@misc{stone_singh_2016, title={Bias-Variance Tradeoffs in Recombination Rate Estimation}, volume={202}, ISSN={["1943-2631"]}, DOI={10.1534/genetics.115.185561}, abstractNote={Abstract}, number={2}, journal={GENETICS}, author={Stone, Eric A. and Singh, Nadia D.}, year={2016}, month={Feb}, pages={857–859} }
 @article{skelly_magwene_stone_2016, title={Sporadic, Global Linkage Disequilibrium Between Unlinked Segregating Sites}, volume={202}, ISSN={["1943-2631"]}, DOI={10.1534/genetics.115.177816}, abstractNote={Abstract}, number={2}, journal={GENETICS}, author={Skelly, Daniel A. and Magwene, Paul M. and Stone, Eric A.}, year={2016}, month={Feb}, pages={427-+} }
 @article{olarte_worthington_horn_moore_singh_monacell_dorner_stone_xie_carbone_2015, title={Enhanced diversity and aflatoxigenicity in interspecific hybrids ofAspergillus flavusandAspergillus parasiticus}, volume={24}, ISSN={0962-1083}, url={http://dx.doi.org/10.1111/mec.13153}, DOI={10.1111/mec.13153}, abstractNote={Abstract}, number={8}, journal={Molecular Ecology}, publisher={Wiley}, author={Olarte, Rodrigo A. and Worthington, Carolyn J. and Horn, Bruce W. and Moore, Geromy G. and Singh, Rakhi and Monacell, James T. and Dorner, Joe W. and Stone, Eric A. and Xie, De-Yu and Carbone, Ignazio}, year={2015}, month={Apr}, pages={1889–1909} }
 @misc{vensko_stone_2015, title={Recent progress and open questions in Drosophila dosage compensation}, volume={9}, ISSN={["1933-6942"]}, DOI={10.1080/19336934.2015.1074786}, abstractNote={Sexual dimorphism is observed in many traits across diverse taxa, and often it is quite extreme. Within a species, individuals of opposing sex can appear strikingly different, reflecting differences at the molecular level that may be similarly striking. Among the most extreme cases of such molecular sexual dimorphism is the quantity of sex chromosomes that each sex possesses. Hemizygous sex chromosomes are common to many species, and various mechanisms have evolved to regulate transcriptional activity to ensure appropriate sex chromosome-to-autosome gene expression stoichiometry. Among the most thoroughly investigated of these mechanisms is Drosophila melanogaster's male-specific lethal (MSL) complex-mediated dosage compensation. In Drosophila, the male X chromosome transcription is upregulated approximately two-fold in somatic tissues to counterbalance the effects of sex chromosome hemizygosity on transcript abundance. Despite dramatic advances in our understanding of the Drosophila dosage compensation, many questions remain unanswered, and our understanding of its molecular underpinnings remains incomplete. In this review, we synthesize recent progress in the field as a means to highlight open questions, including how the MSL complex targets the X chromosome, how dosage compensation has shaped evolution of X-linked genes, and the degree to which MSL complex-mediated dosage compensation varies in activity across somatic tissues.}, number={1}, journal={FLY}, author={Vensko, Steven P., II and Stone, Eric A.}, year={2015}, month={Jan}, pages={29–35} }
 @article{strope_skelly_kozmin_mahadevan_stone_magwene_dietrich_mccusker_2015, title={The 100-genomes strains, an S. cerevisiae resource that illuminates its natural phenotypic and genotypic variation and emergence as an opportunistic pathogen}, volume={25}, ISSN={["1549-5469"]}, DOI={10.1101/gr.185538.114}, abstractNote={Saccharomyces cerevisiae, a well-established model for species as diverse as humans and pathogenic fungi, is more recently a model for population and quantitative genetics. S. cerevisiae is found in multiple environments—one of which is the human body—as an opportunistic pathogen. To aid in the understanding of the S. cerevisiae population and quantitative genetics, as well as its emergence as an opportunistic pathogen, we sequenced, de novo assembled, and extensively manually edited and annotated the genomes of 93 S. cerevisiae strains from multiple geographic and environmental origins, including many clinical origin strains. These 93 S. cerevisiae strains, the genomes of which are near-reference quality, together with seven previously sequenced strains, constitute a novel genetic resource, the “100-genomes” strains. Our sequencing coverage, high-quality assemblies, and annotation provide unprecedented opportunities for detailed interrogation of complex genomic loci, examples of which we demonstrate. We found most phenotypic variation to be quantitative and identified population, genotype, and phenotype associations. Importantly, we identified clinical origin associations. For example, we found that an introgressed PDR5 was present exclusively in clinical origin mosaic group strains; that the mosaic group was significantly enriched for clinical origin strains; and that clinical origin strains were much more copper resistant, suggesting that copper resistance contributes to fitness in the human host. The 100-genomes strains are a novel, multipurpose resource to advance the study of S. cerevisiae population genetics, quantitative genetics, and the emergence of an opportunistic pathogen.}, number={5}, journal={GENOME RESEARCH}, author={Strope, Pooja K. and Skelly, Daniel A. and Kozmin, Stanislav G. and Mahadevan, Gayathri and Stone, Eric A. and Magwene, Paul M. and Dietrich, Fred S. and McCusker, John H.}, year={2015}, month={May}, pages={762–774} }
