Publications

@article{Zaeske2026,

title = {Facile generation of Hermes insertion mutants in prototrophic Candida glabrata for use in nutrient-limited environments},

author = {Anna M Zaeske and Abigail A Harrington and Timothy J Nickels and Andrew N Gale and Winston Timp and Nicole Alayo and Yasmine Hassoun and David S Perlin and Erika Shor and Kyle W Cunningham},

url = {https://journals.asm.org/doi/pdf/10.1128/spectrum.00848-26},

doi = {https://doi.org/10.1128/spectrum.00848-26},

year  = {2026},

date = {2026-05-29},

journal = {Microbiology Spectrum},

pages = {e00848-26},

abstract = { Transposon mutagenesis coupled with deep sequencing (Tn-seq) is currently being deployed in microbial eukaryotes, including the opportunistic yeast pathogen Candida glabrata, for functional genomics research. This method depends on the generation of highly diverse pools of transposon insertion mutants to cover all genes while minimizing the presence of markers and remnants of engineering. Up to now, pools of Hermes transposon insertion mutants in C. glabrata were gen erated in uracil-requiring ura3∆ auxotrophs, limiting their use in nutrient-restricted environments, such as those of the host. Indeed, we found that ura3∆ mutants were outcompeted by URA3+ prototrophs during colonization of the mouse gastrointestinal tract. To avoid using auxotrophs in Tn-seq experiments, a new scheme was developed for generating prototrophic pools of Hermes insertion mutants. The scheme involved introducing a recessive cycloheximide resistance mutation in the chromosomal RPL28 gene, which did not alter fitness during mouse colonization. When implemented in several different strains of C. glabrata, high insertion densities were obtained, and differences in subtelomeric chromatin compaction were observed that correlated with natural variation in the silencing gene, SIR3. However, all the strains lacked insertions in the PDR1 and CDR1 genes, which are necessary for resistance to cycloheximide and other antifungals. We directly tested the effect of pdr1∆ mutants and found that they exhibited moderate fitness defects in the gastrointestinal tract of mice even in the absence of antifungals. Thus, the new scheme easily generates high-quality pools of insertion mutants in prototrophic C. glabrata with only minor and knowable limitations.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Xu2026,

title = {Haplotype-resolved centromeric chromatin organization from a complete diploid human genome},

author = {Yuan Xu and Hailey Loucks and Julian Menendez and Fedor Ryabov and Julian K Lucas and Monika Cechova and Luke Morina and Emily Xu and Danilo Dubocanin and Cy Chittenden and Mobin Asri and Ivo Violich and Christian Ortiz and Joshua MV Gardner and Todd Hillaker and Sara O’Rourke and Brandy McNulty and Tamara A Potapova and Matthew W Mitchell and Jacob P Schwartz and Aaron F Straight and Jennifer L Gerton and Winston Timp and Ivan A Alexandrov and Nicolas Altemose and Karen H Miga},

url = {https://www.biorxiv.org/content/10.64898/2026.03.27.714900.full.pdf},

doi = {https://doi.org/10.64898/2026.03.27.714900},

year  = {2026},

date = {2026-03-31},

journal = {bioRxiv},

abstract = {Centromeres ensure proper chromosome segregation during cell division, yet the organization and regulation of centromeric chromatin within satellite DNA arrays remain incompletely understood. Here, we leverage the complete diploid human genome benchmark (T2T-HG002) to provide a detailed study of centromeric sequence and chromatin architecture on individual haplotypes. Using adaptive-sampling-enriched, ultra-long-read DiMeLo-seq, we achieve single-molecule chromatin profiling across all centromeres, revealing that along single chromatin fibers, CENP-A, the histone variant specifying centromere identity, forms multiple discrete subdomains within hypomethylated centromere dip regions (CDRs) that are flanked by H3K9me3-enriched heterochromatin. Despite underlying sequence variation, CDRs localize to sequence-homogeneous domains and maintain relatively balanced CENP-A dosage and aggregate length across all chromosomes and between haplotypes. Further, we show that bidirectional changes to centromeric and pericentromeric DNA methylation are accompanied by changes to centromeric chromatin architecture. In passaged cells with centromeric hypomethylation, subdomain boundaries are eroded, and adjacent CENP-A domains tend to merge and expand. Conversely, in pluripotent stem cells with centromeric hypermethylation, CDRs are fundamentally reorganized, such that discrete hypomethylated domains are frequently consolidated into broader contiguous tracts. These methylation-associated CDR restructuring events suggest that DNA methylation acts as a principal regulator of human centromere organization, with implications for understanding centromere plasticity, epigenetic inheritance, and chromosomal instability in development and disease.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Neale2026,

title = {A reference genome sequence for the exceptionally long-lived Great Basin bristlecone pine, Pinus longaeva},

author = {David B Neale and Aleksey V Zimin and Constance I Millar and Patrick E McGuire and Jessica A Hosea and Edward Li and Daniela Puiu and Winston Timp and Steven L Salzberg},

url = {https://academic.oup.com/g3journal/advance-article-pdf/doi/10.1093/g3journal/jkag064/67384076/jkag064.pdf},

doi = {https://doi.org/10.1093/g3journal/jkag064},

year  = {2026},

date = {2026-03-17},

journal = {G3: Genes, Genomes, Genetics},

volume = {16},

issue = {6},

pages = {jkag064},

abstract = {Great Basin bristlecone pine (Pinus longaeva), one of two species of bristlecone pine, the other being Rocky Mountain bristlecone pine (P. aristata), is endemic to the high Great Basin mountains in eastern California, Nevada, and Utah. It is the upper treeline forest tree in this region, found mostly between 2900 and 3600 m. The primary goal of this project was to generate a reference genome sequence for P. longaeva that, among its many possible applications, will serve as an important genetic resource to better understand the genetic mechanisms underlying its extreme longevity and its adaptation to the extreme environmental conditions where it is found. A combination of short-read and long-read sequences were generated from haploid megagametophyte and diploid needle tissues, respectively. A customized genome assembly approach was used to construct a highly contiguous 23.8-gigabase genome with a scaffold N50 size of 1.2 gigabases. The chloroplast and mitochondrial genomes were assembled separately into circular chromosomes with lengths of 120 kilobases and 8.68 megabases, respectively. While the number of disease resistance genes known as nucleotide-binding leucine-rich repeat receptors (NLRs) and larger-than-average telomere lengths relative to other conifers have been suggested as genetic mechanisms for controlling longevity, we did not find strong evidence for their involvement. Clearly further study is needed.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rudnizky2026,

title = {Chromatin boundary permeability is controlled by CTCF conformational ensembles},

author = {Sergei Rudnizky and Peter J Murray and Emily W Sørensen and Theo_J R Koenig and Sushil Pangeni and Raquel Merino-Urteaga and Hemani Chhabra and Laura Caccianini and Iain F Davidson and Manuel Osorio-Valeriano and Paul W Hook and Paul Meneses and Jingzhou Hao and Jasmin S Zarb and Nikos S Hatzakis and Winston Timp and Lucas Farnung and Seychelle M Vos and Jan-Michael Peters and Aleksei Aksimentiev and Taekjip Ha},

url = {https://par.nsf.gov/servlets/purl/10686249},

doi = {https://doi.org/10.1101/2025.11.25.690553},

year  = {2026},

date = {2026-02-12},

journal = {bioRxiv},

abstract = {Genomes are organized into chromatin loops through cohesin-mediated extrusion, with CTCF acting as a polar boundary element. As cohesin approaches CTCF at kilobase-per-second speeds, it must rapidly choose whether to stall or bypass. How CTCF encodes this probabilistic decision within a brief encounter window has remained unclear. Here we show that CTCF governs this probabilistic outcome by rapidly sampling a dynamic ensemble of conformations generated by spontaneous rearrangements of its DNA-binding zinc fingers. This ensemble is tuned by DNA sequence, CpG methylation, nearby nucleosomes, and the cohesin regulator PDS5A before cohesin engagement. Upon cohesin binding, PDS5A enhances loop-anchor mechanical stability, reinforcing orientation-dependent boundaries. These findings establish conformational ensemble tuning, rather than static occupancy, as a regulatory principle linking base pair-scale motions to megabase-scale genome organization.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Fan2026,

title = {Limited genome evolution of Cryptococcus neoformans following an accidental infection in the research laboratory},

author = {Yunfan Fan and Madhura Kulkarni and Sean X Zhang and Winston Timp and David J Sullivan and Daniel FQ Smith and Arturo Casadevall and J Marie Hardwick},

url = {https://journals.asm.org/doi/10.1128/asmcr.00209-25},

doi = {https://doi.org/10.1128/asmcr.00209-25},

year  = {2026},

date = {2026-02-03},

urldate = {2026-02-03},

journal = {ASM Case Reports},

pages = {e00209-25},

abstract = {Background: Cutaneous infections resulting from accidental exposure to fungal pathogen Cryptococcus neoformans in research laboratories are rarely reported in the literature. To fill a gap in published guidance for handling these situations promptly when they arise, we describe a case report plus three additional examples as a guide to effective resolution.



Case Summary: An immunocompetent laboratory researcher developed primary cutaneous cryptococcosis following accidental infection with Cryptococcus neoformans H99 via a needle scrape that was initially assumed not to have penetrated the skin. On day 8 after the incident, a characteristic nodular erythematous lesion developed on a finger at the exposure site. Antibacterial therapy was initiated for the clinical impres sion of bacterial cellulitis as clinical tests for cryptococcal serum antigen and cultures of aspirates from the wound site on day 13 after incident were negative. Eight-week fluconazole therapy initiated on day 15 after the incident was curative. Whole genome sequencing of yeast grown from wound exudate collected on day 18 confirmed high sequence similarity to H99 Cryptococcus neoformans var. grubii and sequence diver gence from an archived sample isolated from an immunocompromised individual. Three additional cases with potential exposures to C. neoformans in the research lab received prophylactic fluconazole and remained asymptomatic.



Conclusion: In a span of 5 years, four laboratory researchers from two research groups at the same institution sustained accidental exposures to C. neoformans, and all were successfully treated. These cases reinforce and update the recommendations for initiating antifungal therapy immediately after laboratory accidents involving C. neoformans.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Fuller2025,

title = {Novel enzymatic DNA produced from a text file achieves comparable immune responses as plasmid vaccine},

author = {James Fuller and Erik Kvam and Sandrine Creton and Courtney Hall and Nicholas J Tursi and Kerry Blatney and Rebecca Ryan and Xavier Godron and David B Weiner and Winston Timp and Weston Griffin and John Nelson and Deborah H Fuller},

url = {https://www.nature.com/articles/s41541-025-01329-0},

doi = {https://doi.org/10.1038/s41541-025-01329-0},

year  = {2025},

date = {2025-12-13},

urldate = {2025-12-13},

journal = {npj Vaccines},

volume = {11},

pages = {9},

abstract = {DNA vaccines have garnered considerable attention due to their recent success in humans for SARS-CoV-2 and immunotherapy for cancer. However, conventional methods for creating and manufacturing DNA vaccines at-scale are slow and rate-limiting for timely response. Herein, we introduce a rapid and completely synthetic workflow that harnesses enzymes to create bulk DNA from a sequence text file. This synthetic workflow termed Enzymatic DNA Synthesis & Rolling-Circle Amplification (EDS-RCA) leverages multiple enzymes to print DNA oligos and assemble them into genes prior to cloning into circular constructs for rolling-circle amplification (RCA). We show that the resulting EDS-RCA DNA elicits comparable vaccine immunogenicity as standard plasmid format, despite the DNA being a large concatemeric repeat. The EDS-RCA method generated the hemagglutinin gene of H1N1 at a mean per-base error rate as low as ~1 mutation every 10,000 bases and, upon DNA vaccination, elicited strong antibody and cellular immune responses. Skin delivery of EDS-DNA using gene gun facilitated striking vaccine dose-sparing capabilities in comparison to intramuscular electroporation methods. In total, DNA vaccines produced by EDS-RCA are immunogenic and amenable to numerous delivery-modalities with preclinical mouse models and could offer an alternative for rapid scale-up of DNA vaccines for future human use.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rudnizky2025,

