A new NHGRI Sample Repository for Human Genetic Research collection of induced pluripotent stem cell lines.

A new NHGRI Sample Repository for Human Genetic Research collection of induced pluripotent stem cell lines | bioRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-M677548'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search New Results A new NHGRI Sample Repository for Human Genetic Research collection of induced pluripotent stem cell lines View ORCID Profile Tatyana Pozner , Christine Grandizio , Matthew W Mitchell , Xiaoxia Cui , Amber Neilson , Monica F. Sentmanat , Ting Wang , Nathan O Stitziel , Nahid Turan , View ORCID Profile Laura B Scheinfeldt doi: https://doi.org/10.1101/2025.08.05.668740 Tatyana Pozner 1 Coriell Institute for Medical Research , Camden, NJ 08003, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Tatyana Pozner Christine Grandizio 1 Coriell Institute for Medical Research , Camden, NJ 08003, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Matthew W Mitchell 1 Coriell Institute for Medical Research , Camden, NJ 08003, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Xiaoxia Cui 2 Department of Genetics, Washington University School of Medicine , St. Louis, MO 63110, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Amber Neilson 2 Department of Genetics, Washington University School of Medicine , St. Louis, MO 63110, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Monica F. Sentmanat 2 Department of Genetics, Washington University School of Medicine , St. Louis, MO 63110, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Ting Wang 2 Department of Genetics, Washington University School of Medicine , St. Louis, MO 63110, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Nathan O Stitziel 3 Department of Medicine, Washington University School of Medicine , St. Louis, MO 63110, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Nahid Turan 1 Coriell Institute for Medical Research , Camden, NJ 08003, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Laura B Scheinfeldt 1 Coriell Institute for Medical Research , Camden, NJ 08003, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Laura B Scheinfeldt For correspondence: lscheinfeldt{at}coriell.org Abstract Full Text Info/History Metrics Supplementary material Preview PDF Abstract We describe here a new NHGRI Sample Repository for Human Genetic Research collection of induced pluripotent stem cell (iPSC) lines reprogrammed from whole blood derived peripheral blood mononuclear cells (PBMCs). PBMCs were reprogrammed using Sendai viral vectors carrying transcription factors OCT4, SOX2, KLF4, and c-MYC. All iPSC lines exhibit a normal karyotype, express common stemness and pluripotency markers, and demonstrate the ability to differentiate into cell types representing all three germ layers. This iPSC collection (n=7) will have accompanying public, near telomere to telomere genomic data through the Human Pangenome Reference Consortium, and provides an invaluable new in vitro resource for studying common genetic and genomic variation and its functional implications. Introduction The NHGRI Sample Repository for Human Genetic Research (NHGRI Repository) housed at the Coriell Institute for Medical Research (Coriell) facilitates studies of human genetic and genomic variation by establishing, characterizing and distributing a large (n>3,700) publicly available collection of renewable biospecimens donated by communities living around the world, including the communities that have participated in the 1000 Genomes Project and the Human Pangenome Reference Consortium 1 - 3 . NHGRI Repository participants have consented to their biospecimens being used for a wide range of general research and to public data sharing of large-scale genomic data collected from their samples. This new collection of seven induced pluripotent stem cell (iPSC) lines was generated from peripheral blood samples collected as part of a larger effort to improve the human reference genome to better represent human genetic variation 2 , 4 , 5 . This collection is an important new resource to improve our understanding of tissue-specific gene regulation and cellular function. Results We reprogrammed seven iPSC lines (NHGRI Repository identifiers: HG06799, HG06800, HG06801, HG06802, HG06803, and HG06804, HG06807) from peripheral blood mononuclear cells (PBMCs) using the CytoTune 2.0 Sendai Reprogramming Kit (Thermo Fisher Scientific), which includes the pluripotency factors OCT4, SOX2, KLF4, and c-MYC. Five of the seven iPSC lines