{"success":true,"data":{"author":"Duchini et al. and Felix Marsh-Wakefield; curated by SPORA","bucketAccessType":"public","bucketName":"csmp-hub/unumlocalia","bucketPrefix":"","category":"Health & Biomedical","cloudProvider":"huggingface","createdAt":"2026-11-17T19:29:33.172Z","description":"A matched multimodal resource from four human tissue cores (hepatocellular carcinoma, matched non-tumor liver, tonsil and hepatocellular adenoma) in which H&E, Xenium in situ spatial transcriptomics with a 5,001-target RNA panel, and COMET sequential immunofluorescence with 15 protein markers plus DAPI were all measured on the same tissue section. This package crops the H&E into 513 tiles of 512x512 pixels at about 0.203 micrometers per pixel with unchanged pixel values, and converts the supplied Xenium cell and nucleus boundaries into instance masks (original numeric IDs preserved, nucleus-to-cell pairs listed). The full source has 46,076 cells and 45,891 nuclei; objects.parquet holds every boundary and link, and measurements/ carries four further measurement files from the source. About 1.6 GB (measured 2026-11-17). Images and masks are stored as PNG or TIFF bytes inside Parquet; read them with polars or pandas plus Pillow, or with Hugging Face datasets. Use for predicting gene or protein expression from H&E, multimodal registration and cell segmentation benchmarks. Curated and packaged on Hugging Face by the SPORA project (csmp-hub), which keeps the original license and citation files. The original Zenodo release 21713660 is CC BY 4.0; credit Duchini and colleagues and Felix Marsh-Wakefield and cite the study (doi 10.64898/2026.08.17.742355).","displayTitle":"UnumLocalia: same-section H&E, Xenium 5,001-gene spatial transcriptomics and COMET protein imaging of liver and tonsil","doi":"10.5281/zenodo.21713660","huggingFaceUrl":"https://huggingface.co/datasets/csmp-hub/unumlocalia","id":"58ab6fa0-2b94-5908-a577-ddd391f88883","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/records/21713660","objectCountEstimate":15,"probeStatus":"ok","referenceUrl":"https://doi.org/10.64898/2026.08.17.742355","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"csmp-hub/unumlocalia\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"csmp-hub/unumlocalia\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=csmp-hub, license:cc-by-4.0, size_categories:n<1K, format:parquet, downloads=106"],"format":"mixed","generatedAt":"2026-11-17T19:40:20.198Z","layout":{"example":"class-distribution.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"compartment,class,source_instances,exported_unique_instances\r\nnuclei,unknown,45891,45890\r\ncells,unknown,46076,46075\r\ncomet_nuclei,unknown,42417,33950\r\ncomet_cells,unknown,51533,39438\r\n","encoding":"utf8","key":"class-distribution.csv","truncatedAt":512}],"sampleObjects":["class-distribution.csv","crop-index.parquet","examples.png","instance-counts.csv","measurements/core01_hcc.csv.gz"],"sidecars":[{"bytes":"Attribution 4.0 International\n\n=======================================================================\n\nCreative Commons Corporation (\"Creative Commons\") is not a law firm and\ndoes not provide legal services or legal advice. Distribution of\nCreative Commons public licenses does not create a lawyer-client or\nother relationship. Creative Commons makes its licenses and related\ninformation available on an \"as-is\" basis. Creative Commons gives no\nwarranties regarding its licenses, any material licensed under their\nterms and conditions, or any related information. Creative Commons\ndisclaims all liability for damages resulting from their use to the\nfullest extent possible.\n\nUsing Creative Commons Public Licenses\n\nCreative Commons public licenses provide a standard set of terms and\nconditions that creators and other rights holders may use to share\noriginal works of authorship and other material subject to copyright\nand certain other rights specified in the public license below. The\nfollowing considerations are for informational purposes only, are not\nexhaustive, and do not form part of our licenses.\n\n     Considerations for licensors: Our public licenses are\n     intended for use by those authorized to give the public\n     permission to use material in ways otherwise restricted by\n     copyright and certain other rights. Our licenses are\n     irrevocable. Licensors should read and understand the terms\n     and conditions of the license they choose before applying it.