PUBLICATIONS

@article{pmid42561915,

title = {A complete genome for the common marmoset},

author = {Prajna Hebbar and Tamara Potapova and Hailey Loucks and Karina Ray and Murillo F Rodrigues and Fedor Ryabov and Joanna Malukiewicz and DongAhn Yoo and Leonardo Gomes de Lima and Annat Haber and Sonal Kumar and Swati Banerjee and Matthew Borchers and Gage H Garcia and Joshua Gardner and Stephanie Hachem and Harrison D Heath and Seung Kwon Ha and Mira Mastoras and Brandy McNulty and Julian Menendez and Katherine M Munson and Karol Pal and JungEun Park and Simon Plösch and Christian Roos and William E Seligmann and Valery Shepelev and Catrina Spruce and Ivo Violich and Lutz Walter and Kateryna D Makova and Amantha Thathiah and Stacey J Sukoff Rizzo and Afonso C Silva and Gregory W Carter and Karen H Miga and Evan E Eichler and Donald F Conrad and Jennifer L Gerton and Ivan A Alexandrov and Benedict Paten},

doi = {10.1016/j.cell.2026.07.017},

issn = {1097-4172},

year  = {2026},

date = {2026-08-01},

urldate = {2026-08-01},

journal = {Cell},

volume = {189},

number = {16},

pages = {4891--4908.e12},

abstract = {The common marmoset is a New World monkey widely used to study primate evolution and human disease. We present a telomere-to-telomere (T2T) reference assembly for the species, plus three near-T2T haplotypes. These resolve previously inaccessible regions, including the centromeres, sex chromosomes, subterminal satellites, acrocentric chromosomes, and the major histocompatibility complex (MHC). We find marmoset centromeres carry dimeric alpha satellites with chromosomal specificity, flanked by inactive layers interpreted as ancestral centromere remnants. We assemble gene-poor, satellite-rich short arms of the acrocentrics and find that most can harbor rDNA and all share pseudo-homolog regions (PHRs). PHR-sharing chromosomes also share closely related centromeric satellites, consistent with a model of ongoing rDNA-facilitated recombinational exchange between heterologous chromosomes. We further identify over 500 marmoset-lineage-specific transcribed genes with previously unknown transcript models or expansions. These resources, along with a preliminary pangenome, improve the utility of the marmoset as a model organism and address gaps in primate genome evolution.},

keywords = {NHP Genetics},

pubstate = {published},

tppubtype = {article}

}

@article{pmid41664592,

title = {Mapping whole-organism genetic comorbidities across model Species using unified ontologies},

author = {Caitlin Peaslee and Madison Held and Eloise Fadial and Donald F Conrad},

doi = {10.1093/genetics/iyag038},

issn = {1943-2631},

year  = {2026},

date = {2026-04-01},

urldate = {2026-04-01},

journal = {Genetics},

volume = {232},

number = {4},

abstract = {Understanding how genetic variation contributes to organism-wide phenotypes is critical for identifying mechanisms of disease. Here, we present a computational approach to analyze whole-organism comorbidities associated with genes underlying non-obstructive azoospermia (NOA), the most severe form of male infertility. We curated 204 mouse genes with experimentally validated spermatogenic failure and mapped their orthologs and phenotype annotations across humans, M. musculus, D. rerio, D. melanogaster, and C. elegans using a unified cross-species phenotype structure. This framework integrates a newly developed reproductive phenotype ontology with standardized whole-body phenotype categories to enable direct cross-species comparisons, using thousands of genotype-phenotype associations stored in model organism databases. Our analysis shows that most NOA genes have conserved orthologs across models, and that perturbation of these genes is frequently associated with non-reproductive phenotypes. In particular, integumentary defects and neoplastic phenotypes recur across species, supporting a shared genetic basis for epidemiological links between male infertility and systemic disease. Gene-level comorbidity patterns are partially predictable from single-cell RNA-seq, whole-body gene expression, and Gene Ontology annotations, suggesting that fundamental biological constraints shape the systemic consequences of reproductive gene dysfunction. Clustering genes by comorbidity profiles further distinguished genes with isolated reproductive effects from those with broad organismal consequences. This work demonstrates the power of ontology-based cross-species analysis for identifying pleiotropic effects of Mendelian disease mutations, and provides a resource, CoMorbidity DataBase Mapper (CoMo DBM), for joint analysis of genotype-phenotype associations in model organism databases.},

keywords = {GEMINI, Genomic Variation, Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40815353,

title = {Identification of missense DMC1 variants in males with non-obstructive azoospermia},

author = {Noor Ullah and Christopher Pombar and Rachel Hvasta-Gloria and Andrea J Berman and Michelle Malizio and Muhammad Jaseem Khan and Rubina Nazli and Sadia Fatima and Antoni Riera-Escamilla and Helen Castillo-Madeen and Agnieszka Malcher and Marta Olszewska and Miguel J Xavier and Kristiina Lillepea and Avirup Dutta and Carlos A Castro and Anu Valkna and Rain Inno and Kyle E Orwig and Donald F Conrad and Maciej Kurpisz and Joris A Veltman and Maris Laan and Alexander N Yatsenko},

doi = {10.1007/s10815-025-03591-6},

issn = {1573-7330},

year  = {2025},

date = {2025-11-01},

urldate = {2025-11-01},

journal = {J Assist Reprod Genet},

volume = {42},

number = {11},

pages = {3723--3735},

abstract = {PURPOSE: Human male infertility is a significant reproductive condition, with non-obstructive azoospermia (NOA) being the most severe form, resulting from impaired spermatogenesis. Many genetic variants have been identified as negatively impacting sperm development and maturation at multiple stages, leading to spermatogenic failure (SPGF). Here, we aim to study such variants, particularly those in the critical, highly conserved, meiosis-specific DMC1 (DNA meiotic recombinase 1) gene, to identify genetic candidates for male infertility and to strengthen DMC1's existing genotype-phenotype relationships.nnMETHODS: We used whole exome sequencing (WES) and in silico analysis to investigate select DMC1 variants in a large cohort of infertile sporadic and familial cases (n = 3150).nnRESULTS: Our familial analyses identified a homozygous DMC1 missense variant, p.Thr55Ile, in two NOA-affected male siblings. We also report additional homozygous missense variants, p.Thr164Ala and p.Tyr194Cys, and one notable, rare single heterozygous variant, p.Asp160Gly, in unrelated sporadic patients. Our 3D protein modeling indicates that each of our identified variants would significantly impact the structure and functional activity of DMC1 protein.nnCONCLUSION: Our extensive genomic study identified three rare, recessive DMC1 variants in human NOA patients. Further, we report an alternative maturation arrest phenotype than previously observed in DMC1-related NOA. We also provide preliminary support for the possible exploration of select single heterozygous variants in the DMC1 gene, potentially expanding the male infertility field's understanding of the disease states and inheritance patterns associated with variants in DMC1.},

keywords = {GEMINI, Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40846510,

title = {Genetic and epigenetic landscape of male infertility},

author = {Emma R James and Maliha Tasnim and Antoni Riera-Escamilla and Katinka Vigh-Conrad and Benjamin R Emery and Donald F Conrad and Kenneth I Aston},

doi = {10.1016/j.tig.2025.07.007},

issn = {0168-9525},

year  = {2025},

date = {2025-10-01},

urldate = {2025-10-01},

journal = {Trends Genet},

volume = {41},

number = {10},

pages = {883--898},

abstract = {Male infertility is a global health problem, affecting up to 6% of reproductive age men worldwide. It has an enormous personal and societal burden, along with public health implications beyond the inability to reproduce, including reduced future health and longevity. While the impact of infertility has long been appreciated, the molecular architecture of the disease is largely unknown. Nevertheless, the past decade has witnessed significant advances in our understanding of the molecular basis of male infertility. Here, we describe the contributions of genetic and epigenetic mechanisms to infertility-associated phenotypes and their impact beyond reproduction. This review focuses on progress in understanding defects in sperm production and function, and the potential impact of these advances on diagnosis, treatments, and improved health.},

keywords = {GEMINI, Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40545437,

title = {The rising role of genetics in andrology research and clinical practice},

author = {Maris Laan and Kenneth I Aston and Donald F Conrad},

doi = {10.1111/andr.70073},

issn = {2047-2927},

year  = {2025},

date = {2025-07-01},

urldate = {2025-07-01},

journal = {Andrology},

volume = {13},

number = {5},

pages = {983--985},

keywords = {Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40591933,

title = {CCDC89 is required for optimal sperm motility and male fertility in mammals},

author = {Moira K O'Bryan and Gülizar Saritas and Joseph Nguyen and Sofia B Winge and Anne E O'Connor and Helen Castillo-Madeen and Donald F Conrad and Maddison Graffeo and Reza Nosrati and Jessica E M Dunleavy and Kristian Almstrup and Brendan J Houston},

doi = {10.1093/humrep/deaf126},

issn = {1460-2350},

year  = {2025},

date = {2025-07-01},

urldate = {2025-07-01},

journal = {Hum Reprod},

abstract = {STUDY QUESTION: What is the role of coiled-coil domain-containing protein 89 (CCDC89) in mammalian male fertility?nnSUMMARY ANSWER: The presence of CCDC89 is required for normal sperm motility and therefore optimal male fertility in mice, while CCDC89 variants affected spermatogenesis in both mice and humans.nnWHAT IS KNOWN ALREADY: Coiled-coiled domain-containing proteins play a variety of roles in biological processes, including cell division, the production of motile sperm, and the regulation of their motility.nnSTUDY DESIGN, SIZE, DURATION: DNA from infertile men with azoospermia was sequenced to identify genetic variants as per the Genetics of Male Infertility Initiative (GEMINI) study. Genetic variants were identified in CCDC89 in three men, by whole exome sequencing. A testis biopsy from infertile Patient 1 (CCDC89 variant c. G903T) was available and used to inspect tissue pathology. Ccdc89 knockout (Ccdc89-/-) and Ccdc89E297D/E297D mutant mouse models were generated to define the role of CCDC89 in male fertility and the role of the specific CCDC89 genetic variant, c. G903T, in the pathogenesis of infertility.nnPARTICIPANTS/MATERIALS, SETTING, METHODS: CCDC89 RNA expression and protein localization were investigated in a testis biopsy from a control male with normal spermatogenesis. Male fertility of the mutant mouse lines was assessed via breeding, histology, daily sperm production, electron microscopy, computer-assisted and high-speed sperm motility analysis, and in vitro fertilization.nnMAIN RESULTS AND THE ROLE OF CHANCE: Ccdc89-/- male mice were sub-fertile, with impaired progressive sperm motility and curvilinear velocity due to a rigid sperm tail midpiece without any overt structural defects. While Ccdc89E297D/E297D males were fertile, their testis weights and germ cell content were reduced, suggesting a potential role of the c. G903T variant, observed in each of the two men, in the pathogenesis of their spermatogenic impairment. We also identified a new genetic variant in CCDC89 (c.G1024A) in another infertile man, that was in trans with the c. G903T genetic variant.nnLARGE SCALE DATA: N/A.nnLIMITATIONS, REASONS FOR CAUTION: The identification of additional infertile men with genetic variants in CCDC89, and quality clinical data, are required to determine prognostic reliability regarding CCDC89 variants. There are likely to be species-specific differences in gene function.nnWIDER IMPLICATIONS OF THE FINDINGS: Our data highlight a role for CCDC89, in regulating the sperm tail waveform, that is required for optimal sperm fertilization capacity and male fertility. We highlight CCDC89 as a regulator of male fertility in mammals, where variants in CCDC89 can affect spermatogenesis and may be a risk factor for human male infertility. This study underscores the importance of validating clinical genetic findings.nnSTUDY FUNDING/COMPETING INTEREST(S): This work was supported by a National Health and Medical Research Council grant (APP1120356), National Institutes of Health grants (R01HD078641 and P50HD096723), the Novo Nordisk Foundation (grant numbers NNF210C0069913 and NNF21C0069969), the Capital Region of Denmark, the Independent Research Fund (grant number: 1030-00381B), and the Svend Andersen Foundation (grant number: 84-A.08), and the Christian and Ottilia Brorsons (No. 12038-1) and Frimodt-Heineke Foundation travel grants for research exchange. The authors have no conflicts of interest.},