in the collection were reprogrammed at Coriell (HG06800, HG06801, HG06802, HG06803, and HG06804), and two of the seven iPSC lines in the collection were reprogrammed at Washington University (HG06799, HG06807). All iPSCs in the collection passed all quality control assessments 6 ( Table 1 ): they display typical iPSC morphology under phase contrast microscopy, exhibit alkaline phosphatase activity ( Figure S1 ), and are positive for Stage-Specific Embryonic Antigen 4 (SSEA-4; Figure 1A ). In addition, the expression of several pluripotency markers was evaluated in cell lines reprogrammed at Coriell, using an immunocytochemical assay ( Figure 2 ). We assessed post-thaw cell viability by culturing a frozen vial, with iPSC colony area increasing 6-28-fold over a 3-5 day period ( Table S1 ). We performed cytogenomic G-banding analysis to confirm normal karyotypes ( Figure 1B ). We did not detect any Sendai virus (SeV) genome or transgenes by qRT-PCR using SeV-specific primers ( Table S2 ) after passage 10 in the five iPSCs reprogrammed at Coriell. In addition, we did not detect any SeV genome or transgenes by qRT-PCR using SeV-specific primers ( Table S2 ) in the two iPSCs reprogrammed at Washington University. We confirmed pluripotency by an embryoid body (EB) formation assay ( Figure 1C ). The lines are free of mycoplasma contamination ( Table 1 , Table S3 ), and microsatellite profiling has confirmed iPSC authenticity ( Table 1 , Table S3 ). View this table: View inline View popup Download powerpoint Table 1. Quality Control characterization and validation of iPSCs reprogrammed at Coriell. Download figure Open in new tab Figure 1. Characterization and quality control assessment of induced pluripotent stem cells (iPSCs). A) Stage specific embryonic antigen 4 (SSEA4) staining, B) G-banding karyograms. C) Fold change in expression of pluripotency genes and tri-lineage specific genes between undifferentiated cells and cells differentiated by embryoid body formation. Download figure Open in new tab Figure 2. Pluripotency assessment of cell lines reprogrammed at Coriell. Example immunofluorescence images showing expression of key pluripotency markers SOX2, OCT4, SSEA4, and TRA-1-60 in iPSCs. Scale bar: 200 μm. Methods Samples The samples included in the new NHGRI Repository iPSC resource were collected as part of a larger effort to improve the human reference genome with more comprehensive coverage of the genome, as well as to increase representation of human genetic variation 2 , 4 , 5 . The participants that generously agreed to donate to the repository consented to the creation of immortalized cell lines, including iPSCs, to their cell lines and DNA being made available for general research usage, and to large-scale genomic data collected from their samples being made public. In addition, these samples are in the process of being characterized by the HPRC with near telomere to telomere genomic assemblies, and these public data will add important genetic and genomic characterizations to this iPSC collection. The recommended language for referring to these samples is: African Americans living in St. Louis, Missouri, which may be abbreviated to ASL after the full description is provided ( https://catalog.coriell.org/1/NHGRI/About/Guidelines-for-Referring-to-Populations ). Reprogramming and Cell Culture The five iPSCs reprogrammed at Coriell were reprogrammed from PBMCs using CytoTune 2.0 (Thermo Fisher Scientific) Sendai vectors encoding OCT4, SOX2, KLF4, C-MYC, and EmGFP. One day after transduction, we cultured cells in complete StemPro™-34 medium (ThermoFisher Scientific) supplemented with L-Glutamine (2mM), CSF (100 ng/ml), FLT-3 (100 ng/ml), IL-3 (20 ng/ml) and IL-6 (20 ng/ml) and replated them on day 3 post transduction on mouse embryonic fibroblasts (MEF) coated culture dishes. From day 3 through day 7 post-transduction, the medium was replaced every other day with fresh complete StemPro™-34 medium without cytokines. On day 7 post-transduction, half of the culture medium was replaced with iPSC culture medium consisting of DMEM/F12 (Gibco) supplemented with 20% (v/v) KnockOut Serum Replacement (Invitrogen), 2 mM L-glutamine (Invitrogen), 1× non-essential amino acids (Invitrogen), 55 µM 2-mercaptoethanol (Invitrogen) and bFGF (10ng/mL). From day 8 onward, the culture medium was fully replaced daily. After 2-3 weeks post transduction, we selected 24 colonies and expanded them. At passage 10, we cryopreserved the lines. Cells were transitioned to Matrigel and maintained in mTeSR1 prior to