@article{jain_bakolitsa_brenner_radivojac_moult_repo_hoskins_andreoletti_barsky_chellapan_et al._2024, title={CAGI, the Critical Assessment of Genome Interpretation, establishes progress and prospects for computational genetic variant interpretation methods}, volume={25}, ISSN={["1474-760X"]}, DOI={10.1186/s13059-023-03113-6}, abstractNote={Abstract
                Background
                The Critical Assessment of Genome Interpretation (CAGI) aims to advance the state-of-the-art for computational prediction of genetic variant impact, particularly where relevant to disease. The five complete editions of the CAGI community experiment comprised 50 challenges, in which participants made blind predictions of phenotypes from genetic data, and these were evaluated by independent assessors.
              
                Results
                Performance was particularly strong for clinical pathogenic variants, including some difficult-to-diagnose cases, and extends to interpretation of cancer-related variants. Missense variant interpretation methods were able to estimate biochemical effects with increasing accuracy. Assessment of methods for regulatory variants and complex trait disease risk was less definitive and indicates performance potentially suitable for auxiliary use in the clinic.
              
                Conclusions
                Results show that while current methods are imperfect, they have major utility for research and clinical applications. Emerging methods and increasingly large, robust datasets for training and assessment promise further progress ahead.
              }, number={1}, journal={GENOME BIOLOGY}, author={Jain, Shantanu and Bakolitsa, Constantina and Brenner, Steven E. and Radivojac, Predrag and Moult, John and Repo, Susanna and Hoskins, Roger A. and Andreoletti, Gaia and Barsky, Daniel and Chellapan, Ajithavalli and et al.}, year={2024}, month={Feb} }
 @article{guerrero_dorji_harris_shoulders_ogbunugafor_2024, title={Evolutionary druggability for low-dimensional fitness landscapes toward new metrics for antimicrobial applications}, url={https://doi.org/10.7554/eLife.88480.3}, DOI={10.7554/eLife.88480.3}, abstractNote={The term ‘druggability’ describes the molecular properties of drugs or targets in pharmacological interventions and is commonly used in work involving drug development for clinical applications. There are no current analogues for this notion that quantify the drug-target interaction with respect to a given target variant’s sensitivity across a breadth of drugs in a panel, or a given drug’s range of effectiveness across alleles of a target protein. Using data from low-dimensional empirical fitness landscapes composed of 16 β-lactamase alleles and 7 β-lactam drugs, we introduce two metrics that capture (i) the average susceptibility of an allelic variant of a drug target to any available drug in a given panel (‘ variant vulnerability’ ), and (ii) the average applicability of a drug (or mixture) across allelic variants of a drug target (‘ drug applicability ’). Finally, we (iii) disentangle the quality and magnitude of interactions between loci in the drug target and the seven drug environments in terms of their mutation by mutation by environment (G x G x E) interactions, offering mechanistic insight into the variant variability and drug applicability metrics. Summarizing, we propose that our framework can be applied to other datasets and pathogen-drug systems to understand which pathogen variants in a clinical setting are the most concerning (low variant vulnerability), and which drugs in a panel are most likely to be effective in an infection defined by standing genetic variation in the pathogen drug target (high drug applicability).}, journal={eLife}, author={Guerrero, Rafael F and Dorji, Tandin and Harris, Ra'Mal M and Shoulders, Matthew D and Ogbunugafor, C Brandon}, year={2024}, month={Jun} }
 @article{khan_guerrero_wapner_hahn_raja_salleb-aouissi_grobman_simhan_silver_chung_et al._2024, title={Genetic polymorphisms associated with adverse pregnancy outcomes in nulliparas}, volume={14}, ISSN={["2045-2322"]}, DOI={10.1038/s41598-024-61218-9}, abstractNote={Adverse pregnancy outcomes (APOs) affect a large proportion of pregnancies and represent an important cause of morbidity and mortality worldwide. Yet the pathophysiology of APOs is poorly understood, limiting our ability to prevent and treat these conditions. To search for genetic markers of maternal risk for four APOs, we performed multi-ancestry genome-wide association studies (GWAS) for pregnancy loss, gestational length, gestational diabetes, and preeclampsia. We clustered participants by their genetic ancestry and focused our analyses on three sub-cohorts with the largest sample sizes: European, African, and Admixed American. Association tests were carried out separately for each sub-cohort and then meta-analyzed together. Two novel loci were significantly associated with an increased risk of pregnancy loss: a cluster of SNPs located downstream of the TRMU gene (top SNP: rs142795512), and the SNP rs62021480 near RGMA. In the GWAS of gestational length we identified two new variants, rs2550487 and rs58548906 near WFDC1 and AC005052.1, respectively. Lastly, three new loci were significantly associated with gestational diabetes (top SNPs: rs72956265, rs10890563, rs79596863), located on or near ZBTB20, GUCY1A2, and RPL7P20, respectively. Fourteen loci previously correlated with preterm birth, gestational diabetes, and preeclampsia were found to be associated with these outcomes as well.}, number={1}, journal={SCIENTIFIC REPORTS}, author={Khan, Raiyan R. and Guerrero, Rafael F. and Wapner, Ronald J. and Hahn, Matthew W. and Raja, Anita and Salleb-Aouissi, Ansaf and Grobman, William A. and Simhan, Hyagriv and Silver, Robert M. and Chung, Judith H. and et al.}, year={2024}, month={May} }
 @article{bursell_rohilla_ramirez_cheng_schwarzkopf_guerrero_heil_2024, title={Mixed outcomes in recombination rates after domestication: Revisiting theory and data}, url={https://doi.org/10.1101/2024.08.07.607048}, DOI={10.1101/2024.08.07.607048}, abstractNote={Abstract The process of domestication has altered many phenotypes. Selection on these phenotypes has long been hypothesized to indirectly select for increases in recombination rate. This hypothesis is consistent with theory on the evolution of recombination rate, but empirical support has been unclear. We review relevant theory, lab-based experiments, and data comparing recombination rates in wild progenitors and their domesticated counterparts. We utilize population sequencing data and a deep learning method to infer genome-wide recombination rates for new comparisons of chicken/red junglefowl, sheep/mouflon, and goat/bezoar. We find evidence of increased recombination in domestic goats compared to bezoars, but more mixed results in chicken, and generally decreased recombination in domesticated sheep compared to mouflon. Our results add to a growing body of literature in plants and animals that finds no consistent evidence of an increase in recombination with domestication.}, author={Bursell, Madeline and Rohilla, Manav and Ramirez, Lucia and Cheng, Yuhuan and Schwarzkopf, Enrique J. and Guerrero, Rafael F. and Heil, Caiti Smukowski}, year={2024}, month={Aug} }
 @article{ogbunugafor_guerrero_miller-dickson_shakhnovich_shoulders_2023, title={Epistasis and pleiotropy shape biophysical protein subspaces associated with drug resistance}, volume={108}, ISSN={["2470-0053"]}, url={https://doi.org/10.1103/PhysRevE.108.054408}, DOI={10.1103/PhysRevE.108.054408}, abstractNote={Protein space is a rich analogy for genotype-phenotype maps, where amino acid sequence is organized into a high-dimensional space that highlights the connectivity between protein variants. It is a useful abstraction for understanding the process of evolution, and for efforts to engineer proteins towards desirable phenotypes. Few mentions of protein space consider how protein phenotypes can be described in terms of their biophysical components, nor do they rigorously interrogate how forces like epistasis-describing the nonlinear interaction between mutations and their phenotypic consequences-manifest across these components. In this study, we deconstruct a low-dimensional protein space of a bacterial enzyme (dihydrofolate reductase; DHFR) into "subspaces" corresponding to a set of kinetic and thermodynamic traits [k_{cat}, K_{M}, K_{i}, and T_{m} (melting temperature)]. We then examine how combinations of three mutations (eight alleles in total) display pleiotropy, or unique effects on individual subspace traits. We examine protein spaces across three orthologous DHFR enzymes (Escherichia coli, Listeria grayi, and Chlamydia muridarum), adding a genotypic context dimension through which epistasis occurs across subspaces. In doing so, we reveal that protein space is a deceptively complex notion, and that future applications to bioengineering should consider how interactions between amino acid substitutions manifest across different phenotypic subspaces.}, number={5}, journal={PHYSICAL REVIEW E}, author={Ogbunugafor, C. Brandon and Guerrero, Rafael F. and Miller-Dickson, Miles D. and Shakhnovich, Eugene I. and Shoulders, Matthew D.}, year={2023}, month={Nov} }