 @article{vensko_stone_2015, title={X-to-autosome expression and msl-2 transcript abundance correlate among Drosophila melanogaster somatic tissues}, volume={3}, ISSN={["2167-8359"]}, DOI={10.7717/peerj.771}, abstractNote={In Drosophila melanogaster, the male-specific lethal (MSL) complex has been studied extensively for its role in upregulating male X-linked genes. Recent advances in high-throughput technologies have improved our understanding of how the MSL complex mediates dosage compensation through chromosome-wide chromatin modifications. Most studies, however, have focused on cell line models that cannot reflect any potential heterogeneity of in vivo dosage compensation. Comparisons between cell line and organismal gene-level dosage compensation upregulation suggest the possibility of variation in MSL complex activity among somatic tissues. We hypothesize the degree, up to but not exceeding 2-fold, to which the MSL complex upregulates male X-linked genes varies quantitatively by tissue type. In this model, MSL complex abundance acts as a rheostat to control the extent of upregulation. Using publicly available expression data, we provide evidence for our model in Drosophila somatic tissues. Specifically, we find X-to-autosome expression correlates with the tissue-specific expression of msl-2 which encodes an essential male-specific component of the MSL complex. This result suggests MSL complex mediated dosage compensation varies quantitatively by tissue type. Furthermore, this result has consequences for models explaining the organismal-scale molecular and evolutionary consequences of MSL-mediated dosage compensation.}, journal={PEERJ}, author={Vensko, Steven P., II and Stone, Eric A.}, year={2015}, month={Feb} }
 @article{durham_magwire_stone_leips_2014, title={Genome-wide analysis in Drosophila reveals age-specific effects of SNPs on fitness traits}, volume={5}, ISSN={["2041-1723"]}, DOI={10.1038/ncomms5338}, abstractNote={Most organisms exhibit senescence; a decline in physiological function with age. In nature, rates of senescence vary extensively among individuals and this variation has a significant genetic component; however, we know little about the genes underlying senescence. Here we show the first evidence that individual alleles influence fecundity in an age-specific manner and so the genetic basis of natural variation in fecundity changes dramatically with age. We complete a genome-wide association to identify single-nucleotide polymorphisms (SNPs) affecting lifespan and age-specific fecundity using the Drosophila melanogaster Genetic Reference Panel. We identify 1,031 SNPs affecting fecundity and 52 influencing lifespan. Only one SNP is associated with both early- and late-age fecundity. The age-specific effect of candidate genes on fecundity is validated using RNA interference. In addition, there is a dramatic increase in the number of SNPs influencing fecundity with age. This result provides support for the mutation accumulation theory of aging.}, journal={NATURE COMMUNICATIONS}, author={Durham, Mary F. and Magwire, Michael M. and Stone, Eric A. and Leips, Jeff}, year={2014}, month={Jul} }
 @article{huang_massouras_inoue_peiffer_ramia_tarone_turlapati_zichner_zhu_lyman_et al._2014, title={Natural variation in genome architecture among 205 Drosophila melanogaster Genetic Reference Panel lines}, volume={24}, number={7}, journal={Genome Research}, author={Huang, W. and Massouras, A. and Inoue, Y. and Peiffer, J. and Ramia, M. and Tarone, A. M. and Turlapati, L. and Zichner, T. and Zhu, D. H. and Lyman, R. F. and et al.}, year={2014}, pages={1193–1208} }
 @article{vensko_stone_2014, title={No Evidence for a Global Male-Specific Lethal Complex-Mediated Dosage Compensation Contribution to the Demasculinization of the Drosophila melanogaster X Chromosome}, volume={9}, ISSN={["1932-6203"]}, DOI={10.1371/journal.pone.0103659}, abstractNote={In Drosophila melanogaster males, the expression of X-linked genes is regulated by mechanisms that operate on a chromosomal scale. One such mechanism, male-specific lethal complex-dependent X-linked dosage compensation, is thought to broadly enhance the expression of male X-linked genes through two-fold transcriptional upregulation. The evolutionary consequences of this form of dosage compensation are not well understood, particularly with regard to genes more highly expressed in males. It has been observed the X chromosome arrangement of these male-biased genes is non-random, consistent with what one might expect if there is a selective advantage for male-biased genes to avoid dosage compensation. Separately, it has been noted that the male-specific lethal complex and its dosage compensation mechanism appear absent in some male tissues, thus providing a control for the selection hypothesis. Here we utilized publicly available datasets to reassess the arrangement of X-linked male-biased expressed genes after accounting for expression in tissues not dosage compensated by the male-specific lethal complex. Our results do not corroborate previous observations supporting organismal-wide detrimental effects by dosage compensation on X-linked male-biased expressed genes. We instead find no evidence that dosage compensation has played a role in the arrangement of dosage compensated male-biased genes on the X chromosome.}, number={8}, journal={PLOS ONE}, author={Vensko, Steven P., II and Stone, Eric A.}, year={2014}, month={Aug} }
 @article{robinson_stone_singh_2014, title={Population Genomic Analysis Reveals No Evidence for GC-Biased Gene Conversion in Drosophila melanogaster}, volume={31}, ISSN={["1537-1719"]}, DOI={10.1093/molbev/mst220}, abstractNote={Gene conversion is the nonreciprocal exchange of genetic material between homologous chromosomes. Multiple lines of evidence from a variety of taxa strongly suggest that gene conversion events are biased toward GC-bearing alleles. However, in Drosophila, the data have largely been indirect and unclear, with some studies supporting the predictions of a GC-biased gene conversion model and other data showing contradictory findings. Here, we test whether gene conversion events are GC-biased in Drosophila melanogaster using whole-genome polymorphism and divergence data. Our results provide no support for GC-biased gene conversion and thus suggest that this process is unlikely to significantly contribute to patterns of polymorphism and divergence in this system.}, number={2}, journal={MOLECULAR BIOLOGY AND EVOLUTION}, author={Robinson, Matthew C. and Stone, Eric A. and Singh, Nadia D.}, year={2014}, month={Feb}, pages={425–433} }
