Publications

@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{Volkel2024,

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

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

url = {https://www.biorxiv.org/content/biorxiv/early/2024/06/18/2024.06.18.599582.full.pdf},

doi = {https://doi.org/10.1101/2024.06.18.599582},

year  = {2024},

date = {2024-06-18},

journal = {bioRxiv},

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 seconds/read. Our new Alignment Matrix Trellis soft decoder improves throughput by 257x 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 4x larger than prior MSA-based decoders. We also compare RNA to DNA, and find that RNA has 85% as many error free reads as compared to DNA.

},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Cunningham2024,

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

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

url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11092758/},

doi = {https://doi.org/10.1101%2F2024.05.02.592251},

year  = {2024},

date = {2024-05-03},

journal = {bioRxiv},

abstract = {C. glabrata 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 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 1000-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 drugging of which by SDZ 90-215 or myriocin enhanced the potency of micafungin in vitro . These findings provide insights into 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{Morina2024,

title = {Investigating Subpopulation Dynamics in Clonal CHO-K1 Cells with Single-Cell RNA Sequencing},

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

url = {https://www.biorxiv.org/content/biorxiv/early/2024/05/24/2024.05.22.595338.full.pdf},

doi = {https://doi.org/10.1101/2024.05.22.595338},

year  = {2024},

date = {2024-03-24},

urldate = {2024-03-24},

journal = {bioRxiv},

abstract = {Chinese Hamster Ovary (CHO) cells are used to 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 ability to produce the protein of interest over time, known as their stability. But these CHO cells have primarily been studied in bulk, working under the assumption that these bulk samples are identical because of genetic clonality across the sample; however, this does not address other forms of cellular heterogeneity in these ostensibly clonal cells. It is possible these variable stability phenotypes 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 the unstable clone 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{Kovaka2024,

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.ncbi.nlm.nih.gov/pmc/articles/PMC10942365/},

doi = {https://doi.org/10.1101%2F2024.03.05.583511},

year  = {2024},

date = {2024-03-10},

journal = {bioRxiv},

abstract = {Nanopore signal analysis enables detection of nucleotide modifications from native DNA and RNA sequencing, providing both accurate genetic/transcriptomic and epigenetic information without additional library preparation. Presently, only a limited set of modifications can be directly basecalled (e.g. 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 ONT’s 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{thatavarty2023,

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 Zvi Bar},

url = {https://www.biorxiv.org/content/biorxiv/early/2023/11/20/2023.11.20.567792.full.pdf},

doi = {https://doi.org/10.1101/2023.11.20.567792},

year  = {2023},

date = {2023-11-20},

urldate = {2023-11-20},

journal = {bioRxiv},

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{saba2023,

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://www.ncbi.nlm.nih.gov/pmc/articles/PMC10635049/},

doi = {https://doi.org/10.1101%2F2023.11.01.565189},

year  = {2023},

date = {2023-11-02},

urldate = {2023-11-02},

journal = {bioRxiv},

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 implicate LARP1 in 40S- or 80S-ribosome complexes that repress and stabilize TOPs. However, a mechanistic understanding of how LARP1 and TOPs interact with these complexes to coordinate TOP outcomes is lacking. Here, we show that LARP1 senses the cellular supply of ribosomes by directly binding non-translating ribosomal subunits. Cryo-EM structures reveal a previously uncharacterized domain of LARP1 bound to and occluding the 40S mRNA channel. Free cytosolic ribosomes induce sequestration of TOPs in repressed 80S-LARP1-TOP complexes independent of alterations in mTOR signaling. Together, this work demonstrates a general ribosome-sensing function of LARP1 that allows it to tune ribosome protein synthesis to cellular demand.},