title = {Ultrafast CTCF dynamics control cohesin barrier function},

author = {Sergei Rudnizky and Peter J Murray and Emily W Sørensen and Theo JR Koenig and Sushil Pangeni and Raquel Merino-Urteaga and Hemani Chhabra and Laura Caccianini and Iain F Davidson and Manuel Osorio-Valeriano and Paul W Hook and Paul Meneses and Jingzhou Hao and Jasmin S Zarb and Nikos S Hatzakis and Winston Timp and Lucas Farnung and Seychelle M Vos and Jan-Michael Peters and Aleksei Aksimentiev and Taekjip Ha},

url = {https://www.biorxiv.org/content/biorxiv/early/2025/11/29/2025.11.25.690553.full.pdf},

doi = {https://doi.org/10.1101/2025.11.25.690553},

year  = {2025},

date = {2025-11-29},

journal = {bioRxiv},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Keuthan2025,

title = {Dynamic changes in mRNA isoform usage during human retinal development},

author = {Casey J Keuthan and Sowmya Parthiban and Yen-Yu Chang and Xiaoqian Shan and Xiaoli Chang and Ethan Yan and Sheridan Cavalier and Winston Timp and Stephanie C Hicks and Donald J Zack},

url = {https://www.biorxiv.org/content/10.1101/2025.11.26.689062v1.full.pdf},

doi = {https://doi.org/10.1101/2025.11.26.689062},

year  = {2025},

date = {2025-11-26},

urldate = {2025-11-26},

journal = {bioRxiv},

abstract = {Background: Alternative mRNA splicing is a key mechanism for generating isoform diversity in eukaryotic cells. However, the extent of the splicing changes that occur during complex regulatory processes like neurodevelopment are still incompletely characterized.



Results: We performed nanopore-based long-read RNA sequencing on differentiating human stem cell-derived retinal organoids to identify temporal patterns of isoform usage across developmental stages. We found that retinal organoids undergo dynamic shifts in isoform usage throughout differentiation, which were not necessarily accompanied with changes in overall gene expression, as was the case for many genes involved in the regulation of mRNA splicing itself. Further analysis of human stem cell-derived retinal ganglion cells uncovered neuron-specific splicing signatures. Additionally, allele-specific expression analysis revealed extensive allelic imbalance in induced pluripotent stem cell- derived organoid cultures.



Conclusions: By combining direct long-read RNA sequencing with human stem cell retinal models we could explore isoform-level changes in differentiating human cells at unprecedented detail. These results uncovered dynamic shifts in transcript usage during retinal differentiation, adding to our knowledge base of post-transcriptional RNA processing in the developing central nervous system and human in vitro culture systems.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Bertocchi2025,

title = {Write and Read: Harnessing Synthetic DNA Modifications for Nanopore Sequencing},

author = {Uri Bertocchi and Assaf Grunwald and Gal Goldner and Eliran Eitan and Sigal Avraham and Shani Dvir and Jasline Deek and Yael Michaeli and Brian Yao and Jennifer Listgarten and Jared T Simpson and Winston Timp and Yuval Ebenstein},

url = {https://pubs.acs.org/doi/full/10.1021/acsnano.5c12530},

doi = {https://doi.org/10.1021/acsnano.5c12530},

year  = {2025},

date = {2025-11-03},

journal = {ACS nano},

volume = {19},

issue = {44},

pages = {38553-38562},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Garimella2025,

title = {Population-scale long-read sequencing in the All of Us research program},

author = {Kiran V Garimella and Qiuhui Li and Julie Wertz and Samuel K Lee and Fabio Cunial and Yongqing Huang and Yulia Mostovoy and Ryan Lorig-Roach and Adam English and Hang Su and Shawn Levy and Donna M Muzny and Chelsea Berngruber and Matt C Danzi and William T Harvey and Emily L LaPlante and Karynne Patterson and Allison N Rozanski and Sophie Schwartz and Beri Shifaw and Yuanyuan Wang and Isaac Wong and Isaac RL Xu and Shadi Zaheri and Stephan Zuchner and Xinchang Zheng and Shannon Dugan-Perez and Michal Izydorczyk and Heer Mehta and Richard A Gibbs and Lee Lichtenstein and Namrata Gupta and Niall Lennon and Stacey Gabriel and Winston Timp and Kimberly F Doheny and Tara Dutka and Anjene Musick and Chia-Lin Wei and Fritz J Sedlazeck and Michael C Schatz and Michael E Talkowski and Evan E Eichler},

url = {https://pmc.ncbi.nlm.nih.gov/articles/PMC12622093/},

doi = {https://doi.org/10.1101/2025.10.02.25336942},

year  = {2025},

date = {2025-10-05},

journal = {medRxiv},

abstract = {The All of Us Research Program (AoU) is a national biobank seeking to enroll one million individuals in the United States to link genomic and biomedical data, including short- and long-read whole-genome sequencing (srWGS/LRS), with rich electronic health record (EHR) information. Here, we present the first large-scale analyses of long-read sequencing (LRS) in AoU and offer a new framework for deriving genomic insights into complex structural variation (SV) of relevance to human health and disease. We performed joint analyses of 1,027 individuals self-identifying as Black or African American, sequenced to ~8x coverage with Pacific Biosciences HiFi technology and processed using cloud-native pipelines. From these LRS data we constructed a comprehensive variant callset encompassing known (FMR1 and HTT) and novel repeat expansions, clinically relevant haplotypes at loci inaccessible to srWGS, and haplotypes relevant to disease risk (HLA) and pharmacogenomics (CYP2D6), including SNVs, indels, and SVs. We developed methods for cohort-level variant calling and a scalable workflow to impute >750,000 of these SVs into existing srWGS datasets for trait association and human disease studies. Expanding to 10,000 self-identified Black or African American AoU participants with srWGS and matched EHRs, we identified 291 SV-disease associations (p < 1×10−5) spanning 226 conditions with 50.9% of associations involving SVs absent from the matched srWGS callset. Across the 226 traits, after fine-mapping using SVs and SNVs we identified 191 SV-disease pairs spanning 160 traits (70.8%) where the SV had the strongest association within the locus. Associations specific to those with computed ancestry similar to the African reference population exhibited larger effect sizes and lower allele frequencies, consistent with high-risk, ancestry-specific variants. These results demonstrate that the integration of LRS into AoU and future biobank initiatives can provide transformative new insights into genomic variation with potentially profound impact on precision medicine.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hansen2025,

title = {A complete diploid human genome benchmark for personalized genomics},

author = {Nancy F Hansen and Nathan Dwarshuis and Hyun Joo Ji and Arang Rhie and Hailey Loucks and Glennis A Logsdon and Mitchell R Vollger and Jessica M Storer and Juhyun Kim and Eleni Adam and Nicolas Altemose and Dmitry Antipov and Mobin Asri and Sofia Barreira and Stephanie C Bohaczuk and Andrey V Bzikadze and Sara A Carioscia and Andrew Carroll and Kuan-Hao Chao and Yanan Chu and Arun Das and Peter Ebert and Adam English and Mark Fleharty and Laura E Fleming and Giulio Formenti and Andrea Guarracino and Gabrielle A Hartley and Katharine Jenike and Jenna Kalleberg and Yu Kang and Robert King and Josipa Lipovac and Mira Mastoras and Matthew W Mitchell and Shloka Negi and Nathan D Olson and Keisuke K Oshima and Luis F Paulin and Brandon D Pickett and David Porubsky and Jane Ranchalis and Desh Ranjan and Mikko Rautiainen and Harold Riethman and Robert D Schnabel and Fritz J Sedlazeck and Kishwar Shafin and Mile Sikic and Steven J Solar and Alexander P Sweeten and Winston Timp and Justin Wagner and DongAhn Yoo and Ying Zhou and Erik Garrison and Evan E Eichler and Michael C Schatz and Andrew B Stergachis and Rachel J O’Neill and Karen H Miga and Steven L Salzberg and Sergey Koren and Justin M Zook and Adam M Phillippy},

url = {https://pmc.ncbi.nlm.nih.gov/articles/PMC12458380/},

doi = {https://doi.org/10.1101/2025.09.21.677443},

year  = {2025},

date = {2025-09-21},

journal = {bioRxiv},

abstract = {Human genome resequencing typically involves mapping reads to a reference genome to call variants; however, this approach suffers from both technical and reference biases, leaving many duplicated and structurally polymorphic regions of the genome unmapped. Consequently, existing variant benchmarks, generated by the same methods, fail to assess these complex regions. To address this limitation, we present a telomere-to-telomere genome benchmark that achieves near-perfect accuracy (i.e. no detectable errors) across 99.4% of the complete, diploid HG002 genome. This benchmark adds 701.4 Mb of autosomal sequence and both sex chromosomes (216.8 Mb), totaling 15.3% of the genome that was absent from prior benchmarks. We also provide a diploid annotation of genes, transposable elements, segmental duplications, and satellite repeats, including 39,144 protein-coding genes across both haplotypes. To facilitate application of the benchmark, we developed tools for measuring the accuracy of sequencing reads, phased variant call sets, and genome assemblies against a diploid reference. Genome-wide analyses show that state-of-the-art de novo assembly methods resolve 2–7% more sequence and outperform variant calling accuracy by an order of magnitude, yielding just one error per 100 kb across 99.9% of the benchmark regions. Adoption of genome-based benchmarking is expected to accelerate the development of cost-effective methods for complete genome sequencing, expanding the reach of genomic medicine to the entire genome and enabling a new era of personalized genomics.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Cavalier2025,

title = {Single-cell long-read sequencing of the experience-induced transcriptome},

author = {Sheridan Cavalier and Paul W Hook and Richard L Huganir and Winston Timp},

url = {https://www.biorxiv.org/content/biorxiv/early/2025/09/12/2025.09.12.674885.full.pdf},

doi = {https://doi.org/10.1101/2025.09.12.674885},

year  = {2025},

date = {2025-09-12},

urldate = {2025-09-12},

journal = {bioRxiv},

abstract = {Neural activity drives transcriptional events that are critical for learning. Activity-induced transcript isoform expression and alternative splicing are cell-type specific events typically obscured by sequencing approaches that restrict read length. We combined single-cell transcriptomics with Nanopore long-read sequencing to resolve these phenomena, generating the first dataset profiling learning-induced gene and isoform expression in individual mouse hippocampal cells.



Due to their length, the majority of reads we generated could be uniquely mapped to their respective gene and isoform features in the mouse reference. ∼20k cells from 16 mouse samples were sequenced and clustered on the basis of gene expression, yielding 21 hippocampal cell types. Differential expression analysis revealed 1,266 significantly experience-variable isoforms, revealing novel splicing behavior in many synaptic genes.