incorporation into the NHGRI Repository. The two iPSCs reprogrammed at the Genome Engineering & Stem Cell Center (GESC@MGI) at Washington University were reprogrammed from erythroid progenitors enriched and expanded from PBMCs in StemSpan SFEM II medium (STEMCELL Technologies) with a StemSpan Erythroid expansion supplement (STEMCELL Technologies). The progenitors were cultured in this medium on the day of transduction using CytoTune 2.0 (Thermo Fisher Scientific) and transferred to a 1:1 ratio of erythroid medium:mTeSR+ (STEMCELL Technologies). On day 3 post transduction, the cells were transferred to 1:3 ratio of erythroid medium:mTeSR+. On day 4 post transduction, cells were transferred to 100% mTeSR+ and plated on a Matrigel-coated surface. After 2-3 weeks,12 colonies were selected, and three clones with the best morphology were expanded at passage 5 and subsequently cryopreserved. We thawed all cryopreserved cells by warming at 37°C, tested them for sterility, and cultured them on Matrigel-coated plates in mTeSR1 supplemented with ROCK inhibitor for 24 hours. Media were then changed daily. We passaged the cells at 75-85% confluency using Versene (2 minutes and room temperature) or ReLeSR (5-7 min, 37°C). Alkaline Phosphatase Staining We stained iPSCs using the StemTAG™ Alkaline Phosphatase Staining Kit (Cell Biolabs, Inc.). Immunocytochemistry We characterized the cells using a PSC Immunocytochemistry Kit with SOX2/TRA-1-60 and SSEA4/OCT4 antibody pairs. After fixation, permeabilization, and blocking, we applied primary antibodies (3h, 4°C), followed by secondary antibodies (1h, RT). We added DAPI during the final PBS wash (5 min). Flow Cytometry We quantified surface antigen expression of iPSC markers by flow cytometry. We dissociated the cells with Trypsin, washed the cells with PBS, and incubated the cells with fluorophore-conjugated antibodies (Table S2) for 15 min at room temperature. We used the MACSQuant Flow Cytometer and MACSQuantify software for all related analyses. G-Banded Karyotyping Twenty metaphase cells were counted and examined, and five selected metaphase cells were karyotyped. Cell Line Authentication We assessed cell line identity and authenticity by extracting DNA from each line and comparing the microsatellite (MSAT) marker profile to the DNA extracted from the whole blood sample submission as previously described 7 . Mycoplasma Detection and Sterility Testing We tested for mycoplasma contamination using the MycoSEQ™ Mycoplasma Detection Kit, a real-time PCR assay detecting over 90 species with <10 copies sensitivity. We assessed cell culture sterility via growth assays on trypticase soy agar and Sabouraud dextrose. Sendai Virus Detection We extracted total RNA using the RNeasy Plus Mini Kit. We synthesized cDNA from RNA using the High Capacity cDNA Reverse Transcription Kit. We quantified gene expression by qRT-PCR (primers used at Coriell and primers used at GESC@MGI are listed in Table S2 ). Differentiation Potential We assessed pluripotency via embryoid body (EB) formation. We cultured EBs in DMEM with 10% FBS, 1% L-glutamine, NEAA, and sodium pyruvate for 10 days. We extracted RNA using the RNeasy Mini Kit and quantified RNA by NanoDrop One. We synthesized cDNA, analyzed gene expression by qRT-PCR, and normalized Ct values to GAPDH. We calculated relative expression as fold change compared to undifferentiated cells using the Livak-Schmittgen method 8 . Discussion Here, we introduce a new collection of seven iPSCs that have been incorporated into the NHGRI Repository. These cell lines were created from whole blood samples donated by African Americans living in St. Louis, MO. The iPSC lines are currently available to the research community through the NHGRI Repository, housed at the Coriell Institute for Medical Research ( https://www.coriell.org/1/NHGRI ). A distinctive feature of this collection is that each iPSC line has a corresponding lymphoblastoid cell line (LCL), and DNAs extracted from these LCLs are in the process of being extensively genome sequenced through the Human Pangenome Reference Consortium; telomere-to-telomere (T2T) assemblies for a subset of three of these LCLs are publicly available through related efforts 3 ( https://github.com/biomonika/HPP/tree/main/T2T-Pedigree-project%20 ). All associated genomic data will be publicly accessible and will include high-quality, robust, long-read, near telomere-to-telomere (T2T) assemblies 2 . The availability of matched iPSC and LCL lines enables comparative studies of cellular phenotypes and