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{Nurk2022,

title = {The complete sequence of a human genome},

author = {Sergey Nurk and Sergey Koren and Arang Rhie and Mikko Rautiainen and Andrey V Bzikadze and Alla Mikheenko and Mitchell R Vollger and Nicolas Altemose and Lev Uralsky and Ariel Gershman and Sergey Aganezov and Savannah J Hoyt and Mark Diekhans and Glennis A Logsdon and Michael Alonge and Stylianos E Antonarakis and Matthew Borchers and Gerard G Bouffard and Shelise Y Brooks and Gina V Caldas and Nae-Chyun Chen and Haoyu Cheng and Chen-Shan Chin and William Chow and Leonardo G de Lima and Philip C Dishuck and Richard Durbin and Tatiana Dvorkina and Ian T Fiddes and Giulio Formenti and Robert S Fulton and Arkarachai Fungtammasan and Erik Garrison and Patrick GS Grady and Tina A Graves-Lindsay and Ira M Hall and Nancy F Hansen and Gabrielle A Hartley and Marina Haukness and Kerstin Howe and Michael W Hunkapiller and Chirag Jain and Miten Jain and Erich D Jarvis and Peter Kerpedjiev and Melanie Kirsche and Mikhail Kolmogorov and Jonas Korlach and Milinn Kremitzki and Heng Li and Valerie V Maduro and Tobias Marschall and Ann M McCartney and Jennifer McDaniel and Danny E Miller and James C Mullikin and Eugene W Myers and Nathan D Olson and Benedict Paten and Paul Peluso and Pavel A Pevzner and David Porubsky and Tamara Potapova and Evgeny I Rogaev and Jeffrey A Rosenfeld and Steven L Salzberg and Valerie A Schneider and Fritz J Sedlazeck and Kishwar Shafin and Colin J Shew and Alaina Shumate and Ying Sims and Arian FA Smit and Daniela C Soto and Ivan Sović and Jessica M Storer and Aaron Streets and Beth A Sullivan and Françoise Thibaud-Nissen and James Torrance and Justin Wagner and Brian P Walenz and Aaron Wenger and Jonathan MD Wood and Chunlin Xiao and Stephanie M Yan and Alice C Young and Samantha Zarate and Urvashi Surti and Rajiv C McCoy and Megan Y Dennis and Ivan A Alexandrov and Jennifer L Gerton and Rachel J O’Neill and Winston Timp and Justin M Zook and Michael C Schatz and Evan E Eichler and Karen H Miga and Adam M Phillippy},

url = {https://www.science.org/doi/10.1126/science.abj6987},

doi = {10.1126/science.abj6987},

issn = {0036-8075},

year  = {2022},

date = {2022-04-01},

urldate = {2021-01-01},

journal = {Science},

volume = {376},

issue = {6588},

pages = {44-53},

publisher = {Cold Spring Harbor Laboratory},

abstract = {Since its initial release in 2000, the human reference genome has covered only the euchromatic fraction of the genome, leaving important heterochromatic regions unfinished. Addressing the remaining 8% of the genome, the Telomere-to-Telomere (T2T) Consortium presents a complete 3.055 billion–base pair sequence of a human genome, T2T-CHM13, that includes gapless assemblies for all chromosomes except Y, corrects errors in the prior references, and introduces nearly 200 million base pairs of sequence containing 1956 gene predictions, 99 of which are predicted to be protein coding. The completed regions include all centromeric satellite arrays, recent segmental duplications, and the short arms of all five acrocentric chromosomes, unlocking these complex regions of the genome to variational and functional studies.},

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}

}

@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{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{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{Stephenson2022,

title = {Direct detection of RNA modifications and structure using single molecule nanopore sequencing},

author = {William Stephenson and Roham Razaghi and Steven Busan and Kevin M Weeks and Winston Timp and Peter Smibert},

url = {https://www.sciencedirect.com/science/article/pii/S2666979X22000143},

doi = {10.1016/j.xgen.2022.100097},

issn = {2666-979X},

year  = {2022},

date = {2022-02-09},

urldate = {2020-05-01},

journal = {Cell Genomics},

volume = {2},

issue = {2},

pages = {100097},

publisher = {Cold Spring Harbor Laboratory},

abstract = {Modifications are present on many classes of RNA, including tRNA, rRNA, and mRNA. These modifications modulate diverse biological processes such as genetic recoding and mRNA export and folding. In addition, modifications can be introduced to RNA molecules using chemical probing strategies that reveal RNA structure and dynamics. Many methods exist to detect RNA modifications by short-read sequencing; however, limitations on read length inherent to short-read-based methods dissociate modifications from their native context, preventing single-molecule modification analysis. Here, we demonstrate direct RNA nanopore sequencing to detect endogenous and exogenous RNA modifications on long RNAs at the single-molecule level. We detect endogenous 2′-O-methyl and base modifications across E. coli and S. cerevisiae ribosomal RNAs as shifts in current signal and dwell times distally through …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Razaghi2022,