This work is the first to comprehensively profile activity-induced isoform expression, demonstrating that single cell long-read sequencing can reveal new layers of transcriptional complexity.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Johnson2025,

title = {Single-cell RNA sequencing identifies subtypes of cancer-associated fibroblasts in early and late stages of mycosis fungoides},

author = {Courtney M Johnson and Weishan Li and Soroosh Solhjoo and Vrinda Madan and Iman Ali and Kalvin Nash and Stephanie Hicks and Winston Timp},

url = {https://www.medrxiv.org/content/medrxiv/early/2025/09/10/2025.09.07.25335167.full.pdf},

doi = {https://doi.org/10.1101/2025.09.07.25335167},

year  = {2025},

date = {2025-09-10},

journal = {medRxiv},

abstract = { Mycosis fungoides (MF), the most common cutaneous T-cell lymphoma, is characterized by infiltration of malignant T-cells into the skin. While early-stage disease (IA-IIA) follows an indolent course, approximately 25% of patients progress to late-stage disease (IIB-IVB) with significantly worse prognosis and a median survival of 1-5 years. Identifying which early-stage MF patients are at high risk for disease progression remains difficult. This may be affected by the complex interaction between malignant tumor cells and the tumor microenvironment. Increased numbers of cancer-associated fibroblasts (CAF) are found in early-stage MF and have been shown to support tumor growth, but the subtypes have not yet been classified in lesional MF tissue. We performed single-cell RNA sequencing on skin samples from healthy individuals, early- stage MF patients, and late-stage MF patients to investigate the fibroblast population. Analysis of the highly differentially expressed genes in the fibroblast populations revealed nine distinct subclusters, comprising five major types: ECM/structural, vascular/metabolic, immune-modulatory, antigen-presenting, and developmental fibroblasts. Stage-specific differences revealed that the vascular/metabolic subcluster was enriched in early-stage MF, while the ECM/structural subcluster was enriched in late-stage MF. An antigen-presenting subcluster, a novel and underrecognized subtype, was identified by its high expression of MHC class II genes and pathways essential for antigen processing and presentation of exogenous peptides. These inappropriate antigen-presenting fibroblasts may play a role in chronic T-cell exhaustion seen in late- stage diseases. Further studies with additional patient samples will validate these findings and clarify the role of these subtypes in diagnosing and predicting the outcome of mycosis fungoides.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Thatavarty2025,

title = {Detecting Protein-DNA binding in single molecules using antibody guided methylation},

author = {Apoorva Thatavarty and Naor Sagy and Michael R Erdos and Isac Lee and Jared T Simpson and Winston Timp and Francis S Collins and Daniel Z Bar},

url = {https://link.springer.com/article/10.1186/s13072-025-00602-9},

doi = {https://doi.org/10.1186/s13072-025-00602-9},

year  = {2025},

date = {2025-07-01},

urldate = {2025-07-01},

journal = {Epigenetics & Chromatin},

volume = {18},

issue = {1},

pages = {39},

abstract = {Characterization of DNA binding sites for specific proteins is of fundamental importance in molecular biology. It is commonly addressed experimentally by chromatin immunoprecipitation and sequencing (ChIP-seq) of bulk samples (103 -107 cells). We have developed an alternative method that uses a Chromatin Antibody-mediated Methylating Protein (ChAMP) composed of a GpC methyltransferase fused to protein G. By tethering ChAMP to a primary antibody directed against the DNA-binding protein of interest, and selectively switching on its enzymatic activity in situ, we generated distinct and identifiable methylation patterns adjacent to the protein binding sites. This method is compatible with methods of single-cell methylation-detection and single molecule methylation identification. Indeed, as every binding event generates multiple nearby methylations, we were able to confidently detect protein binding in long single molecules.

},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Grossman2025,

title = {Three annotated chromosome-level de novo genome assemblies of Lomentospora prolificans provide evidence for a chromosomal translocation event},

author = {Nina T Grossman and Yunfan Fan and Aleksey V Zimin and Maggie P Wear and Anne Jedlicka and Amanda Dziedzic and Livia C Liporagi-Lopes and Winston Timp and Arturo Casadevall},

url = {https://academic.oup.com/g3journal/article/15/6/jkaf091/8119346},

doi = {https://doi.org/10.1093/g3journal/jkaf091},

year  = {2025},

date = {2025-04-24},

urldate = {2025-04-24},

journal = {G3: Genes, Genomes, Genetics},

volume = {15},

issue = {6},

pages = {jkaf091},

abstract = {Lomentospora prolificans is a fungal pathogen responsible for serious, often fatal, illness in patients with compromised immune systems. Treatment is rarely successful because L. prolificans is inherently resistant to all major classes of antifungal drugs. In this study, we publish 3 chromosome-level de novo genome assemblies, including the first complete-level assembly of L. prolificans, along with genome annotations. The L. prolificans genome is packaged in 11 nuclear chromosomes and 1 mitochondrial chromosome, has 36.7–37.1 Mb, and encodes for a putative 7,357–7,640 genes. The length and composition of contigs in 1 strain varied from those of the other 2 strains, supporting the hypothesis that a chromosomal translocation took place. These assemblies were confirmed with pulsed-field gel electrophoresis. The availability of more complete genomes will hopefully help the search for new antifungal drugs and provides insights into the evolutionary history of this pathogenic fungus.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Montano2025,

title = {Evolution of genome-wide methylation profiling technologies},

author = {Carolina Montano and Winston Timp},

url = {https://pmc.ncbi.nlm.nih.gov/articles/PMC12047278/},

doi = {https://doi.org/10.1101/gr.278407.123},

year  = {2025},

date = {2025-04-14},

journal = {Genome Research},

volume = {35},

issue = {4},

pages = {572},

abstract = {In this mini-review, we explore the advancements in genome-wide DNA methylation profiling, tracing the evolution from traditional methods such as methylation arrays and whole-genome bisulfite sequencing to the cutting-edge single-molecule profiling enabled by long-read sequencing (LRS) technologies. We highlight how LRS is transforming clinical and translational research, particularly by its ability to simultaneously measure genetic and epigenetic information, providing a more comprehensive understanding of complex disease mechanisms. We discuss current challenges and future directions in the field, emphasizing the need for innovative computational tools and robust, reproducible approaches to fully harness the capabilities of LRS in molecular diagnostics.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Fu2025,

title = {Computational analysis of DNA methylation from long-read sequencing},

author = {Yilei Fu and Winston Timp and Fritz J Sedlazeck},

url = {https://www.nature.com/articles/s41576-025-00822-5},

doi = {https://doi.org/10.1038/s41576-025-00822-5},

year  = {2025},

date = {2025-03-28},

journal = {Nature Reviews Genetics},

volume = {26},

issue = {9},

pages = {620-634},

abstract = {DNA methylation is a critical epigenetic mechanism in numerous biological processes, including gene regulation, development, ageing and the onset of various diseases such as cancer. Studies of methylation are increasingly using single-molecule long-read sequencing technologies to simultaneously measure epigenetic states such as DNA methylation with genomic variation. These long-read data sets have spurred the continuous development of advanced computational methods to gain insights into the roles of methylation in regulating chromatin structure and gene regulation. In this Review, we discuss the computational methods for calling methylation signals, contrasting methylation between samples, analysing cell-type diversity and gaining additional genomic insights, and then further discuss the challenges and future perspectives of tool development for DNA methylation research.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kovaka2025,

title = {Uncalled4 improves nanopore DNA and RNA modification detection via fast and accurate signal alignment},

author = {Sam Kovaka and Paul W Hook and Katharine M Jenike and Vikram Shivakumar and Luke B Morina and Roham Razaghi and Winston Timp and Michael C Schatz},

url = {https://www.nature.com/articles/s41592-025-02631-4},

doi = {https://doi.org/10.1038/s41592-025-02631-4},

year  = {2025},

date = {2025-03-28},

urldate = {2024-03-10},

journal = {Nature Methods},

volume = {22},

issue = {4},

pages = {681-691},

abstract = {Nanopore signal analysis enables detection of nucleotide modifications from native DNA and RNA sequencing, providing both accurate genetic or transcriptomic and epigenetic information without additional library preparation. At present, only a limited set of modifications can be directly basecalled (for example, 5-methylcytosine), while most others require exploratory methods that often begin with alignment of nanopore signal to a nucleotide reference. We present Uncalled4, a toolkit for nanopore signal alignment, analysis and visualization. Uncalled4 features an efficient banded signal alignment algorithm, BAM signal alignment file format, statistics for comparing signal alignment methods and a reproducible de novo training method for k-mer-based pore models, revealing potential errors in Oxford Nanopore Technologies’ state-of-the-art DNA model. We apply Uncalled4 to RNA 6-methyladenine (m6A) detection in seven human cell lines, identifying 26% more modifications than Nanopolish using m6Anet, including in several genes where m6A has known implications in cancer. Uncalled4 is available open source at github.com/skovaka/uncalled4.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Li2025,

title = {Unraveling the hidden complexity of cancer through long-read sequencing},

author = {Qiuhui Li and Ayse G Keskus and Justin Wagner and Michal B Izydorczyk and Winston Timp and Fritz J Sedlazeck and Alison P Klein and Justin M Zook and Mikhail Kolmogorov and Michael C Schatz},

url = {https://pmc.ncbi.nlm.nih.gov/articles/PMC12047254/},

doi = {https://doi.org/10.1101/gr.280041.124},

year  = {2025},

date = {2025-03-20},

urldate = {2025-04-01},

journal = {Genome Research},

volume = {35},

issue = {4},

pages = {599},

abstract = {Cancer is fundamentally a disease of the genome, characterized by extensive genomic, transcriptomic, and epigenomic alterations. Most current studies predominantly use short-read sequencing, gene panels, or microarrays to explore these alterations; however, these technologies can systematically miss or misrepresent certain types of alterations, especially structural variants, complex rearrangements, and alterations within repetitive regions. Long-read sequencing is rapidly emerging as a transformative technology for cancer research by providing a comprehensive view across the genome, transcriptome, and epigenome, including the ability to detect alterations that previous technologies have overlooked. In this Perspective, we explore the current applications of long-read sequencing for both germline and somatic cancer analysis. We provide an overview of the computational methodologies tailored to long-read data and highlight key discoveries and resources within cancer genomics that were previously inaccessible with prior technologies. We also address future opportunities and persistent challenges, including the experimental and computational requirements needed to scale to larger sample sizes, the hurdles in sequencing and analyzing complex cancer genomes, and opportunities for leveraging machine learning and artificial intelligence technologies for cancer informatics. We further discuss how the telomere-to-telomere genome and the emerging human pangenome could enhance the resolution of cancer genome analysis, potentially revolutionizing early detection and disease monitoring in patients. Finally, we outline strategies for transitioning long-read sequencing from research applications to routine clinical practice.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Morina2025,

title = {Investigating subpopulation dynamics in clonal CHO-K1 cells with single-cell RNA sequencing},

author = {Luke B Morina and Haoyu Chris Cao and Siqi Chen and Swetha Kumar and Kevin S McFarland and Natalia I Majewska and Michael J Betenbaugh and Winston Timp},

url = {https://www.sciencedirect.com/science/article/pii/S0168165625000094?via%3Dihub},

doi = {https://doi.org/10.1016/j.jbiotec.2025.01.010},

year  = {2025},

date = {2025-03-01},

urldate = {2025-03-01},

journal = {Journal of Biotechnology},

volume = {399},

pages = {91-98},

abstract = {Chinese Hamster Ovary (CHO) cells produce monoclonal antibodies and other biotherapeutics at industrial scale. Despite their ubiquitous nature in the biopharmaceutical industry, little is known about the behaviors of individual transfected clonal CHO cells. Most CHO cells are assessed on their stability, their ability to produce the protein of interest over time. But CHO cells have primarily been studied in bulk, instead assuming that these bulk samples are homogenous because of presumed genetic clonality across the sample. This does not address cellular heterogeneity in these ostensibly clonal cells. These variable stability phenotypes may reflect heterogeneity within the clonal samples. In this study, we performed single-cell RNA sequencing on two clonal CHO-K1 cell populations with different stability phenotypes over a 90 day culture period. Our data showed that the instability of one of the clone’s gene expression was due in part to the emergence of a low-producing subpopulation in the aged samples. This low-producing subpopulation did not exhibit markers of cellular stress which were expressed in the higher-producing populations. Further multiomic investigation should be performed to better characterize this heterogeneity.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Mahlke2025,