keywords = {GEMINI, Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40598224,

title = {A novel mechanism of sperm midpiece epididymal maturation and the role of CCDC112 in sperm midpiece formation and establishing an optimal flagella waveform},

author = {Maddison L Graffeo and Joseph Nguyen and Farin Yazdan Parast and Jessica E M Dunleavy and Denis Korneev and Hongyi Yang and Hidenobu Okuda and Anne E O'Connor and Donald F Conrad and Reza Nosrati and Brendan J Houston and Moira K O'Bryan},

doi = {10.1186/s12964-025-02320-x},

issn = {1478-811X},

year  = {2025},

date = {2025-07-01},

urldate = {2025-07-01},

journal = {Cell Commun Signal},

volume = {23},

number = {1},

pages = {319},

abstract = {BACKGROUND: The mitochondrial sheath is a defining feature of mammalian sperm with proposed functions in structural support and energy production for flagella movement. Recently, coiled coil domain containing (CCDC) protein 112 (CCDC112) was suggested to play a role in the regulation of ciliogenesis. CCDC112 is a poorly characterised protein and there is virtually no knowledge of its in vivo function.nnMETHODS: Here, we define CCDC112 as crucial for male fertility using a Ccdc112 loss-of-function mouse line. To characterize and analyze male fertility, and to identify a novel process of epididymal midpiece maturation, we utilized a range of assays including fertility testing, scanning electron microscopy, high-resolution sperm motility and power output analysis, in vitro fertilization, intracytoplasmic sperm injection, mitochondria stress test assays and glycolytic flux assays. Localization of CCDC112 in cilia was assessed via the transfection of IMCD-3 cells with a CCDC112-eGFP vector and subsequent immunofluorescent staining.nnRESULTS: Results reveal CCDC112 as a requirement for male fertility in the mouse with an essential role in mitochondrial sheath formation. Our data reveal the critical role of CCDC112 in mitochondrial morphogenesis during midpiece formation, with the lack of CCDC112 leading to significantly reduced respiration capacity, irregular flagellar waveforms, diminished progressive motility and ultimately male sterility. In the absence of CCDC112, sperm are unable to traverse the female reproductive tract to the site of fertilization and in vitro have a poor capacity to penetrate the zonae pellucidae of oocytes or fuse with the oocyte. We further unveil a previously unrecognized process of epididymal mitochondrial sheath maturation. We show the sperm midpiece is structurally immature upon exiting the testis and maturation continues during transit from the caput to the cauda epididymis. Finally, we identify CCDC112 as a component of the distal appendages of the mother centriole in IMCD-3 cells suggestive of a facilitative role for CCDC112 in protein entry into the ciliary compartment within germ cells.nnCONCLUSION: Collectively, we establish CCDC112 as a key regulator of sperm midpiece assembly and function while further expanding our understanding on functional sperm production, energy generation and flagella kinematics.},

keywords = {GEMINI, Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40204980,

title = {Benchmark of computational methods to detect digenism in sequencing data},

author = {Marie-Sophie C Ogloblinsky and Donald F Conrad and Anaïs Baudot and Elisabeth Tournier-Lasserve and and Emmanuelle Génin and Gaëlle Marenne},

doi = {10.1038/s41431-025-01834-9},

issn = {1476-5438},

year  = {2025},

date = {2025-04-01},

urldate = {2025-04-01},

journal = {Eur J Hum Genet},

abstract = {Digenic inheritance is characterized by the combined alteration of two different genes leading to a disease. It could explain the etiology of many currently undiagnosed rare diseases. With the advent of next-generation sequencing technologies, the identification of digenic inheritance patterns has become more technically feasible, yet still poses significant challenges without any gold standard method. Here, we present a comprehensive overview of the existing methods developed to detect digenic inheritance in sequencing data and provide a classification in cohort-based and individual-based methods. The latter category of methods appeared the most applicable to rare diseases, especially the ones not needing patient phenotypic description as input. We discuss the availability of the different methods, their output and scalability to inform potential users. Focusing on methods to detect digenic inheritance in the case of very rare or heterogeneous diseases, we propose a benchmark using different real-life scenarios involving known digenic and putative neutral pairs of genes. Among these different methods, DiGePred stood out as the one giving the least number of false positives, ARBOCK as giving the greatest number of true positives, and DIEP as having the best balance between both. By synthesizing the state-of-the-art techniques and providing insights into their practical utility, this benchmark serves as a valuable resource for researchers and clinicians in selecting suitable methodologies for detecting digenic inheritance in a wide range of disorders using sequencing data.},

keywords = {Genomic Variation},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40174856,

title = {Genetic and genomic insights into male reproductive tract development},

author = {Madison Held and Helen Castillo-Madeen and Katinka A Vigh-Conrad and Kenneth I Aston and Donald F Conrad},

doi = {10.1016/j.fertnstert.2025.03.024},

issn = {1556-5653},

year  = {2025},

date = {2025-03-01},

urldate = {2025-03-01},

journal = {Fertil Steril},

abstract = {Genetic and genomic analysis continues to drive important insights into male reproductive tract (MRT) development. Here, we briefly review normal MRT development, highlighting recent discoveries of cell types and cellular processes delivered by single-cell sequencing. We report a systematic review of phenotype terms and genes linked to MRT development, identifying 35 terms from the Human Phenotype Ontology associated with 269 unique genes. A parallel review of mouse data revealed differences in the phenotype terms available and the number and identity of genes linked to MRT defects, indicating opportunities for harmonization of knowledge. We used a published single-cell atlas of the developing testis to characterize the regulation of MRT genes across cell types and stages of fetal testis development. Single-cell RNA sequencing data support the conclusion that Leydig cells and Sertoli cells are the primary testicular cell types expressing MRT genes. Furthermore, we find post-conception weeks 6, 8, and 16 to be the key points of upregulation of testicular MRT genes. New advances, especially in imaging and spatially resolved molecular measurements, provide exciting prospects for MRT research and diagnosis, and we expect rapid progress in the coming years. Continued investigation in this space is essential to understand the genetic basis of MRT development and how MRT defects are related to medical outcomes in adult life.},

keywords = {Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid39961022,

title = {SATINN v2: automated image analysis for mouse testis histology with multi-laboratory data integration},

author = {Ran Yang and Fritzie T Celino-Brady and Jessica E M Dunleavy and Katinka A Vigh-Conrad and Georgia Rae Atkins and Rachel L Hvasta and Christopher R X Pombar and Alexander N Yatsenko and Kyle E Orwig and Moira K O'Bryan and Ana C Lima and Donald F Conrad},

doi = {10.1093/biolre/ioaf033},

issn = {1529-7268},

year  = {2025},

date = {2025-02-01},

urldate = {2025-02-01},

journal = {Biol Reprod},

abstract = {Analysis of testis histology is fundamental to the study of male fertility, but it is a slow task with a high skill threshold. Here, we describe new neural network models for the automated classification of cell types and tubule stages from whole-slide brightfield images of mouse testis. The cell type classifier recognizes 14 cell types, including multiple steps of meiosis I prophase, with an external validation accuracy of 96%. The tubule stage classifier distinguishes all 12 canonical tubule stages with external validation accuracy of 63%, which increases to 96% when allowing for ±1 stage tolerance. We addressed generalizability of SATINN, through extensive training diversification and testing on external (non-training population) wildtype and mutant datasets. This allowed us to use SATINN to successfully process data generated in multiple laboratories. We used SATINN to analyze testis images from 8 different mutant lines, generated from 3 different labs with a range of tissue processing protocols. Finally, we show that it is possible to use SATINN output to cluster histology images in latent space, which, when applied to the 8 mutant lines, reveals known relationships in their pathology. This work represents significant progress towards a tool for robust, automated testis histopathology that can be used by multiple labs.},

keywords = {Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid39903672,

title = {Deletion of an evolutionarily conserved TAD boundary impacts spermatogenesis in mice†},

author = {Ana C Lima and Mariam Okhovat and Alexandra M Stendahl and Ran Yang and Jake VanCampen and Kimberly A Nevonen and Jarod Herrera and Weiyu Li and Lana Harshman and Lev M Fedorov and Katinka A Vigh-Conrad and Nadav Ahituv and Donald F Conrad and Lucia Carbone},

doi = {10.1093/biolre/ioaf017},

issn = {1529-7268},

year  = {2025},

date = {2025-02-01},

urldate = {2025-02-01},

journal = {Biol Reprod},

abstract = {Spermatogenesis is a complex process that can be disrupted by genetic and epigenetic changes, potentially leading to male infertility. Recent research has rapidly increased the number of protein coding mutations causally linked to impaired spermatogenesis in humans and mice. However, the role of non-coding mutations remains largely unexplored. As a case study to evaluate the effects of non-coding mutations on spermatogenesis, we first identified an evolutionarily conserved topologically associated domain (TAD) boundary near two genes with important roles in mammalian testis function: Dmrtb1 and Lrp8. We then used CRISPR-Cas9 to generate a mouse line where 26 kb of the boundary was removed including a strong and evolutionarily conserved CTCF binding site. ChIP-seq and Hi-C experiments confirmed the removal of the CTCF site and a resulting mild increase in the DNA-DNA interactions across the domain boundary. Mutant mice displayed significant changes in testis gene expression, higher frequency of histological abnormalities, a drop of 47-52% in efficiency of meiosis, a 15-18% reduction in efficiency of spermatogenesis, and consistently, a 12-28% decrease in daily sperm production compared to littermate controls. Despite these quantitative changes in testis function, mutant mice show no significant changes in fertility. This suggests that non-coding deletions affecting testis gene regulation may have smaller effects on fertility compared to coding mutations of the same genes. Our results demonstrate that disruption of a TAD boundary can have a negative impact on sperm production and highlight the importance of considering non-coding mutations in the analysis of patients with male infertility.},

keywords = {Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid39777458,

title = {Diminished DNA binding affinity of DMRT1 caused by heterozygous DM domain mutations is a cause of male infertility},

author = {Tihana Marić and Helen Castillo-Madeen and Monika Logara Klarić and Antun Barišić and Lovro Trgovec-Greif and Mark W Murphy and Anna-Grete Juchnewitsch and Kristiina Lillepea and Avirup Dutta and Lucija Žunić and Alexandra M Stendahl and Margus Punab and Kristjan Pomm and Daniel M Mendoza and Alexandra M Lopes and Ana Merkler Šorgić and Oliver Vugrek and Joao Gonçalves and Kristian Almstrup and Kenneth I Aston and Robert Belužić and Davor Ježek and Branimir Bertoša and Maris Laan and Ana Katušić Bojanac and Donald F Conrad and Maja Barbalić},

doi = {10.1093/hmg/ddae197},

issn = {1460-2083},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Hum Mol Genet},

abstract = {The most severe form of male infertility is idiopathic non-obstructive azoospermia (NOA), a complete sperm absence in the ejaculate. We performed exome sequencing in the Croatian infertile brothers with NOA and found a variant in DMRT1 (Doublesex and mab-3 related transcription factor 1) gene that was further assessed by the EMSA assay and molecular dynamic simulations. We additionally screened for DMRT1 mutations in 1940 infertile men diagnosed with spermatogenic failure, 644 normozoospermic controls, and 105 females with primary ovarian insufficiency (POI) recruited to the GEnetics of Male INfertility Initiative (GEMINI) or Estonian Andrology (ESTAND) cohorts. DMRT1 p.Pro74Leu (chr9:g.842059C > T) variant was detected in infertile brothers in the highly conserved position within the DNA binding DM domain of the protein. EMSA assay showed reduced DNA binding of DMRT1P74L and molecular dynamic simulations showed differences in structural and dynamical properties between the wild type protein and DMRT1P74L. Plausible disease-causing DMRT1 variants were only identified in infertile men (13/1940; 0.67%), and none in 639 fertile controls. Burden testing showed an excess of rare deleterious DM domain mutations in the infertility cohort compared to gnomAD v.4.0 population-based controls (Fisher's exact test, p = 1.44 x 10-5). Three rare deleterious variants in DMRT1 were found in 104 cases of POI. The findings of this study strengthen the evidence of DMRT1 variants being a causal factor for male infertility and provide the distribution of likely pathogenic variants across the gene. This is also the first study to suggest that DMRT1 variants may also be linked to POI.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid39780503,