title = {Modbamtools: Analysis of single-molecule epigenetic data for long-range profiling, heterogeneity, and clustering},

author = {Roham Razaghi and Paul W Hook and Shujun Ou and Michael Schatz and Kasper D Hansen and Miten Jain and Winston Timp},

url = {https://www.biorxiv.org/content/10.1101/2022.07.07.499188v1},

doi = {https://doi.org/10.1101/2022.07.07.499188},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

journal = {bioRxiv},

abstract = {The advent of long-read sequencing methods provides new opportunities for profiling the epigenome - especially as the methylation signature comes for "free" when native DNA is sequenced on either Oxford Nanopore or Pacific Biosciences instruments. However, we lack tools to visualize and analyze data generated from these new sources. Recent efforts from the GA4GH consortium have standardized methods to encode modification location and probabilities in the BAM format. Leveraging this standard format, we developed a technology-agnostic tool, modbamtools to visualize, manipulate and compare base modification/methylation data in a fast and robust way. modbamtools can produce high quality, interactive, and publication-ready visualizations as well as provide modules for downstream analysis of base modifications. Modbamtools comprehensive manual and tutorial can be found at https://rrazaghi.github.io/modbamtools/.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Neale2022,

title = {Assembled and annotated 26.5 Gbp coast redwood genome: a resource for estimating evolutionary adaptive potential and investigating hexaploid origin},

author = {David B Neale and Aleksey V Zimin and Sumaira Zaman and Alison D Scott and Bikash Shrestha and Rachael E Workman and Daniela Puiu and Brian J Allen and Zane J Moore and Manoj K Sekhwal and Amanda R De La Torre and Patrick E McGuire and Emily Burns and Winston Timp and Jill L Wegrzyn and Steven L Salzberg},

url = {https://academic.oup.com/g3journal/article/12/1/jkab380/6460957},

doi = {10.1093/g3journal/jkab380},

year  = {2022},

date = {2022-01-01},

journal = {G3},

volume = {12},

issue = {1},

pages = {jkab380},

abstract = {Sequencing, assembly, and annotation of the 26.5 Gbp hexaploid genome of coast redwood (Sequoia sempervirens) was completed leading toward discovery of genes related to climate adaptation and investigation of the origin of the hexaploid genome. Deep-coverage short-read Illumina sequencing data from haploid tissue from a single seed were combined with long-read Oxford Nanopore Technologies sequencing data from diploid needle tissue to create an initial assembly, which was then scaffolded using proximity ligation data to produce a highly contiguous final assembly, SESE 2.1, with a scaffold N50 size of 44.9 Mbp. The assembly included several scaffolds that span entire chromosome arms, confirmed by the presence of telomere and centromere sequences on the ends of the scaffolds. The structural annotation produced 118,906 genes with 113 containing introns that exceed 500 Kbp in length …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kandathil2021,

title = {Plasma virome and the risk of blood-borne infection in persons with substance use disorder},

author = {Abraham J Kandathil and Andrea L Cox and Kimberly Page and David Mohr and Roham Razaghi and Khalil G Ghanem and Susan A Tuddenham and Yu-Hsiang Hsieh and Jennifer L Evans and Kelly E Coller and Winston Timp and David D Celentano and Stuart C Ray and David L Thomas},

url = {https://www.nature.com/articles/s41467-021-26980-8},

doi = {10.1038/s41467-021-26980-8},

issn = {2041-1723},

year  = {2021},

date = {2021-11-25},

journal = {Nature Communications},

volume = {12},

issue = {1},

pages = {1-7},

abstract = {There is an urgent need for innovative methods to reduce transmission of bloodborne pathogens like HIV and HCV among people who inject drugs (PWID). We investigate if PWID who acquire non-pathogenic bloodborne viruses like anelloviruses and pegiviruses might be at greater risk of acquiring a bloodborne pathogen. PWID who later acquire HCV accumulate more non-pathogenic viruses in plasma than matched controls who do not acquire HCV infection. Additionally, phylogenetic analysis of those non-pathogenic virus sequences reveals drug use networks. Here we find first in Baltimore and confirm in San Francisco that the accumulation of non-pathogenic viruses in PWID is a harbinger for subsequent acquisition of pathogenic viruses, knowledge that may guide the prioritization of the public health resources to combat HIV and HCV.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Mahmoud2021-zq,