title = {Evolution and instability of human centromeres are accelerated by heterochromatin boundary loss and CENP-A overexpression},

author = {Megan A Mahlke and Lior Lumerman and Poulomi Nath and Cy Chittenden and Savannah Hoyt and Jonas Koeppel and Yuan Xu and Rebecca Raphael and Kylie Zaffina and Paul W Hook and Winston Timp and Karen H Miga and Peter J Campbell and Rachel J O’Neill and Nicolas Altemose and Yael Nechemia-Arbely},

url = {https://www.biorxiv.org/content/biorxiv/early/2025/04/07/2025.02.03.636285.full.pdf},

doi = {https://doi.org/10.1101/2025.02.03.636285},

year  = {2025},

date = {2025-02-03},

journal = {bioRxiv},

abstract = {Centromere location is specified by CENP-A, a centromere-specific histone that epigenetically defines centromere identity. How CENP-A is maintained at one location in rapidly evolving centromeric DNA is unknown. Using single-cell-derived clones of human cell lines, we demonstrate single-cell heterogeneity in CENP-A position within cell populations at neocentromeres and a native centromere. CENP-A heterogeneity is accompanied by unique DNA methylation and H3K9me3 patterns, with DNA methylation shifting according to CENP-A position. We further demonstrate centromere epigenetic evolution over prolonged proliferation, with native centromeres maintaining stable heterochromatin boundaries, but neocentromeres exhibiting DNA methylation instability, H3K9me3 gain, boundary loss and fragility. Lastly, prolonged CENP-A and HJURP overexpression leads to centromere and neocentromere expansion, gradual CENP-A depletion, neocentromere destabilization and CENP-A re-localization that is accompanied by local heterochromatin remodeling. This study reveals the naturally evolving epigenetic plasticity of human centromeres and neocentromeres and highlights the importance of repressive chromatin boundaries in maintaining centromere stability.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Volkel2025,

title = {Nanopore decoding with speed and versatility for data storage},

author = {Kevin D Volkel and Paul W Hook and Albert Keung and Winston Timp and James M Tuck},

url = {https://academic.oup.com/bioinformatics/article/41/1/btaf006/7945662},

doi = {https://doi.org/10.1093/bioinformatics/btaf006},

year  = {2025},

date = {2025-01-08},

urldate = {2025-01-08},

journal = {Bioinformatics},

volume = {41},

issue = {1},

pages = {btaf006},

abstract = {Motivation: As nanopore technology reaches ever higher throughput and accuracy, it becomes an increasingly viable candidate for reading out DNA data storage. Nanopore sequencing offers considerable flexibility by allowing long reads, real-time signal analysis, and the ability to read both DNA and RNA. We need flexible and efficient designs that match nanopore’s capabilities, but relatively few designs have been explored and many have significant inefficiency in read density, error rate, or compute time. To address these problems, we designed a new single-read per-strand decoder that achieves low byte error rates, offers high throughput, scales to long reads, and works well for both DNA and RNA molecules. We achieve these results through a novel soft decoding algorithm that can be effectively parallelized on a GPU. Our faster decoder allows us to study a wider range of system designs.



Results: We demonstrate our approach on HEDGES, a state-of-the-art DNA-constrained convolutional code. We implement one hard decoder that runs serially and two soft decoders that run on GPUs. Our evaluation for each decoder is applied to the same population of nanopore reads collected from a synthesized library of strands. These same strands are synthesized with a T7 promoter to enable RNA transcription and decoding. Our results show that the hard decoder has a byte error rate over 25%, while the prior state of the art soft decoder can achieve error rates of 2.25%. However, that design also suffers a low throughput of 183 s/read. Our new Alignment Matrix Trellis soft decoder improves throughput by 257× with the trade-off of a higher byte error rate of 3.52% compared to the state of the art. Furthermore, we use the faster speed of our algorithm to explore more design options. We show that read densities of 0.33 bits/base can be achieved, which is 4× larger than prior MSA-based decoders. We also compare RNA to DNA, and find that RNA has 85% as many error-free reads when compared to DNA.

Availability and implementation



Source code for our soft decoder and data used to generate figures is available publicly in the Github repository https://github.com/dna-storage/hedges-soft-decoder (10.5281/zenodo.11454877). All raw FAST5/FASTQ data are available at 10.5281/zenodo.11985454 and 10.5281/zenodo.12014515.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Billingsley2024,

title = {Long-read sequencing of hundreds of diverse brains provides insight into the impact of structural variation on gene expression and DNA methylation},

author = {Kimberley J Billingsley and Melissa Meredith and Kensuke Daida and Pilar Alvarez Jerez and Shloka Negi and Laksh Malik and Rylee M Genner and Abraham Moller and Xinchang Zheng and Sophia B Gibson and Mira Mastoras and Breeana Baker and Cedric Kouam and Kimberly Paquette and Paige Jarreau and Mary B Makarious and Anni Moore and Samantha Hong and Dan Vitale and Syed Shah and Jean Monlong and Caroline B Pantazis and Mobin Asri and Kishwar Shafin and Paolo Carnevali and Stefano Marenco and Pavan Auluck and Ajeet Mandal and Karen H Miga and Arang Rhie and Xylena Reed and Jinhui Ding and Mark R Cookson and Mike Nalls and Andrew Singleton and Danny E Miller and Mark Chaisson and Winston Timp and JRaphael Gibbs and Adam M Phillippy and Mikhail Kolmogorov and Miten Jain and Fritz J Sedlazeck and Benedict Paten and Cornelis Blauwendraat},

url = {https://pmc.ncbi.nlm.nih.gov/articles/PMC11702628/},

doi = {https://www.biorxiv.org/content/10.1101/2024.12.16.628723v1},

year  = {2024},

date = {2024-12-17},

urldate = {2024-12-17},

journal = {bioRxiv},

abstract = {Structural variants (SVs) drive gene expression in the human brain and are causative of many neurological conditions. However, most existing genetic studies have been based on short-read sequencing methods, which capture fewer than half of the SVs present in any one individual. Long-read sequencing (LRS) enhances our ability to detect disease-associated and functionally relevant structural variants (SVs); however, its application in large-scale genomic studies has been limited by challenges in sample preparation and high costs. Here, we leverage a new scalable wet-lab protocol and computational pipeline for whole-genome Oxford Nanopore Technologies sequencing and apply it to neurologically normal control samples from the North American Brain Expression Consortium (NABEC) (European ancestry) and Human Brain Collection Core (HBCC) (African or African admixed ancestry) cohorts. Through this work, we present a publicly available long-read resource from 351 human brain samples (median N50: 27 Kbp and at an average depth of ~40x genome coverage). We discover approximately 234,905 SVs and produce locally phased assemblies that cover 95% of all protein-coding genes in GRCh38. Utilizing matched expression datasets for these samples, we apply quantitative trait locus (QTL) analyses and identify SVs that impact gene expression in post-mortem frontal cortex brain tissue. Further, we determine haplotype-specific methylation signatures at millions of CpGs and, with this data, identify cis-acting SVs. In summary, these results highlight that large-scale LRS can identify complex regulatory mechanisms in the brain that were inaccessible using previous approaches. We believe this new resource provides a critical step toward understanding the biological effects of genetic variation in the human brain.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Saba2024,

title = {LARP1 senses free ribosomes to coordinate supply and demand of ribosomal proteins},

author = {James A Saba and Zixuan Huang and Kate L Schole and Xianwen Ye and Shrey D Bhatt and Yi Li and Winston Timp and Jingdong Cheng and Rachel Green},

url = {https://pmc.ncbi.nlm.nih.gov/articles/PMC11649897/},

doi = {https://doi.org/10.1038/s44318-024-00294-z},

year  = {2024},

date = {2024-12-16},

urldate = {2024-12-16},

journal = {The EMBO Journal},

volume = {43},

issue = {24},

pages = {6555-6572},

abstract = {Terminal oligopyrimidine motif-containing mRNAs (TOPs) encode all ribosomal proteins in mammals and are regulated to tune ribosome synthesis to cell state. Previous studies have implicated LARP1 in 40S- or 80S-ribosome complexes that are thought to repress and stabilize TOPs. However, a molecular understanding of how LARP1 and TOPs interact with these ribosome complexes is lacking. Here, we show that LARP1 directly binds non-translating ribosomal subunits. Cryo-EM structures reveal a previously uncharacterized domain of LARP1 bound to and occluding the mRNA channel of the 40S subunit. Increased availability of free ribosomal subunits downstream of various stresses promote 60S joining at the same interface to form LARP1-80S complexes. Simultaneously, LARP1 engages the TOP via its previously characterized La/PAM2 and DM15 domains. Contrary to expectations, ribosome binding within these complexes is not required for LARP1-mediated TOP repression or stabilization, two canonical LARP1 functions. Together, this work provides molecular insight into how LARP1 directly binds ribosomal subunits and challenges existing models describing the function of repressed LARP1-40S/80S-TOP complexes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Lin2024,

title = {A primordial DNA store and compute engine},

author = {Kevin N Lin and Kevin Volkel and Cyrus Cao and Paul W Hook and Rachel E Polak and Andrew S Clark and Adriana San Miguel and Winston Timp and James M Tuck and Orlin D Velev and Albert J Keung},

url = {https://www.nature.com/articles/s41565-024-01771-6},

doi = {https://doi.org/10.1038/s41565-024-01771-6},

year  = {2024},

date = {2024-08-22},

urldate = {2024-08-22},

journal = {Nature Nanotechnology},

pages = {1-11},

abstract = {Any modern information system is expected to feature a set of primordial features and functions: a substrate stably carrying data; the ability to repeatedly write, read, erase, reload and compute on specific data from that substrate; and the overall ability to execute such functions in a seamless and programmable manner. For nascent molecular information technologies, proof-of-principle realization of this set of primordial capabilities would advance the vision for their continued development. Here we present a DNA-based store and compute engine that captures these primordial capabilities. This system comprises multiple image files encoded into DNA and adsorbed onto ~50-μm-diameter, highly porous, hierarchically branched, colloidal substrate particles comprised of naturally abundant cellulose acetate. Their surface areas are over 200 cm2 mg−1 with binding capacities of over 1012 DNA oligos mg−1, 10 TB mg−1 or 104 TB cm−3. This ‘dendricolloid’ stably holds DNA files better than bare DNA with an extrapolated ability to be repeatedly lyophilized and rehydrated over 170 times compared with 60 times, respectively. Accelerated ageing studies project half-lives of ~6,000 and 2 million years at 4 °C and −18 °C, respectively. The data can also be erased and replaced, and non-destructive file access is achieved through transcribing from distinct synthetic promoters. The resultant RNA molecules can be directly read via nanopore sequencing and can also be enzymatically computed to solve simplified 3 × 3 chess and sudoku problems. Our study establishes a feasible route for utilizing the high information density and parallel computational advantages of nucleic acids.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Nickels2024,

title = {Transposon-sequencing (Tn-seq) of the Candida glabrata reference strain CBS138 reveals epigenetic plasticity, structural variation, and intrinsic mechanisms of resistance to micafungin},

author = {Timothy J Nickels and Andrew N Gale and Abigail A Harrington and Winston Timp and Kyle W Cunningham},

url = {https://academic.oup.com/g3journal/advance-article/doi/10.1093/g3journal/jkae173/7719367},