lineage-specific gene regulation. Moreover, the accompanying genomic data will facilitate a more comprehensive investigation of genetic and genomic variation and its functional consequences. This resource will be particularly valuable for investigating tissue-specific gene regulation, cellular differentiation pathways, and the functional consequences of genetic and genomic variation on cellular function. Furthermore, these well-characterized lines will serve as important reference materials for future studies involving iPSCs. Funder Information Declared National Human Genome Research Institute , 5U24HG008736 Footnotes In this revision we added two iPSC lines that were reprogrammed at Washington University, and we updated the author list to include additional co-authors who contributed to this work. Consistent with these changes, we expanded the Methods section with particular emphasis on an expanded Reprogramming and Cell Culture subsection. References 1. ↵ Byrska-Bishop M , Evani US , Zhao X , et al. High-coverage whole-genome sequencing of the expanded 1000 Genomes Project cohort including 602 trios . Cell 2022 ; 185 ( 18 ): 3426 – 3440 e19 , doi: 10.1016/j.cell.2022.08.004 OpenUrl CrossRef PubMed 2. ↵ Liao WW , Asri M , Ebler J , et al. A draft human pangenome reference . Nature 2023 ; 617 ( 7960 ): 312 – 324 , doi: 10.1038/s41586-023-05896-x OpenUrl CrossRef PubMed 3. ↵ Cechova M , Potapova TA , Rechtsteiner A , et al. Complete genomes of a multi-generational pedigree to expand studies of genetic and epigenetic inheritance . bioRxiv 2025 , doi: 10.64898/2025.12.14.693655 OpenUrl Abstract / FREE Full Text 4. ↵ Jarvis ED , Formenti G , Rhie A , et al. Semi-automated assembly of high-quality diploid human reference genomes . Nature 2022 ; 611 ( 7936 ): 519 – 531 , doi: 10.1038/s41586-022-05325-5 OpenUrl CrossRef PubMed 5. ↵ Wang T , Antonacci-Fulton L , Howe K , et al. The Human Pangenome Project: a global resource to map genomic diversity . Nature 2022 ; 604 ( 7906 ): 437 – 446 , doi: 10.1038/s41586-022-04601-8 OpenUrl CrossRef PubMed 6. ↵ Pozner T , Grandizio C , Mitchell MW , et al. Human iPSC Reprogramming Success: The Impact of Approaches and Source Materials . Stem Cells Int 2025 ; 2025 ( 2223645 , doi: 10.1155/sci/2223645 OpenUrl CrossRef PubMed 7. ↵ Smith G , Mathews D , Sander-Effron S , et al. Microsatellite Markers in Biobanking: A New Multiplexed Assay . Biopreserv Biobank 2021 ; 19 ( 5 ): 438 – 443 , doi: 10.1089/bio.2021.0042 OpenUrl CrossRef PubMed 8. ↵ Livak KJ , Schmittgen TD . Analysis of relative gene expression data using real-time quantitative PCR and the 2(-Delta Delta C(T)) Method . Methods 2001 ; 25 ( 4 ): 402 – 8 , doi: 10.1006/meth.2001.1262 OpenUrl CrossRef PubMed Web of Science View the discussion thread. Back to top Previous Next Posted February 14, 2026. Download PDF Supplementary Material Email Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following A new NHGRI Sample Repository for Human Genetic Research collection of induced pluripotent stem cell lines Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share A new NHGRI Sample Repository for Human Genetic Research collection of induced pluripotent stem cell lines Tatyana Pozner , Christine Grandizio , Matthew W Mitchell , Xiaoxia Cui , Amber Neilson , Monica F. Sentmanat , Ting Wang , Nathan O Stitziel , Nahid Turan , Laura B Scheinfeldt bioRxiv 2025.08.05.668740; doi: https://doi.org/10.1101/2025.08.05.668740 Share This Article: Copy Citation Tools A new NHGRI Sample Repository for Human Genetic Research collection of induced pluripotent stem cell lines Tatyana Pozner , Christine Grandizio , Matthew W Mitchell , Xiaoxia Cui , Amber Neilson , Monica F. Sentmanat , Ting Wang , Nathan O Stitziel , Nahid Turan , Laura B Scheinfeldt bioRxiv 2025.08.05.668740; doi: https://doi.org/10.1101/2025.08.05.668740 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Cell Biology Subject Areas All Articles Animal Behavior and Cognition (7629) Biochemistry (17660) Bioengineering (13881) Bioinformatics (41911) Biophysics (21436) Cancer Biology (18578) Cell Biology (25482) Clinical Trials (138) Developmental Biology (13371) Ecology (19887) Epidemiology (2067) Evolutionary Biology (24302) Genetics (15599) Genomics (22482) Immunology (17728) Microbiology (40363) Molecular Biology (17163) Neuroscience (88536) Paleontology (666) Pathology (2830) Pharmacology and Toxicology (4821) Physiology (7637) Plant Biology (15129) Scientific Communication and Education (2045) Synthetic Biology (4290) Systems Biology (9817) Zoology (2269)