\n     Licensors should also secure all rights necessary before\n     applying our licenses so that the public can reuse the\n     material as expected. Licensors should clearly mark any\n     material not subject to the license. This includes other CC-\n     licensed material, or material used under an exception or\n     limitation to copyright. More considerations for licensors:\n    wiki.creativecommons.org/Considerations_for_licensors\n\n     Considerations for the public: By using one of our public\n     licenses, a licensor grants the public permission to use the\n     licensed material under specified terms and conditions. If\n     the licensor's permission is not necessary for any reason--for\n     example, because of any applicable exception or limitation to\n     copyright--then that use is not regulated by the license. Our\n     licenses grant only permissions under copyright and certain\n     other rights that a licensor has authority to grant. Use of\n     the licensed material may still be restricted for other\n     reasons, including because others have copyright or other\n     rights in the material. A licensor may make special requests,\n     such as asking that all changes be marked or described.\n     Although not required by our licenses, you are encouraged to\n     respect those requests where reasonable. More considerations\n     for the public:\n    wiki.creativecommons.org/Considerations_for_licensees\n\n=======================================================================\n\nCreative Commons Attribution 4.0 International Public License\n\nBy exercising the Licensed Rights (defined below), You accept and agree\nto be bound by the terms and conditions of this Creative Commons\nAttribution 4.0 International Public License (\"Public License\"). To the\nextent this Public License may be interpreted as a contract, You are\ngranted the Licensed Rights in consideration of Your acceptance of\nthese terms and conditions, and the Licensor grants You such rights in\nconsideration of benefits the Licensor receives from making the\nLicensed Material available under these terms and conditions.\n\n\nSection 1 -- Definitions.\n\n  a. Adapted Material means material subject to Copyright and Similar\n     Rights that is derived from or based upon the Licensed Material\n     and in which the Licensed Material is translated, altered,\n     arranged, transformed, or otherwise modified in a manner requiring\n     permission under the Copyright and Similar Rights held by the\n     Licensor. For purposes of this Public License, where the Licensed\n     Material is a musical work, performance, or sound recording,\n ","encoding":"utf8","key":"LICENSE","name":"LICENSE","size":18657,"truncated":true},{"bytes":"---\nlicense: cc-by-4.0\ntask_categories:\n- image-segmentation\nconfigs:\n- config_name: default\n  data_files:\n  - split: train\n    path: train.parquet\n---\n\n# UnumLocalia\n\nMatched H&E, spatial RNA and protein images from four human tissue cores:\nhepatocellular carcinoma, matched non-tumour liver, tonsil and hepatocellular\nadenoma. Xenium provides cell and nucleus boundaries alongside a 5,001-target\nRNA panel. COMET adds 15 protein markers and DAPI. The measurements and H&E\ncome from the same tissue section.\n\nThe data are [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).\nCredit Duchini and colleagues and Felix Marsh-Wakefield, cite the\n[study](https://doi.org/10.64898/2026.08.17.742355) and\n[original release](https://doi.org/10.5281/zenodo.21713660), and describe any\nchanges when sharing derived data. This version crops images and converts\nsupplied boundaries into pixel masks.\n\n## Images and masks\n\nThere are 513 H&E crops, each 512 × 512 pixels at about 0.203125 µm per\npixel. H&E pixels are unchanged. Each crop has separate nucleus and cell\ninstance masks. Background is 0. Original Xenium numeric IDs are preserved;\n`pairs` links nucleus IDs to cell IDs. The full source has 46,076 cells and\n45,891 nucleus instances. Some cells have multiple nuclei and 2,121 cells have\nno supplied nucleus boundary. Crops can cut through instances; the full links\nand boundaries are retained in `objects.parquet` and `source/`.\n\n![Example nucleus and cell boundaries](examples.png)\n\n`image_if` holds all 16 COMET channels as a native uint16 CYX TIFF crop.\nThe IF crop has its own size and pixel grid at 0.28 µm per pixel. Its values\nare unchanged. `if_x`, `if_y` and `he_to_if` give the coordinates needed to\ncompare it with H&E. `if_valid` marks H&E pixels covered by the IF image.\nDo not place the two arrays directly on top of each other without this mapping.\nSome H&E crops extend beyond the available COMET image. `has_if` marks whether\na native IF crop is available; otherwise `image_if` is empty and `if_valid` is 0.\n\nThe channel list includes DAPI, CK8, VEGF, CD45RA, vimentin, E-Cadherin, CD1c,\nIL-10, podoplanin, FXIIIa, CD66, CD20, alpha-SMA, CD45, HepPar1 and CD206.