doi = {https://doi.org/10.1093/g3journal/jkae173},

year  = {2024},

date = {2024-07-24},

urldate = {2024-07-24},

journal = {G3: Genes, Genomes, Genetics},

pages = {jkae173},

abstract = {Candida glabrata (also called Nakaseomyces glabratus) is an opportunistic pathogen that can resist common antifungals and rapidly acquire multidrug resistance. A large amount of genetic variation exists between isolates, which complicates generalizations. Portable transposon-sequencing (Tn-seq) methods can efficiently provide genome-wide information on strain differences and genetic mechanisms. Using the Hermes transposon, the CBS138 reference strain and a commonly studied derivative termed 2001 were subjected to Tn-seq in control conditions and after exposure to varying doses of the clinical antifungal micafungin. The approach revealed large differences between these strains, including a 131-kb tandem duplication and a variety of fitness differences. Additionally, both strains exhibited up to 1,000-fold increased transposon accessibility in subtelomeric regions relative to the BG2 strain, indicative of open subtelomeric chromatin in these isolates and large epigenetic variation within the species. Unexpectedly, the Pdr1 transcription factor conferred resistance to micafungin through targets other than CDR1. Other micafungin resistance pathways were also revealed including mannosyltransferase activity and biosynthesis of the lipid precursor sphingosine, the inhibition of which by SDZ 90–215 and myriocin enhanced the potency of micafungin in vitro. These findings provide insights into the complexity of the C. glabrata species as well as strategies for improving antifungal efficacy.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Anantharam2024,

title = {Long-read Nanopore-based sequencing of anelloviruses},

author = {Raghavendran Anantharam and Dylan Duchen and Andrea L Cox and Winston Timp and David L Thomas and Steven J Clipman and Abraham J Kandathil},

url = {https://www.mdpi.com/1999-4915/16/5/723},

doi = {https://doi.org/10.3390/v16050723},

year  = {2024},

date = {2024-05-02},

journal = {Viruses},

volume = {16},

issue = {5},

pages = {723},

abstract = {Routinely used metagenomic next-generation sequencing (mNGS) techniques often fail to detect low-level viremia (<104 copies/mL) and appear biased towards viruses with linear genomes. These limitations hinder the capacity to comprehensively characterize viral infections, such as those attributed to the Anelloviridae family. These near ubiquitous non-pathogenic components of the human virome have circular single-stranded DNA genomes that vary in size from 2.0 to 3.9 kb and exhibit high genetic diversity. Hence, species identification using short reads can be challenging. Here, we introduce a rolling circle amplification (RCA)-based metagenomic sequencing protocol tailored for circular single-stranded DNA genomes, utilizing the long-read Oxford Nanopore platform. The approach was assessed by sequencing anelloviruses in plasma drawn from people who inject drugs (PWID) in two geographically distinct cohorts. We detail the methodological adjustments implemented to overcome difficulties inherent in sequencing circular genomes and describe a computational pipeline focused on anellovirus detection. We assessed our protocol across various sample dilutions and successfully differentiated anellovirus sequences in conditions simulating mixed infections. This method provides a robust framework for the comprehensive characterization of circular viruses within the human virome using the Oxford Nanopore.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Zuniga2024,

title = {Sustained ERK signaling promotes G2 cell cycle exit and primes cells for whole-genome duplication},

author = {Adler Guerrero Zuniga and Timothy J Aikin and Connor McKenney and Yovel Lendner and Alain Phung and Paul W Hook and Amy Meltzer and Winston Timp and Sergi Regot},

url = {https://www.sciencedirect.com/science/article/pii/S1534580724002004},

doi = {https://doi.org/10.1016/j.devcel.2024.03.032},

year  = {2024},

date = {2024-04-18},

urldate = {2024-04-18},

journal = {Developmental Cell},

volume = {59},

issue = {13},

pages = {1724-1736},

abstract = {Whole-genome duplication (WGD) is a frequent event in cancer evolution that fuels chromosomal instability. WGD can result from mitotic errors or endoreduplication, yet the molecular mechanisms that drive WGD remain unclear. Here, we use live single-cell analysis to characterize cell-cycle dynamics upon aberrant Ras-ERK signaling. We find that sustained ERK signaling in human cells leads to reactivation of the APC/C in G2, resulting in tetraploid G0-like cells that are primed for WGD. This process is independent of DNA damage or p53 but dependent on p21. Transcriptomics analysis and live-cell imaging showed that constitutive ERK activity promotes p21 expression, which is necessary and sufficient to inhibit CDK activity and which prematurely activates the anaphase-promoting complex (APC/C). Finally, either loss of p53 or reduced ERK signaling allowed for endoreduplication, completing a WGD event. Thus, sustained ERK signaling-induced G2 cell cycle exit represents an alternative path to WGD.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Neale2024,

title = {A genome sequence for the threatened whitebark pine},

author = {David B Neale and Aleksey V Zimin and Amy Meltzer and Akriti Bhattarai and Maurice Amee and Laura Figueroa Corona and Brian J Allen and Daniela Puiu and Jessica Wright and Amanda R De La Torre and Patrick E McGuire and Winston Timp and Steven L Salzberg and Jill L Wegrzyn},

url = {https://academic.oup.com/g3journal/article-pdf/14/5/jkae061/57426862/jkae061.pdf},

doi = {https://doi.org/10.1093/g3journal/jkae061},

year  = {2024},

date = {2024-03-25},

journal = {G3: Genes, Genomes, Genetics},

volume = {14},

issue = {5},

pages = {jkae061},

abstract = {Whitebark pine (WBP, Pinus albicaulis) is a white pine of subalpine regions in the Western contiguous United States and Canada. WBP has become critically threatened throughout a significant part of its natural range due to mortality from the introduced fungal pathogen white pine blister rust (WPBR, Cronartium ribicola) and additional threats from mountain pine beetle (Dendroctonus ponderosae), wildfire, and maladaptation due to changing climate. Vast acreages of WBP have suffered nearly complete mortality. Genomic technologies can contribute to a faster, more cost-effective approach to the traditional practices of identifying disease-resistant, climate-adapted seed sources for restoration. With deep-coverage Illumina short reads of haploid megagametophyte tissue and Oxford Nanopore long reads of diploid needle tissue, followed by a hybrid, multistep assembly approach, we produced a final assembly containing 27.6 Gb of sequence in 92,740 contigs (N50 537,007 bp) and 34,716 scaffolds (N50 2.0 Gb). Approximately 87.2% (24.0 Gb) of total sequence was placed on the 12 WBP chromosomes. Annotation yielded 25,362 protein-coding genes, and over 77% of the genome was characterized as repeats. WBP has demonstrated the greatest variation in resistance to WPBR among the North American white pines. Candidate genes for quantitative resistance include disease resistance genes known as nucleotide-binding leucine-rich repeat receptors (NLRs). A combination of protein domain alignments and direct genome scanning was employed to fully describe the 3 subclasses of NLRs. Our high-quality reference sequence and annotation provide a marked improvement in NLR identification compared to previous assessments that leveraged de novo-assembled transcriptomes},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{tague2023,

title = {Comprehensive screening of a light-inducible split Cre recombinase with domain insertion profiling},

author = {Nathan Tague and Virgile Andreani and Yunfan Fan and Winston Timp and Mary J Dunlop},

url = {https://pubs.acs.org/doi/full/10.1021/acssynbio.3c00328},

doi = {https://doi.org/10.1021/acssynbio.3c00328},

year  = {2023},

date = {2023-10-03},

urldate = {2023-10-03},

journal = {ACS Synthetic Biology},

volume = {12},

issue = {10},

pages = {2834-2842},

abstract = {Splitting proteins with light- or chemically inducible dimers provides a mechanism for post-translational control of protein function. However, current methods for engineering stimulus-responsive split proteins often require significant protein engineering expertise and the laborious screening of individual constructs. To address this challenge, we use a pooled library approach that enables rapid generation and screening of nearly all possible split protein constructs in parallel, where results can be read out by using sequencing. We perform our method on Cre recombinase with optogenetic dimers as a proof of concept, resulting in comprehensive data on the split sites throughout the protein. To improve the accuracy in predicting split protein behavior, we develop a Bayesian computational approach to contextualize errors inherent to experimental procedures. Overall, our method provides a streamlined approach for achieving inducible post-translational control of a protein of interest.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{volkel2023,

title = {FrameD: framework for DNA-based data storage design, verification, and validation},

author = {Kevin D Volkel and Kevin N Lin and Paul W Hook and Winston Timp and Albert J Keung and James M Tuck},

url = {https://academic.oup.com/bioinformatics/article/39/10/btad572/7274858},

doi = {https://doi.org/10.1093/bioinformatics/btad572},

year  = {2023},

date = {2023-10-01},

journal = {Bioinformatics},

volume = {39},

issue = {10},

pages = {btad572},

abstract = {Motivation

DNA-based data storage is a quickly growing field that hopes to harness the massive theoretical information density of DNA molecules to produce a competitive next-generation storage medium suitable for archival data. In recent years, many DNA-based storage system designs have been proposed. Given that no common infrastructure exists for simulating these storage systems, comparing many different designs along with many different error models is increasingly difficult. To address this challenge, we introduce FrameD, a simulation infrastructure for DNA storage systems that leverages the underlying modularity of DNA storage system designs to provide a framework to express different designs while being able to reuse common components.



Results

We demonstrate the utility of FrameD and the need for a common simulation platform using a case study. Our case study compares designs that utilize strand copies differently, some that align strand copies using multiple sequence alignment algorithms and others that do not. We found that the choice to include multiple sequence alignment in the pipeline is dependent on the error rate and the type of errors being injected and is not always beneficial. In addition to supporting a wide range of designs, FrameD provides the user with transparent parallelism to deal with a large number of reads from sequencing and the need for many fault injection iterations. We believe that FrameD fills a void in the tools publicly available to the DNA storage community by providing a modular and extensible framework with support for massive parallelism. As a result, it will help accelerate the design process of future DNA-based storage systems.



Availability and implementation

The source code for FrameD along with the data generated during the demonstration of FrameD is available in a public Github repository at https://github.com/dna-storage/framed, (https://dx.doi.org/10.5281/zenodo.7757762).},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{kolmogorov2023,

title = {Scalable Nanopore sequencing of human genomes provides a comprehensive view of haplotype-resolved variation and methylation},

author = {Mikhail Kolmogorov and Kimberley J Billingsley and Mira Mastoras and Melissa Meredith and Jean Monlong and Ryan Lorig-Roach and Mobin Asri and Pilar Alvarez Jerez and Laksh Malik and Ramita Dewan and Xylena Reed and Rylee M Genner and Kensuke Daida and Sairam Behera and Kishwar Shafin and Trevor Pesout and Jeshuwin Prabakaran and Paolo Carnevali and Jianzhi Yang and Arang Rhie and Sonja W Scholz and Bryan J Traynor and Karen H Miga and Miten Jain and Winston Timp and Adam M Phillippy and Mark Chaisson and Fritz J Sedlazeck and Cornelis Blauwendraat and Benedict Paten},

url = {https://www.nature.com/articles/s41592-023-01993-x},

doi = {https://doi.org/10.1038/s41592-023-01993-x},

year  = {2023},

date = {2023-09-14},

journal = {Nature Methods},

volume = {20},

issue = {10},

pages = {1483-1492},

abstract = {Long-read sequencing technologies substantially overcome the limitations of short-reads but have not been considered as a feasible replacement for population-scale projects, being a combination of too expensive, not scalable enough or too error-prone. Here we develop an efficient and scalable wet lab and computational protocol, Napu, for Oxford Nanopore Technologies long-read sequencing that seeks to address those limitations. We applied our protocol to cell lines and brain tissue samples as part of a pilot project for the National Institutes of Health Center for Alzheimer’s and Related Dementias. Using a single PromethION flow cell, we can detect single nucleotide polymorphisms with F1-score comparable to Illumina short-read sequencing. Small indel calling remains difficult within homopolymers and tandem repeats, but achieves good concordance to Illumina indel calls elsewhere. Further, we can discover structural variants with F1-score on par with state-of-the-art de novo assembly methods. Our protocol phases small and structural variants at megabase scales and produces highly accurate, haplotype-specific methylation calls.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{rhei2023,

