased assembly is further demonstrated with the complete recovery of both 2.5 kb insertion/deletion haplotypes of the PUN1 locus in the F1 sample that represents pungent and non-pungent peppers.ConclusionsThe most contiguous pepper genome assembly to date has been generated through this work which demonstrates that Linked-Read library technology provides a rapid tool to assemble de novo complex highly repetitive heterozygous plant genomes. This technology can provide an opportunity to cost-effectively develop high-quality reference genome assemblies for other complex plants and compare structural and gene differences through accurate haplotype reconstruction.}, author={Hulse-Kemp, Amanda M. and Maheshwari, Shamoni and Stoffel, Kevin and Hill, Theresa A. and Jaffe, David and Williams, Stephen and Weisenfeld, Neil and Ramakrishnan, Srividya and Kumar, Vijay and Shah, Preyas and et al.}, year={2017}, month={Jun} }
 @article{hulse-kemp_ashrafi_plieske_lemm_stoffel_hill_luerssen_pethiyagoda_lawley_ganal_et al._2016, title={A HapMap leads to a Capsicum annuum SNP infinium array: a new tool for pepper breeding}, volume={3}, ISSN={["2052-7276"]}, url={https://doi.org/10.1038/hortres.2016.36}, DOI={10.1038/hortres.2016.36}, abstractNote={The Capsicum genus (Pepper) is a part of the Solanacae family. It has been important in many cultures worldwide for its key nutritional components and uses as spices, medicines, ornamentals and vegetables. Worldwide population growth is associated with demand for more nutritionally valuable vegetables while contending with decreasing resources and available land. These conditions require increased efficiency in pepper breeding to deal with these imminent challenges. Through resequencing of inbred lines we have completed a valuable haplotype map (HapMap) for the pepper genome based on single-nucleotide polymorphisms (SNP). The identified SNPs were annotated and classified based on their gene annotation in the pepper draft genome sequence and phenotype of the sequenced inbred lines. A selection of one marker per gene model was utilized to create the PepperSNP16K array, which simultaneously genotyped 16 405 SNPs, of which 90.7% were found to be informative. A set of 84 inbred and hybrid lines and a mapping population of 90 interspecific F2 individuals were utilized to validate the array. Diversity analysis of the inbred lines shows a distinct separation of bell versus chile/hot pepper types and separates them into five distinct germplasm groups. The interspecific population created between Tabasco (C. frutescens chile type) and P4 (C. annuum blocky type) produced a linkage map with 5546 markers separated into 1361 bins on twelve 12 linkage groups representing 1392.3 cM. This publically available genotyping platform can be used to rapidly assess a large number of markers in a reproducible high-throughput manner for pepper. As a standardized tool for genetic analyses, the PepperSNP16K can be used worldwide to share findings and analyze QTLs for important traits leading to continued improvement of pepper for consumers. Data and information on the array are available through the Solanaceae Genomics Network.}, number={1}, journal={HORTICULTURE RESEARCH}, publisher={Springer Science and Business Media LLC}, author={Hulse-Kemp, Amanda M. and Ashrafi, Hamid and Plieske, Joerg and Lemm, Jana and Stoffel, Kevin and Hill, Theresa and Luerssen, Hartmut and Pethiyagoda, Charit L. and Lawley, Cindy T. and Ganal, Martin W. and et al.}, year={2016}, month={Jul} }
 @article{page_liechty_alexander_clemons_hulse-kemp_ashrafi_van_stelly_udall_2016, title={Correction: DNA Sequence Evolution and Rare Homoeologous Conversion in Tetraploid Cotton.}, volume={12}, url={http://europepmc.org/abstract/med/27447832}, DOI={10.1371/journal.pgen.1006206}, abstractNote={[This corrects the article DOI: 10.1371/journal.pgen.1006012.].}, number={7}, journal={PLoS genetics}, author={Page, JT and Liechty, ZS and Alexander, RH and Clemons, K and Hulse-Kemp, AM and Ashrafi, H and Van, Deynze A and Stelly, DM and Udall, JA}, year={2016}, month={Jul}, pages={1006206,} }