 @article{ogbunugafor_guerrero_shakhnovich_shoulders_2023, title={Epistasis meets pleiotropy in shaping biophysical protein subspaces associated with antimicrobial resistance}, url={https://doi.org/10.1101/2023.04.09.535490}, DOI={10.1101/2023.04.09.535490}, abstractNote={AbstractProtein space is a rich analogy for genotype-phenotype maps, where amino acid sequence is organized into a high-dimensional space that highlights the connectivity between protein variants. It is a useful abstraction for understanding the process of evolution, and for efforts to engineer proteins towards desirable phenotypes. Few framings of protein space consider how higher-level protein phenotypes can be described in terms of their biophysical dimensions, nor do they rigorously interrogate how forces like epistasis—describing the nonlinear interaction between mutations and their phenotypic consequences—manifest across these dimensions. In this study, we deconstruct a low-dimensional protein space of a bacterial enzyme (dihydrofolate reductase; DHFR) into “subspaces” corresponding to a set of kinetic and thermodynamic traits [(kcat, KM,Ki, andTm(melting temperature)]. We then examine how three mutations (eight alleles in total) display pleiotropy in their interactions across these subspaces. We extend this approach to examine protein spaces across three orthologous DHFR enzymes (Escherichia coli, Listeria grayi, andChlamydia muridarum), adding a genotypic context dimension through which epistasis occurs across subspaces. In doing so, we reveal that protein space is a deceptively complex notion, and that the process of protein evolution and engineering should consider how interactions between amino acid substitutions manifest across different phenotypic subspaces.}, author={Ogbunugafor, C. Brandon and Guerrero, Rafael F. and Shakhnovich, Eugene I. and Shoulders, Matthew D.}, year={2023}, month={Apr} }
 @article{guerrero_dorji_harris_shoulders_ogbunugafor_2024, title={Evolutionary druggability for low-dimensional fitness landscapes toward new metrics for antimicrobial applications}, volume={12}, ISSN={["2050-084X"]}, url={https://doi.org/10.7554/eLife.88480}, DOI={10.7554/eLife.88480}, abstractNote={The term ‘druggability’ describes the molecular properties of drugs or targets in pharmacological interventions and is commonly used in work involving drug development for clinical applications. There are no current analogues for this notion that quantify the drug-target interaction with respect to a given target variant’s sensitivity across a breadth of drugs in a panel, or a given drug’s range of effectiveness across alleles of a target protein. Using data from low-dimensional empirical fitness landscapes composed of 16 β-lactamase alleles and 7 β-lactam drugs, we introduce two metrics that capture (i) the average susceptibility of an allelic variant of a drug target to any available drug in a given panel (‘ variant vulnerability’ ), and (ii) the average applicability of a drug (or mixture) across allelic variants of a drug target (‘ drug applicability ’). Finally, we (iii) disentangle the quality and magnitude of interactions between loci in the drug target and the seven drug environments in terms of their mutation by mutation by environment (G x G x E) interactions, offering mechanistic insight into the variant variability and drug applicability metrics. Summarizing, we propose that our framework can be applied to other datasets and pathogen-drug systems to understand which pathogen variants in a clinical setting are the most concerning (low variant vulnerability), and which drugs in a panel are most likely to be effective in an infection defined by standing genetic variation in the pathogen drug target (high drug applicability).}, journal={ELIFE}, author={Guerrero, Rafael F. and Dorji, Tandin and Harris, Ra'Mal M. and Shoulders, Matthew D. and Ogbunugafor, C. Brandon}, year={2024}, month={Jun} }
 @article{guerrero_dorji_harris_shoulders_ogbunugafor_2023, title={Evolutionary druggability: leveraging low-dimensional fitness landscapes towards new metrics for antimicrobial applications}, url={https://doi.org/10.1101/2023.04.08.536116}, DOI={10.1101/2023.04.08.536116}, abstractNote={AbstractThe term “druggability” describes the molecular properties of drugs or targets in pharmacological interventions and is commonly used in work involving drug development for clinical applications. There are no current analogues for this notion that quantify the drug-target interaction with respect to a given target variant’s sensitivity across a breadth of drugs in a panel, or a given drug’s range of effectiveness across alleles of a target protein. Using data from low-dimensional empirical fitness landscapes composed of 16β-lactamase alleles and sevenβ-lactam drugs, we introduce two metrics that capture (i) the average susceptibility of an allelic variant of a drug target to any available drug in a given panel (“variant vulnerability”), and (ii) the average applicability of a drug (or mixture) across allelic variants of a drug target (“drug applicability”). Finally, we (iii) disentangle the quality and magnitude of interactions between loci in the drug target and the seven drug environments in terms of their mutation by mutation by environment (G x G x E) interactions, offering mechanistic insight into the variant variability and drug applicability metrics. Summarizing, we propose that our framework can be applied to other datasets and pathogen-drug systems to understand which pathogen variants in a clinical setting are the most concerning (low variant vulnerability), and which drugs in a panel are most likely to be effective in an infection defined by standing genetic variation in the pathogen drug target (high drug applicability).}, author={Guerrero, Rafael F. and Dorji, Tandin and Harris, Ra’Mal M. and Shoulders, Matthew D. and Ogbunugafor, C. Brandon}, year={2023}, month={Apr} }
 @article{yan_blue_truong_zhang_guerrero_liu_honigberg_parry_mcneil_simhan_et al._2023, title={Genetic Associations with Placental Proteins in Maternal Serum Identify Biomarkers for Hypertension in Pregnancy}, url={https://doi.org/10.1101/2023.05.25.23290460}, DOI={10.1101/2023.05.25.23290460}, abstractNote={ABSTRACTPreeclampsia (PE), a gestational hypertensive disorder, ranks as the second leading cause of maternal mortality worldwide. While PE is considered a multifactorial disease, placental insufficiency is believed to drive its progression. To noninvasively study placental physiology related to adverse pregnancy outcomes (APOs) and predict these outcomes before symptom onset, we measured nine placental protein levels in first- and second-trimester serum samples from 2,352 nulliparous pregnant women in the Nulliparous Pregnancy Outcomes Study: Monitoring Mothers- to-Be (nuMoM2b) study. The proteins analyzed include VEGF, PlGF, ENG, sFlt-1, ADAM-12, PAPP-A, fβHCG, INHA, and AFP. Currently, little is known about the genetic variants contributing to the heritability of these proteins during pregnancy, and no studies have explored the causal relationships between early pregnancy proteins and gestational hypertensive disorders. Our study has three objectives. First, we conducted genome-wide association study (GWAS) of nine placental proteins in maternal serum during the first and second trimesters and the difference between time points to understand how genetics may influence placental proteins in early pregnancy. Second, we examined whether early pregnancy placental proteins are causal factors for PE and gestational hypertension (gHTN). Lastly, we investigated the causal relationship between PE/gHTN and long-term HTN. In conclusion, our study discovered significant genetic associations with placental proteins ADAM-12, VEGF, and sFlt-1, offering insights into their regulation during pregnancy. Mendelian randomization (MR) analyses demonstrated evidence of causal relationships between placental proteins, particularly ADAM-12, and gHTN, potentially informing prevention and treatment strategies. Our findings suggest that placental proteins like ADAM-12 could serve as biomarkers for postpartum HTN risk.}, author={Yan, Qi and Blue, Nathan R. and Truong, Buu and Zhang, Yu and Guerrero, Rafael F. and Liu, Nianjun and Honigberg, Michael C. and Parry, Samuel and McNeil, Rebecca B. and Simhan, Hyagriv N. and et al.}, year={2023}, month={May} }