title = {PRINCESS: comprehensive detection of haplotype resolved SNVs, SVs, and methylation},

author = {Medhat Mahmoud and Harshavardhan Doddapaneni and Winston Timp and Fritz J Sedlazeck},

year  = {2021},

date = {2021-09-01},

journal = {Genome Biology},

volume = {22},

number = {1},

pages = {268},

abstract = {Long-read sequencing has been shown to have advantages in 

 structural variation (SV) detection and methylation calling. Many 

 studies focus either on SV, methylation, or phasing of SNV; 

 however, only the combination of variants provides a 

 comprehensive insight into the sample and thus enables novel 

 findings in biology or medicine. PRINCESS is a structured 

 workflow that takes raw sequence reads and generates a fully 

 phased SNV, SV, and methylation call set within a few hours. 

 PRINCESS achieves high accuracy and long phasing even on low 

 coverage datasets and can resolve repetitive, complex medical 

 relevant genes that often escape detection. PRINCESS is publicly 

 available at https://github.com/MeHelmy/princess under the MIT 

 license.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Lietard2021,

title = {Chemical and photochemical error rates in light-directed synthesis of complex DNA libraries},

author = {Jory Lietard and Adrien Leger and Yaniv Erlich and Norah Sadowski and Winston Timp and Mark M Somoza},

url = {https://doi.org/10.1093/nar/gkab505},

doi = {10.1093/nar/gkab505},

issn = {0305-1048},

year  = {2021},

date = {2021-07-09},

urldate = {2021-07-09},

journal = {Nucleic Acids Research},

volume = {49},

issue = {12},

pages = {6687-6701},

abstract = {Nucleic acid microarrays are the only tools that can supply very large oligonucleotide libraries, cornerstones of the nascent fields of de novo gene assembly and DNA data storage. Although the chemical synthesis of oligonucleotides is highly developed and robust, it is not error free, requiring the design of methods that can correct or compensate for errors, or select for high-fidelity oligomers. However, outside the realm of array manufacturers, little is known about the sources of errors and their extent. In this study, we look at the error rate of DNA libraries synthesized by photolithography and dissect the proportion of deletion, insertion and substitution errors. We find that the deletion rate is governed by the photolysis yield. We identify the most important substitution error and correlate it to phosphoramidite coupling. Besides synthetic failures originating from the coupling cycle, we uncover the role of imperfections …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Fan2021,

title = {Genome and transcriptome of a pathogenic yeast, Candida nivariensis},

author = {Yunfan Fan and Andrew N Gale and Anna Bailey and Kali Barnes and Kiersten Colotti and Michal Mass and Luke B Morina and Bailey Robertson and Remy Schwab and Niki Tselepidakis and Winston Timp},

url = {https://academic.oup.com/g3journal/advance-article-pdf/doi/10.1093/g3journal/jkab137/38337897/jkab137.pdf},

doi = {10.1093/g3journal/jkab137},

year  = {2021},

date = {2021-04-01},

urldate = {2021-04-01},

journal = {G3},

volume = {11},

issue = {7},

pages = {jkab137},

publisher = {Cold Spring Harbor Laboratory},

abstract = {We present a highly contiguous genome and transcriptome of the pathogenic yeast, Candida nivariensis. We sequenced both the DNA and RNA of this species using both the Oxford Nanopore Technologies (ONT) and Illumina platforms. We assembled the genome into an 11.8 Mb draft composed of 16 contigs with an N50 of 886 Kb, including a circular mitochondrial sequence of 28 Kb. Using direct RNA nanopore sequencing and Illumina cDNA sequencing, we constructed an annotation of our new assembly, supplemented by lifting over genes from Saccharomyces cerevisiae and Candida glabrata.Competing Interest StatementWT holds two patents (US 8,748,091 and US 8,394,584) licensed to ONT. YF and WT have received travel funding from ONT.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{10.1093/g3journal/jkaa047b,