title = {Introduction to androgenetics: terminology, approaches, and impactful studies across 60 years},

author = {Arvand Akbari and Laura Kasak and Maris Laan},

doi = {10.1111/andr.13835},

issn = {2047-2927},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Andrology},

abstract = {Across six decades, androgenetics has consistently concentrated on discovering genetic causes and enhancing the molecular diagnostics of male infertility, disorders of sex development, and their broader implications on health, such as cancer and other comorbidities. Despite vast clinical knowledge, the training of andrologists often lacks fundamental basics in medical genetics. This work, as part of the Special Issue of Andrology "Genetics in Andrology", provides the core terminology in medical genetics and technological advancements in genomics, required to understand the ever-progressing research in the field. It also gives an overview of study designs and approaches that have frequently led to discoveries in androgenetics. The rapid progress in the methodological toolbox in human genetics is illustrated by numerous examples of impactful androgenetic studies over 60 years, and their clinical implications.},

keywords = {Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid39815096,

title = {The human and non-human primate developmental GTEx projects},

author = {Tim H H Coorens and Amy Guillaumet-Adkins and Rothem Kovner and Rebecca L Linn and Victoria H J Roberts and Amrita Sule and Patrick M Van Hoose},

doi = {10.1038/s41586-024-08244-9},

issn = {1476-4687},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Nature},

volume = {637},

number = {8046},

pages = {557--564},

abstract = {Many human diseases are the result of early developmental defects. As most paediatric diseases and disorders are rare, children are critically underrepresented in research. Functional genomics studies primarily rely on adult tissues and lack critical cell states in specific developmental windows. In parallel, little is known about the conservation of developmental programmes across non-human primate (NHP) species, with implications for human evolution. Here we introduce the developmental Genotype-Tissue Expression (dGTEx) projects, which span humans and NHPs and aim to integrate gene expression, regulation and genetics data across development and species. The dGTEx cohort will consist of 74 tissue sites across 120 human donors from birth to adulthood, and developmentally matched NHP age groups, with additional prenatal and adult animals, with 126 rhesus macaques (Macaca mulatta) and 72 common marmosets (Callithrix jacchus). The data will comprise whole-genome sequencing, extensive bulk, single-cell and spatial gene expression profiles, and chromatin accessibility data across tissues and development. Through community engagement and donor diversity, the human dGTEx study seeks to address disparities in genomic research. Thus, dGTEx will provide a reference human and NHP dataset and tissue bank, enabling research into developmental changes in expression and gene regulation, childhood disorders and the effect of genetic variation on development.},

keywords = {NHP Genetics},

pubstate = {published},

tppubtype = {article}

}

@article{pmid39808663,

title = {Estimating realized relatedness in free-ranging macaques by inferring identity-by-descent segments},

author = {Annika Freudiger and Vladimir M Jovanovic and Yilei Huang and Noah Snyder-Mackler and Donald F Conrad and Brian Miller and Michael J Montague and Hendrikje Westphal and Peter F Stadler and Stefanie Bley and Julie E Horvath and Lauren J N Brent and Michael L Platt and Angelina Ruiz-Lambides and Jenny Tung and Katja Nowick and Harald Ringbauer and Anja Widdig},

doi = {10.1073/pnas.2401106122},

issn = {1091-6490},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Proc Natl Acad Sci U S A},

volume = {122},

number = {3},

pages = {e2401106122},

abstract = {Biological relatedness is a key consideration in studies of behavior, population structure, and trait evolution. Except for parent-offspring dyads, pedigrees capture relatedness imperfectly. The number and length of identical-by-descent DNA segments (IBD) yield the most precise relatedness estimates. Here, we leverage different methods for estimating IBD segments from low-depth whole genome resequencing data to demonstrate the feasibility and value of resolving fine-scaled gradients of relatedness in free-living animals. Using primarily 4 to 6× depth data from a rhesus macaque () population with long-term pedigree data, we show that we can infer the number and length of IBD segments across the genome with high accuracy even at 0.5× sequencing depth. In line with expectations based on simulation, the resulting estimates demonstrate substantial variation in genetic relatedness within kin classes, leading to overlapping distributions between kin classes. By comparing the IBD-based estimates with pedigree and short tandem repeat-based methods, we show that IBD estimates are more reliable and provide more detailed information on kinship. The inferred IBD segments also identify cryptic genetic relatives not represented in the pedigree and reveal elevated recombination rates in females relative to males, which enables the majority of close maternal and paternal kin to be distinguished with genotype data alone. Our findings represent a breakthrough in the ability to study the predictors and consequences of genetic relatedness in natural populations, contributing to our understanding of a fundamental component of population structure in the wild.},

keywords = {NHP Genetics},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40494321,

title = {Easy-PSAP: An Integrated Workflow to Prioritize Pathogenic Variants in Sequence Data from a Single Individual},

author = {Marie-Sophie C Ogloblinsky and Marc B Gros-La-Faige and Daniel P Lewinsohn and Mathilde Nguyen and Lourdes Velo-Suarez and Anthony Herzig and Thomas E Ludwig and Helen Castillo-Madeen and Donald F Conrad and Emmanuelle Génin and Gaëlle Marenne},

doi = {10.1159/000543671},

issn = {1423-0062},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Hum Hered},

volume = {90},

number = {1},

pages = {33--40},

abstract = {INTRODUCTION: Next-generation sequencing (NGS) data analysis has become an integral part of clinical genetic diagnosis, raising the question of variant prioritization. The Population Sampling Probability (PSAP) method has been developed to tackle the issue of variant prioritization in the exome of a single patient, by leveraging allele frequencies from population databases and a variant pathogenicity score.nnMETHODS: Here, we present Easy-PSAP, a completely new implementation of the PSAP method comprising two user-friendly and highly adaptable pipelines. Easy-PSAP allows the gene-based recalibration of any in silico pathogenicity prediction score compared to scores of variants seen in the general population, including popular scores like CADD or AlphaMissense. Easy-PSAP can evaluate genetic variants at the scale of a whole exome or a whole genome using information from the latest population and annotation databases.nnRESULTS: Through simulations on synthetic disease exomes, we show that Easy-PSAP is able to rank more than 50% of causal pathogenic variants in the top 10 variants for an autosomal dominant model of transmission and in top 1 for an autosomal recessive model of transmission.nnDISCUSSION: These findings, along with the accessibility of the pipeline to both researchers and clinicians, make Easy-PSAP a state-of-the-art tool for variant prioritization in NGS data that can continue to evolve as new frameworks and databases become available. Easy-PSAP is implemented in R and bash within an open-source Snakemake framework. It is available on GitHub alongside conda environments containing the required dependencies (<ext-link ext-link-type="uri" xlink:href="https://github.com/msogloblinsky/Easy-PSAP" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/msogloblinsky/Easy-PSAP</ext-link>).},

keywords = {Genomic Variation},

pubstate = {published},

tppubtype = {article}

}

@article{pmid41080698,

title = {A partially automated method for DNA extraction from marmoset hair follicles to avoid blood chimerism},

author = {Alexandra M Stendahl and Qiangge Zhang and Ana C Lima and Curtis Mello and James Nemesh and Sam Peterson and Jenna Castro and Fritzie T Celino-Brady and Karina Ray and Xian Gao and Yuanyuan Hou and Chenjie Shen and Katinka A Vigh-Conrad and Fenna Krienen and Guoping Feng and Steven A McCarroll and Donald F Conrad and Ricardo C H Del Rosario},

doi = {10.3389/fgene.2025.1608504},

issn = {1664-8021},

year  = {2025},

date = {2025-01-01},

journal = {Front Genet},

volume = {16},

pages = {1608504},

abstract = {Marmosets are valuable non-human primate models, however their unique reproduction results in high levels of blood chimerism, making blood unreliable for DNA sequencing. Hair follicles have lower levels of chimerism however DNA extraction from hair follicles is challenging due to the limited tissue. We developed a non-invasive, partially automated protocol for hair follicle collection and DNA extraction scalable to hundreds of samples. This method uses a proteinase K cell lysis solution in conjunction with Promega's Maxwell RSC's paramagnetic silica-based particles to purify DNA. We applied this protocol to samples collected from over 300 animals and from two different species. We were able to generate high quality libraries for whole genome sequencing (WGS) from approximately 150 hair follicles. Libraries built from >0.15 µg DNA had an average duplication rate of 0.19, analogous to libraries built from blood. Sequenced DNA had average chimerism rates of 2.3%. DNA extraction from hair follicles offers a reliable method for whole genome sequencing with minimal chimerism. The partial automation improves efficiency by reducing lab time and extraction variability. The protocol is applicable to a range of projects requiring low-input DNA sources or automated, high-throughput sample processing. Peer review data availability: Data on DNA yields and resulting whole genome sequencing libraries are provided as Supplementary Tables. The raw whole genome sequencing data produced from these libraries are archived online at the NIH Sequence Read Archive.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid40494321b,

title = {Easy-PSAP: An Integrated Workflow to Prioritize Pathogenic Variants in Sequence Data from a Single Individual},

author = {Marie-Sophie C Ogloblinsky and Marc B Gros-La-Faige and Daniel P Lewinsohn and Mathilde Nguyen and Lourdes Velo-Suarez and Anthony Herzig and Thomas E Ludwig and Helen Castillo-Madeen and Donald F Conrad and Emmanuelle Génin and Gaëlle Marenne},

doi = {10.1159/000543671},

issn = {1423-0062},

year  = {2025},

date = {2025-01-01},

journal = {Hum Hered},

volume = {90},

number = {1},

pages = {33--40},

abstract = {INTRODUCTION: Next-generation sequencing (NGS) data analysis has become an integral part of clinical genetic diagnosis, raising the question of variant prioritization. The Population Sampling Probability (PSAP) method has been developed to tackle the issue of variant prioritization in the exome of a single patient, by leveraging allele frequencies from population databases and a variant pathogenicity score.nnMETHODS: Here, we present Easy-PSAP, a completely new implementation of the PSAP method comprising two user-friendly and highly adaptable pipelines. Easy-PSAP allows the gene-based recalibration of any in silico pathogenicity prediction score compared to scores of variants seen in the general population, including popular scores like CADD or AlphaMissense. Easy-PSAP can evaluate genetic variants at the scale of a whole exome or a whole genome using information from the latest population and annotation databases.nnRESULTS: Through simulations on synthetic disease exomes, we show that Easy-PSAP is able to rank more than 50% of causal pathogenic variants in the top 10 variants for an autosomal dominant model of transmission and in top 1 for an autosomal recessive model of transmission.nnDISCUSSION: These findings, along with the accessibility of the pipeline to both researchers and clinicians, make Easy-PSAP a state-of-the-art tool for variant prioritization in NGS data that can continue to evolve as new frameworks and databases become available. Easy-PSAP is implemented in R and bash within an open-source Snakemake framework. It is available on GitHub alongside conda environments containing the required dependencies (https://github.com/msogloblinsky/Easy-PSAP).},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid39318036,

title = {PSAP-Genomic-Regions: A Method Leveraging Population Data to Prioritize Coding and Non-Coding Variants in Whole Genome Sequencing for Rare Disease Diagnosis},

author = {Marie-Sophie C Ogloblinsky and Ozvan Bocher and Chaker Aloui and Anne-Louise Leutenegger and Ozan Ozisik and Anaïs Baudot and Elisabeth Tournier-Lasserve and Helen Castillo-Madeen and Daniel Lewinsohn and Donald F Conrad and Emmanuelle Génin and Gaëlle Marenne},