 @article{page_liechty_alexander_clemons_hulse-kemp_ashrafi_van deynze_stelly_udall_2016, title={DNA Sequence Evolution and Rare Homoeologous Conversion in Tetraploid Cotton}, volume={12}, ISSN={["1553-7404"]}, url={http://europepmc.org/abstract/med/27168520}, DOI={10.1371/journal.pgen.1006012}, abstractNote={Allotetraploid cotton species are a vital source of spinnable fiber for textiles. The polyploid nature of the cotton genome raises many evolutionary questions as to the relationships between duplicated genomes. We describe the evolution of the cotton genome (SNPs and structural variants) with the greatly improved resolution of 34 deeply re-sequenced genomes. We also explore the evolution of homoeologous regions in the AT- and DT-genomes and especially the phenomenon of conversion between genomes. We did not find any compelling evidence for homoeologous conversion between genomes. These findings are very different from other recent reports of frequent conversion events between genomes. We also identified several distinct regions of the genome that have been introgressed between G. hirsutum and G. barbadense, which presumably resulted from breeding efforts targeting associated beneficial alleles. Finally, the genotypic data resulting from this study provides access to a wealth of diversity sorely needed in the narrow germplasm of cotton cultivars.}, number={5}, journal={PLOS GENETICS}, publisher={Public Library of Science (PLoS)}, author={Page, Justin T. and Liechty, Zach S. and Alexander, Rich H. and Clemons, Kimberly and Hulse-Kemp, Amanda M. and Ashrafi, Hamid and Van Deynze, Allen and Stelly, David M. and Udall, Joshua A.}, editor={Bomblies, KirstenEditor}, year={2016}, month={May} }
 @article{hulse-kemp_ashrafi_stoffel_zheng_saski_scheffler_fang_chen_van deynze_stelly_et al._2015, title={BAC-End Sequence-Based SNP Mining in Allotetraploid Cotton (Gossypium) Utilizing Resequencing Data, Phylogenetic Inferences, and Perspectives for Genetic Mapping.}, volume={5}, url={http://europepmc.org/abstract/med/25858960}, DOI={10.1534/g3.115.017749}, abstractNote={Abstract
               A bacterial artificial chromosome library and BAC-end sequences for cultivated cotton (Gossypium hirsutum L.) have recently been developed. This report presents genome-wide single nucleotide polymorphism (SNP) mining utilizing resequencing data with BAC-end sequences as a reference by alignment of 12 G. hirsutum L. lines, one G. barbadense L. line, and one G. longicalyx Hutch and Lee line. A total of 132,262 intraspecific SNPs have been developed for G. hirsutum, whereas 223,138 and 470,631 interspecific SNPs have been developed for G. barbadense and G. longicalyx, respectively. Using a set of interspecific SNPs, 11 randomly selected and 77 SNPs that are putatively associated with the homeologous chromosome pair 12 and 26, we mapped 77 SNPs into two linkage groups representing these chromosomes, spanning a total of 236.2 cM in an interspecific F2 population (G. barbadense 3-79 × G. hirsutum TM-1). The mapping results validated the approach for reliably producing large numbers of both intraspecific and interspecific SNPs aligned to BAC-ends. This will allow for future construction of high-density integrated physical and genetic maps for cotton and other complex polyploid genomes. The methods developed will allow for future Gossypium resequencing data to be automatically genotyped for identified SNPs along the BAC-end sequence reference for anchoring sequence assemblies and comparative studies.}, number={6}, journal={G3&#58; Genes|Genomes|Genetics}, publisher={Genetics Society of America}, author={Hulse-Kemp, A.M. and Ashrafi, H. and Stoffel, K. and Zheng, X. and Saski, C.A. and Scheffler, B.E. and Fang, D.D. and Chen, Z.J. and Van Deynze, A. and Stelly, D.M. and et al.}, year={2015}, month={Jun}, pages={1095–1105} }
 @article{hulse-kemp_lemm_plieske_ashrafi_buyyarapu_fang_frelichowski_giband_hague_hinze_et al._2015, place={Bethesda}, title={Development of a 63K SNP Array for Cotton and High-Density Mapping of Intraspecific and Interspecific Populations of Gossypium spp.}, volume={5}, url={http://europepmc.org/abstract/med/25908569}, DOI={10.1534/g3.115.018416}, abstractNote={Abstract
               High-throughput genotyping arrays provide a standardized resource for plant breeding communities that are useful for a breadth of applications including high-density genetic mapping, genome-wide association studies (GWAS), genomic selection (GS), complex trait dissection, and studying patterns of genomic diversity among cultivars and wild accessions. We have developed the CottonSNP63K, an Illumina Infinium array containing assays for 45,104 putative intraspecific single nucleotide polymorphism (SNP) markers for use within the cultivated cotton species Gossypium hirsutum L. and 17,954 putative interspecific SNP markers for use with crosses of other cotton species with G. hirsutum. The SNPs on the array were developed from 13 