 @misc{stone_2014, title={Predictor performance with stratified data and imbalanced classes}, volume={11}, ISSN={["1548-7105"]}, DOI={10.1038/nmeth.3045}, number={8}, journal={NATURE METHODS}, author={Stone, Eric A.}, year={2014}, month={Aug}, pages={782–783} }
 @article{griffing_lynch_stone_2014, title={Structural properties of the minimum cut of partially-supplied graphs}, volume={177}, ISSN={["1872-6771"]}, DOI={10.1016/j.dam.2014.05.043}, abstractNote={It is well known that information about the structure of a graph is contained within its minimum cut. Here we investigate how the minimum cut of one graph informs the structure of a second, related graph. We consider pairs of graphs G and H, with respective Laplacian matrices L and M, and call H partially supplied provided that M is a Schur complement of L. Our results show how the minimum cut of H relates to the structure of the larger graph G.}, journal={DISCRETE APPLIED MATHEMATICS}, author={Griffing, Alexander R. and Lynch, Benjamin R. and Stone, Eric A.}, year={2014}, month={Nov}, pages={152–157} }
 @article{griffing_lynch_stone_2013, title={An eigenvector interlacing property of graphs that arise from trees by Schur complementation of the Laplacian}, volume={438}, ISSN={["0024-3795"]}, DOI={10.1016/j.laa.2012.10.005}, abstractNote={The literature is replete with rich connections between the structure of a graph G=(V,E) and the spectral properties of its Laplacian matrix L. This paper establishes similar connections between the structure of G and the Laplacian L∗ of a second graph G∗. Our interest lies in L∗ that can be obtained from L by Schur complementation, in which case we say that G∗ is partially-supplied with respect to G. In particular, we specialize to where G is a tree with points of articulation r∈R and consider the partially-supplied graph G∗derived from G by taking the Schur complement with respect to R in L. Our results characterize how the eigenvectors of the Laplacian of G∗ relate to each other and to the structure of the tree.}, number={3}, journal={LINEAR ALGEBRA AND ITS APPLICATIONS}, author={Griffing, Alexander R. and Lynch, Benjamin R. and Stone, Eric A.}, year={2013}, month={Feb}, pages={1078–1094} }
 @article{guo_tsai_hardison_james_motsinger-reif_thames_stone_deng_piedrahita_2013, title={Differentially expressed microRNAs and affected biological pathways revealed by modulated modularity clustering (MMC) analysis of human preeclamptic and IUGR placentas}, volume={34}, ISSN={0143-4004}, url={http://dx.doi.org/10.1016/j.placenta.2013.04.007}, DOI={10.1016/j.placenta.2013.04.007}, abstractNote={This study focuses on the implementation of modulated modularity clustering (MMC) a new cluster algorithm for the identification of molecular signatures of preeclampsia and intrauterine growth restriction (IUGR), and the identification of affected microRNAs Eighty-six human placentas from normal (40), growth-restricted (27), and preeclamptic (19) term pregnancies were profiled using Illumina Human-6 Beadarrays. MMC was utilized to generate modules based on similarities in placental transcriptome. Gene Set Enrichment Analysis (GSEA) was used to predict affected microRNAs. Expression levels of these candidate microRNAs were investigated in seventy-one human term placentas as follows: control (29); IUGR (26); and preeclampsia (16). MMC identified two modules, one representing IUGR placentas and one representing preeclamptic placentas. 326 differentially expressed genes in the module representing IUGR and 889 differentially expressed genes in a module representing preeclampsia were identified. Functional analysis of molecular signatures associated with IUGR identified P13K/AKT, mTOR, p70S6K, apoptosis and IGF-1 signaling as being affected. Analysis of variance of GSEA-predicted microRNAs indicated that miR-194 was significantly down-regulated both in preeclampsia (p = 0.0001) and IUGR (p = 0.0304), and miR-149 was significantly down-regulated in preeclampsia (p = 0.0168). Implementation of MMC, allowed identification of genes disregulated in IUGR and preeclampsia. The reliability of MMC was validated by comparing to previous linear modeling analysis of preeclamptic placentas. MMC allowed the elucidation of a molecular signature associated with preeclampsia and a subset of IUGR samples. This allowed the identification of genes, pathways, and microRNAs affected in these diseases.}, number={7}, journal={Placenta}, publisher={Elsevier BV}, author={Guo, L. and Tsai, S.Q. and Hardison, N.E. and James, A.H. and Motsinger-Reif, A.A. and Thames, B. and Stone, E.A. and Deng, C. and Piedrahita, J.A.}, year={2013}, month={Jul}, pages={599–605} }
 @article{singh_stone_aquadro_clark_2013, title={Fine-scale heterogeneity in crossover rate in the garnet-scalloped region of the Drosophila melanogaster X chromosome}, volume={194}, number={2}, journal={Genetics}, author={Singh, N. D. and Stone, E. A. and Aquadro, C. F. and Clark, A. G.}, year={2013}, pages={375–112} }