doi = {10.1002/gepi.22593},

issn = {1098-2272},

year  = {2024},

date = {2024-09-01},

urldate = {2024-09-01},

journal = {Genet Epidemiol},

abstract = {The introduction of Next-Generation Sequencing technologies in the clinics has improved rare disease diagnosis. Nonetheless, for very heterogeneous or very rare diseases, more than half of cases still lack molecular diagnosis. Novel strategies are needed to prioritize variants within a single individual. The Population Sampling Probability (PSAP) method was developed to meet this aim but only for coding variants in exome data. Here, we propose an extension of the PSAP method to the non-coding genome called PSAP-genomic-regions. In this extension, instead of considering genes as testing units (PSAP-genes strategy), we use genomic regions defined over the whole genome that pinpoint potential functional constraints. We conceived an evaluation protocol for our method using artificially generated disease exomes and genomes, by inserting coding and non-coding pathogenic ClinVar variants in large data sets of exomes and genomes from the general population. PSAP-genomic-regions significantly improves the ranking of these variants compared to using a pathogenicity score alone. Using PSAP-genomic-regions, more than 50% of non-coding ClinVar variants were among the top 10 variants of the genome. On real sequencing data from six patients with Cerebral Small Vessel Disease and nine patients with male infertility, all causal variants were ranked in the top 100 variants with PSAP-genomic-regions. By revisiting the testing units used in the PSAP method to include non-coding variants, we have developed PSAP-genomic-regions, an efficient whole-genome prioritization tool which offers promising results for the diagnosis of unresolved rare diseases.},

keywords = {Genomic Variation},

pubstate = {published},

tppubtype = {article}

}

@article{pmid39300832,

title = {Utility of exome sequencing in primary spermatogenic disorders: From research to diagnostics},

author = {Antoni Riera-Escamilla and Liina Nagirnaja},

doi = {10.1111/andr.13753},

issn = {2047-2927},

year  = {2024},

date = {2024-09-01},

urldate = {2024-09-01},

journal = {Andrology},

abstract = {BACKGROUND: Primary spermatogenic disorders represent a severe form of male infertility whereby sperm production is impaired due to testicular dysfunction, leading to reduced quality or quantity of spermatozoa. Gene-centered research has certainly demonstrated the importance of the genetic factor in the etiology of both poor sperm morphology or motility and reduced sperm count. In the last decade, next-generation sequencing has expanded the research to whole exome which has transformed our understanding of male infertility genetics, but uncertainty persists in its diagnostic yield, especially in large unrelated populations.nnOBJECTIVE: To evaluate the utility of exome sequencing in detecting genetic factors contributing to various traits of primary spermatogenic disorders, which is a crucial step before interpreting the diagnostic yield of the platform.nnMATERIALS AND METHODS: We manually curated 415 manuscripts and included 19 research studies that predominantly performed whole exome sequencing in cohorts of unrelated cases with primary spermatogenic defects.nnRESULTS: The detection rate, defined as the fraction of cases with an identifiable genetic cause, typically remained below 25% for quantitative defects of spermatozoa, whereas improved rates were observed for traits of abnormal sperm morphology/motility and in populations enriched with consanguineous families. Unlike the quantitative defects, the genetic architecture of the qualitative issues of spermatozoa featured a small number of recurrent genes describing a large fraction of studied cases. These observations were also in line with the lower biological complexity of the pathways affected by the reported genes.nnDISCUSSION AND CONCLUSIONS: This review demonstrates the variability in detection rates of exome sequencing across semen phenotypes, which may have an impact on the expectations of the diagnostic yield in the clinical setting.},

keywords = {Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid39122675,

title = {Inherited defects of piRNA biogenesis cause transposon de-repression, impaired spermatogenesis, and human male infertility},

author = {Birgit Stallmeyer and Clara Bühlmann and Rytis Stakaitis and Ann-Kristin Dicke and Farah Ghieh and Luisa Meier and Ansgar Zoch and David MacKenzie MacLeod and Johanna Steingröver and Özlem Okutman and Daniela Fietz and Adrian Pilatz and Antoni Riera-Escamilla and Miguel J Xavier and Christian Ruckert and Sara Di Persio and Nina Neuhaus and Ali Sami Gurbuz and Ahmet Şalvarci and Nicolas Le May and Kevin McEleny and Corinna Friedrich and Godfried van der Heijden and Margot J Wyrwoll and Sabine Kliesch and Joris A Veltman and Csilla Krausz and Stéphane Viville and Donald F Conrad and Dónal O'Carroll and Frank Tüttelmann},

doi = {10.1038/s41467-024-50930-9},

issn = {2041-1723},

year  = {2024},

date = {2024-08-01},

urldate = {2024-08-01},

journal = {Nat Commun},

volume = {15},

number = {1},

pages = {6637},

abstract = {piRNAs are crucial for transposon silencing, germ cell maturation, and fertility in male mice. Here, we report on the genetic landscape of piRNA dysfunction in humans and present 39 infertile men carrying biallelic variants in 14 different piRNA pathway genes, including PIWIL1, GTSF1, GPAT2, MAEL, TDRD1, and DDX4. In some affected men, the testicular phenotypes differ from those of the respective knockout mice and range from complete germ cell loss to the production of a few morphologically abnormal sperm. A reduced number of pachytene piRNAs was detected in the testicular tissue of variant carriers, demonstrating impaired piRNA biogenesis. Furthermore, LINE1 expression in spermatogonia links impaired piRNA biogenesis to transposon de-silencing and serves to classify variants as functionally relevant. These results establish the disrupted piRNA pathway as a major cause of human spermatogenic failure and provide insights into transposon silencing in human male germ cells.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38997255,

title = {AXDND1 is required to balance spermatogonial commitment and for sperm tail formation in mice and humans},

author = {Brendan J Houston and Joseph Nguyen and D Jo Merriner and Anne E O'Connor and Alexandra M Lopes and Liina Nagirnaja and Corinna Friedrich and Sabine Kliesch and Frank Tüttelmann and Kenneth I Aston and Donald F Conrad and Robin M Hobbs and Jessica E M Dunleavy and Moira K O'Bryan},

doi = {10.1038/s41419-024-06874-5},

issn = {2041-4889},

year  = {2024},

date = {2024-07-01},

urldate = {2024-07-01},

journal = {Cell Death Dis},

volume = {15},

number = {7},

pages = {499},

abstract = {Dynein complexes are large, multi-unit assemblies involved in many biological processes via their critical roles in protein transport and axoneme motility. Using next-generation sequencing of infertile men presenting with low or no sperm in their ejaculates, we identified damaging variants in the dynein-related gene AXDND1. We thus hypothesised that AXDND1 is a critical regulator of male fertility. To test this hypothesis, we produced a knockout mouse model. Axdnd1 males were sterile at all ages but presented with an evolving testis phenotype wherein they could undergo one round of histologically replete spermatogenesis followed by a rapid depletion of the seminiferous epithelium. Marker experiments identified a role for AXDND1 in maintaining the balance between differentiation-committed and self-renewing spermatogonial populations, resulting in disproportionate production of differentiating cells in the absence of AXDND1 and increased sperm production during initial spermatogenic waves. Moreover, long-term spermatogonial maintenance in the Axdnd1 knockout was compromised, ultimately leading to catastrophic germ cell loss, destruction of blood-testis barrier integrity and immune cell infiltration. In addition, sperm produced during the first wave of spermatogenesis were immotile due to abnormal axoneme structure, including the presence of ectopic vesicles and abnormalities in outer dense fibres and microtubule doublet structures. Sperm output was additionally compromised by a severe spermiation defect and abnormal sperm individualisation. Collectively these data identify AXDND1 as an atypical dynein complex-related protein with a role in protein/vesicle transport of relevance to spermatogonial function and sperm tail formation in mice and humans. This study underscores the importance of studying the consequences of gene loss-of-function on both the establishment and maintenance of male fertility.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38570187,

title = {Genetic mutation of  results in male infertility due to abnormal sperm tail composition},

author = {Brendan J Houston and D Jo Merriner and G Gemma Stathatos and Joseph H Nguyen and Anne E O'Connor and Alexandra M Lopes and Donald F Conrad and Mark Baker and Jessica Em Dunleavy and Moira K O'Bryan},

doi = {10.26508/lsa.202302452},

issn = {2575-1077},

year  = {2024},

date = {2024-06-01},

urldate = {2024-06-01},

journal = {Life Sci Alliance},

volume = {7},

number = {6},

abstract = {The transition zone is a specialised gate at the base of cilia/flagella, which separates the ciliary compartment from the cytoplasm and strictly regulates protein entry. We identified a potential new regulator of the male germ cell transition zone, CEP76. We demonstrated that CEP76 was involved in the selective entry and incorporation of key proteins required for sperm function and fertility into the ciliary compartment and ultimately the sperm tail. In the mutant, sperm tails were shorter and immotile as a consequence of deficits in essential sperm motility proteins including DNAH2 and AKAP4, which accumulated at the sperm neck in the mutant. Severe annulus, fibrous sheath, and outer dense fibre abnormalities were also detected in sperm lacking CEP76. Finally, we identified that CEP76 dictates annulus positioning and structure. This study suggests CEP76 as a male germ cell transition zone protein and adds further evidence to the hypothesis that the spermatid transition zone and annulus are part of the same functional structure.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38614076,

title = {Toward clinical exomes in diagnostics and management of male infertility},

author = {Kristiina Lillepea and Anna-Grete Juchnewitsch and Laura Kasak and Anu Valkna and Avirup Dutta and Kristjan Pomm and Olev Poolamets and Liina Nagirnaja and Erik Tamp and Eisa Mahyari and Vladimir Vihljajev and Stanislav Tjagur and Sofia Papadimitriou and Antoni Riera-Escamilla and Nassim Versbraegen and Ginevra Farnetani and Helen Castillo-Madeen and Mailis Sütt and Viljo Kübarsepp and Sven Tennisberg and Paul Korrovits and Csilla Krausz and Kenneth I Aston and Tom Lenaerts and Donald F Conrad and Margus Punab and Maris Laan},

doi = {10.1016/j.ajhg.2024.03.013},

issn = {1537-6605},

year  = {2024},

date = {2024-05-01},

journal = {Am J Hum Genet},

volume = {111},

number = {5},

pages = {877--895},

abstract = {Infertility, affecting ∼10% of men, is predominantly caused by primary spermatogenic failure (SPGF). We screened likely pathogenic and pathogenic (LP/P) variants in 638 candidate genes for male infertility in 521 individuals presenting idiopathic SPGF and 323 normozoospermic men in the ESTAND cohort. Molecular diagnosis was reached for 64 men with SPGF (12%), with findings in 39 genes (6%). The yield did not differ significantly between the subgroups with azoospermia (20/185, 11%), oligozoospermia (18/181, 10%), and primary cryptorchidism with SPGF (26/155, 17%). Notably, 19 of 64 LP/P variants (30%) identified in 28 subjects represented recurrent findings in this study and/or with other male infertility cohorts. NR5A1 was the most frequently affected gene, with seven LP/P variants in six SPGF-affected men and two normozoospermic men. The link to SPGF was validated for recently proposed candidate genes ACTRT1, ASZ1, GLUD2, GREB1L, LEO1, RBM5, ROS1, and TGIF2LY. Heterozygous truncating variants in BNC1, reported in female infertility, emerged as plausible causes of severe oligozoospermia. Data suggested that several infertile men may present congenital conditions with less pronounced or pleiotropic phenotypes affecting the development and function of the reproductive system. Genes regulating the hypothalamic-pituitary-gonadal axis were affected in >30% of subjects with LP/P variants. Six individuals had more than one LP/P variant, including five with two findings from the gene panel. A 4-fold increased prevalence of cancer was observed in men with genetic infertility compared to the general male population (8% vs. 2%; p = 4.4 × 10). Expanding genetic testing in andrology will contribute to the multidisciplinary management of SPGF.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38577799,

title = {The human infertility single-cell testis atlas (HISTA): an interactive molecular scRNA-Seq reference of the human testis},

author = {Eisa Mahyari and Katinka A Vigh-Conrad and Clément Daube and Ana C Lima and Jingtao Guo and Douglas T Carrell and James M Hotaling and Kenneth I Aston and Donald F Conrad},