 @article{honigberg_truong_khan_xiao_bhatta_vy_guerrero_schuermans_selvaraj_patel_et al._2023, title={Polygenic prediction of preeclampsia and gestational hypertension}, volume={5}, ISSN={["1546-170X"]}, DOI={10.1038/s41591-023-02374-9}, abstractNote={Preeclampsia and gestational hypertension are common pregnancy complications associated with adverse maternal and child outcomes. Current tools for prediction, prevention and treatment are limited. Here we tested the association of maternal DNA sequence variants with preeclampsia in 20,064 cases and 703,117 control individuals and with gestational hypertension in 11,027 cases and 412,788 control individuals across discovery and follow-up cohorts using multi-ancestry meta-analysis. Altogether, we identified 18 independent loci associated with preeclampsia/eclampsia and/or gestational hypertension, 12 of which are new (for example, MTHFR–CLCN6, WNT3A, NPR3, PGR and RGL3), including two loci (PLCE1 and FURIN) identified in the multitrait analysis. Identified loci highlight the role of natriuretic peptide signaling, angiogenesis, renal glomerular function, trophoblast development and immune dysregulation. We derived genome-wide polygenic risk scores that predicted preeclampsia/eclampsia and gestational hypertension in external cohorts, independent of clinical risk factors, and reclassified eligibility for low-dose aspirin to prevent preeclampsia. Collectively, these findings provide mechanistic insights into the hypertensive disorders of pregnancy and have the potential to advance pregnancy risk stratification. A multi-ancestry genetic meta-analysis identifies 12 new loci associated with preeclampsia and gestational hypertension and proposes the integration of polygenic scores and clinical factors for disease prediction}, journal={NATURE MEDICINE}, author={Honigberg, Michael C. and Truong, Buu and Khan, Raiyan R. and Xiao, Brenda and Bhatta, Laxmi and Vy, Ha My T. and Guerrero, Rafael F. and Schuermans, Art and Selvaraj, Margaret Sunitha and Patel, Aniruddh P. and et al.}, year={2023}, month={May} }
 @article{yan_guerrero_khan_surujnarine_wapner_hahn_raja_sallebaouissi_grobman_simhan_et al._2023, title={Searching and visualizing genetic associations of pregnancy traits by using GnuMoM2b}, url={https://doi.org/10.1101/2023.05.25.23290500}, DOI={10.1101/2023.05.25.23290500}, abstractNote={AbstractAdverse pregnancy outcomes (APOs) are major risk factors for women’s health during pregnancy and even in the years after pregnancy. Due to the heterogeneity of APOs, only few genetic associations have been identified. In this report, we conducted genome-wide association studies (GWAS) of 479 traits that are possibly related to APOs using a large and racially diverse study, Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be (nuMoM2b). To display the extensive results, we developed a web-based tool GnuMoM2b (https://gnumom2b.cumcobgyn.org/) for searching, visualizing, and sharing results from GWAS of 479 pregnancy traits as well as phenome-wide association studies (PheWAS) of more than 17 million single nucleotide polymorphisms (SNPs). The genetic results from three ancestries (Europeans, Africans, and Admixed Americans) and meta-analyses are populated in GnuMoM2b. In conclusion, GnuMoM2b is a valuable resource for extraction of pregnancy-related genetic results and shows the potential to facilitate meaningful discoveries.}, author={Yan, Qi and Guerrero, Rafael F. and Khan, Raiyan R. and Surujnarine, Andy A. and Wapner, Ronald J. and Hahn, Matthew W. and Raja, Anita and SallebAouissi, Ansaf and Grobman, William A. and Simhan, Hyagriv and et al.}, year={2023}, month={Jun} }
 @article{yan_guerrero_khan_surujnarine_wapner_hahn_raja_salleb-aouissi_grobman_simhan_et al._2023, title={Searching and visualizing genetic associations of pregnancy traits by using GnuMoM2b}, volume={225}, ISSN={["1943-2631"]}, DOI={10.1093/genetics/iyad151}, abstractNote={Abstract
               Adverse pregnancy outcomes (APOs) are major risk factors for women's health during pregnancy and even in the years after pregnancy. Due to the heterogeneity of APOs, only few genetic associations have been identified. In this report, we conducted genome-wide association studies (GWASs) of 479 traits that are possibly related to APOs using a large and racially diverse study, Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be (nuMoM2b). To display extensive results, we developed a web-based tool GnuMoM2b (https://gnumom2b.cumcobgyn.org/) for searching, visualizing, and sharing results from a GWAS of 479 pregnancy traits as well as phenome-wide association studies of more than 17 million single nucleotide polymorphisms. The genetic results from 3 ancestries (Europeans, Africans, and Admixed Americans) and meta-analyses are populated in GnuMoM2b. In conclusion, GnuMoM2b is a valuable resource for extraction of pregnancy-related genetic results and shows the potential to facilitate meaningful discoveries.}, number={2}, journal={GENETICS}, author={Yan, Qi and Guerrero, Rafael F. and Khan, Raiyan R. and Surujnarine, Andy A. and Wapner, Ronald J. and Hahn, Matthew W. and Raja, Anita and Salleb-Aouissi, Ansaf and Grobman, William A. and Simhan, Hyagriv and et al.}, year={2023}, month={Oct} }
 @article{pagel_chu_ramola_guerrero_chung_parry_reddy_silver_steller_yee_et al._2022, title={Association of Genetic Predisposition and Physical Activity With Risk of Gestational Diabetes in Nulliparous Women}, volume={5}, ISSN={["2574-3805"]}, DOI={10.1001/jamanetworkopen.2022.29158}, abstractNote={Key Points Question Are genetic predisposition to diabetes and physical activity in early pregnancy cooperatively associated with risk of gestational diabetes (GD) among nulliparous women? Findings In this cohort study of 3533 women, a high polygenic risk score (PRS) and low level of physical activity were associated with increased risk of GD. The estimated odds for participants with high PRS and low level of physical activity was 3.4 but was near or less than the baseline level of 1.0 with either low PRS or high activity. Meaning These findings suggest that physical activity in early pregnancy is associated with reduced risk of GD and reversal of excess risk in genetically predisposed individuals, and PRS may have utility in identifying women for targeted interventions.}, number={8}, journal={JAMA NETWORK OPEN}, author={Pagel, Kymberleigh A. and Chu, Hoyin and Ramola, Rashika and Guerrero, Rafael F. and Chung, Judith H. and Parry, Samuel and Reddy, Uma M. and Silver, Robert M. and Steller, Jonathan G. and Yee, Lynn M. and et al.}, year={2022}, month={Aug} }
 @article{guerrero_khan_wapner_hahn_raja_salleb-aouissi_grobman_simhan_silver_chung_et al._2022, title={Genetic Polymorphisms Associated with Adverse Pregnancy Outcomes in Nulliparas}, url={https://doi.org/10.1101/2022.02.28.22271641}, DOI={10.1101/2022.02.28.22271641}, abstractNote={ABSTRACTBackgroundAdverse pregnancy outcomes (APOs) affect a large proportion of pregnancies and represent an important cause of morbidity and mortality worldwide. Yet, the pathophysiology of APOs is poorly understood, limiting our ability to prevent and treat these conditions.ObjectiveTo search for genetic risk markers for four APOs, we performed genome-wide association studies (GWAS) for preterm birth, preeclampsia, gestational diabetes, and pregnancy loss.Study DesignA total of 9,757 nulliparas from the nuMoM2b study were genotyped. We clustered participants by their genetic ancestry and focused our analyses on the three sub-cohorts with the largest sample sizes: European (EUR, n=6,082), African (AFR, n=1,425), and American (AMR, n=846). Association tests were carried out separately for each sub-cohort and brought together via meta-analysis. Four APOs were tested by GWAS: preeclampsia (n=7,909), gestational length (n=4,781), gestational diabetes (n=7,617), and pregnancy loss (n=7,809). Using the results of the genome-wide associations for each APO, SNP-based heritability of these traits was inferred using LDscore. Putative regulatory effects were inferred by transcriptome-wide association analysis.ResultsTwo variants were significantly associated with pregnancy loss (rs62021480: OR = 3.29, P = 7.83×10−11, and rs142795512: OR = 4.72, P = 9.64×10−9), implicating genes TRMU and RGMA in this APO. An intronic variant was significantly associated with gestational length (rs73842644: beta = -0.667, P = 4.9×10−8). Three loci were significantly associated with gestational diabetes (rs72956265: OR = 3.09, P = 2.98×10−8, rs10890563: OR = 1.88, P = 3.53×10−8, rs117689036: OR = 3.15, P = 1.46×10−8), located on or near ZBTB20, GUCY1A2, and MDGA2, respectively. Several loci previously correlated with preterm birth (in genes WNT4, EBF1, PER3, IL10, and ADCY5), gestational diabetes (in TCF7L2), and preeclampsia (in MTHFR) were found to be associated with these outcomes in our cohort as well.ConclusionOur study identified genetic associations with gestational diabetes, pregnancy loss, and gestational length. We also confirm correlations of several previously identified variants with these APOs.Disclosure StatementThe authors declare no conflict of interestSource of financial supportPrecision Health Initiative of Indiana University, National Institutes of Health award R01HD101246 to DMH and PR. Cooperative agreement funding from the National Heart, Lung, and Blood Institute and the Eunice Kennedy Shriver National Institute of Child Health and Human Development: grant U10-HL119991 to RTI International; grant U10-HL119989 to Case Western Reserve University; grants U10-HL120034 and R01LM013327 to Columbia University; grant U10-HL119990 to Indiana University; grant U10-HL120006 to the University of Pittsburgh; grant U10-HL119992 to Northwestern University; grant U10-HL120019 to the University of California, Irvine; grant U10-HL119993 to University of Pennsylvania; and grant U10-HL120018 to the University of Utah. National Center for Research Resources and the National Center for Advancing Translational Sciences, National Institutes of Health to Clinical and Translational Science Institutes at Indiana University (grant UL1TR001108) and University of California, Irvine (grant UL1TR000153).}, author={Guerrero, Rafael F. and Khan, Raiyan R. and Wapner, Ronald J. and Hahn, Matthew W. and Raja, Anita and Salleb-Aouissi, Ansaf and Grobman, William A. and Simhan, Hyagriv and Silver, Robert and Chung, Judith H. and et al.}, year={2022}, month={Mar} }