 @article{moore_elliott_singh_horn_dorner_stone_chulze_barros_naik_wright_et al._2013, title={Sexuality Generates Diversity in the Aflatoxin Gene Cluster: Evidence on a Global Scale}, volume={9}, ISSN={1553-7374}, url={http://dx.doi.org/10.1371/journal.ppat.1003574}, DOI={10.1371/journal.ppat.1003574}, abstractNote={Aflatoxins are produced by Aspergillus flavus and A. parasiticus in oil-rich seed and grain crops and are a serious problem in agriculture, with aflatoxin B1 being the most carcinogenic natural compound known. Sexual reproduction in these species occurs between individuals belonging to different vegetative compatibility groups (VCGs). We examined natural genetic variation in 758 isolates of A. flavus, A. parasiticus and A. minisclerotigenes sampled from single peanut fields in the United States (Georgia), Africa (Benin), Argentina (Córdoba), Australia (Queensland) and India (Karnataka). Analysis of DNA sequence variation across multiple intergenic regions in the aflatoxin gene clusters of A. flavus, A. parasiticus and A. minisclerotigenes revealed significant linkage disequilibrium (LD) organized into distinct blocks that are conserved across different localities, suggesting that genetic recombination is nonrandom and a global occurrence. To assess the contributions of asexual and sexual reproduction to fixation and maintenance of toxin chemotype diversity in populations from each locality/species, we tested the null hypothesis of an equal number of MAT1-1 and MAT1-2 mating-type individuals, which is indicative of a sexually recombining population. All samples were clone-corrected using multi-locus sequence typing which associates closely with VCG. For both A. flavus and A. parasiticus, when the proportions of MAT1-1 and MAT1-2 were significantly different, there was more extensive LD in the aflatoxin cluster and populations were fixed for specific toxin chemotype classes, either the non-aflatoxigenic class in A. flavus or the B1-dominant and G1-dominant classes in A. parasiticus. A mating type ratio close to 1∶1 in A. flavus, A. parasiticus and A. minisclerotigenes was associated with higher recombination rates in the aflatoxin cluster and less pronounced chemotype differences in populations. This work shows that the reproductive nature of the population (more sexual versus more asexual) is predictive of aflatoxin chemotype diversity in these agriculturally important fungi.}, number={8}, journal={PLoS Pathogens}, publisher={Public Library of Science (PLoS)}, author={Moore, Geromy G. and Elliott, Jacalyn L. and Singh, Rakhi and Horn, Bruce W. and Dorner, Joe W. and Stone, Eric A. and Chulze, Sofia N. and Barros, German G. and Naik, Manjunath K. and Wright, Graeme C. and et al.}, editor={McDonald, Bruce A.Editor}, year={2013}, month={Aug}, pages={e1003574} }
 @article{felix_hughes_stone_drnevich_leips_2012, title={Age-specific variation in immune response in drosophila melanogaster has a genetic basis}, volume={191}, number={3}, journal={Genetics}, author={Felix, T. M. and Hughes, K. A. and Stone, E. A. and Drnevich, J. M. and Leips, J.}, year={2012}, pages={989–584} }
 @article{olarte_horn_dorner_monacell_singh_stone_carbone_2012, title={Effect of sexual recombination on population diversity in aflatoxin production by Aspergillus flavus and evidence for cryptic heterokaryosis}, volume={21}, ISSN={["1365-294X"]}, DOI={10.1111/j.1365-294x.2011.05398.x}, abstractNote={Abstract}, number={6}, journal={MOLECULAR ECOLOGY}, author={Olarte, Rodrigo A. and Horn, Bruce W. and Dorner, Joe W. and Monacell, James T. and Singh, Rakhi and Stone, Eric A. and Carbone, Ignazio}, year={2012}, month={Mar}, pages={1453–1476} }
 @article{stone_2012, title={Joint genotyping on the fly: Identifying variation among a sequenced panel of inbred lines}, volume={22}, ISSN={["1549-5469"]}, DOI={10.1101/gr.129122.111}, abstractNote={High-throughput sequencing is enabling remarkably deep surveys of genomic variation. It is now possible to completely sequence multiple individuals from a single species, yet the identification of variation among them remains an evolving computational challenge. This challenge is compounded for experimental organisms when strains are studied instead of individuals. In response, we present the Joint Genotyper for Inbred Lines (JGIL) as a method for obtaining genotypes and identifying variation among a large panel of inbred strains or lines. JGIL inputs the sequence reads from each line after their alignment to a common reference. Its probabilistic model includes site-specific parameters common to all lines that describe the frequency of nucleotides segregating in the population from which the inbred panel was derived. The distribution of line genotypes is conditional on these parameters and reflects the experimental design. Site-specific error probabilities, also common to all lines, parameterize the distribution of reads conditional on line genotype and realized coverage. Both sets of parameters are estimated per site from the aggregate read data, and posterior probabilities are calculated to decode the genotype of each line. We present an application of JGIL to 162 inbred Drosophila melanogaster lines from the Drosophila Genetic Reference Panel. We explore by simulation the effect of varying coverage, sequencing error, mapping error, and the number of lines. In doing so, we illustrate how JGIL is robust to moderate levels of error. Supported by these analyses, we advocate the importance of modeling the data and the experimental design when possible.}, number={5}, journal={GENOME RESEARCH}, author={Stone, Eric A.}, year={2012}, month={May}, pages={966–974} }
 @article{myers_casals_gauthier_hamdan_keebler_boyko_bustamante_piton_spiegelman_henrion_et al._2011, title={A population genetic approach to mapping neurological disorder genes using deep resequencing}, volume={7}, number={2}, journal={PLoS Genetics}, author={Myers, R. A. and Casals, F. and Gauthier, J. and Hamdan, F. F. and Keebler, J. and Boyko, A. R. and Bustamante, C. D. and Piton, A. M. and Spiegelman, D. and Henrion, E. and et al.}, year={2011} }
 @article{maragh_miller_bessling_mcgaughey_wessels_graaf_stone_bertoli-avella_gearhart_fisher_et al._2011, title={Identification of RNA binding motif proteins essential for cardiovascular development}, volume={11}, ISSN={["1471-213X"]}, DOI={10.1186/1471-213x-11-62}, abstractNote={Abstract}, journal={BMC DEVELOPMENTAL BIOLOGY}, author={Maragh, Samantha and Miller, Ronald A. and Bessling, Seneca L. and McGaughey, David M. and Wessels, Marja W. and Graaf, Bianca and Stone, Eric A. and Bertoli-Avella, Aida M. and Gearhart, John D. and Fisher, Shannon and et al.}, year={2011}, month={Oct} }