doi = {10.1111/andr.13637},

issn = {2047-2927},

year  = {2024},

date = {2024-04-01},

urldate = {2024-04-01},

journal = {Andrology},

abstract = {BACKGROUND: Single-cell RNA-seq (scRNA-Seq) has been widely adopted to study gene expression of the human testis. Several datasets of scRNA-Seq from human testis have been generated from different groups processed with different informatics pipelines. An integrated atlas of scRNA-Seq expression constructed from multiple donors, developmental ages, and fertility states would be widely useful for the testis research community.nnOBJECTIVE: To describe the generation and use of the human infertility single-cell testis atlas (HISTA), an interactive web tool for understanding human spermatogenesis through scRNA-Seq analysis.nnMETHODS: We obtained scRNA-Seq datasets derived from 12 donors, including healthy adult controls, juveniles, and several infertility cases, and reprocessed these data using methods to remove batch effects. Using Shiny, an open-source environment for data visualization, we created numerous interactive tools for exploring the data, some of which support simple statistical hypothesis testing. We used the resulting HISTA browser and its underlying data to demonstrate HISTA's value for testis researchers.nnRESULTS: A primary application of HISTA is to search by a single gene or a set of genes; thus, we present various analyses that quantify and visualize gene expression across the testis cells and pathology. HISTA also contains machine-learning-derived gene modules ("components") that capture the entire transcriptional landscape of the testis tissue. We show how the use of these components can simplify the highly complex data in HISTA and assist with the interpretation of genes with unknown functions. Finally, we demonstrate the diverse ways HISTA can be used for new data analysis, including hypothesis testing.nnDISCUSSION AND CONCLUSIONS: HISTA is a research environment that can help scientists organize and understand the high-dimensional transcriptional landscape of the human testis. HISTA has already contributed to published testis research and can be updated as needed with input from the research community or downloaded and modified for individual needs.},

keywords = {Human Reproduction, Single Cell Genomics},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38297832,

title = {Heterozygous loss-of-function SMC3 variants are associated with variable growth and developmental features},

author = {Morad Ansari and Kamli N W Faour and Akiko Shimamura and Graeme Grimes and Emeline M Kao and Erica R Denhoff and Ana Blatnik and Daniel Ben-Isvy and Lily Wang and Benjamin M Helm and Helen Firth and Amy M Breman and Emilia K Bijlsma and Aiko Iwata-Otsubo and Thomy J L de Ravel and Vincent Fusaro and Alan Fryer and Keith Nykamp and Lara G Stühn and Tobias B Haack and G Christoph Korenke and Panayiotis Constantinou and Kinga M Bujakowska and Karen J Low and Emily Place and Jennifer Humberson and Melanie P Napier and Jessica Hoffman and Jane Juusola and Matthew A Deardorff and Wanqing Shao and Shira Rockowitz and Ian Krantz and Maninder Kaur and Sarah Raible and Victoria Dortenzio and Sabine Kliesch and Moriel Singer-Berk and Emily Groopman and Stephanie DiTroia and Sonia Ballal and Siddharth Srivastava and Kathrin Rothfelder and Saskia Biskup and Jessica Rzasa and Jennifer Kerkhof and Haley McConkey and Bekim Sadikovic and Sarah Hilton and Siddharth Banka and Frank Tüttelmann and Donald F Conrad and Anne O'Donnell-Luria and Michael E Talkowski and David R FitzPatrick and Philip M Boone},

doi = {10.1016/j.xhgg.2024.100273},

issn = {2666-2477},

year  = {2024},

date = {2024-04-01},

journal = {HGG Adv},

volume = {5},

number = {2},

pages = {100273},

abstract = {Heterozygous missense variants and in-frame indels in SMC3 are a cause of Cornelia de Lange syndrome (CdLS), marked by intellectual disability, growth deficiency, and dysmorphism, via an apparent dominant-negative mechanism. However, the spectrum of manifestations associated with SMC3 loss-of-function variants has not been reported, leading to hypotheses of alternative phenotypes or even developmental lethality. We used matchmaking servers, patient registries, and other resources to identify individuals with heterozygous, predicted loss-of-function (pLoF) variants in SMC3, and analyzed population databases to characterize mutational intolerance in this gene. Here, we show that SMC3 behaves as an archetypal haploinsufficient gene: it is highly constrained against pLoF variants, strongly depleted for missense variants, and pLoF variants are associated with a range of developmental phenotypes. Among 14 individuals with SMC3 pLoF variants, phenotypes were variable but coalesced on low growth parameters, developmental delay/intellectual disability, and dysmorphism, reminiscent of atypical CdLS. Comparisons to individuals with SMC3 missense/in-frame indel variants demonstrated an overall milder presentation in pLoF carriers. Furthermore, several individuals harboring pLoF variants in SMC3 were nonpenetrant for growth, developmental, and/or dysmorphic features, and some had alternative symptomatologies with rational biological links to SMC3. Analyses of tumor and model system transcriptomic data and epigenetic data in a subset of cases suggest that SMC3 pLoF variants reduce SMC3 expression but do not strongly support clustering with functional genomic signatures of typical CdLS. Our finding of substantial population-scale LoF intolerance in concert with variable growth and developmental features in subjects with SMC3 pLoF variants expands the scope of cohesinopathies, informs on their allelic architecture, and suggests the existence of additional clearly LoF-constrained genes whose disease links will be confirmed only by multilayered genomic data paired with careful phenotyping.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38359823,

title = {C19ORF84 connects piRNA and DNA methylation machineries to defend the mammalian germ line},

author = {Ansgar Zoch and Gabriela Konieczny and Tania Auchynnikava and Birgit Stallmeyer and Nadja Rotte and Madeleine Heep and Rebecca V Berrens and Martina Schito and Yuka Kabayama and Theresa Schöpp and Sabine Kliesch and Brendan Houston and Liina Nagirnaja and Moira K O'Bryan and Kenneth I Aston and Donald F Conrad and Juri Rappsilber and Robin C Allshire and Atlanta G Cook and Frank Tüttelmann and Dónal O'Carroll},

doi = {10.1016/j.molcel.2024.01.014},

issn = {1097-4164},

year  = {2024},

date = {2024-03-01},

journal = {Mol Cell},

volume = {84},

number = {6},

pages = {1021--1035.e11},

abstract = {In the male mouse germ line, PIWI-interacting RNAs (piRNAs), bound by the PIWI protein MIWI2 (PIWIL4), guide DNA methylation of young active transposons through SPOCD1. However, the underlying mechanisms of SPOCD1-mediated piRNA-directed transposon methylation and whether this pathway functions to protect the human germ line remain unknown. We identified loss-of-function variants in human SPOCD1 that cause defective transposon silencing and male infertility. Through the analysis of these pathogenic alleles, we discovered that the uncharacterized protein C19ORF84 interacts with SPOCD1. DNMT3C, the DNA methyltransferase responsible for transposon methylation, associates with SPOCD1 and C19ORF84 in fetal gonocytes. Furthermore, C19ORF84 is essential for piRNA-directed DNA methylation and male mouse fertility. Finally, C19ORF84 mediates the in vivo association of SPOCD1 with the de novo methylation machinery. In summary, we have discovered a conserved role for the human piRNA pathway in transposon silencing and C19ORF84, an uncharacterized protein essential for orchestrating piRNA-directed DNA methylation.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37723288,

title = {Improved phenotypic classification of male infertility to promote discovery of genetic causes},

author = {Margot J Wyrwoll and Godfried W van der Heijden and Csilla Krausz and Kenneth I Aston and Sabine Kliesch and Robert McLachlan and Liliana Ramos and Donald F Conrad and Moira K O'Bryan and Joris A Veltman and Frank Tüttelmann},

doi = {10.1038/s41585-023-00816-0},

issn = {1759-4820},

year  = {2024},

date = {2024-02-01},

journal = {Nat Rev Urol},

volume = {21},

number = {2},

pages = {91--101},

abstract = {An increasing number of genes are being described in the context of non-syndromic male infertility. Linking the underlying genetic causes of non-syndromic male infertility with clinical data from patients is important to establish new genotype-phenotype correlations. This process can be facilitated by using universal nomenclature, but no standardized vocabulary is available in the field of non-syndromic male infertility. The International Male Infertility Genomics Consortium aimed at filling this gap, providing a standardized vocabulary containing nomenclature based on the Human Phenotype Ontology (HPO). The "HPO tree" was substantially revised compared with the previous version and is based on the clinical work-up of infertile men, including physical examination and hormonal assessment. Some causes of male infertility can already be suspected based on the patient's clinical history, whereas in other instances, a testicular biopsy is needed for diagnosis. We assembled 49 HPO terms that are linked in a logical hierarchy and showed examples of morphological features of spermatozoa and testicular histology of infertile men with identified genetic diagnoses to describe the phenotypes. This work will help to record patients' phenotypes systematically and facilitate communication between geneticists and andrologists. Collaboration across institutions will improve the identification of patients with the same phenotypes, which will promote the discovery of novel genetic causes for non-syndromic male infertility.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38654924,

title = {Undiagnosed RASopathies in infertile men},

author = {Anna-Grete Juchnewitsch and Kristjan Pomm and Avirup Dutta and Erik Tamp and Anu Valkna and Kristiina Lillepea and Eisa Mahyari and Stanislav Tjagur and Galina Belova and Viljo Kübarsepp and Helen Castillo-Madeen and Antoni Riera-Escamilla and Lisanna Põlluaas and Liina Nagirnaja and Olev Poolamets and Vladimir Vihljajev and Mailis Sütt and Nassim Versbraegen and Sofia Papadimitriou and Robert I McLachlan and Keith A Jarvi and Peter N Schlegel and Sven Tennisberg and Paul Korrovits and Katinka Vigh-Conrad and Moira K O'Bryan and Kenneth I Aston and Tom Lenaerts and Donald F Conrad and Laura Kasak and Margus Punab and Maris Laan},

doi = {10.3389/fendo.2024.1312357},

issn = {1664-2392},

year  = {2024},

date = {2024-01-01},

journal = {Front Endocrinol (Lausanne)},

volume = {15},

pages = {1312357},

abstract = {RASopathies are syndromes caused by congenital defects in the Ras/mitogen-activated protein kinase (MAPK) pathway genes, with a population prevalence of 1 in 1,000. Patients are typically identified in childhood based on diverse characteristic features, including cryptorchidism (CR) in >50% of affected men. As CR predisposes to spermatogenic failure (SPGF; total sperm count per ejaculate 0-39 million), we hypothesized that men seeking infertility management include cases with undiagnosed RASopathies. Likely pathogenic or pathogenic (LP/P) variants in 22 RASopathy-linked genes were screened in 521 idiopathic SPGF patients (including 155 CR cases) and 323 normozoospermic controls using exome sequencing. All 844 men were recruited to the ESTonian ANDrology (ESTAND) cohort and underwent identical andrological phenotyping. RASopathy-specific variant interpretation guidelines were used for pathogenicity assessment. LP/P variants were identified in  (two),  (three),  (one),  (one),  (one),  (one), and  (one). The findings affected six of 155 cases with CR and SPGF, three of 366 men with SPGF only, and one (of 323) normozoospermic subfertile man. The subgroup "CR and SPGF" had over 13-fold enrichment of findings compared to controls (3.9%  0.3%; Fisher's exact test,  = 5.5 × 10). All ESTAND subjects with LP/P variants in the Ras/MAPK pathway genes presented congenital genitourinary anomalies, skeletal and joint conditions, and other RASopathy-linked health concerns. Rare forms of malignancies (schwannomatosis and pancreatic and testicular cancer) were reported on four occasions. The Genetics of Male Infertility Initiative (GEMINI) cohort (1,416 SPGF cases and 317 fertile men) was used to validate the outcome. LP/P variants in  (three),  (three), and  (one) were identified in six SPGF cases (including 4/31 GEMINI cases with CR) and one normozoospermic man. Undiagnosed RASopathies were detected in total for 17 ESTAND and GEMINI subjects, 15 SPGF patients (10 with CR), and two fertile men. Affected RASopathy genes showed high expression in spermatogenic and testicular somatic cells. In conclusion, congenital defects in the Ras/MAPK pathway genes represent a new congenital etiology of syndromic male infertility. Undiagnosed RASopathies were especially enriched among patients with a history of cryptorchidism. Given the relationship between RASopathies and other conditions, infertile men found to have this molecular diagnosis should be evaluated for known RASopathy-linked health concerns, including specific rare malignancies.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37937809,