 @article{honigberg_truong_khan_xiao_bhatta_vy_guerrero_schuermans_selvaraj_patel_et al._2022, title={Genome-wide meta-analysis identifies novel maternal risk variants and enables polygenic prediction of preeclampsia and gestational hypertension}, url={https://doi.org/10.1101/2022.11.30.22282929}, DOI={10.1101/2022.11.30.22282929}, abstractNote={AbstractPreeclampsia and gestational hypertension are common pregnancy complications associated with adverse maternal and offspring outcomes. Current tools for prediction, prevention, and treatment are limited. We tested the association of maternal DNA sequence variants with preeclampsia in 20,064 cases and 703,117 controls and with gestational hypertension in 11,027 cases and 412,788 controls across discovery and follow-up cohorts using multi-ancestry meta-analysis. Altogether, we identified 18 independent loci associated with preeclampsia/eclampsia and/or gestational hypertension, 12 of which are novel (e.g.,MTHFR-CLCN6,WNT3A,NPR3,PGR, andRGL3), including two loci (PLCE1,FURIN) identified in multi-trait analysis. Identified loci highlight the role of natriuretic peptide signaling, angiogenesis, renal glomerular function, trophoblast development, and immune dysregulation. We derived genome-wide polygenic risk scores that predicted preeclampsia/eclampsia and gestational hypertension in external datasets, independent of first trimester risk markers. Collectively, these findings provide mechanistic insights into the hypertensive disorders of pregnancy and advance pregnancy risk stratification.}, author={Honigberg, Michael C. and Truong, Buu and Khan, Raiyan R. and Xiao, Brenda and Bhatta, Laxmi and Vy, Thi Ha and Guerrero, Rafael F. and Schuermans, Art and Selvaraj, Margaret Sunitha and Patel, Aniruddh P. and et al.}, year={2022}, month={Dec} }
 @article{pagel_chu_ramola_guerrero_chung_parry_reddy_silver_steller_yee_et al._2022, title={The influence of genetic predisposition and physical activity on risk of Gestational Diabetes Mellitus in the nuMoM2b cohort}, url={https://doi.org/10.1101/2022.03.08.22271868}, DOI={10.1101/2022.03.08.22271868}, abstractNote={AbstractImportancePolygenic risk scores (PRS) for Type II Diabetes Mellitus (T2DM) can improve risk prediction for Gestational Diabetes Mellitus (GDM), yet the strength of the relationship between genetic and lifestyle risk factors has not been quantified.ObjectiveTo assess the effects of PRS and physical activity on existing GDM risk models and identify patient subgroups who may receive the most benefits from receiving a PRS or activity intervention.Design, Settings, and ParticipantsThe Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be (nuMoM2b) study was established to study individuals without previous pregnancy lasting 20 weeks or more (nulliparous) and to elucidate factors associated with adverse pregnancy outcomes. A sub-cohort of 3,533 participants with European ancestry were used for risk assessment and performance evaluation.ExposuresSelf-reported total physical activity in early pregnancy was quantified as metabolic equivalent of tasks (METs) in hours/week. Polygenic risk scores were calculated for T2DM using contributions of 85 single nucleotide variants, weighted by their association in the DIAbetes Genetics Replication And Meta-analysis (DIAGRAM) Consortium data.Main Outcomes and MeasuresPrediction of the development of GDM from clinical, genetic, and environmental variables collected in early pregnancy. The risk model is assessed using measures of model discrimination and calibration. Odds ratio and positive likelihood ratio were used for evaluating the effect of PRS and physical activity on GDM risk.ResultsIn high-risk population subgroups (body mass index ≥ 25 or age ≥ 35), individuals with PRS in the top 25th percentile or METs below 450 have significantly increased odds of GDM diagnosis. Participants with both high PRS and low METs have three times higher odds of GDM diagnosis than the population. Conversely, participants with high PRS and METs ≥ 450 do not exhibit increased odds of GDM diagnosis, and those with low METs and low PRS have reduced odds of GDM. The relationship between PRS and METs was found to be nonadditive.Conclusions and RelevanceIn high-risk patient subgroups the addition of PRS resulted in increased risk of GDM diagnosis, suggesting the benefits of targeted PRS ascertainment to encourage early intervention. Increased physical activity is associated with decreased risk of GDM, particularly among individuals genetically predisposed to T2DM.Key PointsQuestionDo genetic predisposition to diabetes and physical activity in early pregnancy cooperatively impact risk of Gestational Diabetes Mellitus (GDM) among nulliparas?FindingsRisk of GDM diagnosis increases significantly for nulliparas with high polygenic risk score (PRS) and with low physical activity. The odds ratio of developing GDM with high PRS was estimated to be 2.2, 1.6 with low physical activity, and 3.5 in combination.MeaningPhysical activity in early pregnancy is associated with reduced risk of GDM and reversal of excess risk in genetically predisposed individuals. The interaction between PRS and physical activity may identify subjects for targeted interventions.}, author={Pagel, Kymberleigh A. and Chu, Hoyin and Ramola, Rashika and Guerrero, Rafael F. and Chung, Judith H. and Parry, Samuel and Reddy, Uma M. and Silver, Robert M. and Steller, Jonathan G. and Yee, Lynn M. and et al.}, year={2022}, month={Mar} }
 @article{wu_haak_anderson_hahn_moyle_guerrero_2021, title={Inferring the Genetic Basis of Sex Determination from the Genome of a Dioecious Nightshade}, volume={38}, ISSN={["1537-1719"]}, url={https://doi.org/10.1093/molbev/msab089}, DOI={10.1093/molbev/msab089}, abstractNote={Abstract
               Dissecting the genetic mechanisms underlying dioecy (i.e., separate female and male individuals) is critical for understanding the evolution of this pervasive reproductive strategy. Nonetheless, the genetic basis of sex determination remains unclear in many cases, especially in systems where dioecy has arisen recently. Within the economically important plant genus Solanum (∼2,000 species), dioecy is thought to have evolved independently at least 4 times across roughly 20 species. Here, we generate the first genome sequence of a dioecious Solanum and use it to ascertain the genetic basis of sex determination in this species. We de novo assembled and annotated the genome of Solanum appendiculatum (assembly size: ∼750 Mb scaffold N50: 0.92 Mb; ∼35,000 genes), identified sex-specific sequences and their locations in the genome, and inferred that males in this species are the heterogametic sex. We also analyzed gene expression patterns in floral tissues of males and females, finding approximately 100 genes that are differentially expressed between the sexes. These analyses, together with observed patterns of gene-family evolution specific to S. appendiculatum, consistently implicate a suite of genes from the regulatory network controlling pectin degradation and modification in the expression of sex. Furthermore, the genome of a species with a relatively young sex-determination system provides the foundational resources for future studies on the independent evolution of dioecy in this clade.}, number={7}, journal={MOLECULAR BIOLOGY AND EVOLUTION}, publisher={Oxford University Press (OUP)}, author={Wu, Meng and Haak, David C. and Anderson, Gregory J. and Hahn, Matthew W. and Moyle, Leonie C. and Guerrero, Rafael F.}, editor={Purugganan, MichaelEditor}, year={2021}, month={Jul}, pages={2946–2957} }
 @article{stamboulian_guerrero_hahn_radivojac_2020, title={The ortholog conjecture revisited: the value of orthologs and paralogs in function prediction}, volume={36}, ISSN={["1460-2059"]}, DOI={10.1093/bioinformatics/btaa468}, abstractNote={Abstract
               
                  Motivation
                  The computational prediction of gene function is a key step in making full use of newly sequenced genomes. Function is generally predicted by transferring annotations from homologous genes or proteins for which experimental evidence exists. The ‘ortholog conjecture’ proposes that orthologous genes should be preferred when making such predictions, as they evolve functions more slowly than paralogous genes. Previous research has provided little support for the ortholog conjecture, though the incomplete nature of the data cast doubt on the conclusions.