 @article{dworkin_anderson_idaghdour_parker_stone_gibson_2011, title={The Effects of Weak Genetic Perturbations on the Transcriptome of the Wing Imaginal Disc and Its Association With Wing Shape in Drosophila melanogaster}, volume={187}, ISSN={["1943-2631"]}, DOI={10.1534/genetics.110.125922}, abstractNote={Abstract}, number={4}, journal={GENETICS}, author={Dworkin, Ian and Anderson, Julie A. and Idaghdour, Youssef and Parker, Erin Kennerly and Stone, Eric A. and Gibson, Greg}, year={2011}, month={Apr}, pages={1171–U314} }
 @article{mcferrin_stone_2011, title={The non-random clustering of non-synonymous substitutions and its relationship to evolutionary rate}, volume={12}, ISSN={["1471-2164"]}, DOI={10.1186/1471-2164-12-415}, abstractNote={Protein sequences are subject to a mosaic of constraint. Changes to functional domains and buried residues, for example, are more apt to disrupt protein structure and function than are changes to residues participating in loops or exposed to solvent. Regions of constraint on the tertiary structure of a protein often result in loose segmentation of its primary structure into stretches of slowly- and rapidly-evolving amino acids. This clustering can be exploited, and existing methods have done so by relying on local sequence conservation as a signature of selection to help identify functionally important regions within proteins. We invert this paradigm by leveraging the regional nature of protein structure and function to both illuminate and make use of genome-wide patterns of local sequence conservation.Our hypothesis is that the regional nature of structural and functional constraints will assert a positive autocorrelation on the evolutionary rates of neighboring sites, which, in a pairwise comparison of orthologous proteins, will manifest itself as the clustering of non-synonymous changes across the amino acid sequence. We introduce a dispersion ratio statistic to test this and related hypotheses. Using genome-wide interspecific comparisons of orthologous protein pairs, we reveal a strong log-linear relationship between the degree of clustering and the intensity of constraint. We further demonstrate how this relationship varies with the evolutionary distance between the species being compared. We provide some evidence that proteins with a history of positive selection deviate from genome-wide trends.We find a significant association between the evolutionary rate of a protein and the degree to which non-synonymous changes cluster along its primary sequence. We show that clustering is a non-redundant predictor of evolutionary rate, and we speculate that conflicting signals of clustering and constraint may be indicative of a historical period of relaxed selection.}, journal={BMC GENOMICS}, author={McFerrin, Lisa G. and Stone, Eric A.}, year={2011}, month={Aug} }
 @article{conrad_keebler_depristo_lindsay_zhang_casals_idaghdour_hartl_torroja_garimella_et al._2011, title={Variation in genome-wide mutation rates within and between human families}, volume={43}, number={7}, journal={Nature Genetics}, author={Conrad, D. F. and Keebler, J. E. M. and DePristo, M. A. and Lindsay, S. J. and Zhang, Y. J. and Casals, F. and Idaghdour, Y. and Hartl, C. L. and Torroja, C. and Garimella, K. V. and et al.}, year={2011}, pages={712–137} }
 @article{stone_2011, title={Why the Phylogenetic Regression Appears Robust to Tree Misspecification}, volume={60}, ISSN={["1063-5157"]}, DOI={10.1093/sysbio/syq098}, abstractNote={The phylogenetic comparative method uses estimates of evolutionary relationships to explicitly model the covariance structure of interspecific data. By accounting for common ancestry, the coevolution between 2 or more traits, as a response to one another or to environmental variables, can be studied without confounding similarities due to identity by descent. Because the true phylogeny is unknowable, an estimate must be used, introducing a source of error into phylogenetic comparative analysis that can be difficult to quantify. This manuscript aims to elucidate how tree misspecification is propagated through a comparative analysis. I focus on the phylogenetic regression under a Brownian motion model of evolution and consider the effect of local phylogenetic perturbations on the regression fit. Motivated by Felsenstein's method of independent contrasts, I derive a matrix square root of the phylogenetic covariance matrix that has an obvious phylogenetic interpretation. I use this result to transform the perturbed phylogenetic regression model into an ordinary linear regression in which one interpretable point has been affected. The simplicity of this formulation allows the contributions of data and phylogeny to be disentangled when studying the effect of tree misspecification. Consequentially, I find that branch length misspecification can be easily explained in terms of the reweighting of contrast scores between subtrees. An analytical consideration of this and other perturbations helps to explain why the phylogenetic regression appears generally to be robust to tree misspecification, and I am able to identify conditions under which the regression may not yield robust results. I discuss why soft polytomies do not meet these problematic conditions, leading to the conclusion that unresolved bifurcations should have only modest effects on the regression fit.}, number={3}, journal={SYSTEMATIC BIOLOGY}, author={Stone, Eric A.}, year={2011}, month={May}, pages={245–260} }
 @article{gauthier_champagne_lafreniere_xiong_spiegelman_brustein_lapointe_peng_cote_noreau_et al._2010, title={De novo mutations in the gene encoding the synaptic scaffolding protein SHANK3 in patients ascertained for schizophrenia}, volume={107}, number={17}, journal={Proceedings of the National Academy of Sciences of the United States of America}, author={Gauthier, J. and Champagne, N. and Lafreniere, R. G. and Xiong, L. and Spiegelman, D. and Brustein, E. and Lapointe, M. and Peng, H. S. and Cote, M. and Noreau, A. and et al.}, year={2010}, pages={7863–7868} }