different discovery sets that represent a diverse range of G. hirsutum germplasm and five other species: G. barbadense L., G. tomentosum Nuttal × Seemann, G. mustelinum Miers × Watt, G. armourianum Kearny, and G. longicalyx J.B. Hutchinson and Lee. The array was validated with 1,156 samples to generate cluster positions to facilitate automated analysis of 38,822 polymorphic markers. Two high-density genetic maps containing a total of 22,829 SNPs were generated for two F2 mapping populations, one intraspecific and one interspecific, and 3,533 SNP markers were co-occurring in both maps. The produced intraspecific genetic map is the first saturated map that associates into 26 linkage groups corresponding to the number of cotton chromosomes for a cross between two G. hirsutum lines. The linkage maps were shown to have high levels of collinearity to the JGI G. raimondii Ulbrich reference genome sequence. The CottonSNP63K array, cluster file and associated marker sequences constitute a major new resource for the global cotton research community.}, number={6}, author={Hulse-Kemp, AM and Lemm, J and Plieske, J and Ashrafi, H and Buyyarapu, R and Fang, DD and Frelichowski, J and Giband, M and Hague, S and Hinze, LL and et al.}, year={2015}, month={Apr}, pages={1187–1209,} }
 @article{zhang_hu_jiang_fang_guan_chen_zhang_saski_scheffler_stelly_et al._2015, title={Sequencing of allotetraploid cotton (Gossypium hirsutum L. acc. TM-1) provides a resource for fiber improvement.}, volume={33}, url={http://europepmc.org/abstract/med/25893781}, DOI={10.1038/nbt.3207}, abstractNote={Two draft sequences of Gossypium hirsutum, the most widely cultivated cotton species, provide insights into genome structure, genome rearrangement, gene evolution and cotton fiber biology. Upland cotton is a model for polyploid crop domestication and transgenic improvement. Here we sequenced the allotetraploid Gossypium hirsutum L. acc. TM-1 genome by integrating whole-genome shotgun reads, bacterial artificial chromosome (BAC)-end sequences and genotype-by-sequencing genetic maps. We assembled and annotated 32,032 A-subgenome genes and 34,402 D-subgenome genes. Structural rearrangements, gene loss, disrupted genes and sequence divergence were more common in the A subgenome than in the D subgenome, suggesting asymmetric evolution. However, no genome-wide expression dominance was found between the subgenomes. Genomic signatures of selection and domestication are associated with positively selected genes (PSGs) for fiber improvement in the A subgenome and for stress tolerance in the D subgenome. This draft genome sequence provides a resource for engineering superior cotton lines.}, number={5}, journal={Nature biotechnology}, author={Zhang, T and Hu, Y and Jiang, W and Fang, L and Guan, X and Chen, J and Zhang, J and Saski, CA and Scheffler, BE and Stelly, DM and et al.}, year={2015}, month={May}, pages={531–537,} }
 @article{hulse-kemp_ashrafi_zheng_wang_hoegenauer_maeda_yang_stoffel_matvienko_clemons_et al._2014, title={Development and bin mapping of gene-associated interspecific SNPs for cotton (Gossypium hirsutum L.) introgression breeding efforts.}, volume={15}, url={http://europepmc.org/abstract/med/25359292}, DOI={10.1186/1471-2164-15-945}, abstractNote={Cotton (Gossypium spp.) is the largest producer of natural fibers for textile and is an important crop worldwide. Crop production is comprised primarily of G. hirsutum L., an allotetraploid. However, elite cultivars express very small amounts of variation due to the species monophyletic origin, domestication and further bottlenecks due to selection. Conversely, wild cotton species harbor extensive genetic diversity of prospective utility to improve many beneficial agronomic traits, fiber characteristics, and resistance to disease and drought. Introgression of traits from wild species can provide a natural way to incorporate advantageous traits through breeding to generate higher-producing cotton cultivars and more sustainable production systems. Interspecific introgression efforts by conventional methods are very time-consuming and costly, but can be expedited using marker-assisted selection. Using transcriptome sequencing we have developed the first gene-associated single nucleotide polymorphism (SNP) markers for wild cotton species G. tomentosum, G. mustelinum, G. armourianum and G. longicalyx. Markers were also developed for a secondary cultivated species G. barbadense cv. 3–79. A total of 62,832 non-redundant SNP markers were developed from the five wild