               
               
                  Results
                  We use experimental annotations from over 40 000 proteins, drawn from over 80 000 publications, to revisit the ortholog conjecture in two pairs of species: (i) Homo sapiens and Mus musculus and (ii) Saccharomyces cerevisiae and Schizosaccharomyces pombe. By making a distinction between questions about the evolution of function versus questions about the prediction of function, we find strong evidence against the ortholog conjecture in the context of function prediction, though questions about the evolution of function remain difficult to address. In both pairs of species, we quantify the amount of information that would be ignored if paralogs are discarded, as well as the resulting loss in prediction accuracy. Taken as a whole, our results support the view that the types of homologs used for function transfer are largely irrelevant to the task of function prediction. Maximizing the amount of data used for this task, regardless of whether it comes from orthologs or paralogs, is most likely to lead to higher prediction accuracy.
               
               
                  Availability and implementation
                  https://github.com/predragradivojac/oc.
               
               
                  Supplementary information
                  Supplementary data are available at Bioinformatics online.
               }, journal={BIOINFORMATICS}, author={Stamboulian, Moses and Guerrero, Rafael F. and Hahn, Matthew W. and Radivojac, Predrag}, year={2020}, month={Jul}, pages={219–226} }
 @article{kasak_hunter_udani_bakolitsa_hu_adhikari_babbi_casadio_gough_guerrero_et al._2019, title={CAGI SickKids challenges: Assessment of phenotype and variant predictions derived from clinical and genomic data of children with undiagnosed diseases}, volume={40}, url={https://doi.org/10.1002/humu.23874}, DOI={10.1002/humu.23874}, abstractNote={Whole‐genome sequencing (WGS) holds great potential as a diagnostic test. However, the majority of patients currently undergoing WGS lack a molecular diagnosis, largely due to the vast number of undiscovered disease genes and our inability to assess the pathogenicity of most genomic variants. The CAGI SickKids challenges attempted to address this knowledge gap by assessing state‐of‐the‐art methods for clinical phenotype prediction from genomes. CAGI4 and CAGI5 participants were provided with WGS data and clinical descriptions of 25 and 24 undiagnosed patients from the SickKids Genome Clinic Project, respectively. Predictors were asked to identify primary and secondary causal variants. In addition, for CAGI5, groups had to match each genome to one of three disorder categories (neurologic, ophthalmologic, and connective), and separately to each patient. The performance of matching genomes to categories was no better than random but two groups performed significantly better than chance in matching genomes to patients. Two of the ten variants proposed by two groups in CAGI4 were deemed to be diagnostic, and several proposed pathogenic variants in CAGI5 are good candidates for phenotype expansion. We discuss implications for improving in silico assessment of genomic variants and identifying new disease genes.}, number={9}, journal={Human Mutation}, publisher={Wiley}, author={Kasak, Laura and Hunter, Jesse M. and Udani, Rupa and Bakolitsa, Constantina and Hu, Zhiqiang and Adhikari, Aashish N. and Babbi, Giulia and Casadio, Rita and Gough, Julian and Guerrero, Rafael F. and et al.}, year={2019}, month={Sep}, pages={1373–1391} }
 @article{guerrero_scarpino_rodrigues_hartl_ogbunugafor_2019, title={Proteostasis Environment Shapes Higher-Order Epistasis Operating on Antibiotic Resistance}, volume={212}, url={https://doi.org/10.1534/genetics.119.302138}, DOI={10.1534/genetics.119.302138}, abstractNote={Abstract
               Epistasis is widely regarded as one of the most important phenomena in genetics. It proposes that the combined effects of mutations cannot be easily predicted from their individual effects. In the present study...
               Recent studies have affirmed that higher-order epistasis is ubiquitous and can have large effects on complex traits. Yet, we lack frameworks for understanding how epistatic interactions are influenced by central features of cell physiology. In this study, we assess how protein quality control machinery—a critical component of cell physiology—affects epistasis for different traits related to bacterial resistance to antibiotics. Specifically, we disentangle the interactions between different protein quality control genetic backgrounds and two sets of mutations: (i) SNPs associated with resistance to antibiotics in an essential bacterial enzyme (dihydrofolate reductase, or DHFR) and (ii) differing DHFR bacterial species-specific amino acid background sequences (Escherichia coli, Listeria grayi, and Chlamydia muridarum). In doing so, we improve on generic observations that epistasis is widespread by discussing how patterns of epistasis can be partly explained by specific interactions between mutations in an essential enzyme and genes associated with the proteostasis environment. These findings speak to the role of environmental and genotypic context in modulating higher-order epistasis, with direct implications for evolutionary theory, genetic modification technology, and efforts to manage antimicrobial resistance.}, number={2}, journal={Genetics}, publisher={Genetics Society of America}, author={Guerrero, Rafael F. and Scarpino, Samuel V. and Rodrigues, João V. and Hartl, Daniel L. and Ogbunugafor, C. Brandon}, year={2019}, month={Jun}, pages={565–575} }
 @article{guerrero_hahn_2018, title={Quantifying the risk of hemiplasy in phylogenetic inference}, volume={115}, url={https://doi.org/10.1073/pnas.1811268115}, DOI={10.1073/pnas.1811268115}, abstractNote={Significance
          Convergent evolution provides key evidence for the action of natural selection. The process of convergence is often inferred because the same trait appears in multiple species that are not closely related. However, different parts of the genome can reveal different relationships among species, with some genes or regions uniting lineages that appear unrelated in the species tree. If changes in traits occur in these discordant regions, a false pattern of convergence can be produced (known as “hemiplasy”). Here, we provide a way to quantify the probability that hemiplasy occurs and contrast it with the probability of convergence. We find that hemiplasy is likely to explain many apparent cases of convergent evolution, even when the fraction of discordant regions is low.}, number={50}, journal={Proceedings of the National Academy of Sciences}, publisher={Proceedings of the National Academy of Sciences}, author={Guerrero, Rafael F. and Hahn, Matthew W.}, year={2018}, month={Dec}, pages={12787–12792} }
 @article{berrio_guerrero_aglyamova_okhovat_matz_phelps_2018, title={Complex selection on a regulator of social cognition: Evidence of balancing selection, regulatory interactions and population differentiation in the prairie vole Avpr1a locus}, url={https://doi.org/10.1111/mec.14455}, DOI={10.1111/mec.14455}, abstractNote={AbstractAdaptive variation in social behaviour depends upon standing genetic variation, but we know little about how evolutionary forces shape genetic diversity relevant to brain and behaviour. In prairie voles (Microtus ochrogaster), variants at the Avpr1a locus predict expression of the vasopressin 1a receptor in the retrosplenial cortex (RSC), a brain region that mediates spatial and contextual memory; cortical V1aR abundance in turn predicts diversity in space use and sexual fidelity in the field. To examine the potential contributions of adaptive and neutral forces to variation at the Avpr1a locus, we explore sequence diversity at the Avpr1a locus and throughout the genome in two populations of wild prairie voles. First, we refine results demonstrating balancing selection at the locus by comparing the frequency spectrum of variants at the locus to a random sample of the genome. Next, we find that the four single nucleotide polymorphisms that predict high V1aR expression in the RSC are in stronger linkage disequilibrium than expected by chance despite high recombination among intervening variants, suggesting that epistatic selection maintains their association. Analysis of population structure and a haplotype network for two populations revealed that this excessive LD was unlikely to be due to admixture alone. Furthermore, the two populations differed considerably in the region shown to be a regulator of V1aR expression despite the extremely low levels of genomewide genetic differentiation. Together, our data suggest that complex selection on Avpr1a locus favours specific combinations of regulatory polymorphisms, maintains the resulting alleles at population‐specific frequencies, and may contribute to unique patterns of spatial cognition and sexual fidelity among populations.}, journal={Molecular Ecology}, author={Berrio, Alejandro and Guerrero, Rafael F. and Aglyamova, Galina V. and Okhovat, Mariam and Matz, Mikhail V. and Phelps, Steven M.}, year={2018}, month={Jan} }