 @article{awadalla_gauthier_myers_casals_hamdan_griffing_cote_henrion_spiegelman_tarabeux_et al._2010, title={Direct measure of the de novo mutation rate in autism and schizophrenia cohorts}, volume={87}, number={3}, journal={American Journal of Human Genetics}, author={Awadalla, P. and Gauthier, J. and Myers, R. A. and Casals, F. and Hamdan, F. F. and Griffing, A. R. and Cote, M. and Henrion, E. and Spiegelman, D. and Tarabeux, J. and et al.}, year={2010}, pages={316–324} }
 @article{binkley_karra_kirby_hosobuchi_stone_sidow_2010, title={ProPhylER: A curated online resource for protein function and structure based on evolutionary constraint analyses}, volume={20}, ISSN={["1549-5469"]}, DOI={10.1101/gr.097121.109}, abstractNote={ProPhylER (Protein Phylogeny and Evolutionary Rates) is a next-generation curated proteome resource that uses comparative sequence analysis to predict constraint and mutation impact for eukaryotic proteins. Its purpose is to inform any research program for which protein function and structure are relevant, by the predictive power of evolutionary constraint analyses. ProPhylER currently has nearly 9000 clusters of related proteins, including more than 200,000 sequences. It serves data via two interfaces. The “ProPhylER Interface” displays predictive analyses in sequence space; the “CrystalPainter” maps evolutionary constraints onto solved protein structures. Here we summarize ProPhylER's data content and analysis pipeline, demonstrate the use of ProPhylER's interfaces, and evaluate ProPhylER's unique regional analysis of evolutionary constraint. The high accuracy of ProPhylER's regional analysis complements the high resolution of its single-site analysis to effectively guide and inform structure–function investigations and predict the impact of polymorphisms.}, number={1}, journal={GENOME RESEARCH}, author={Binkley, Jonathan and Karra, Kalpana and Kirby, Andrew and Hosobuchi, Midori and Stone, Eric A. and Sidow, Arend}, year={2010}, month={Jan}, pages={142–154} }
 @article{choi_stone_kishino_thorne_2009, title={Estimates of natural selection due to protein tertiary structure inform the ancestry of biallelic loci}, volume={441}, DOI={10.1016/j.gene.2008.07.020}, abstractNote={We consider the inference of which of two alleles is ancestral when the alleles have a single nonsynonymous difference and when natural selection acts via protein tertiary structure. Whereas the probability that an allele is ancestral under neutrality is equal to its frequency, under selection this probability depends on allele frequency and on the magnitude and direction of selection pressure. Although allele frequencies can be well estimated from intraspecific data, small fitness differences have a large evolutionary impact but can be difficult to estimate with only intraspecific data. Methods for predicting aspects of phenotype from genotype can supplement intraspecific sequence data. Recently developed statistical techniques can assess effects of phenotypes, such as protein tertiary structure on molecular evolution. While these techniques were initially designed for comparing protein-coding genes from different species, the resulting interspecific inferences can be assigned population genetic interpretations to assess the effect of selection pressure, and we use them here along with intraspecific allele frequency data to estimate the probability that an allele is ancestral. We focus on 140 nonsynonymous single nucleotide polymorphisms of humans that are in proteins with known tertiary structures. We find that our technique for employing protein tertiary structure information yields some biologically plausible results but that it does not substantially improve the inference of ancestral human allele types.}, number={1-2}, journal={Gene}, author={Choi, S. C. and Stone, E. A. and Kishino, H. and Thorne, J. L.}, year={2009}, pages={45–52} }
 @article{stone_ayroles_2009, title={Modulated Modularity Clustering as an Exploratory Tool for Functional Genomic Inference}, volume={5}, ISSN={["1553-7404"]}, DOI={10.1371/journal.pgen.1000479}, abstractNote={In recent years, the advent of high-throughput assays, coupled with their diminishing cost, has facilitated a systems approach to biology. As a consequence, massive amounts of data are currently being generated, requiring efficient methodology aimed at the reduction of scale. Whole-genome transcriptional profiling is a standard component of systems-level analyses, and to reduce scale and improve inference clustering genes is common. Since clustering is often the first step toward generating hypotheses, cluster quality is critical. Conversely, because the validation of cluster-driven hypotheses is indirect, it is critical that quality clusters not be obtained by subjective means. In this paper, we present a new objective-based clustering method and demonstrate that it yields high-quality results. Our method, modulated modularity clustering (MMC), seeks community structure in graphical data. MMC modulates the connection strengths of edges in a weighted graph to maximize an objective function (called modularity) that quantifies community structure. The result of this maximization is a clustering through which tightly-connected groups of vertices emerge. Our application is to systems genetics, and we quantitatively compare MMC both to the hierarchical clustering method most commonly employed and to three popular spectral clustering approaches. We further validate MMC through analyses of human and Drosophila melanogaster expression data, demonstrating that the clusters we obtain are biologically meaningful. We show MMC to be effective and suitable to applications of large scale. In light of these features, we advocate MMC as a standard tool for exploration and hypothesis generation.}, number={5}, journal={PLOS GENETICS}, author={Stone, Eric A. and Ayroles, Julien F.}, year={2009}, month={May} }