title = {Deleterious genetic changes in AGTPBP1 result in teratozoospermia with sperm head and flagella defects},

author = {Yu-Hua Lin and Ya-Yun Wang and Tsung-Hsuan Lai and Jih-Lung Teng and Chi-Wei Lin and Chih-Chun Ke and I-Shing Yu and Hui-Ling Lee and Chying-Chyuan Chan and Chi-Hua Tung and Donald F Conrad and Moira K O'Bryan and Ying-Hung Lin},

doi = {10.1111/jcmm.18031},

issn = {1582-4934},

year  = {2024},

date = {2024-01-01},

journal = {J Cell Mol Med},

volume = {28},

number = {2},

pages = {e18031},

abstract = {Approximately 10%-15% of couples worldwide are infertile, and male factors account for approximately half of these cases. Teratozoospermia is a major cause of male infertility. Although various mutations have been identified in teratozoospermia, these can vary among ethnic groups. In this study, we performed whole-exome sequencing to identify genetic changes potentially causative of teratozoospermia. Out of seven genes identified, one, ATP/GTP Binding Protein 1 (AGTPBP1), was characterized, and three missense changes were identified in two patients (Affected A: p.Glu423Asp and p.Pro631Leu; Affected B: p.Arg811His). In those two cases, severe sperm head and tail defects were observed. Moreover, AGTPBP1 localization showed a fragmented pattern compared to control participants, with specific localization in the neck and annulus regions. Using murine models, we found that AGTPBP1 is localized in the manchette structure, which is essential for sperm structure formation. Additionally, in Agtpbp1-null mice, we observed sperm head and tail defects similar to those in sperm from AGTPBP1-mutated cases, along with abnormal polyglutamylation tubulin and decreasing △-2 tubulin levels. In this study, we established a link between genetic changes in AGTPBP1 and human teratozoospermia for the first time and identified the role of AGTPBP1 in deglutamination, which is crucial for sperm formation.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38073178,

title = {Genome sequencing of Pakistani families with male infertility identifies deleterious genotypes in SPAG6, CCDC9, TKTL1, TUBA3C, and M1AP},

author = {Muhammad Riaz Khan and Arvand Akbari and Thomas J Nicholas and Helen Castillo-Madeen and Muhammad Ajmal and Taqweem Ul Haq and Maris Laan and Aaron R Quinlan and Jasvinder S Ahuja and Aftab Ali Shah and Donald F Conrad},

doi = {10.1111/andr.13570},

issn = {2047-2927},

year  = {2023},

date = {2023-12-01},

urldate = {2023-12-01},

journal = {Andrology},

abstract = {BACKGROUND: There are likely to be hundreds of monogenic forms of human male infertility. Whole genome sequencing (WGS) is the most efficient way to make progress in mapping the causative genetic variants, and ultimately improve clinical management of the disease in each patient. Recruitment of consanguineous families is an effective approach to ascertain the genetic forms of many diseases.nnOBJECTIVES: To apply WGS to large consanguineous families with likely hereditary male infertility and identify potential genetic cases.nnMATERIALS AND METHODS: We recruited seven large families with clinically diagnosed male infertility from rural Pakistan, including five with a history of consanguinity. We generated WGS data on 26 individuals (3-5 per family) and analyzed the resulting data with a computational pipeline to identify potentially causal single nucleotide variants, indels, and copy number variants.nnRESULTS: We identified plausible genetic causes in five of the seven families, including a homozygous 10 kb deletion of exon 2 in a well-established male infertility gene (M1AP), and biallelic missense substitutions (SPAG6, CCDC9, TUBA3C) and an in-frame hemizygous deletion (TKTL1) in genes with emerging relevance.nnDISCUSSION AND CONCLUSION: The rate of genetic findings using the current approach (71%) was much higher than what we recently achieved using whole-exome sequencing (WES) of unrelated singleton cases (20%). Furthermore, we identified a pathogenic single-exon deletion in M1AP that would be undetectable by WES. Screening more families with WGS, especially in underrepresented populations, will further reveal the types of variants underlying male infertility and accelerate the use of genetics in the patient management.},

keywords = {GEMINI, Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid38062027,

title = {TAD evolutionary and functional characterization reveals diversity in mammalian TAD boundary properties and function},

author = {Mariam Okhovat and Jake VanCampen and Kimberly A Nevonen and Lana Harshman and Weiyu Li and Cora E Layman and Samantha Ward and Jarod Herrera and Jackson Wells and Rory R Sheng and Yafei Mao and Blaise Ndjamen and Ana C Lima and Katinka A Vigh-Conrad and Alexandra M Stendahl and Ran Yang and Lev Fedorov and Ian R Matthews and Sarah A Easow and Dylan K Chan and Taha A Jan and Evan E Eichler and Sandra Rugonyi and Donald F Conrad and Nadav Ahituv and Lucia Carbone},

doi = {10.1038/s41467-023-43841-8},

issn = {2041-1723},

year  = {2023},

date = {2023-12-01},

urldate = {2023-12-01},

journal = {Nat Commun},

volume = {14},

number = {1},

pages = {8111},

abstract = {Topological associating domains (TADs) are self-interacting genomic units crucial for shaping gene regulation patterns. Despite their importance, the extent of their evolutionary conservation and its functional implications remain largely unknown. In this study, we generate Hi-C and ChIP-seq data and compare TAD organization across four primate and four rodent species and characterize the genetic and epigenetic properties of TAD boundaries in correspondence to their evolutionary conservation. We find 14% of all human TAD boundaries to be shared among all eight species (ultraconserved), while 15% are human-specific. Ultraconserved TAD boundaries have stronger insulation strength, CTCF binding, and enrichment of older retrotransposons compared to species-specific boundaries. CRISPR-Cas9 knockouts of an ultraconserved boundary in a mouse model lead to tissue-specific gene expression changes and morphological phenotypes. Deletion of a human-specific boundary near the autism-related AUTS2 gene results in the upregulation of this gene in neurons. Overall, our study provides pertinent TAD boundary evolutionary conservation annotations and showcases the functional importance of TAD evolution.},

keywords = {NHP Genetics},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37984997,

title = {A naturally occurring variant of  causes maternal germline hypermutation in primates},

author = {Alexandra M Stendahl and Rashesh Sanghvi and Samuel Peterson and Karina Ray and Ana C Lima and Raheleh Rahbari and Donald F Conrad},

doi = {10.1101/gr.277977.123},

issn = {1549-5469},

year  = {2023},

date = {2023-12-01},

journal = {Genome Res},

volume = {33},

number = {12},

pages = {2053--2059},

abstract = {As part of an ongoing genome sequencing project at the Oregon National Primate Research Center, we identified a rhesus macaque with a rare homozygous frameshift mutation in the gene methyl-CpG binding domain 4, DNA glycosylase (). MBD4 is responsible for the repair of C > T deamination mutations at CpG dinucleotides and has been linked to somatic hypermutation and cancer predisposition in humans. We show here that MBD4-associated hypermutation also affects the germline: The six offspring of the -null dam have a fourfold to sixfold increase in de novo mutation burden. This excess burden was predominantly C > T mutations at CpG dinucleotides consistent with  loss of function in the dam. There was also a significant excess of C > T at CpA sites, indicating an important, unappreciated role for MBD4 to repair deamination in CpA contexts. The -null dam developed sustained eosinophilia later in life, but we saw no other signs of neoplastic processes associated with  loss of function in humans nor any obvious disease in the hypermutated offspring. This work provides the first evidence for a genetic factor causing hypermutation in the maternal germline of a mammal and adds to the very small list of naturally occurring variants known to modulate germline mutation rates in mammals.},

keywords = {NHP Genetics},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37244752,

title = {Rhesus macaque fetal and placental growth demographics: A resource for laboratory animal researchers},

author = {Victoria H J Roberts and Jenna N Castro and Brady M Wessel and Donald F Conrad and Anne D Lewis and Jamie O Lo},

doi = {10.1002/ajp.23526},

issn = {1098-2345},

year  = {2023},

date = {2023-08-01},

urldate = {2023-08-01},

journal = {Am J Primatol},

volume = {85},

number = {8},

pages = {e23526},

abstract = {Rhesus macaques (Macaca mulatta) are amongst the most common nonhuman primate species used in biomedical research. These animals provide a precious resource for translational studies and opportunities to maximize rhesus data use are encouraged. Here we compile data produced from 10 years of investigator-driven pregnancy studies conducted at the Oregon National Primate Research Center (ONPRC). All pregnancies were generated within the consistent and reproducible protocols of the ONPRC time-mated breeding program. The data included are from control animals who did not experience in utero perturbations or experimental manipulations. A total of 86 pregnant rhesus macaques were delivered by cesarean section over a range of gestational days (G) 50 to G159 (where term is G165 ± 10 days in the rhesus macaque), with subsequent immediate tissue harvesting following standardized protocols. Fetal and placental growth measures, and all major organ weights are reported. All data are presented relative to gestational age for the entire cohort and in addition, data are stratified by fetal sex. The outcome is a large reference resource for use by laboratory animal researchers in future comparative fetal development studies.},

keywords = {NHP Genetics},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37459509,

title = {In vivo versus in silico assessment of potentially pathogenic missense variants in human reproductive genes},

author = {Xinbao Ding and Priti Singh and Kerry Schimenti and Tina N Tran and Robert Fragoza and Jimmaline Hardy and Kyle E Orwig and Marta Olszewska and Maciej K Kurpisz and Alexander N Yatsenko and Donald F Conrad and Haiyuan Yu and John C Schimenti},

doi = {10.1073/pnas.2219925120},

issn = {1091-6490},

year  = {2023},

date = {2023-07-01},

journal = {Proc Natl Acad Sci U S A},

volume = {120},

number = {30},

pages = {e2219925120},

abstract = {Infertility is a heterogeneous condition, with genetic causes thought to underlie a substantial fraction of cases. Genome sequencing is becoming increasingly important for genetic diagnosis of diseases including idiopathic infertility; however, most rare or minor alleles identified in patients are variants of uncertain significance (VUS). Interpreting the functional impacts of VUS is challenging but profoundly important for clinical management and genetic counseling. To determine the consequences of these variants in key fertility genes, we functionally evaluated 11 missense variants in the genes , , ,  and  by generating genome-edited mouse models. Nine variants were classified as deleterious by most functional prediction algorithms, and two disrupted a protein-protein interaction (PPI) in the yeast two hybrid (Y2H) assay. Though these genes are essential for normal meiosis or spermiogenesis in mice, only one variant, observed in the  gene of a male infertility patient, compromised fertility or gametogenesis in the mouse models. To explore the disconnect between predictions and outcomes, we compared pathogenicity calls of missense variants made by ten widely used algorithms to 1) those annotated in ClinVar and 2) those evaluated in mice. All the algorithms performed poorly in terms of predicting the effects of human missense variants modeled in mice. These studies emphasize caution in the genetic diagnoses of infertile patients based primarily on pathogenicity prediction algorithms and emphasize the need for alternative and efficient in vitro or in vivo functional validation models for more effective and accurate VUS description to either pathogenic or benign categories.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37267208,

title = {Consensus label propagation with graph convolutional networks for single-cell RNA sequencing cell type annotation},

author = {Daniel P Lewinsohn and Katinka A Vigh-Conrad and Donald F Conrad and Cory B Scott},