title = {De novo genome assembly of the tobacco hornworm moth (Manduca sexta)},

author = {Ariel Gershman and Tatiana G Romer and Yunfan Fan and Roham Razaghi and Wendy A Smith and Winston Timp},

url = {https://doi.org/10.1093/g3journal/jkaa047},

doi = {10.1093/g3journal/jkaa047},

issn = {2160-1836},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {G3 Genes|Genomes|Genetics},

volume = {11},

number = {1},

pages = {jkaa047},

abstract = {The tobacco hornworm, Manduca sexta, is a lepidopteran insect that is used extensively as a model system for studying insect biology, development, neuroscience, and immunity. However, current studies rely on the highly fragmented reference genome Msex_1.0, which was created using now-outdated technologies and is hindered by a variety of deficiencies and inaccuracies. We present a new reference genome for M. sexta, JHU_Msex_v1.0, applying a combination of modern technologies in a de novo assembly to increase continuity, accuracy, and completeness. The assembly is 470 Mb and is ∼20× more continuous than the original assembly, with scaffold N50 > 14 Mb. We annotated the assembly by lifting over existing annotations and supplementing with additional supporting RNA-based data for a total of 25,256 genes. The new reference assembly is accessible in annotated form for public use. We demonstrate that improved continuity of the M. sexta genome improves resequencing studies and benefits future research on M. sexta as a model organism.},

note = {jkaa047},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{clark2021epigenetically,

title = {Epigenetically regulated digital signaling defines epithelial innate immunity at the tissue level},

author = {Helen R Clark and Connor McKenney and Nathan M Livingston and Ariel Gershman and Seema Sajjan and Isaac S Chan and Andrew J Ewald and Winston Timp and Bin Wu and Abhyudai Singh and Sergi Regot},

year  = {2021},

date = {2021-01-01},

journal = {Nature Communications},

volume = {12},

number = {1},

pages = {1--13},

publisher = {Nature Publishing Group},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{thielen_jci_insight,

title = {Genomic diversity of SARS-CoV-2 during early introduction into the Baltimore–Washington metropolitan area},

author = {Peter M Thielen and Shirlee Wohl and Thomas Mehoke and Srividya Ramakrishnan and Melanie Kirsche and Oluwaseun Falade-Nwulia and Nídia S Trovão and Amanda Ernlund and Craig Howser and Norah Sadowski and Paul C Morris and Mark Hopkins and Matthew Schwartz and Yunfan Fan and Victoria Gniazdowski and Justin Lessler and Lauren Sauer and Michael C Schatz and Jared D Evans and Stuart C Ray and Winston Timp and Heba H Mostafa},

url = {https://insight.jci.org/articles/view/144350},

doi = {10.1172/jci.insight.144350},

year  = {2021},

date = {2021-01-01},

journal = {JCI Insight},

volume = {6},

number = {6},

publisher = {The American Society for Clinical Investigation},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Weinguny_cho_2021b,

title = {Subcloning induces changes in the DNA-methylation pattern of outgrowing Chinese hamster ovary cell colonies},

author = {Marcus Weinguny and Gerald Klanert and Peter Eisenhut and Isac Lee and Winston Timp and Nicole Borth},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/biot.202000350},

doi = {https://doi.org/10.1002/biot.202000350},

year  = {2021},

date = {2021-01-01},

journal = {Biotechnology Journal},

pages = {2000350},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{yee_metagenomic_2020b,

title = {Metagenomic next-generation sequencing of rectal swabs for the surveillance of antimicrobial-resistant organisms on the Illumina Miseq and Oxford MinION platforms},

author = {Rebecca Yee and Florian P Breitwieser and Stephanie Hao and Belita N A Opene and Rachael E Workman and Pranita D Tamma and Jennifer Dien-Bard and Winston Timp and Patricia J Simner},