 @article{stone_griffing_2009, title={On the Fiedler vectors of graphs that arise from trees by Schur complementation of the Laplacian}, volume={431}, ISSN={["0024-3795"]}, DOI={10.1016/j.laa.2009.06.024}, abstractNote={The utility of Fiedler vectors in interrogating the structure of graphs has generated intense interest and motivated the pursuit of further theoretical results. This paper focuses on how the Fiedler vectors of one graph reveal structure in a second graph that is related to the first. Specifically, we consider a point of articulation r in the graph G whose Laplacian matrix is L and derive a related graph G{r} whose Laplacian is the matrix obtained by taking the Schur complement with respect to r in L. We show how Fiedler vectors of G{r} relate to the structure of G and we provide bounds for the algebraic connectivity of G{r} in terms of the connected components at r in G. In the case where G is a tree with points of articulation r ∈ R, we further consider the graph GR derived from G by taking the Schur complement with respect to R in L. We show that Fiedler vectors of GR valuate the pendent vertices of G in a manner consistent with the structure of the tree.}, number={10}, journal={LINEAR ALGEBRA AND ITS APPLICATIONS}, author={Stone, Eric A. and Griffing, Alexander R.}, year={2009}, month={Oct}, pages={1869–1880} }
 @article{hobolth_stone_2009, title={SIMULATION FROM ENDPOINT-CONDITIONED, CONTINUOUS-TIME MARKOV CHAINS ON A FINITE STATE SPACE, WITH APPLICATIONS TO MOLECULAR EVOLUTION}, volume={3}, ISSN={["1932-6157"]}, DOI={10.1214/09-AOAS247}, abstractNote={Analyses of serially-sampled data often begin with the assumption that the observations represent discrete samples from a latent continuous-time stochastic process. The continuous-time Markov chain (CTMC) is one such generative model whose popularity extends to a variety of disciplines ranging from computational finance to human genetics and genomics. A common theme among these diverse applications is the need to simulate sample paths of a CTMC conditional on realized data that is discretely observed. Here we present a general solution to this sampling problem when the CTMC is defined on a discrete and finite state space. Specifically, we consider the generation of sample paths, including intermediate states and times of transition, from a CTMC whose beginning and ending states are known across a time interval of length T. We first unify the literature through a discussion of the three predominant approaches: (1) modified rejection sampling, (2) direct sampling, and (3) uniformization. We then give analytical results for the complexity and efficiency of each method in terms of the instantaneous transition rate matrix Q of the CTMC, its beginning and ending states, and the length of sampling time T. In doing so, we show that no method dominates the others across all model specifications, and we give explicit proof of which method prevails for any given Q, T, and endpoints. Finally, we introduce and compare three applications of CTMCs to demonstrate the pitfalls of choosing an inefficient sampler.}, number={3}, journal={ANNALS OF APPLIED STATISTICS}, author={Hobolth, Asger and Stone, Eric A.}, year={2009}, month={Sep}, pages={1204–1231} }
 @article{stone_sidow_2007, title={Constructing a meaningful evolutionary average at the phylogenetic center of mass}, volume={8}, ISSN={["1471-2105"]}, DOI={10.1186/1471-2105-8-222}, abstractNote={As a consequence of the evolutionary process, data collected from related species tend to be similar. This similarity by descent can obscure subtler signals in the data such as the evidence of constraint on variation due to shared selective pressures. In comparative sequence analysis, for example, sequence similarity is often used to illuminate important regions of the genome, but if the comparison is between closely related species, then similarity is the rule rather than the interesting exception. Furthermore, and perhaps worse yet, the contribution of a divergent third species may be masked by the strong similarity between the other two. Here we propose a remedy that weighs the contribution of each species according to its phylogenetic placement.We first solve the problem of summarizing data related by phylogeny, and we explain why an average should operate on the entire evolutionary trajectory that relates the data. This perspective leads to a new approach in which we define the average in terms of the phylogeny, using the data and a stochastic model to obtain a probability on evolutionary trajectories. With the assumption that the data evolve according to a Brownian motion process on the tree, we show that our evolutionary average can be computed as convex combination of the species data. Thus, our approach, called the BranchManager, defines both an average and a novel taxon weighting scheme. We compare the BranchManager to two other methods, demonstrating why it exhibits desirable properties. In doing so, we devise a framework for comparison and introduce the concept of a representative point at which the average is situated.The BranchManager uses as its representative point the phylogenetic center of mass, a choice which has both intuitive and practical appeal. Because our average is intrinsic to both the dataset and to the phylogeny, we expect it and its corresponding weighting scheme to be useful in all sorts of studies where interspecies data need to be combined. Obvious applications include evolutionary studies of morphology, physiology or behaviour, but quantitative measures such as sequence hydrophobicity and gene expression level are amenable to our approach as well. Other areas of potential impact include motif discovery and vaccine design. A Java implementation of the BranchManager is available for download, as is a script written in the statistical language R.}, journal={BMC BIOINFORMATICS}, author={Stone, Eric A. and Sidow, Arend}, year={2007}, month={Jun} }