species which can be utilized for interspecific germplasm introgression into cultivated G. hirsutum and are directly associated with genes. Over 500 of the G. barbadense markers have been validated by whole-genome radiation hybrid mapping. Overall 1,060 SNPs from the five different species have been screened and shown to produce acceptable genotyping assays. This large set of 62,832 SNPs relative to cultivated G. hirsutum will allow for the first high-density mapping of genes from five wild species that affect traits of interest, including beneficial agronomic and fiber characteristics. Upon mapping, the markers can be utilized for marker-assisted introgression of new germplasm into cultivated cotton and in subsequent breeding of agronomically adapted types, including cultivar development.}, number={1}, journal={BMC Genomics}, publisher={Springer Nature}, author={Hulse-Kemp, AM and Ashrafi, H and Zheng, X and Wang, F and Hoegenauer, KA and Maeda, AB and Yang, SS and Stoffel, K and Matvienko, M and Clemons, K and et al.}, year={2014}, pages={945} }
 @article{gomez-raya_hulse_thain_rauw_2013, title={Haplotype phasing after joint estimation of recombination and linkage disequilibrium in breeding populations}, volume={4}, DOI={10.1186/2049-1891-4-30}, abstractNote={A novel method for haplotype phasing in families after joint estimation of recombination fraction and linkage disequilibrium is developed. Results from Monte Carlo computer simulations show that the newly developed E.M. algorithm is accurate if true recombination fraction is 0 even for single families of relatively small sizes. Estimates of recombination fraction and linkage disequilibrium were 0.00 (SD 0.00) and 0.19 (SD 0.03) for simulated recombination fraction and linkage disequilibrium of 0.00 and 0.20, respectively. A genome fragmentation phasing strategy was developed and used for phasing haplotypes in a sire and 36 progeny using the 50 k Illumina BeadChip by: a) estimation of the recombination fraction and LD in consecutive SNPs using family information, b) linkage analyses between fragments, c) phasing of haplotypes in parents and progeny and in following generations. Homozygous SNPs in progeny allowed determination of paternal fragment inheritance, and deduction of SNP sequence information of haplotypes from dams. The strategy also allowed detection of genotyping errors. A total of 613 recombination events were detected after linkage analysis was carried out between fragments. Hot and cold spots were identified at the individual (sire level). SNPs for which the sire and calf were heterozygotes became informative (over 90%) after the phasing of haplotypes. Average of regions of identity between half-sibs when comparing its maternal inherited haplotypes (with at least 20 SNP) in common was 0.11 with a maximum of 0.29 and a minimum of 0.05. A Monte-Carlo simulation of BTA1 with the same linkage disequilibrium structure and genetic linkage as the cattle family yielded a 99.98 and 99.94% of correct phases for informative SNPs in sire and calves, respectively.}, number={1}, journal={J Anim Sci Biotechnol}, publisher={Springer Science + Business Media}, author={Gomez-Raya, Luis and Hulse, Amanda M and Thain, David and Rauw, Wendy M}, year={2013}, pages={30} }
 @article{page_huynh_liechty_grupp_stelly_hulse_ashrafi_deynze_wendel_udall_2013, title={Insights into the Evolution of Cotton Diploids and Polyploids from Whole-Genome Re-sequencing}, volume={3}, DOI={10.1534/g3.113.007229}, abstractNote={Abstract
               Understanding the composition, evolution, and function of the Gossypium hirsutum (cotton) genome is complicated by the joint presence of two genomes in its nucleus (AT and DT genomes). These two genomes were derived from progenitor A-genome and D-genome diploids involved in ancestral allopolyploidization. To better understand the allopolyploid genome, we re-sequenced the genomes of extant diploid relatives that contain the A1 (Gossypium herbaceum), A2 (Gossypium arboreum), or D5 (Gossypium raimondii) genomes. We conducted a comparative analysis using deep re-sequencing of multiple accessions of each diploid species and identified 24 million SNPs between the A-diploid and D-diploid genomes. These analyses facilitated the construction of a robust index of conserved SNPs between the A-genomes and D-genomes at all detected polymorphic loci. This index is widely applicable for read mapping efforts of other diploid and allopolyploid Gossypium accessions. Further analysis also revealed locations of putative duplications and deletions in the A-genome relative to the D-genome reference sequence. The approximately 25,400 deleted regions included more than 50% deletion of 978 genes, including many involved with starch synthesis. In the polyploid genome, we also detected 1,472 conversion events between homoeologous chromosomes, including events that overlapped 113 genes. Continued characterization of the Gossypium genomes will further enhance our ability to manipulate fiber and agronomic production of cotton.