 @article{guerrero_muir_josway_moyle_2017, title={Pervasive antagonistic interactions among hybrid incompatibility loci}, volume={13}, DOI={10.1371/journal.pgen.1006817}, abstractNote={Species barriers, expressed as hybrid inviability and sterility, are often due to epistatic interactions between divergent loci from two lineages. Theoretical models indicate that the strength, direction, and complexity of these genetic interactions can strongly affect the expression of interspecific reproductive isolation and the rates at which new species evolve. Nonetheless, empirical analyses have not quantified the frequency with which loci are involved in interactions affecting hybrid fitness, and whether these loci predominantly interact synergistically or antagonistically, or preferentially involve loci that have strong individual effects on hybrid fitness. We systematically examined the prevalence of interactions between pairs of short chromosomal regions from one species (Solanum habrochaites) co-introgressed into a heterospecific genetic background (Solanum lycopersicum), using lines containing pairwise combinations of 15 chromosomal segments from S. habrochaites in the background of S. lycopersicum (i.e., 95 double introgression lines). We compared the strength of hybrid incompatibility (either pollen sterility or seed sterility) expressed in each double introgression line to the expected additive effect of its two component single introgressions. We found that epistasis was common among co-introgressed regions. Interactions for hybrid dysfunction were substantially more prevalent in pollen fertility compared to seed fertility phenotypes, and were overwhelmingly antagonistic (i.e., double hybrids were less unfit than expected from additive single introgression effects). This pervasive antagonism is expected to attenuate the rate at which hybrid infertility accumulates among lineages over time (i.e., giving diminishing returns as more reproductive isolation loci accumulate), as well as decouple patterns of accumulation of sterility loci and hybrid incompatibility phenotypes. This decoupling effect might explain observed differences between pollen and seed fertility in their fit to theoretical predictions of the accumulation of isolation loci, including the ‘snowball’ effect.}, number={6}, journal={PLOS Genetics}, publisher={Public Library of Science (PLoS)}, author={Guerrero, Rafael F. and Muir, Christopher D. and Josway, Sarah and Moyle, Leonie C.}, editor={Köhler, ClaudiaEditor}, year={2017}, month={Jun}, pages={e1006817} }
 @article{guerrero_hahn_2017, title={Speciation as a Sieve for Ancestral Polymorphism}, volume={8}, url={https://doi.org/10.1111/mec.14290}, DOI={10.1111/mec.14290}, abstractNote={AbstractBecause they are considered rare, balanced polymorphisms are often discounted as crucial constituents of genome‐wide variation in sequence diversity. Despite its perceived rarity, however, long‐term balancing selection can elevate genetic diversity and significantly affect observed divergence between species. Here, we discuss how ancestral balanced polymorphisms can be “sieved” by the speciation process, which sorts them unequally across descendant lineages. After speciation, ancestral balancing selection is revealed by genomic regions of high divergence between species. This signature, which resembles that of other evolutionary processes, can potentially confound genomic studies of population divergence and inferences of “islands of speciation.”}, journal={Molecular Ecology}, publisher={Wiley-Blackwell}, author={Guerrero, Rafael F. and Hahn, Matthew W.}, year={2017}, month={Aug} }
 @article{marais_guerrero_lasky_scarpino_2017, title={Topological features of a gene co-expression network predict patterns of natural diversity in environmental response}, volume={284}, url={https://doi.org/10.1098/rspb.2017.0914}, DOI={10.1098/rspb.2017.0914}, abstractNote={
            Molecular interactions affect the evolution of complex traits. For instance, adaptation may be constrained by pleiotropic or epistatic effects, both of which can be reflected in the structure of molecular interaction networks. To date, empirical studies investigating the role of molecular interactions in phenotypic evolution have been idiosyncratic, offering no clear patterns. Here, we investigated the network topology of genes putatively involved in local adaptation to two abiotic stressors—drought and cold—in
            Arabidopsis thaliana
            . Our findings suggest that the gene-interaction topologies for both cold and drought stress response are non-random, with genes that show genetic variation in drought expression response (eGxE) being significantly more peripheral and cold response genes being significantly more central than genes which do not show GxE. We suggest that the observed topologies reflect different constraints on the genetic pathways involved in environmental response. The approach presented here may inform predictive models linking genetic variation in molecular signalling networks with phenotypic variation, specifically traits involved in environmental response.
          }, number={1856}, journal={Proceedings of the Royal Society B: Biological Sciences}, publisher={The Royal Society}, author={Marais, David L. Des and Guerrero, Rafael F. and Lasky, Jesse R. and Scarpino, Samuel V.}, year={2017}, month={Jun}, pages={20170914} }
 @article{transcriptomic analysis links gene expression to unilateral pollen-pistil reproductive barriers._2017, volume={4}, url={http://europepmc.org/abstract/med/28438120}, DOI={10.1186/s12870-017-1032-4}, abstractNote={Unilateral incompatibility (UI) is an asymmetric reproductive barrier that unidirectionally prevents gene flow between species and/or populations. UI is characterized by a compatible interaction between partners in one direction, but in the reciprocal cross fertilization fails, generally due to pollen tube rejection by the pistil. Although UI has long been observed in crosses between different species, the underlying molecular mechanisms are only beginning to be characterized. The wild tomato relative Solanum habrochaites provides a unique study system to investigate the molecular basis of this reproductive barrier, as populations within the species exhibit both interspecific and interpopulation UI. Here we utilized a transcriptomic approach to identify genes in both pollen and pistil tissues that may be key players in UI. We confirmed UI at the pollen-pistil level between a self-incompatible population and a self-compatible population of S. habrochaites. A comparison of gene expression between pollinated styles exhibiting the incompatibility response and unpollinated controls revealed only a small number of differentially expressed transcripts. Many more differences in transcript profiles were identified between UI-competent versus UI-compromised reproductive tissues. A number of intriguing candidate genes were highly differentially expressed, including a putative pollen arabinogalactan protein, a stylar Kunitz family protease inhibitor, and a stylar peptide hormone Rapid ALkalinization Factor. Our data also provide transcriptomic evidence that fundamental processes including reactive oxygen species (ROS) signaling are likely key in UI pollen-pistil interactions between both populations and species. Gene expression analysis of reproductive tissues allowed us to better understand the molecular basis of interpopulation incompatibility at the level of pollen-pistil interactions. Our transcriptomic analysis highlighted specific genes, including those in ROS signaling pathways that warrant further study in investigations of UI. To our knowledge, this is the first report to identify candidate genes involved in unilateral barriers between populations within a species.}, journal={BMC plant biology}, year={2017}, month={Apr} }
 @article{guerrero_posto_moyle_hahn_2016, title={Genome-wide patterns of regulatory divergence revealed by introgression lines}, volume={70}, DOI={10.1111/evo.12875}, abstractNote={Understanding the genetic basis for changes in transcriptional regulation is an important aspect of understanding phenotypic evolution. Using interspecific introgression lines, we infer the mechanisms of divergence in genome-wide patterns of gene expression between the nightshades Solanum pennellii and S. lycopersicum (domesticated tomato). We find that cis- and frans-regulatory changes have had qualitatively similar contributions to divergence in this clade, unlike results from other systems. Additionally, expression data from four tissues (shoot apex, ripe fruit, pollen, and seed) suggest that introgressed regions in these hybrid lines tend to be down-regulated, while background (non-introgressed) genes tend to be up-regulated. Finally, we find no evidence for an association between the magnitude of differential expression in NILs and previously determined sterility phenotypes. Our results contradict previous predictions of the predominant role of cis- over frans-regulatory divergence between species, and do not support a major role for gross genome-wide misregulation in reproductive isolation between these species.}, number={3}, journal={Evolution}, publisher={Wiley-Blackwell}, author={Guerrero, Rafael F. and Posto, Amanda L. and Moyle, Leonie C. and Hahn, Matthew W.}, year={2016}, month={Feb}, pages={696–706} }
 @article{pease_guerrero_sherman_hahn_moyle_2016, title={Molecular mechanisms of postmating prezygotic reproductive isolation uncovered by transcriptome analysis}, volume={25}, url={https://doi.org/10.1111/mec.13679}, DOI={10.1111/mec.13679}, abstractNote={AbstractLittle is known about the physiological responses and genetic mutations associated with reproductive isolation between species, especially for postmating prezygotic isolating barriers. Here, we examine changes in gene expression that accompany the expression of ‘unilateral incompatibility’ (UI)—a postmating prezygotic barrier in which fertilization is prevented by gamete rejection in the reproductive tract [in this case of pollen tubes (male gametophytes)] in one direction of a species cross, but is successful in the reciprocal crossing direction. We use whole‐transcriptome sequencing of multiple developmental stages of male and female tissues in two Solanum species that exhibit UI to: (i) identify transcript differences between UI‐competent and UI noncompetent tissues; (ii) characterize transcriptional changes specifically associated with the phenotypic expression of UI; and (iii) using these comparisons, evaluate the behaviour of a priori candidate loci for UI and identify new candidates for future manipulative work. In addition to describing transcriptome‐wide changes in gene expression that accompany this isolating barrier, we identify at least five strong candidates for involvement in postmating prezygotic incompatibility between species. These include three novel candidates and two candidates that are strongly supported by prior developmental, functional, and quantitative trait locus mapping studies. These latter genes are known molecular players in the intraspecific expression of mate choice via genetic self‐incompatibility, and our study supports prior evidence that these inter‐ and intraspecific postmating prezygotic reproductive behaviours share specific genetic and molecular mechanisms.}, number={11}, journal={Molecular Ecology}, publisher={Wiley}, author={Pease, James B. and Guerrero, Rafael F. and Sherman, Natasha A. and Hahn, Matthew W. and Moyle, Leonie C.}, year={2016}, month={Jun}, pages={2592–2608} }