url = {https://doi.org/10.1007/s10096-020-03996-4},

doi = {10.1007/s10096-020-03996-4},

issn = {1435-4373},

year  = {2021},

date = {2021-01-01},

urldate = {2020-08-01},

journal = {European Journal of Clinical Microbiology & Infectious Diseases},

volume = {40},

issue = {1},

pages = {95-102},

abstract = {Antimicrobial resistance (AMR) is a public health threat where efficient surveillance is needed to prevent outbreaks. Existing methods for detection of gastrointestinal colonization of multidrug-resistant organisms (MDRO) are limited to specific organisms or resistance mechanisms. Metagenomic next-generation sequencing (mNGS) is a more rapid and agnostic diagnostic approach for microbiome and resistome investigations. We determined if mNGS can detect MDRO from rectal swabs in concordance with standard microbiology results. We performed and compared mNGS performance on short-read Illumina MiSeq (N = 10) and long-read Nanopore MinION (N = 5) platforms directly from rectal swabs to detect vancomycin-resistant enterococci (VRE) and carbapenem-resistant Gram-negative organisms (CRO). We detected Enterococcus faecium (N = 8) and Enterococcus faecalis (N = 2) with associated van genes (9/10) in concordance with VRE culture-based results. We studied the microbiome and identified CRO, Pseudomonas aeruginosa (N = 1), Enterobacter cloacae (N = 1), and KPC-producing Klebsiella pneumoniae (N = 1). Nanopore real-time analysis detected the blaKPC gene in 2.3 min and provided genetic context (blaKPC harbored on pKPC_Kp46 IncF plasmid). Illumina sequencing provided accurate allelic variant determination (i.e., blaKPC-2) and strain typing of the K. pneumoniae (ST-15). We demonstrated an agnostic approach for surveillance of MDRO, examining advantages of both short- and long-read mNGS methods for AMR detection.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{10.1371/journal.ppat.1009537,

title = {A plasmid locus associated with textitKlebsiella clinical infections encodes a microbiome-dependent gut fitness factor},

author = {Jay Vornhagen and Christine M. Bassis and Srividya Ramakrishnan and Robert Hein and Sophia Mason and Yehudit Bergman and Nicole Sunshine and Yunfan Fan and Caitlyn L. Holmes and Winston Timp and Michael C. Schatz and Vincent B. Young and Patricia J. Simner and Michael A. Bachman},

url = {https://doi.org/10.1371/journal.ppat.1009537},

doi = {10.1371/journal.ppat.1009537},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {PLOS Pathogens},

volume = {17},

number = {4},

pages = {1-34},

publisher = {Public Library of Science},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Polinskieabe8290,

title = {The American lobster genome reveals insights on longevity, neural, and immune adaptations},

author = {Jennifer M. Polinski and Aleksey V. Zimin and K. Fraser Clark and Andrea B. Kohn and Norah Sadowski and Winston Timp and Andrey Ptitsyn and Prarthana Khanna and Daria Y. Romanova and Peter Williams and Spencer J. Greenwood and Leonid L. Moroz and David R. Walt and Andrea G. Bodnar},

url = {https://advances.sciencemag.org/content/7/26/eabe8290},

doi = {10.1126/sciadv.abe8290},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {Science Advances},

volume = {7},

number = {26},

pages = {eabe8290},

publisher = {American Association for the Advancement of Science},

abstract = {The American lobster, Homarus americanus, is integral to marine ecosystems and supports an important commercial fishery. This iconic species also serves as a valuable model for deciphering neural networks controlling rhythmic motor patterns and olfaction. Here, we report a high-quality draft assembly of the H. americanus genome with 25,284 predicted gene models. Analysis of the neural gene complement revealed extraordinary development of the chemosensory machinery, including a profound diversification of ligand-gated ion channels and secretory molecules. The discovery of a novel class of chimeric receptors coupling pattern recognition and neurotransmitter binding suggests a deep integration between the neural and immune systems. A robust repertoire of genes involved in innate immunity, genome stability, cell survival, chemical defense, and cuticle formation represents a diversity of defense mechanisms essential to thrive in the benthic marine environment. Together, these unique evolutionary adaptations contribute to the longevity and ecological success of this long-lived benthic predator.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{lee_simultaneous_2020,

title = {Simultaneous profiling of chromatin accessibility and methylation on human cell lines with nanopore sequencing},

author = {Isac Lee and Roham Razaghi and Timothy Gilpatrick and Michael Molnar and Ariel Gershman and Norah Sadowski and Fritz J Sedlazeck and Kasper D Hansen and Jared T Simpson and Winston Timp},