title = {The complete sequence of a human Y chromosome},

author = {Arang Rhie and Sergey Nurk and Monika Cechova and Savannah J Hoyt and Dylan J Taylor and Nicolas Altemose and Paul W Hook and Sergey Koren and Mikko Rautiainen and Ivan A Alexandrov and Jamie Allen and Mobin Asri and Andrey V Bzikadze and Nae-Chyun Chen and Chen-Shan Chin and Mark Diekhans and Paul Flicek and Giulio Formenti and Arkarachai Fungtammasan and Carlos Garcia Giron and Erik Garrison and Ariel Gershman and Jennifer L Gerton and Patrick GS Grady and Andrea Guarracino and Leanne Haggerty and Reza Halabian and Nancy F Hansen and Robert Harris and Gabrielle A Hartley and William T Harvey and Marina Haukness and Jakob Heinz and Thibaut Hourlier and Robert M Hubley and Sarah E Hunt and Stephen Hwang and Miten Jain and Rupesh K Kesharwani and Alexandra P Lewis and Heng Li and Glennis A Logsdon and Julian K Lucas and Wojciech Makalowski and Christopher Markovic and Fergal J Martin and Ann M Mc Cartney and Rajiv C McCoy and Jennifer McDaniel and Brandy M McNulty and Paul Medvedev and Alla Mikheenko and Katherine M Munson and Terence D Murphy and Hugh E Olsen and Nathan D Olson and Luis F Paulin and David Porubsky and Tamara Potapova and Fedor Ryabov and Steven L Salzberg and Michael EG Sauria and Fritz J Sedlazeck and Kishwar Shafin and Valery A Shepelev and Alaina Shumate and Jessica M Storer and Likhitha Surapaneni and Angela M Taravella Oill and Françoise Thibaud-Nissen and Winston Timp and Marta Tomaszkiewicz and Mitchell R Vollger and Brian P Walenz and Allison C Watwood and Matthias H Weissensteiner and Aaron M Wenger and Melissa A Wilson and Samantha Zarate and Yiming Zhu and Justin M Zook and Evan E Eichler and Rachel J O’Neill and Michael C Schatz and Karen H Miga and Kateryna D Makova and Adam M Phillippy},

url = {https://www.nature.com/articles/s41586-023-06457-y},

doi = {https://doi.org/10.1038/s41586-023-06457-y},

year  = {2023},

date = {2023-09-14},

journal = {Nature},

volume = {621},

issue = {7978},

pages = {344-354},

abstract = {The human Y chromosome has been notoriously difficult to sequence and assemble because of its complex repeat structure that includes long palindromes, tandem repeats and segmental duplications1,2,3. As a result, more than half of the Y chromosome is missing from the GRCh38 reference sequence and it remains the last human chromosome to be finished4,5. Here, the Telomere-to-Telomere (T2T) consortium presents the complete 62,460,029-base-pair sequence of a human Y chromosome from the HG002 genome (T2T-Y) that corrects multiple errors in GRCh38-Y and adds over 30 million base pairs of sequence to the reference, showing the complete ampliconic structures of gene families TSPY, DAZ and RBMY; 41 additional protein-coding genes, mostly from the TSPY family; and an alternating pattern of human satellite 1 and 3 blocks in the heterochromatic Yq12 region. We have combined T2T-Y with a previous assembly of the CHM13 genome4 and mapped available population variation, clinical variants and functional genomics data to produce a complete and comprehensive reference sequence for all 24 human chromosomes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{zhou2023,

title = {Comparison of red raspberry and wild strawberry fruits reveals mechanisms of fruit type specification},

author = {Junhui Zhou and Muzi Li and Yongping Li and Yuwei Xiao and Xi Luo and Shenglan Gao and Zhimin Ma and Norah Sadowski and Winston Timp and Chris Dardick and Ann Callahan and Stephen M Mount and Zhongchi Liu},

url = {https://academic.oup.com/plphys/article/193/2/1016/7223938},

doi = {https://doi.org/10.1093/plphys/kiad409},

year  = {2023},

date = {2023-07-13},

journal = {Plant Physiology},

volume = {193},

issue = {2},

pages = {1016-1035},

abstract = {Belonging to Rosaceae, red raspberry (Rubus idaeus) and wild strawberry (Fragaria vesca) are closely related species with distinct fruit types. While the numerous ovaries become the juicy drupelet fruits in raspberry, their strawberry counterparts become dry and tasteless achenes. In contrast, while the strawberry receptacle, the stem tip, enlarges to become a red fruit, the raspberry receptacle shrinks and dries. The distinct fruit-forming ability of homologous organs in these 2 species allows us to investigate fruit type determination. We assembled and annotated the genome of red raspberry (R. idaeus) and characterized its fruit development morphologically and physiologically. Subsequently, transcriptomes of dissected and staged raspberry fruit tissues were compared to those of strawberry from a prior study. Class B MADS box gene expression was negatively associated with fruit-forming ability, which suggested a conserved inhibitory role of class B heterodimers, PISTILLATA/TM6 or PISTILLATA/APETALA3, for fruit formation. Additionally, the inability of strawberry ovaries to develop into fruit flesh was associated with highly expressed lignification genes and extensive lignification of the ovary pericarp. Finally, coexpressed gene clusters preferentially expressed in the dry strawberry achenes were enriched in “cell wall biosynthesis” and “ABA signaling,” while coexpressed clusters preferentially expressed in the fleshy raspberry drupelets were enriched in “protein translation.” Our work provides extensive genomic resources as well as several potential mechanisms underlying fruit type specification. These findings provide the framework for understanding the evolution of different fruit types, a defining feature of angiosperms.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{simner2023,

title = {Multicentre genetic diversity study of carbapenem-resistant Enterobacterales: predominance of untypeable pUVA-like blaKPC bearing plasmids},

author = {Patricia J Simner and Yehudit Bergman and Yunfan Fan and Emily B Jacobs and Srividya Ramakrishnan and Jennifer Lu and Shawna Lewis and Ann Hanlon and Pranita D Tamma and Michael C Schatz and Winston Timp and Karen C Carroll},

url = {https://academic.oup.com/jacamr/article/5/3/dlad061/7180147},

doi = {https://doi.org/10.1093/jacamr/dlad061},

year  = {2023},

date = {2023-05-26},

journal = {JAC-Antimicrobial Resistance},

volume = {5},

issue = {3},

pages = {dlad061},

abstract = {Objectives

Carbapenem-resistant Enterobacterales (CRE) are an urgent public health threat. A better understanding of the molecular epidemiology and transmission dynamics of CRE is necessary to limit their dissemination within healthcare settings. We sought to investigate the mechanisms of resistance and spread of CRE within multiple hospitals in Maryland.



Methods

From 2016 to 2018, all CRE were collected from any specimen source from The Johns Hopkins Medical Institutions. The isolates were further characterized using both phenotypic and genotypic approaches, including short- and/or long-read WGS.



Results

From 2016 to 2018, 302 of 40 908 (0.7%) unique Enterobacterales isolates were identified as CRE. Of CRE, 142 (47%) were carbapenemase-producing CRE with KPC (80.3%) predominating among various genera. Significant genetic diversity was identified among all CRE with high-risk clones serving as major drivers of clonal clusters. Further, we found the predominance of pUVA-like plasmids, with a subset harbouring resistance genes to environmental cleaning agents, involved in intergenus dissemination of blaKPC genes.



Conclusions

Our findings provide valuable data to understand the transmission dynamics of all CRE within the greater Maryland region. These data can help guide targeted interventions to limit CRE transmission in healthcare facilities.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hook2023,

title = {Beyond assembly: the increasing flexibility of single-molecule sequencing technology},

author = {Paul W Hook and Winston Timp},

url = {https://www.nature.com/articles/s41576-023-00600-1},

doi = {https://doi.org/10.1038/s41576-023-00600-1},

year  = {2023},

date = {2023-05-09},

journal = {Nature Reviews Genetics},

volume = {24},

issue = {9},

pages = {627-641},

abstract = {The maturation of high-throughput short-read sequencing technology over the past two decades has shaped the way genomes are studied. Recently, single-molecule, long-read sequencing has emerged as an essential tool in deciphering genome structure and function, including filling gaps in the human reference genome, measuring the epigenome and characterizing splicing variants in the transcriptome. With recent technological developments, these single-molecule technologies have moved beyond genome assembly and are being used in a variety of ways, including to selectively sequence specific loci with long reads, measure chromatin state and protein–DNA binding in order to investigate the dynamics of gene regulation, and rapidly determine copy number variation. These increasingly flexible uses of single-molecule technologies highlight a young and fast-moving part of the field that is leading to a more accessible era of nucleic acid sequencing.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Genomic insights into metabolic flux in ruby-throated hummingbirds},

author = {Ariel Gershman and Quinn Hauck and Morag Dick and Jerrica M Jamison and Michael Tassia and Xabier Agirrezabala and Saad Muhammad and Raafay Ali and Rachael E Workman and Mikel Valle and G William Wong and Kenneth C Welch and Winston Timp},

url = {https://genome.cshlp.org/content/33/5/703.full.pdf},

doi = {https://www.genome.org/cgi/doi/10.1101/gr.276779.122},

year  = {2023},

date = {2023-05-01},

urldate = {2023-05-01},

journal = {Genome Research},

volume = {33},

issue = {5},

pages = {703-714},

abstract = {Hummingbirds are very well adapted to sustain efficient and rapid metabolic shifts. They oxidize ingested nectar to directly fuel flight when foraging but have to switch to oxidizing stored lipids derived from ingested sugars during the night or long-distance migratory flights. Understanding how this organism moderates energy turnover is hampered by a lack of information regarding how relevant enzymes differ in sequence, expression, and regulation. To explore these questions, we generated a chromosome level de novo genome assembly of the ruby-throated hummingbird (A. colubris) using a combination of long and short read sequencing and scaffolding using other existing assemblies. We then used hybrid long and short-read RNA-sequencing for a comprehensive transcriptome assembly and annotation. Our genomic and transcriptomic data found positive selection of key metabolic genes in nectivorous avian species and a deletion of critical genes (GLUT4, GCK) involved in glucostasis in other vertebrates. We found expression of fructose-specific GLUT5 putatively in place of insulin-sensitive GLUT4, with predicted protein models suggesting affinity for both fructose and glucose. Alternative isoforms may even act to sequester fructose to preclude limitations from transport in metabolism. Finally, we identified differentially expressed genes from fasted and fed hummingbirds suggesting key pathways for the rapid metabolic switch hummingbirds undergo.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{vandiver2023,

title = {Nanopore sequencing identifies a higher frequency and expanded spectrum of mitochondrial DNA deletion mutations in human aging},

author = {Amy R Vandiver and Austin N Hoang and Allen Herbst and Cathy C Lee and Judd M Aiken and Debbie McKenzie and Michael A Teitell and Winston Timp and Jonathan Wanagat},