 @article{guerrero_muir_josway_moyle_2016, title={Pervasive Antagonistic Interactions Among Hybrid Incompatibility Loci}, url={https://doi.org/10.1101/090886}, DOI={10.1101/090886}, abstractNote={ABSTRACT Species barriers, expressed as hybrid inviability and sterility, are often due to epistatic interactions between divergent loci from two lineages. Theoretical models indicate that the strength, direction, and complexity of these genetic interactions can strongly affect the expression of interspecific reproductive isolation and the rates at which new species evolve. Nonetheless, empirical analyses have not quantified the frequency with which loci are involved in interactions affecting hybrid fitness, and whether these loci predominantly interact synergistically or antagonistically, or preferentially involve loci that have strong individual effects on hybrid fitness. We systematically examined the prevalence of interactions between pairs of short chromosomal regions from one species ( Solanum habrochaites ) co-introgressed into a heterospecific genetic background ( Solanum lycopersicum ). We used lines containing pairwise combinations of 15 chromosomal segments from S. habrochaites crossed into the background of S. lycopersicum ( i.e ., 95 double introgression lines). We compared the strength of hybrid incompatibility (either pollen sterility or seed sterility) expressed in each double introgression line to the expected additive effect of its two component single introgressions. We found that: epistasis was common among co-introgressed regions; epistastic effects for hybrid dysfunction were overwhelmingly antagonistic (i.e., double hybrids were less unfit than expected from additive single introgression effects); and, epistasis was substantially more prevalent in pollen fertility compared to seed fertility phenotypes. Together, these results indicate that higher-order interactions frequently contribute to postzygotic sterility barriers in these species. This pervasive epistasis leads to the decoupling of the patterns of accumulation of isolation loci and isolation phenotypes, and is expected to attenuate the rate of accumulation of hybrid infertility among lineages over time ( i.e ., giving diminishing returns as more reproductive isolation loci accumulate). This decoupling effect might also explain observed differences between pollen and seed fertility in their fit to theoretical predictions of the accumulation of isolation loci, including the ‘snowball’ effect. AUTHOR SUMMARY A characteristic feature of new species is their inability to produce fertile or viable hybrids with other lineages. This post-zygotic reproductive isolation is caused by dysfunctional interactions between genes that have newly evolved changes in the diverging lineages. Whether these interactions occur between pairs of divergent alleles, or involve more complex networks of genes, can have strong effects on how rapidly reproductive isolation—and therefore new species—evolve. The complexity of these interactions, however, is poorly understood in empirical systems. We examined the fertility of hybrids that carried one or two chromosomal regions from a close relative, finding that hybrids with two of these heterospecific regions were frequently less sterile than would be expected from the joint fitness of hybrids that have the same regions singly. This ‘less-than-additive’ effect on hybrid sterility was widespread (observed in 20% of pairwise combinations), and especially pronounced for male sterility. We infer that genes contributing to male sterility form a more tightly connected network than previously thought, implying that reproductive isolation is evolving by incremental dysfunction of complex interactions rather than by independent pairwise incompatibilities. We use simulations to illustrate these expected patterns of accumulation of reproductive isolation when it involves highly interconnected gene networks.}, author={Guerrero, Rafael F. and Muir, Christopher D. and Josway, Sarah and Moyle, Leonie C.}, year={2016}, month={Dec} }
 @article{guerrero_kirkpatrick_2014, title={LOCAL ADAPTATION AND THE EVOLUTION OF CHROMOSOME FUSIONS}, volume={68}, DOI={10.1111/evo.12481}, abstractNote={We use forward and coalescent models of population genetics to study chromosome fusions that reduce the recombination between two locally adapted loci. Under a continent–island model, a fusion spreads and reaches a polymorphic equilibrium when it causes recombination between locally adapted alleles to be less than their selective advantage. In contrast, fusions in a two‐deme model always spread; whether it reaches a polymorphic equilibrium or becomes fixed depends on the relative recombination rates of fused homozygotes and heterozygotes. Neutral divergence around fusion polymorphisms is markedly increased, showing peaks at the point of fusion and at the locally adapted loci. Local adaptation could explain the evolution of many of chromosome fusions, which are some of the most common chromosome rearrangements in nature.}, number={10}, journal={Evolution}, publisher={Wiley-Blackwell}, author={Guerrero, Rafael F. and Kirkpatrick, Mark}, year={2014}, month={Aug}, pages={2747–2756} }
 @article{matrix inversions for chromosomal inversions: a method to construct summary statistics in complex coalescent models_2014, DOI={10.1016/j.tpb.2014.07.005}, abstractNote={Chromosomal inversions allow genetic divergence of locally adapted populations by reducing recombination between chromosomes with different arrangements. While patterns of genetic variation within inverted regions are increasingly documented, inferential methods are largely missing to analyze such data. Previous work has provided expectations for coalescence patterns of neutral sites linked to an inversion polymorphism in two locally adapted populations. Here, we define a method to construct summary statistics in such complex population structure models. Under a scenario of selection on the inversion breakpoints, we first construct estimators of the migration rate between the two habitats, and of the recombination rate of a nucleotide site between the two inversion backgrounds. Next, we analyze the disequilibrium between two sites within an inversion and provide an estimator of the distinct recombination rate between these two sites in homokaryotypes and heterokaryotypes. These estimators should be suitable summary statistics for simulation-based methods that can handle the complex dependences in the data.}, journal={Theoretical Population Biology}, year={2014}, month={Nov} }
 @article{signatures of sex-antagonistic selection on recombining sex chromosomes._2014, volume={6}, url={http://europepmc.org/abstract/med/24578352}, DOI={10.1534/genetics.113.156026}, abstractNote={Abstract
               Sex-antagonistic (SA) selection has major evolutionary consequences: it can drive genomic change, constrain adaptation, and maintain genetic variation for fitness. The recombining (or pseudoautosomal) regions of sex chromosomes are a promising setting in which to study SA selection because they tend to accumulate SA polymorphisms and because recombination allows us to deploy the tools of molecular evolution to locate targets of SA selection and quantify evolutionary forces. Here we use coalescent models to characterize the patterns of polymorphism expected within and divergence between recombining X and Y (or Z and W) sex chromosomes. SA selection generates peaks of divergence between X and Y that can extend substantial distances away from the targets of selection. Linkage disequilibrium between neutral sites is also inflated. We show how the pattern of divergence is altered when the SA polymorphism or the sex-determining region was recently established. We use data from the flowering plant Silene latifolia to illustrate how the strength of SA selection might be quantified using molecular data from recombining sex chromosomes.}, journal={Genetics}, year={2014}, month={Jun} }
 @article{strong reinforcing selection in a texas wildflower._2014, volume={9}, url={http://europepmc.org/abstract/med/25155503}, DOI={10.1016/j.cub.2014.07.027}, abstractNote={Reinforcement, the process of increased reproductive isolation due to selection against hybrids, is an important mechanism by which natural selection contributes to speciation [1Howard D.J. Reinforcement: origin, dynamics and fate of an evolutionary hypothesis.in: Harrison R.G. Hybrid Zones and the Evolutionary Process. Oxford University Press, New York1993: 46-69Google Scholar]. Empirical studies suggest that reinforcement has generated reproductive isolation in many taxa (reviewed in [2Hopkins R. Reinforcement in plants.New Phytol. 2013; 197: 1095-1103Crossref PubMed Scopus (122) Google Scholar, 3Ortiz-Barrientos D. Grealy A. Nosil P. The genetics and ecology of reinforcement: implications for the evolution of prezygotic isolation in sympatry and beyond.Ann. N Y Acad. Sci. 2009; 1168: 156-182Crossref PubMed Scopus (114) Google Scholar, 4Servedio M.R. Noor M.A.F. The role of reinforcement in speciation: theory and data.Annu. Rev. Ecol. Evol. Syst. 2003; 34: 339-364Crossref Scopus (694) Google Scholar]), and theoretical work shows it can act under broad selective conditions [5Kirkpatrick M. Ravigné V. Speciation by natural and sexual selection: models and experiments.Am. Nat. 2002; 159: S22-S35Crossref PubMed Google Scholar, 6Kirkpatrick M. Reinforcement and divergence under assortative mating.Proc. Biol. Sci. 2000; 267: 1649-1655Crossref PubMed Scopus (135) Google Scholar, 7Kirkpatrick M. Reinforcement during ecological speciation.Proc. Biol. Sci. 2001; 268: 1259-1263Crossref PubMed Scopus (73) Google Scholar, 8Kirkpatrick M. Servedio M.R. The reinforcement of mating preferences on an island.Genetics. 