url = {https://www.nature.com/articles/s41592-020-01000-7},

doi = {10.1038/s41592-020-01000-7},

issn = {1548-7105},

year  = {2020},

date = {2020-12-01},

journal = {Nature Methods},

volume = {17},

number = {12},

pages = {1191--1199},

abstract = {Probing epigenetic features on DNA has tremendous potential to advance our understanding of the phased epigenome. In this study, we use nanopore sequencing to evaluate CpG methylation and chromatin accessibility simultaneously on long strands of DNA by applying GpC methyltransferase to exogenously label open chromatin. We performed nanopore sequencing of nucleosome occupancy and methylome (nanoNOMe) on four human cell lines (GM12878, MCF-10A, MCF-7 and MDA-MB-231). The single-molecule resolution allows footprinting of protein and nucleosome binding, and determination of the combinatorial promoter epigenetic signature on individual molecules. Long-read sequencing makes it possible to robustly assign reads to haplotypes, allowing us to generate a fully phased human epigenome, consisting of chromosome-level allele-specific profiles of CpG methylation and chromatin accessibility. We further apply this to a breast cancer model to evaluate differential methylation and accessibility between cancerous and noncancerous cells.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{kovaka_targeted_2020,

title = {Targeted nanopore sequencing by real-time mapping of raw electrical signal with UNCALLED},

author = {Sam Kovaka and Yunfan Fan and Bohan Ni and Winston Timp and Michael C Schatz},

url = {https://www.nature.com/articles/s41587-020-0731-9},

doi = {10.1038/s41587-020-0731-9},

issn = {1546-1696},

year  = {2020},

date = {2020-11-30},

urldate = {2020-11-30},

journal = {Nature Biotechnology},

volume = {39},

issue = {4},

pages = {1--11},

abstract = {Conventional targeted sequencing methods eliminate many of the benefits of nanopore sequencing, such as the ability to accurately detect structural variants or epigenetic modifications. The ReadUntil method allows nanopore devices to selectively eject reads from pores in real time, which could enable purely computational targeted sequencing. However, this requires rapid identification of on-target reads while most mapping methods require computationally intensive basecalling. We present UNCALLED (https://github.com/skovaka/UNCALLED), an open source mapper that rapidly matches streaming of nanopore current signals to a reference sequence. UNCALLED probabilistically considers k-mers that could be represented by the signal and then prunes the candidates based on the reference encoded within a Ferragina–Manzini index. We used UNCALLED to deplete sequencing of known bacterial genomes within a metagenomics community, enriching the remaining species 4.46-fold. UNCALLED also enriched 148 human genes associated with hereditary cancers to 29.6× coverage using one MinION flowcell, enabling accurate detection of single-nucleotide polymorphisms, insertions and deletions, structural variants and methylation in these genes.},

note = {Publisher: Nature Publishing Group},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pokrass_cell-cycle-dependent_2020b,

title = {Cell-Cycle-Dependent ERK Signaling Dynamics Direct Fate Specification in the Mammalian Preimplantation Embryo},

author = {Michael J Pokrass and Kathleen A Ryan and Tianchi Xin and Brittany Pielstick and Winston Timp and Valentina Greco and Sergi Regot},

doi = {10.1016/j.devcel.2020.09.013},

issn = {1878-1551},

year  = {2020},

date = {2020-11-09},

journal = {Developmental Cell},

volume = {55},

number = {3},

pages = {328--340.e5},

abstract = {Despite the noisy nature of single cells, multicellular organisms robustly generate different cell types from one zygote. This process involves dynamic cross regulation between signaling and gene expression that is difficult to capture with fixed-cell approaches. To study signaling dynamics and fate specification during preimplantation development, we generated a transgenic mouse expressing the ERK kinase translocation reporter and measured ERK activity in single cells of live embryos. Our results show primarily active ERK in both the inner cell mass and trophectoderm cells due to fibroblast growth factor (FGF) signaling. Strikingly, a subset of mitotic events results in a short pulse of ERK inactivity in both daughter cells that correlates with elevated endpoint NANOG levels. Moreover, endogenous tagging of Nanog in embryonic stem cells reveals that ERK inhibition promotes enhanced stabilization of NANOG protein after mitosis. Our data show that cell cycle, signaling, and differentiation are coordinated during preimplantation development.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}