doi = {10.1093/bioinformatics/btad360},

issn = {1367-4811},

year  = {2023},

date = {2023-06-01},

urldate = {2023-06-01},

journal = {Bioinformatics},

volume = {39},

number = {6},

abstract = {MOTIVATION: Single-cell RNA sequencing (scRNA-seq) data, annotated by cell type, is useful in a variety of downstream biological applications, such as profiling gene expression at the single-cell level. However, manually assigning these annotations with known marker genes is both time-consuming and subjective.nnRESULTS: We present a Graph Convolutional Network (GCN)-based approach to automate the annotation process. Our process builds upon existing labeling approaches, using state-of-the-art tools to find cells with highly confident label assignments through consensus and spreading these confident labels with a semi-supervised GCN. Using simulated data and two scRNA-seq datasets from different tissues, we show that our method improves accuracy over a simple consensus algorithm and the average of the underlying tools. We also compare our method to a nonparametric neighbor majority approach, showing comparable results. We then demonstrate that our GCN method allows for feature interpretation, identifying important genes for cell type classification. We present our completed pipeline, written in PyTorch, as an end-to-end tool for automating and interpreting the classification of scRNA-seq data.nnAVAILABILITY AND IMPLEMENTATION: Our code for conducting the experiments in this paper and using our model is available at https://github.com/lewinsohndp/scSHARP.},

keywords = {Single Cell Genomics},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37053313,

title = {The origins and functional effects of postzygotic mutations throughout the human life span},

author = {Nicole B Rockweiler and Avinash Ramu and Liina Nagirnaja and Wing H Wong and Michiel J Noordam and Casey W Drubin and Ni Huang and Brian Miller and Ellen Z Todres and Katinka A Vigh-Conrad and Antonino Zito and Kerrin S Small and Kristin G Ardlie and Barak A Cohen and Donald F Conrad},

doi = {10.1126/science.abn7113},

issn = {1095-9203},

year  = {2023},

date = {2023-04-01},

urldate = {2023-04-01},

journal = {Science},

volume = {380},

number = {6641},

pages = {eabn7113},

abstract = {Postzygotic mutations (PZMs) begin to accrue in the human genome immediately after fertilization, but how and when PZMs affect development and lifetime health remain unclear. To study the origins and functional consequences of PZMs, we generated a multitissue atlas of PZMs spanning 54 tissue and cell types from 948 donors. Nearly half the variation in mutation burden among tissue samples can be explained by measured technical and biological effects, and 9% can be attributed to donor-specific effects. Through phylogenetic reconstruction of PZMs, we found that their type and predicted functional impact vary during prenatal development, across tissues, and through the germ cell life cycle. Thus, methods for interpreting effects across the body and the life span are needed to fully understand the consequences of genetic variants.},

keywords = {Genomic Variation},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36997603,

title = {DDX3Y is likely the key spermatogenic factor in the AZFa region that contributes to human non-obstructive azoospermia},

author = {Ann-Kristin Dicke and Adrian Pilatz and Margot J Wyrwoll and Margus Punab and Christian Ruckert and Liina Nagirnaja and Kenneth I Aston and Donald F Conrad and Sara Di Persio and Nina Neuhaus and Daniela Fietz and Maris Laan and Birgit Stallmeyer and Frank Tüttelmann},

doi = {10.1038/s42003-023-04714-4},

issn = {2399-3642},

year  = {2023},

date = {2023-03-01},

journal = {Commun Biol},

volume = {6},

number = {1},

pages = {350},

abstract = {Non-obstructive azoospermia, the absence of sperm in the ejaculate due to disturbed spermatogenesis, represents the most severe form of male infertility. De novo microdeletions of the Y-chromosomal AZFa region are one of few well-established genetic causes for NOA and are routinely analysed in the diagnostic workup of affected men. So far, it is unclear which of the three genes located in the AZFa chromosomal region is indispensible for germ cell maturation. Here we present four different likely pathogenic loss-of-function variants in the AZFa gene DDX3Y identified by analysing exome sequencing data of more than 1,600 infertile men. Three of the patients underwent testicular sperm extraction and revealed the typical AZFa testicular Sertoli cell-only phenotype. One of the variants was proven to be de novo. Consequently, DDX3Y represents the AZFa key spermatogenic factor and screening for variants in DDX3Y should be included in the diagnostic workflow.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37234866,

title = {Genomic study of  variants: prevalence and allelic heterogeneity in men with spermatogenic failure},

author = {Sidra Qureshi and Jimmaline J Hardy and Christopher Pombar and Andrea J Berman and Agnieszka Malcher and Tara Gingrich and Rachel Hvasta and Jannah Kuong and Sarah Munyoki and Kathleen Hwang and Kyle E Orwig and Jawad Ahmed and Marta Olszewska and Maciej Kurpisz and Donald F Conrad and Muhammad Jaseem Khan and Alexander N Yatsenko},

doi = {10.3389/fgene.2023.1134849},

issn = {1664-8021},

year  = {2023},

date = {2023-01-01},

journal = {Front Genet},

volume = {14},

pages = {1134849},

abstract = { Human spermatogenesis is a highly intricate process that requires the input of thousands of testis-specific genes. Defects in any of them at any stage of the process can have detrimental effects on sperm production and/or viability. In particular, the function of many meiotic proteins encoded by germ cell specific genes is critical for maturation of haploid spermatids and viable spermatozoa, necessary for fertilization, and is also extremely sensitive to even the slightest change in coding DNA.  Here, using whole exome and genome approaches, we identified and reported novel, clinically significant variants in testis-expressed gene 15 (), in unrelated men with spermatogenic failure (SPGF).  TEX15 mediates double strand break repair during meiosis. Recessive loss-of-function (LOF)  mutations are associated with SPGF in humans and knockout male mice are infertile. We expand earlier reports documenting heterogeneous allelic pathogenic  variants that cause a range of SPGF phenotypes from oligozoospermia (low sperm) to nonobstructive azoospermia (no sperm) with meiotic arrest and report the prevalence of 0.6% of  variants in our patient cohort. Among identified possible LOF variants, one homozygous missense substitution c.6835G>A (p.Ala2279Thr) co-segregated with cryptozoospermia in a family with SPGF. Additionally, we observed numerous cases of inferred  compound heterozygous variants in  among unrelated individuals with varying degrees of SPGF. Variants included splice site, insertions/deletions (indels), and missense substitutions, many of which resulted in LOF effects (i.e., frameshift, premature stop, alternative splicing, or potentially altered posttranslational modification sites).  In conclusion, we performed an extensive genomic study of familial and sporadic SPGF and identified potentially damaging TEX15 variants in 7 of 1097 individuals of our combined cohorts. We hypothesize that SPGF phenotype severity is dictated by individual  variant's impact on structure and function. Resultant LOFs likely have deleterious effects on crossover/recombination in meiosis. Our findings support the notion of increased gene variant frequency in SPGF and its genetic and allelic heterogeneity as it relates to complex disease such as male infertility.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36572685,

title = {Diverse monogenic subforms of human spermatogenic failure},

author = {Liina Nagirnaja and Alexandra M Lopes and Wu-Lin Charng and Brian Miller and Rytis Stakaitis and Ieva Golubickaite and Alexandra Stendahl and Tianpengcheng Luan and Corinna Friedrich and Eisa Mahyari and Eloise Fadial and Laura Kasak and Katinka Vigh-Conrad and Manon S Oud and Miguel J Xavier and Samuel R Cheers and Emma R James and Jingtao Guo and Timothy G Jenkins and Antoni Riera-Escamilla and Alberto Barros and Filipa Carvalho and Susana Fernandes and João Gonçalves and Christina A Gurnett and Niels Jørgensen and Davor Jezek and Emily S Jungheim and Sabine Kliesch and Robert I McLachlan and Kenan R Omurtag and Adrian Pilatz and Jay I Sandlow and James Smith and Michael L Eisenberg and James M Hotaling and Keith A Jarvi and Margus Punab and Ewa Rajpert-De Meyts and Douglas T Carrell and Csilla Krausz and Maris Laan and Moira K O'Bryan and Peter N Schlegel and Frank Tüttelmann and Joris A Veltman and Kristian Almstrup and Kenneth I Aston and Donald F Conrad},

doi = {10.1038/s41467-022-35661-z},

issn = {2041-1723},

year  = {2022},

date = {2022-12-01},

urldate = {2022-12-01},

journal = {Nat Commun},

volume = {13},

number = {1},

pages = {7953},

abstract = {Non-obstructive azoospermia (NOA) is the most severe form of male infertility and typically incurable. Defining the genetic basis of NOA has proven challenging, and the most advanced classification of NOA subforms is not based on genetics, but simple description of testis histology. In this study, we exome-sequenced over 1000 clinically diagnosed NOA cases and identified a plausible recessive Mendelian cause in 20%. We find further support for 21 genes in a 2-stage burden test with 2072 cases and 11,587 fertile controls. The disrupted genes are primarily on the autosomes, enriched for undescribed human "knockouts", and, for the most part, have yet to be linked to a Mendelian trait. Integration with single-cell RNA sequencing data shows that azoospermia genes can be grouped into molecular subforms with synchronized expression patterns, and analogs of these subforms exist in mice. This analysis framework identifies groups of genes with known roles in spermatogenesis but also reveals unrecognized subforms, such as a set of genes expressed across mitotic divisions of differentiating spermatogonia. Our findings highlight NOA as an understudied Mendelian disorder and provide a conceptual structure for organizing the complex genetics of male infertility, which may provide a rational basis for disease classification.},

keywords = {GEMINI, Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36214638,

title = {SATINN: an automated neural network-based classification of testicular sections allows for high-throughput histopathology of mouse mutants},

author = {Ran Yang and Alexandra M Stendahl and Katinka A Vigh-Conrad and Madison Held and Ana C Lima and Donald F Conrad},

doi = {10.1093/bioinformatics/btac673},

issn = {1367-4811},

year  = {2022},

date = {2022-11-01},

urldate = {2022-11-01},

journal = {Bioinformatics},

volume = {38},

number = {23},

pages = {5288--5298},

abstract = {MOTIVATION: The mammalian testis is a complex organ with a cellular composition that changes smoothly and cyclically in normal adults. While testis histology is already an invaluable tool for identifying and describing developmental differences in evolution and disease, methods for standardized, digital image analysis of testis are needed to expand the utility of this approach.nnRESULTS: We developed SATINN (Software for Analysis of Testis Images with Neural Networks), a multi-level framework for automated analysis of multiplexed immunofluorescence images from mouse testis. This approach uses residual learning to train convolutional neural networks (CNNs) to classify nuclei from seminiferous tubules into seven distinct cell types with an accuracy of 81.7%. These cell classifications are then used in a second-level tubule CNN, which places seminiferous tubules into one of 12 distinct tubule stages with 57.3% direct accuracy and 94.9% within ±1 stage. We further describe numerous cell- and tubule-level statistics that can be derived from wild-type testis. Finally, we demonstrate how the classifiers and derived statistics can be used to rapidly and precisely describe pathology by applying our methods to image data from two mutant mouse lines. Our results demonstrate the feasibility and potential of using computer-assisted analysis for testis histology, an area poised to evolve rapidly on the back of emerging, spatially resolved genomic and proteomic technologies.nnAVAILABILITY AND IMPLEMENTATION: The source code to reproduce the results described here and a SATINN standalone application with graphic-user interface are available from http://github.com/conradlab/SATINN.nnSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},

keywords = {Human Reproduction},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36150389,

title = {The piRNA-pathway factor FKBP6 is essential for spermatogenesis but dispensable for control of meiotic LINE-1 expression in humans},

author = {Margot J Wyrwoll and Channah M Gaasbeek and Ieva Golubickaite and Rytis Stakaitis and Manon S Oud and Liina Nagirnaja and Camille Dion and Emad B Sindi and Harry G Leitch and Channa N Jayasena and Anu Sironen and Ann-Kristin Dicke and Nadja Rotte and Birgit Stallmeyer and Sabine Kliesch and Carlos H P Grangeiro and Thaís F Araujo and Paul Lasko and  and Kathleen D'Hauwers and Roos M Smits and Liliana Ramos and Miguel J Xavier and Don F Conrad and Kristian Almstrup and Joris A Veltman and Frank Tüttelmann and Godfried W van der Heijden},