1999; 151: 865-884PubMed Google Scholar, 9Liou L.W. Price T.D. Speciation by reinforcement of premating isolation.Evolution. 1994; 48: 1451-1459Crossref Google Scholar, 10Bank C. Hermisson J. Kirkpatrick M. Can reinforcement complete speciation?.Evolution. 2012; 66: 229-239Crossref PubMed Scopus (40) Google Scholar, 11Servedio M.R. The evolution of premating isolation: local adaptation and natural and sexual selection against hybrids.Evolution. 2004; 58: 913-924Crossref PubMed Scopus (106) Google Scholar]. However, the strength of selection driving reinforcement has never been measured in nature. Here, we quantify the strength of reinforcing selection in the Texas wildflower Phlox drummondii using a strategy that weds a population genetic model with field data. Reinforcement in this system is caused by variation in two loci that affect flower color [12Hopkins R. Rausher M.D. Identification of two genes causing reinforcement in the Texas wildflower Phlox drummondii.Nature. 2011; 469: 411-414Crossref PubMed Scopus (135) Google Scholar]. We quantify sharp clines in flower color where this species comes into contact with its congener, Phlox cuspidata. We develop a spatially explicit population genetic model for these clines based on the known genetics of flower color. We fit our model to the data using likelihood, and we searched parameter space using Markov chain Monte Carlo methods. We find that selection on flower color genes generated by reinforcement is exceptionally strong. Our findings demonstrate that natural selection can play a decisive role in the evolution of reproductive isolation through the process of reinforcement.}, journal={Current biology : CB}, year={2014}, month={Sep} }
 @article{a sequential coalescent algorithm for chromosomal inversions._2013, volume={9}, url={http://europepmc.org/abstract/med/23632894}, DOI={10.1038/hdy.2013.38}, abstractNote={Chromosomal inversions are common in natural populations and are believed to be involved in many important evolutionary phenomena, including speciation, the evolution of sex chromosomes and local adaptation. While recent advances in sequencing and genotyping methods are leading to rapidly increasing amounts of genome-wide sequence data that reveal interesting patterns of genetic variation within inverted regions, efficient simulation methods to study these patterns are largely missing. In this work, we extend the sequential Markovian coalescent, an approximation to the coalescent with recombination, to include the effects of polymorphic inversions on patterns of recombination. Results show that our algorithm is fast, memory-efficient and accurate, making it feasible to simulate large inversions in large populations for the first time. The SMC algorithm enables studies of patterns of genetic variation (for example, linkage disequilibria) and tests of hypotheses (using simulation-based approaches) that were previously intractable.}, journal={Heredity}, year={2013}, month={Sep} }
 @article{cryptic recombination in the ever-young sex chromosomes of hylid frogs._2012, volume={10}, url={http://europepmc.org/abstract/med/22901240}, DOI={10.1111/j.1420-9101.2012.02591.x}, abstractNote={AbstractSex chromosomes are expected to evolve suppressed recombination, which leads to degeneration of the Y and heteromorphism between the X and Y. Some sex chromosomes remain homomorphic, however, and the factors that prevent degeneration of the Y in these cases are not well understood. The homomorphic sex chromosomes of the European tree frogs (Hyla spp.) present an interesting paradox. Recombination in males has never been observed in crossing experiments, but molecular data are suggestive of occasional recombination between the X and Y. The hypothesis that these sex chromosomes recombine has not been tested statistically, however, nor has the X‐Y recombination rate been estimated. Here, we use approximate Bayesian computation coupled with coalescent simulations of sex chromosomes to quantify X‐Y recombination rate from existent data. We find that microsatellite data from H. arborea, H. intermedia and H. molleri support a recombination rate between X and Y that is significantly different from zero. We estimate that rate to be approximately 105 times smaller than that between X chromosomes. Our findings support the notion that very low recombination rate may be sufficient to maintain homomorphism in sex chromosomes.}, journal={Journal of evolutionary biology}, year={2012}, month={Oct} }
 @article{ayala_guerrero_kirkpatrick_2012, title={REPRODUCTIVE ISOLATION AND LOCAL ADAPTATION QUANTIFIED FOR A CHROMOSOME INVERSION IN A MALARIA MOSQUITO}, volume={67}, DOI={10.1111/j.1558-5646.2012.01836.x}, abstractNote={Chromosome inversions have long been thought to be involved in speciation and local adaptation. We have little quantitative information, however, about the effects that inversion polymorphisms have on reproductive isolation and viability. Here we provide the first estimates from any organism for the total amount of reproductive isolation associated with an inversion segregating in natural populations. We sampled chromosomes from 751 mosquitoes of the malaria vector Anopheles funestus along a 1421 km transect in Cameroon that traverses savannah, highland, and rainforest ecological zones. We then developed a series of population genetic models that account for selection, migration, and assortative mating, and fit the models to the data using likelihood. Results from the best‐fit models suggest there is strong local adaptation, with relative viabilities of homozygotes ranging from 25% to 130% compared to heterozygotes. Viabilities vary qualitatively between regions: the inversion is underdominant in the savannah, whereas in the highlands it is overdominant. The inversion is also implicated in strong assortative mating. In the savannah, the two homozygote forms show 92% reproductive isolation, suggesting that this one inversion can generate most of the genetic barriers needed for speciation.}, number={4}, journal={Evolution}, publisher={Wiley-Blackwell}, author={Ayala, Diego and Guerrero, Rafael F. and Kirkpatrick, Mark}, year={2012}, month={Nov}, pages={946–958} }
 @article{about par: the distinct evolutionary dynamics of the pseudoautosomal region._2011, volume={9}, url={http://europepmc.org/abstract/med/21962971}, DOI={10.1016/j.tig.2011.05.001}, abstractNote={Sex chromosomes differ from other chromosomes in the striking divergence they often show in size, structure, and gene content. Not only do they possess genes controlling sex determination that are restricted to either the X or Y (or Z or W) chromosomes, but in many taxa they also include recombining regions. In these ‘pseudoautosomal regions' (PARs), sequence homology is maintained by meiotic pairing and exchange in the heterogametic sex. PARs are unique genomic regions, exhibiting some features of autosomes, but they are also influenced by their partial sex linkage. Here we review the distribution and structure of PARs among animals and plants, the theoretical predictions concerning their evolutionary dynamics, the reasons for their persistence, and the diversity and content of genes that reside within them. It is now clear that the evolution of the PAR differs in important ways from that of genes in either the non-recombining regions of sex chromosomes or the autosomes.}, journal={Trends in genetics : TIG}, year={2011}, month={Sep} }
 @article{coalescent patterns for chromosomal inversions in divergent populations._2012, volume={2}, url={http://europepmc.org/abstract/med/22201172}, DOI={10.1098/rstb.2011.0246}, abstractNote={Chromosomal inversions allow genetic divergence of locally adapted populations by reducing recombination between chromosomes with different arrangements. Divergence between populations (or hybridization between species) is expected to leave signatures in the neutral genetic diversity of the inverted region. Quantitative expectations for these patterns, however, have not been obtained. Here, we develop coalescent models of neutral sites linked to an inversion polymorphism in two locally adapted populations. We consider two scenarios of local adaptation: selection on the inversion breakpoints and selection on alleles inside the inversion. We find that ancient inversion polymorphisms cause genetic diversity to depart dramatically from neutral expectations. Other situations, however, lead to patterns that may be difficult to detect; important determinants are the age of the inversion and the rate of gene flux between arrangements. We also study inversions under genetic drift, finding that they produce patterns similar to locally adapted inversions of intermediate age. Our results are consistent with empirical observations, and provide the foundation for quantitative analyses of the roles that inversions have played in speciation.}, journal={Philosophical transactions of the Royal Society of London. Series B, Biological sciences}, year={2012}, month={Feb} }
 @article{patterns of neutral genetic variation on recombining sex chromosomes._2010, volume={4}, url={http://europepmc.org/abstract/med/20124026}, DOI={10.1534/genetics.109.113555}, abstractNote={Abstract
               Many animals and plants have sex chromosomes that recombine over much of their length. Here we develop coalescent models for neutral sites on these chromosomes. The emphasis is on expected coalescence times (proportional to the expected amount of neutral genetic polymorphism), but we also derive some results for linkage disequilibria between neutral sites. We analyze the standard neutral model, a model with polymorphic Y chromosomes under balancing selection, and the invasion of a neo-Y chromosome. The results may be useful for testing hypotheses regarding how new sex chromosomes originate and how selection acts upon them.}, journal={Genetics}, year={2010}, month={Apr} }