\nOriginal channel strings are in each row. The image metadata and measurement\ntables spell alpha-SMA differently; the original spellings are retained.\n\nThe COMET/InstanSeg segmentation is provided separately in `inst_comet_cells`\nand `inst_comet_nuclei`. It is an alternative segmentation, with its own IDs.\nIts numeric mask IDs map to original feature UUIDs in `objects.parquet`.\nDo not join these IDs to Xenium IDs.\n\nCOMET masks are unavailable for all 123 non-tumour liver crops because the source\npredictions overlap extensively. `has_comet_masks` is false, both COMET mask\nfields are empty, and `skip_training_comet` is true for those crops. Their Xenium\nmasks remain available. Original COMET geometry is retained for provenance and\nmarked unavailable for use as a mask in `objects.parquet`. The remaining 390\ncrops retain their COMET alternatives; six exact crop pairs were visually\napproved. Other COMET crops remain unreviewed. Native and COMET quality flags\nare independent.\n\n## Cell types and measurements\n\nNo ready-made cell-type classes are supplied. `type` and `type_cell` use 255\nfor unknown instances and 0 for background. Tissue diagnosis describes the core,\nnot every cell. No cell types were inferred for this version.\n\n`measurements/` contains the original per-cell RNA and protein tables, compressed\nwithout changing their CSV contents. Join them to the Xenium objects by core and\nstring `cell_id`. Their numeric `label` column is an export ID and differs from\nboundary IDs. There are 73 boundary cells without a measurement row.\n\n`instance-counts.csv` records each crop's counts for both segmentation\nalternatives. `class-distribution.csv` gives source and exported unique instance\ncounts. Crops near image edges can overlap, so adding per-crop counts repeats\nsome cells.\n\n| Annotation | Source instances | Unique instances represented in crops |\n| --- | ---: | ---: |\n| Xenium nuclei | ","encoding":"utf8","key":"README.md","name":"README.md","size":7371,"truncated":true},{"bytes":"{\n  \"dataset\": \"UnumLocalia\",\n  \"source_doi\": \"10.5281/zenodo.21713660\",\n  \"study_doi\": \"10.64898/2026.08.17.742355\",\n  \"license\": \"cc-by-4.0\",\n  \"crops\": 513,\n  \"patient_groups\": 3,\n  \"splits\": {\n    \"train\": 513\n  },\n  \"native_reviewed_crop_pairs\": 8,\n  \"comet_reviewed_usable_crop_pairs\": 6,\n  \"comet_available_crops\": 390,\n  \"comet_source_excluded_crops\": 123,\n  \"if_unavailable_crops\": 14,\n  \"cell_types\": \"unknown\",\n  \"conversion\": \"Native H&E/IF values preserved; source polygons rasterized with original IDs and explicit pairing. Source overlaps excluded for the non-tumour COMET alternative. Original coordinates, geometry and molecular values retained.\",\n  \"sha256\": {\n    \"README.md\": \"7f450c8ceb6b74cfac0051ff1b06dcba2b76bdb4f795756f1e8723d4520ce41b\",\n    \"LICENSE\": \"9ba9550ad48438d0836ddab3da480b3b69ffa0aac7b7878b5a0039e7ab429411\",\n    \"train.parquet\": \"f6aa858b6c410171b5dd5b997a096f61e79ec75b4c66ce29658954eaf6afe1b8\",\n    \"crop-index.parquet\": \"7ed374a794adb97f7893ca0cf1598c250fe4125da730fb3b0bf19b2165d7561b\",\n    \"objects.parquet\": \"c2da8d88ae73a9576a6eec774b898ad1b4ec17d9d5497dab1ad5120ef045dd2b\",\n    \"instance-counts.csv\": \"75e9d30385737d3cf2a3fa39361809315476bb05658863b780d315a94e99b122\",\n    \"class-distribution.csv\": \"515a161f4490a251319403dd7e9ebde0d9801997945826e05287a46dac373395\",\n    \"examples.png\": \"879a535fa6f52780e845505a1428cb994408789c4fa071bbbe346677be4efc46\",\n    \"validation-summary.json\": \"23b3b0737484b95cf35ca3aeb2a1e44b0002218839abb0c9d6eee84a2ebe1522\",\n    \"measurements/core01_hcc.csv.gz\": \"1ef00e0fcbc344705422ff9478a14bae4cebd87355e71b53df4908c232c914d8\",\n    \"measurements/core02_non_tumour.csv.gz\": \"f92b334da4c1f97791cd800c7080862fcfbc06fb244dd1e844a9a87a71bca5fc\",\n    \"measurements/core03_tonsil.csv.gz\": \"014a407b2da018baea22661223d2dd9a5becf4a5a273752d3a83da9961550c91\",\n    \"measurements/core04_hca.csv.gz\": \"9a44fa7b18989c3f3228fab1f5df40fbe3aac656b149e04335f302c7986811d9\"\n  }\n}\n","encoding":"utf8","key":"manifest.json","name":"manifest.json","size":1940,"truncated":false}],"sourceObjectKey":"class-distribution.csv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/csmp-hub/unumlocalia/class-distribution.csv\")\ndf.head()","starterSamplePath":"class-distribution.csv","totalObjects":15},"summary":"A matched multimodal resource from four human tissue cores (hepatocellular carcinoma, matched non-tumor liver, tonsil and hepatocellular adenoma) in which H&E, Xenium in situ…","title":"UnumLocalia: same-section H&E, Xenium 5,001-gene spatial transcriptomics and COMET protein imaging of liver and tonsil","updatedAt":"2026-11-17T23:19:17.405Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/csmp-hub/unumlocalia"}}