doi = {10.1016/j.ajhg.2022.09.002},

issn = {1537-6605},

year  = {2022},

date = {2022-10-01},

journal = {Am J Hum Genet},

volume = {109},

number = {10},

pages = {1850--1866},

abstract = {Infertility affects around 7% of the male population and can be due to severe spermatogenic failure (SPGF), resulting in no or very few sperm in the ejaculate. We initially identified a homozygous frameshift variant in FKBP6 in a man with extreme oligozoospermia. Subsequently, we screened a total of 2,699 men with SPGF and detected rare bi-allelic loss-of-function variants in FKBP6 in five additional persons. All six individuals had no or extremely few sperm in the ejaculate, which were not suitable for medically assisted reproduction. Evaluation of testicular tissue revealed an arrest at the stage of round spermatids. Lack of FKBP6 expression in the testis was confirmed by RT-qPCR and immunofluorescence staining. In mice, Fkbp6 is essential for spermatogenesis and has been described as being involved in piRNA biogenesis and formation of the synaptonemal complex (SC). We did not detect FKBP6 as part of the SC in normal human spermatocytes, but small RNA sequencing revealed that loss of FKBP6 severely impacted piRNA levels, supporting a role for FKBP6 in piRNA biogenesis in humans. In contrast to findings in piRNA-pathway mouse models, we did not detect an increase in LINE-1 expression in men with pathogenic FKBP6 variants. Based on our findings, FKBP6 reaches a "strong" level of evidence for being associated with male infertility according to the ClinGen criteria, making it directly applicable for clinical diagnostics. This will improve patient care by providing a causal diagnosis and will help to predict chances for successful surgical sperm retrieval.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid35850260,

title = {DDB1- and CUL4-associated factor 12-like protein 1 (Dcaf12l1) is not essential for male fertility in mice},

author = {Brendan J Houston and Alexandra M Lopes and Maris Laan and Liina Nagirnaja and Anne E O'Connor and D Jo Merriner and Joseph Nguyen and Margus Punab and Antoni Riera-Escamilla and Csilla Krausz and Kenneth Ivan Aston and Donald F Conrad and Moira K O'Bryan},

doi = {10.1016/j.ydbio.2022.07.006},

issn = {1095-564X},

year  = {2022},

date = {2022-10-01},

journal = {Dev Biol},

volume = {490},

pages = {66--72},

abstract = {Male infertility is a common condition affecting at least 7% of men worldwide and is often genetic in origin. Using whole exome sequencing, we recently discovered three hemizygous, likely damaging variants in DDB1- and CUL4-associated factor 12-like protein 1 (DCAF12L1) in men with azoospermia. DCAF12L1 is located on the X-chromosome and as identified by single cell sequencing studies, its expression is enriched in human testes and specifically in Sertoli cells and spermatogonia. However, very little is known about the role of DCAF12L1 in spermatogenesis, thus we generated a knockout mouse model to further explore the role of DCAF12L1 in male fertility. Knockout mice were generated using CRISPR/Cas9 technology to remove the entire coding region of Dcaf12l1 and were assessed for fertility over a broad range of ages (2-8 months of age). Despite outstanding genetic evidence in men, loss of DCAF12L1 had no discernible impact on male fertility in mice, as highlighted by breeding trials, histological assessment of the testis and epididymis, daily sperm production and evaluation of sperm motility using computer assisted methods. This disparity is likely due to the parallel evolution, and subsequent divergence, of DCAF12 family members in mice and men or the presence of compounding environmental factors in men.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid35679955,

title = {Zinc finger RNA binding protein 2 (ZFR2) is not required for male fertility in the mouse},

author = {Lachlan M Cauchi and Brendan J Houston and Liina Nagirnaja and Anne E O'Connor and D Jo Merriner and Kenneth I Aston and Peter N Schlegel and Don F Conrad and Richard Burke and Moira K O'Bryan},

doi = {10.1016/j.ydbio.2022.05.020},

issn = {1095-564X},

year  = {2022},

date = {2022-09-01},

journal = {Dev Biol},

volume = {489},

pages = {55--61},

abstract = {BACKGROUND: Thousands of genes are expressed during spermatogenesis and male infertility has a strong genetic component. Within this study, we focus on the role of Zfr2 in male fertility, a gene previously implicated in human male fertility. To date, very little is known about the role of ZFR2 in either humans or mice. To this end, the requirement for ZFR2 in male fertility was assessed using a knockout mouse model.nnRESULTS: Zfr2 was found to be expressed in the testes of both humans and mice. Deletion of Zfr2 was achieved via removal of exon 2 using CRISPR-Cas9 methods. The absence of Zfr2 did not result in a reduction in any fertility parameters assessed. Knockout males were capable of fostering litter sizes equal to wild type males, and there were no effects of Zfr2 knockout on sperm number or motility. We note Zfr2 knockout females were also fertile.nnCONCLUSIONS: The absence of Zfr2 alone is not sufficient to cause a reduction in male fertility in mice.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid35809576,

title = {Large-scale analyses of the X chromosome in 2,354 infertile men discover recurrently affected genes associated with spermatogenic failure},

author = {Antoni Riera-Escamilla and Matthias Vockel and Liina Nagirnaja and Miguel J Xavier and Albert Carbonell and Daniel Moreno-Mendoza and Marc Pybus and Ginevra Farnetani and Viktoria Rosta and Francesca Cioppi and Corinna Friedrich and Manon S Oud and Godfried W van der Heijden and Armin Soave and Thorsten Diemer and Elisabet Ars and Josvany Sánchez-Curbelo and Sabine Kliesch and Moira K O'Bryan and Eduard Ruiz-Castañe and  and Fernando Azorín and Joris A Veltman and Kenneth I Aston and Donald F Conrad and Frank Tüttelmann and Csilla Krausz},

doi = {10.1016/j.ajhg.2022.06.007},

issn = {1537-6605},

year  = {2022},

date = {2022-08-01},

journal = {Am J Hum Genet},

volume = {109},

number = {8},

pages = {1458--1471},

abstract = {Although the evolutionary history of the X chromosome indicates its specialization in male fitness, its role in spermatogenesis has largely been unexplored. Currently only three X chromosome genes are considered of moderate-definitive diagnostic value. We aimed to provide a comprehensive analysis of all X chromosome-linked protein-coding genes in 2,354 azoospermic/cryptozoospermic men from four independent cohorts. Genomic data were analyzed and compared with data in normozoospermic control individuals and gnomAD. While updating the clinical significance of known genes, we propose 21 recurrently mutated genes strongly associated with and 34 moderately associated with azoospermia/cryptozoospermia not previously linked to male infertility (novel). The most frequently affected prioritized gene, RBBP7, was found mutated in ten men across all cohorts, and our functional studies in Drosophila support its role in germ stem cell maintenance. Collectively, our study represents a significant step towards the definition of the missing genetic etiology in idiopathic severe spermatogenic failure and significantly reduces the knowledge gap of X-linked genetic causes of azoospermia/cryptozoospermia contributing to the development of future diagnostic gene panels.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}

@article{pmid35535697,

title = {Actionable secondary findings following exome sequencing of 836 non-obstructive azoospermia cases and their value in patient management},

author = {Laura Kasak and Kristiina Lillepea and Liina Nagirnaja and Kenneth I Aston and Peter N Schlegel and João Gonçalves and Filipa Carvalho and Daniel Moreno-Mendoza and Kristian Almstrup and Michael L Eisenberg and Keith A Jarvi and Moira K O'Bryan and Alexandra M Lopes and Donald F Conrad and  and Margus Punab and Maris Laan},

doi = {10.1093/humrep/deac100},

issn = {1460-2350},

year  = {2022},

date = {2022-06-01},

journal = {Hum Reprod},

volume = {37},

number = {7},

pages = {1652--1663},

abstract = {STUDY QUESTION: What is the load, distribution and added clinical value of secondary findings (SFs) identified in exome sequencing (ES) of patients with non-obstructive azoospermia (NOA)?nnSUMMARY ANSWER: One in 28 NOA cases carried an identifiable, medically actionable SF.nnWHAT IS KNOWN ALREADY: In addition to molecular diagnostics, ES allows assessment of clinically actionable disease-related gene variants that are not connected to the patient's primary diagnosis, but the knowledge of which may allow the prevention, delay or amelioration of late-onset monogenic conditions. Data on SFs in specific clinical patient groups, including reproductive failure, are currently limited.nnSTUDY DESIGN, SIZE, DURATION: The study group was a retrospective cohort of patients with NOA recruited in 10 clinics across six countries and formed in the framework of the international GEMINI (The GEnetics of Male INfertility Initiative) study.nnPARTICIPANTS/MATERIALS, SETTING, METHODS: ES data of 836 patients with NOA were exploited to analyze SFs in 85 genes recommended by the American College of Medical Genetics and Genomics (ACMG), Geisinger's MyCode, and Clinical Genome Resource. The identified 6374 exonic variants were annotated with ANNOVAR and filtered for allele frequency, retaining 1381 rare or novel missense and loss-of-function variants. After automatic assessment of pathogenicity with ClinVar and InterVar, 87 variants were manually curated. The final list of confident disease-causing SFs was communicated to the corresponding GEMINI centers. When patient consent had been given, available family health history and non-andrological medical data were retrospectively assessed.nnMAIN RESULTS AND THE ROLE OF CHANCE: We found a 3.6% total frequency of SFs, 3.3% from the 59 ACMG SF v2.0 genes. One in 70 patients carried SFs in genes linked to familial cancer syndromes, whereas 1 in 60 cases was predisposed to congenital heart disease or other cardiovascular conditions. Retrospective assessment confirmed clinico-molecular diagnoses in several cases. Notably, 37% (11/30) of patients with SFs carried variants in genes linked to male infertility in mice, suggesting that some SFs may have a co-contributing role in spermatogenic impairment. Further studies are needed to determine whether these observations represent chance findings or the profile of SFs in NOA patients is indeed different from the general population.nnLIMITATIONS, REASONS FOR CAUTION: One limitation of our cohort was the low proportion of non-Caucasian ethnicities (9%). Additionally, as comprehensive clinical data were not available retrospectively for all men with SFs, we were not able to confirm a clinico-molecular diagnosis and assess the penetrance of the specific variants.nnWIDER IMPLICATIONS OF THE FINDINGS: For the first time, this study analyzed medically actionable SFs in men with spermatogenic failure. With the evolving process to incorporate ES into routine andrology practice for molecular diagnostic purposes, additional assessment of SFs can inform about future significant health concerns for infertility patients. Timely detection of SFs and respective genetic counseling will broaden options for disease prevention and early treatment, as well as inform choices and opportunities regarding family planning. A notable fraction of SFs was detected in genes implicated in maintaining genome integrity, essential in both mitosis and meiosis. Thus, potential genetic pleiotropy may exist between certain adult-onset monogenic diseases and NOA.nnSTUDY FUNDING/COMPETING INTEREST(S): This work was supported by the Estonian Research Council grants IUT34-12 and PRG1021 (M.L. and M.P.); National Institutes of Health of the United States of America grant R01HD078641 (D.F.C., K.I.A. and P.N.S.); National Institutes of Health of the United States of America grant P50HD096723 (D.F.C. and P.N.S.); National Health and Medical Research Council of Australia grant APP1120356 (M.K.O'B., D.F.C. and K.I.A.); Fundação para a Ciência e a Tecnologia (FCT)/Ministério da Ciência, Tecnologia e Inovação grant POCI-01-0145-FEDER-007274 (A.M.L., F.C. and J.G.) and FCT: IF/01262/2014 (A.M.L.). J.G. was partially funded by FCT/Ministério da Ciência, Tecnologia e Ensino Superior (MCTES), through the Centre for Toxicogenomics and Human Health-ToxOmics (grants UID/BIM/00009/2016 and UIDB/00009/2020). M.L.E. is a consultant for, and holds stock in, Roman, Sandstone, Dadi, Hannah, Underdog and has received funding from NIH/NICHD. Co-authors L.K., K.L., L.N., K.I.A., P.N.S., J.G., F.C., D.M.-M., K.A., K.A.J., M.K.O'B., A.M.L., D.F.C., M.P. and M.L. declare no conflict of interest.nnTRIAL REGISTRATION NUMBER: N/A.},

keywords = {GEMINI},

pubstate = {published},

tppubtype = {article}

}