}, number={10}, journal={G3&#58; Genes|Genomes|Genetics}, publisher={Genetics Society of America}, author={Page, Justin T. and Huynh, Mark D. and Liechty, Zach S. and Grupp, Kara and Stelly, David and Hulse, Amanda M. and Ashrafi, Hamid and Deynze, Allen Van and Wendel, Jonathan F. and Udall, Joshua A.}, year={2013}, pages={1809–1818} }
 @article{cai_yang_hulse_cai_2012, title={Evolutionary Analysis of Sequence Divergence and Diversity of Duplicate Genes in Aspergillus fumigatus}, volume={11}, DOI={10.4137/ebo.s10372}, abstractNote={Gene duplication as a major source of novel genetic material plays an important role in evolution. In this study, we focus on duplicate genes in Aspergillus fumigatus, a ubiquitous filamentous fungus causing life-threatening human infections. We characterize the extent and evolutionary patterns of the duplicate genes in the genome of A. fumigatus. Our results show that A. fumigatus contains a large amount of duplicate genes with pronounced sequence divergence between two copies, and approximately 10% of them diverge asymmetrically, i.e. two copies of a duplicate gene pair diverge at significantly different rates. We use a Bayesian approach of the McDonald-Kreitman test to infer distributions of selective coefficients γ (=2 Nes) and find that (1) the values of γ for two copies of duplicate genes co-vary positively and (2) the average γ for the two copies differs between genes from different gene families. This analysis highlights the usefulness of combining divergence and diversity data in studying the evolution of duplicate genes. Taken together, our results provide further support and refinement to the theories of gene duplication. Through characterizing the duplicate genes in the genome of A. fumigatus, we establish a computational framework, including parameter settings and methods, for comparative study of genetic redundancy and gene duplication between different fungal species.}, journal={EBO}, publisher={Libertas Academica, Ltd.}, author={Cai and Yang, Ence and Hulse, Amanda M. and Cai}, year={2012}, pages={623} }
 @article{hulse_cai_2013, title={Genetic Variants Contribute to Gene Expression Variability in Humans}, volume={193}, DOI={10.1534/genetics.112.146779}, abstractNote={AbstractExpression quantitative trait loci (eQTL) studies have established convincing relationships between genetic variants and gene expression. Most of these studies focused on the mean of gene expression level, but not the variance of gene expression level (i.e., gene expression variability). In the present study, we systematically explore genome-wide association between genetic variants and gene expression variability in humans. We adapt the double generalized linear model (dglm) to simultaneously fit the means and the variances of gene expression among the three possible genotypes of a biallelic SNP. The genomic loci showing significant association between the variances of gene expression and the genotypes are termed expression variability QTL (evQTL). Using a data set of gene expression in lymphoblastoid cell lines (LCLs) derived from 210 HapMap individuals, we identify cis-acting evQTL involving 218 distinct genes, among which 8 genes, ADCY1, CTNNA2, DAAM2, FERMT2, IL6, PLOD2, SNX7, and TNFRSF11B, are cross-validated using an extra expression data set of the same LCLs. We also identify ∼300 trans-acting evQTL between >13,000 common SNPs and 500 randomly selected representative genes. We employ two distinct scenarios, emphasizing single-SNP and multiple-SNP effects on expression variability, to explain the formation of evQTL. We argue that detecting evQTL may represent a novel method for effectively screening for genetic interactions, especially when the multiple-SNP influence on expression variability is implied. The implication of our results for revealing genetic mechanisms of gene expression variability is discussed.}, number={1}, journal={Genetics}, publisher={Genetics Society of America}, author={Hulse, A. M. and Cai, J. J.}, year={2013}, pages={95–108} }