url = {https://onlinelibrary.wiley.com/doi/pdf/10.1111/acel.13842},

doi = {https://doi.org/10.1111/acel.13842},

year  = {2023},

date = {2023-03-27},

journal = {Aging Cell},

volume = {22},

issue = {6},

pages = {e13842},

abstract = {Mitochondrial DNA (mtDNA) deletion mutations cause many human diseases and are linked to age-induced mitochondrial dysfunction. Mapping the mutation spectrum and quantifying mtDNA deletion mutation frequency is challenging with next-generation sequencing methods. We hypothesized that long-read sequencing of human mtDNA across the lifespan would detect a broader spectrum of mtDNA rearrangements and provide a more accurate measurement of their frequency. We employed nanopore Cas9-targeted sequencing (nCATS) to map and quantitate mtDNA deletion mutations and develop analyses that are fit-for-purpose. We analyzed total DNA from vastus lateralis muscle in 15 males ranging from 20 to 81 years of age and substantia nigra from three 20-year-old and three 79-year-old men. We found that mtDNA deletion mutations detected by nCATS increased exponentially with age and mapped to a wider region of the mitochondrial genome than previously reported. Using simulated data, we observed that large deletions are often reported as chimeric alignments. To address this, we developed two algorithms for deletion identification which yield consistent deletion mapping and identify both previously reported and novel mtDNA deletion breakpoints. The identified mtDNA deletion frequency measured by nCATS correlates strongly with chronological age and predicts the deletion frequency as measured by digital PCR approaches. In substantia nigra, we observed a similar frequency of age-related mtDNA deletions to those observed in muscle samples, but noted a distinct spectrum of deletion breakpoints. NCATS-mtDNA sequencing allows the identification of mtDNA deletions on a single-molecule level, characterizing the strong relationship between mtDNA deletion frequency and chronological aging.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{gilpatrick2023,

title = {IVT generation of guideRNAs for Cas9-enrichment nanopore sequencing},

author = {Timothy Gilpatrick and Josh Zhiyong Wang and David Weiss and Alexis L Norris and James Eshleman and Winston Timp},

url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9934585/},

doi = {https://doi.org/10.1101%2F2023.02.07.527484},

year  = {2023},

date = {2023-02-07},

journal = {bioRxiv},

abstract = {Generating high-coverage sequencing coverage at select genomic loci has extensive applications in both research science and genetic medicine. Long-read sequencing technologies (e.g. nanopore sequencing) have expanded our ability to generate sequencing data in regions (e.g. repetitive elements) that are difficult to interrogate with short-read sequencing methods. In work presented here, we expand on our previous work using CRISPR/Cas9 for targeted nanopore sequencing by using in vitro transcribed guideRNAs, with 1100 guideRNAs in a single experiment. This approach decreases the cost per guideRNA, increases the number of guideRNAs that can be multiplexed in a single experiment, and provides a way to rapidly screen numerous guideRNAs for cutting efficiency. We apply this strategy in multiple patient-derived pancreatic cancer cell lines, demonstrating its ability to unveil structural variation in “deletion hotspots” around the tumor suppressor genes p16 (CDKN2A), and SMAD4.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sephtonclark2023,

title = {Similar evolutionary trajectories in an environmental Cryptococcus neoformans isolate after human and murine infection},

author = {Poppy Sephton-Clark and Scott A McConnell and Nina Grossman and Rosanna P Baker and Quigly Dragotakes and Yunfan Fan and Man Shun Fu and Gracen Gerbig and Seth Greengo and J Marie Hardwick and Madhura Kulkarni and Stuart M Levitz and Joshua D Nosanchuk and Shmuel Shoham and Daniel FQ Smith and Piotr Stempinski and Winston Timp and Maggie P Wear and Christina A Cuomo and Arturo Casadevall},

url = {https://www.pnas.org/doi/full/10.1073/pnas.2217111120},

doi = {https://doi.org/10.1073/pnas.2217111120},

year  = {2023},

date = {2023-01-10},

journal = {Proceedings of the National Academy of Sciences},

volume = {120},

issue = {2},

pages = {e2217111120},

abstract = {A pet cockatoo was the suspected source of Cryptococcus neoformans recovered from an immunocompromised patient with cryptococcosis based on molecular analyses available in 2000. Here, we report whole genome sequence analysis of the clinical and cockatoo strains. Both are closely related MATα strains belonging to the VNII lineage, confirming that the human infection likely originated from pet bird exposure. The two strains differ by 61 single nucleotide polymorphisms, including eight nonsynonymous changes involving seven genes. To ascertain whether changes in these genes are selected for during mammalian infection, we passaged the cockatoo strain in mice. Remarkably, isolates obtained from mouse tissue possess a frameshift mutation in one of the seven genes altered in the human sample (LQVO5_000317), a gene predicted to encode an SWI–SNF chromatin-remodeling complex protein. In addition, both cockatoo and patient strains as well as mouse-passaged isolates obtained from brain tissue had a premature stop codon in a homologue of ZFC3 (LQVO5_004463), a predicted single-zinc finger containing protein, which is associated with larger capsules when deleted and reverted to a full-length protein in the mouse-passaged isolates obtained from lung tissue. The patient strain and mouse-passaged isolates show variability in virulence factors, with differences in capsule size, melanization, rates of nonlytic expulsion from macrophages, and amoeba predation resistance. Our results establish that environmental strains undergo genomic and phenotypic changes during mammalian passage, suggesting that animal virulence can be a mechanism for genetic change and that the genomes of clinical isolates may provide a readout of mutations acquired during infection.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Yeh2022,

title = {Treatment of Sindbis Virus-Infected Neurons with Antibody to E2 Alters Synthesis of Complete and nsP1-Expressing Defective Viral RNAs},

author = {Jane X Yeh and Yunfan Fan and Maggie L Bartlett and Xiaoyan Zhang and Norah Sadowski and Debra A Hauer and Winston Timp and Diane E Griffin},

editor = {Anne Moscona, Columbia University Medical College},

url = {https://journals.asm.org/doi/pdf/10.1128/mbio.02221-22},

doi = {http://dx.doi.org/10.1128/mbio.02221-22},

year  = {2022},

date = {2022-09-07},

urldate = {2022-09-07},

journal = {Mbio},

volume = {13},

issue = {5},

pages = {e02221-22},

abstract = {Alphaviruses are positive-sense RNA viruses that are important causes of viral encephalomyelitis. Sindbis virus (SINV), the prototype alphavirus, preferentially infects neurons in mice and is a model system for studying mechanisms of viral clearance from the nervous system. Antibody specific to the SINV E2 glycoprotein plays an important role in SINV clearance, and this effect is reproduced in cultures of infected mature neurons. To determine how anti-E2 antibody affects SINV RNA synthesis, Oxford Nanopore Technologies direct long-read RNA sequencing was used to sequence viral RNAs following antibody treatment of infected neurons. Differentiated AP-7 rat olfactory neuronal cells, an in vitro model for mature neurons, were infected with SINV and treated with anti-E2 antibody. Whole-cell RNA lysates were collected for sequencing of poly(A)-selected RNA 24, 48, and 72 h after infection. Three primary species …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Joldersma2022,

title = {Assembly and annotation of Fragaria vesca 'Yellow Wonder' genome, a model diploid strawberry for molecular genetic research},

author = {Dirk Joldersma and Norah Sadowski and Winston Timp and Zhongchi Liu},

url = {https://www.maxapress.com/article/doi/10.48130/FruRes-2022-0013},

doi = {10.48130},

year  = {2022},

date = {2022-08-30},

urldate = {2022-08-30},

journal = {Fruit Research},

volume = {2},

issue = {1},

pages = {1-5},

abstract = {Fragaria vesca, a wild diploid strawberry, serves as a fundamental research model for cultivated strawberry. The current reference genomes available are limited to two closely-related accessions, Hawaii 4 and CFRA2339. The widely-used model accession'Yellow Wonder'does not yet have its reference genome. In this study, the genome of a 7 th generation inbred'Yellow Wonder'was assembled using a combination of Oxford Nanopore long reads and Illumina short reads. The de novo chromosome-scale assembly of this 220 megabase genome possesses 34,007 genes which were annotated through lift over from the Hawaii 4 genome annotation. Genome comparisons show that the'Yellow Wonder'genome is relatively distinct from the two previously published F. vesca accessions, Hawaii 4 and CFRA2339. The availability of a'Yellow Wonder'reference genome adds another important genomic resource to Fragaria vesca and enables rapid research progress in strawberry.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Long read mitochondrial genome sequencing using Cas9-guided adaptor ligation},

author = {Amy R Vandiver and Brittany Pielstick and Timothy Gilpatrick and Austin N Hoang and Hillary J Vernon and Jonathan Wanagat and Winston Timp},

url = {https://www.sciencedirect.com/science/article/pii/S1567724922000514},

doi = {https://doi.org/10.1016/j.mito.2022.06.003},

issn = {1567-7249},

year  = {2022},

date = {2022-07-01},

urldate = {2022-07-01},

journal = {Mitochondrion},

volume = {65},

pages = {176-183},

abstract = {The mitochondrial genome (mtDNA) is an important source of disease-causing genetic variability, but existing sequencing methods limit understanding, precluding phased measurement of mutations and clear detection of large sporadic deletions. We adapted a method for amplification-free sequence enrichment using Cas9 cleavage to obtain full length nanopore reads of mtDNA. We then utilized the long reads to phase mutations in a patient with an mtDNA-linked syndrome and demonstrated that this method can map age-induced mtDNA deletions. We believe this method will offer deeper insight into our understanding of mtDNA variation.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Tiek2022,

title = {Temozolomide-induced guanine mutations create exploitable vulnerabilities of guanine-rich DNA and RNA regions in drug-resistant gliomas},

author = {Deanna M Tiek and Beril Erdogdu and Roham Razaghi and Lu Jin and Norah Sadowski and Carla Alamillo-Ferrer and J Robert Hogg and Bassem R Haddad and David H Drewry and Carrow I Wells and Julie E Pickett and Xiao Song and Anshika Goenka and Bo Hu and Samuel A Goldlust and William J Zuercher and Mihaela Pertea and Winston Timp and Shi-Yuan Cheng and Rebecca B Riggins},

url = {https://www.science.org/doi/full/10.1126/sciadv.abn3471},

doi = {10.1126/sciadv.abn3471},

issn = {2375-2548},

year  = {2022},

date = {2022-06-22},

urldate = {2022-06-22},

journal = {Science Advances},

volume = {8},

issue = {25},

pages = {eabn3471},

abstract = {Temozolomide (TMZ) is a chemotherapeutic agent that has been the first-line standard of care for the aggressive brain cancer glioblastoma (GBM) since 2005. Although initially beneficial, TMZ resistance is universal and second-line interventions are an unmet clinical need. Here, we took advantage of the known mechanism of action of TMZ to target guanines (G) and investigated G-rich G-quadruplex (G4) and splice site changes that occur upon TMZ resistance. We report that TMZ-resistant GBM has guanine mutations that disrupt the G-rich DNA G4s and splice sites that lead to deregulated alternative splicing. These alterations create vulnerabilities, which are selectively targeted by either the G4-stabilizing drug TMPyP4 or a novel splicing kinase inhibitor of cdc2-like kinase. Last, we show that the G4 and RNA binding protein EWSR1 aggregates in the cytoplasm in TMZ-resistant GBM cells and patient samples …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Chang2022,

title = {Epigenetic comparison of CHO hosts and clones reveals divergent methylation and transcription patterns across lineages},

author = {Meiping Chang and Amit Kumar and Swetha Kumar and Steven Huhn and Winston Timp and Michael Betenbaugh and Zhimei Du},

doi = {https://doi.org/10.1002/bit.28036},

year  = {2022},

date = {2022-04-01},

journal = {Biotechnology and Bioengineering},

volume = {119},

issue = {4},

pages = {1062-0176},

abstract = {In this study, we examined DNA methylation and transcription profiles of recombinant clones derived from two different Chinese hamster ovary hosts. We found striking epigenetic differences between the clones, with global hypomethylation in the host 1 clones that produce bispecific antibody with higher productivity and complex assembly efficiency. Whereas the methylation patterns were found mostly inherited from the host, the host 1 clones exhibited continued demethylation reflected by the hypomethylation of newly emerged differential methylation regions (DMRs) even at the clone development stage. Several interconnected biological functions and pathways including cell adhesion, regulation of ion transport, and cholesterol biosynthesis were significantly altered between the clones at the RNA expression level and contained DMR in the promoter and/or gene‐body of the transcripts, suggesting epigenetic …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Sholes2022,