 @article{hsieh_passador-gurgel_stone_gibson_2007, title={Mixture modeling of transcript abundance classes in natural populations}, volume={8}, ISSN={["1474-760X"]}, DOI={10.1186/gb-2007-8-6-r98}, abstractNote={Populations diverge in genotype and phenotype under the influence of such evolutionary processes as genetic drift, mutation accumulation, and natural selection. Because genotype maps onto phenotype by way of transcription, it is of interest to evaluate how these evolutionary factors influence the structure of variation at the level of transcription. Here, we explore the distributions of cis-acting and trans-acting factors and their relative contributions to expression of transcripts that exhibit two or more classes of abundance among individuals within populations.Expression profiling using cDNA microarrays was conducted in Drosophila melanogaster adult female heads for 58 nearly isogenic lines from a North Carolina population and 50 from a California population. Using a mixture modeling approach, transcripts were identified that exhibit more than one mode of transcript abundance across the samples. Power studies indicate that sample sizes of 50 individuals will generally be sufficient to detect divergent transcript abundance classes. The distribution of transcript abundance classes is skewed toward low frequency minor classes, which is reminiscent of the typical skew in genotype frequencies. Similar results are observed in reported data on gene expression in human lymphoblast cell lines, in which analysis of association with linked polymorphisms implies that cis-acting single nucleotide polymorphisms make only a modest contribution to bimodal distributions of transcript abundance.Population surveys of gene expression may complement genetical genomics as a general approach to quantifying sources of transcriptional variation. Differential expression of transcripts among individuals is due to a complex interplay of cis-acting and trans-acting factors.}, number={6}, journal={GENOME BIOLOGY}, author={Hsieh, Wen-Ping and Passador-Gurgel, Gisele and Stone, Eric A. and Gibson, Greg}, year={2007} }
 @article{cranston_carniti_oakhill_radzio-andzelm_stone_mccallion_hodgson_clarke_mondellini_leyland_et al._2006, title={RET is constitutively activated by novel tandem mutations that alter the active site resulting in multiple endocrine neoplasia type 2B}, volume={66}, ISSN={["1538-7445"]}, DOI={10.1158/0008-5472.CAN-06-0884}, abstractNote={Abstract}, number={20}, journal={CANCER RESEARCH}, author={Cranston, Aaron N. and Carniti, Cristiana and Oakhill, Kim and Radzio-Andzelm, Elzbieta and Stone, Eric A. and McCallion, Andrew S. and Hodgson, Shirley and Clarke, Sue and Mondellini, Piera and Leyland, Jean and et al.}, year={2006}, month={Oct}, pages={10179–10187} }
 @article{huang_richards_carbone_zhu_anholt_ayroles_duncan_jordan_lawrence_magwire_et al., title={Epistasis dominates the genetic architecture of Drosophila quantitative traits}, volume={109}, number={39}, journal={Proceedings of the National Academy of Sciences of the United States of America}, author={Huang, W. and Richards, S. and Carbone, M. A. and Zhu, D. H. and Anholt, R. R. H. and Ayroles, J. F. and Duncan, L. and Jordan, K. W. and Lawrence, F. and Magwire, M. M. and et al.}, pages={15553–15559} }
 @article{ayroles_laflamme_stone_wolfner_mackay, title={Functional genome annotation of Drosophila seminal fluid proteins using transcriptional genetic networks}, volume={93}, number={6}, journal={Genetical Research}, author={Ayroles, J. F. and Laflamme, B. A. and Stone, E. A. and Wolfner, M. F. and Mackay, T. F. C.}, pages={387–395} }
 @article{huang_carbone_magwire_peiffer_lyman_stone_anholt_mackay, title={Genetic basis of transcriptome diversity in Drosophila melanogaster}, volume={112}, number={44}, journal={Proceedings of the National Academy of Sciences of the United States of America}, author={Huang, W. and Carbone, M. A. and Magwire, M. M. and Peiffer, J. A. and Lyman, R. F. and Stone, E. A. and Anholt, R. R. H. and Mackay, T. F. C.}, pages={E6010–6019} }
 @article{massouras_waszak_albarca-aguilera_hens_holcombe_ayroles_dermitzakis_stone_jensen_mackay_et al., title={Genomic variation and its impact on gene expression in Drosophila melanogaster}, volume={8}, number={11}, journal={PLoS Genetics}, author={Massouras, A. and Waszak, S. M. and Albarca-Aguilera, M. and Hens, K. and Holcombe, W. and Ayroles, J. F. and Dermitzakis, E. T. and Stone, E. A. and Jensen, J. D. and Mackay, T. F. C. and et al.} }
 @article{zhou_stone_mackay_anholt, title={Plasticity of the chemoreceptor repertoire in Drosophila melanogaster}, volume={5}, number={10}, journal={PLoS Genetics}, author={Zhou, S. S. and Stone, E. A. and Mackay, T. F. C. and Anholt, R. R. H.} }
 @article{mackay_richards_stone_barbadilla_ayroles_zhu_casillas_han_magwire_cridland_et al., title={The Drosophila melanogaster genetic reference panel}, volume={482}, number={7384}, journal={Nature}, author={Mackay, T. F. C. and Richards, S. and Stone, E. A. and Barbadilla, A. and Ayroles, J. F. and Zhu, D. H. and Casillas, S. and Han, Y. and Magwire, M. M. and Cridland, J. M. and et al.}, pages={173–178} }
 @article{ober_ayroles_stone_richards_zhu_gibbs_stricker_gianola_schlather_mackay_et al., title={Using whole-genome sequence data to predict quantitative trait phenotypes in Drosophila melanogaster}, volume={8}, number={5}, journal={PLoS Genetics}, author={Ober, U. and Ayroles, J. F. and Stone, E. A. and Richards, S. and Zhu, D. H. and Gibbs, R. A. and Stricker, C. and Gianola, D. and Schlather, M. and Mackay, T. F. C. and et al.} }