title = {Chromosome specific telomere lengths and the minimal functional telomere revealed by nanopore sequencing},

author = {Samantha L Sholes and Kayarash Karimian and Ariel Gershman and Thomas J Kelly and Winston Timp and Carol W Greider},

url = {https://genome.cshlp.org/content/32/4/616.full.pdf},

doi = {10.1101/gr.275868.121},

year  = {2022},

date = {2022-04-01},

urldate = {2021-01-01},

journal = {Genome Research},

volume = {32},

issue = {4},

pages = {616-628},

publisher = {Cold Spring Harbor Laboratory},

abstract = {We developed a method to tag telomeres and measure telomere length by nanopore sequencing in the yeast S. cerevisiae. Nanopore allows long read sequencing through the telomere, subtelomere and into unique chromosomal sequence, enabling assignment of telomere length to a specific chromosome end. We observed chromosome end specific telomere lengths that were stable over 120 cell divisions. These stable chromosome specific telomere lengths may be explained by stochastic clonal variation or may represent a new biological mechanism that maintains equilibrium unique to each chromosomes end. We examined the role of RIF1 and TEL1 in telomere length regulation and found that TEL1 is epistatic to RIF1 at most telomeres, consistent with the literature. However, at telomeres that lack subtelomeric Ytextquoteright sequences, tel1Δ rif1Δ double mutants had a very small, but significant, increase in telomere length compared to the tel1Δ single mutant, suggesting an influence of Ytextquoteright elements on telomere length regulation. We sequenced telomeres in a telomerase-null mutant (est2Δ) and found the minimal telomere length to be around 75bp. In these est2Δ mutants there were many apparent telomere recombination events at individual telomeres before the generation of survivors, and these events were significantly reduced in est2Δ rad52Δ double mutants. The rate of telomere shortening in the absence of telomerase was similar across all chromosome ends at about 5 bp per generation. This new method gives quantitative, high resolution telomere length measurement at each individual chromosome end, suggests possible new biological mechanisms regulating telomere length, and provides capability to test new hypotheses.Competing Interest StatementWinston Timp has two patents (8,748,091 and 8,394,584) licensed to Oxford Nanopore Technologies.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Altemose2022,

title = {Complete genomic and epigenetic maps of human centromeres},

author = {Nicolas Altemose and Glennis A Logsdon and Andrey V Bzikadze and Pragya Sidhwani and Sasha A Langley and Gina V Caldas and Savannah J Hoyt and Lev Uralsky and Fedor D Ryabov and Colin J Shew and Michael EG Sauria and Matthew Borchers and Ariel Gershman and Alla Mikheenko and Valery A Shepelev and Tatiana Dvorkina and Olga Kunyavskaya and Mitchell R Vollger and Arang Rhie and Ann M McCartney and Mobin Asri and Ryan Lorig-Roach and Kishwar Shafin and Julian K Lucas and Sergey Aganezov and Daniel Olson and Leonardo Gomes de Lima and Tamara Potapova and Gabrielle A Hartley and Marina Haukness and Peter Kerpedjiev and Fedor Gusev and Kristof Tigyi and Shelise Brooks and Alice Young and Sergey Nurk and Sergey Koren and Sofie R Salama and Benedict Paten and Evgeny I Rogaev and Aaron Streets and Gary H Karpen and Abby F Dernburg and Beth A Sullivan and Aaron F Straight and Travis J Wheeler and Jennifer L Gerton and Evan E Eichler and Adam M Phillippy and Winston Timp and Megan Y Dennis and Rachel J O’Neill and Justin M Zook and Michael C Schatz and Pavel A Pevzner and Mark Diekhans and Charles H Langley and Ivan A Alexandrov and Karen H Miga},

url = {https://www.science.org/doi/full/10.1126/science.abl4178},

doi = {10.1126/science.abl4178},

year  = {2022},

date = {2022-04-01},

urldate = {2022-04-01},

journal = {Science},

volume = {376},

issue = {6588},

pages = {eabl4178},

publisher = {Cold Spring Harbor Laboratory},

abstract = {Existing human genome assemblies have almost entirely excluded highly repetitive sequences within and near centromeres, limiting our understanding of their sequence, evolution, and essential role in chromosome segregation. Here, we present an extensive study of newly assembled peri/centromeric sequences representing 6.2% (189.9 Mb) of the first complete, telomere-to-telomere human genome assembly (T2T-CHM13). We discovered novel patterns of peri/centromeric repeat organization, variation, and evolution at both large and small length scales. We also found that inner kinetochore proteins tend to overlap the most recently duplicated subregions within centromeres. Finally, we compared chromosome X centromeres across a diverse panel of individuals and uncovered structural, epigenetic, and sequence variation at single-base resolution across these regions. In total, this work provides an unprecedented atlas of human centromeres to guide future studies of their complex and critical functions as well as their unique evolutionary dynamics.One-sentence summary Deep characterization of fully assembled human centromeres reveals their architecture and fine-scale organization, variation, and evolution.Competing Interest StatementSK and KHM have received travel funds to speak at symposia organized by Oxford Nanopore. W.T. has two patents (8,748,091 and 8,394,584) licensed to Oxford Nanopore Technologies.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hoyt2021.07.12.451456,

title = {From telomere to telomere: the transcriptional and epigenetic state of human repeat elements},

author = {Savannah J Hoyt and Jessica M Storer and Gabrielle A Hartley and Patrick GS Grady and Ariel Gershman and Leonardo G de Lima and Charles Limouse and Reza Halabian and Luke Wojenski and Matias Rodriguez and Nicolas Altemose and Arang Rhie and Leighton J Core and Jennifer L Gerton and Wojciech Makalowski and Daniel Olson and Jeb Rosen and Arian FA Smit and Aaron F Straight and Mitchell R Vollger and Travis J Wheeler and Michael C Schatz and Evan E Eichler and Adam M Phillippy and Winston Timp and Karen H Miga and Rachel J O’Neill},

url = {https://www.science.org/doi/full/10.1126/science.abk3112},

doi = {10.1126/science.abk3112},

year  = {2022},

date = {2022-04-01},

urldate = {2021-01-01},

journal = {Science},

volume = {376},

issue = {6588},

pages = {eabk3112},

publisher = {Cold Spring Harbor Laboratory},

abstract = {Mobile elements and highly repetitive genomic regions are potent sources of lineage-specific genomic innovation and fingerprint individual genomes. Comprehensive analyses of large, composite or arrayed repeat elements and those found in more complex regions of the genome require a complete, linear genome assembly. Here we present the first de novo repeat discovery and annotation of a complete human reference genome, T2T-CHM13v1.0. We identified novel satellite arrays, expanded the catalog of variants and families for known repeats and mobile elements, characterized new classes of complex, composite repeats, and provided comprehensive annotations of retroelement transduction events. Utilizing PRO-seq to detect nascent transcription and nanopore sequencing to delineate CpG methylation profiles, we defined the structure of transcriptionally active retroelements in humans, including for the first time those found in centromeres. Together, these data provide expanded insight into the diversity, distribution and evolution of repetitive regions that have shaped the human genome.Competing Interest StatementKHM has received travel funds to speak at symposia organized by Oxford Nanopore. WT has two patents (8,748,091 and 8,394,584) licensed to Oxford Nanopore Technologies. All other authors declare that they have no competing interests.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Vollger2022,

title = {Segmental duplications and their variation in a complete human genome},

author = {Mitchell R Vollger and Xavi Guitart and Philip C Dishuck and Ludovica Mercuri and William T Harvey and Ariel Gershman and Mark Diekhans and Arvis Sulovari and Katherine M Munson and Alexandra P Lewis and Kendra Hoekzema and David Porubsky and Ruiyang Li and Sergey Nurk and Sergey Koren and Karen H Miga and Adam M Phillippy and Winston Timp and Mario Ventura and Evan E Eichler},

url = {https://www.science.org/doi/full/10.1126/science.abj6965},

doi = {10.1126/science.abj6965},

isbn = {0036-8075},

year  = {2022},

date = {2022-04-01},

urldate = {2021-01-01},

journal = {Science},

volume = {376},

issue = {6588},

pages = {eabj6965},

publisher = {Cold Spring Harbor Laboratory},

abstract = {Despite their importance in disease and evolution, highly identical segmental duplications (SDs) are among the last regions of the human reference genome (GRCh38) to be fully sequenced. Using a complete telomere-to-telomere human genome (T2T-CHM13), we present a comprehensive view of human SD organization. SDs account for nearly one-third of the additional sequence, increasing the genome-wide estimate from 5.4 to 7.0% [218 million base pairs (Mbp)]. An analysis of 268 human genomes shows that 91% of the previously unresolved T2T-CHM13 SD sequence (68.3 Mbp) better represents human copy number variation. Comparing long-read assemblies from human (n = 12) and nonhuman primate (n = 5) genomes, we systematically reconstruct the evolution and structural haplotype diversity of biomedically relevant and duplicated genes. This analysis reveals patterns of structural heterozygosity …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Gershman2022,

title = {Epigenetic Patterns in a Complete Human Genome},

author = {Ariel Gershman and Michael EG Sauria and Xavi Guitart and Mitchell R Vollger and Paul W Hook and Savannah J Hoyt and Miten Jain and Alaina Shumate and Roham Razaghi and Sergey Koren and Nicolas Altemose and Gina V Caldas and Glennis A Logsdon and Arang Rhie and Evan E Eichler and Michael C Schatz and Rachel J O’Neill and Adam M Phillippy and Karen H Miga and Winston Timp},

url = {https://www.science.org/doi/full/10.1126/science.abj5089},

doi = {10.1126/science.abj5089},

issn = {0036-8075},

year  = {2022},

date = {2022-04-01},

urldate = {2021-01-01},

journal = {Science},

volume = {376},

issue = {6588},

pages = {eabj5089},

publisher = {Cold Spring Harbor Laboratory},

abstract = {The completion of the first telomere-to-telomere human genome, T2T-CHM13, enables exploration of the full epigenome, removing limitations previously imposed by the missing reference sequence. Existing epigenetic studies omit unassembled and unmappable genomic regions (e.g. centromeres, pericentromeres, acrocentric chromosome arms, subtelomeres, segmental duplications, tandem repeats). Leveraging the new assembly, we were able to measure enrichment of epigenetic marks with short reads using k-mer assisted mapping methods. This granted array-level enrichment information to characterize the epigenetic regulation of these satellite repeats. Using nanopore sequencing data, we generated base level maps of the most complete human methylome ever produced. We examined methylation patterns in satellite DNA and revealed organized patterns of methylation along individual molecules. When exploring the centromeric epigenome, we discovered a distinctive dip in centromere methylation consistent with active sites of kinetochore assembly. Through long-read chromatin accessibility measurements (nanoNOMe) paired to CUT&RUN data, we found the hypomethylated region was extremely inaccessible and paired to CENP-A/B binding. With long-reads we interrogated allele-specific, longrange epigenetic patterns in complex macro-satellite arrays such as those involved in X chromosome inactivation. Using the single molecule measurements we can clustered reads based on methylation status alone distinguishing epigenetically heterogeneous and homogeneous areas. The analysis provides a framework to investigate the most elusive regions of the human genome, applying both long and short-read technology to grant new insights into epigenetic regulation.Competing Interest StatementW.T. has two patents (8,748,091 and 8,394,584) licensed to Oxford Nanopore Technologies.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}