{"slug":"data","tag":"data","variants":["data"],"description":"No description yet","count":14,"kinds":{"collection":14},"related":[{"slug":"source","tag":"source","shared":5},{"slug":"virtual-cell","tag":"virtual-cell","shared":2},{"slug":"benchmark","tag":"benchmark","shared":1},{"slug":"news","tag":"news","shared":1},{"slug":"real-world","tag":"real-world","shared":1}],"records":[{"id":"src-ema-chmp","kind":"collection","name":"EMA news and CHMP meeting highlights","route":"/collections/src-ema-chmp/","tldr":"The EMA's CHMP highlights show Europe's approval pipeline one month ahead of European Commission decisions."},{"id":"src-nice-ta","kind":"collection","name":"NICE technology appraisals","route":"/collections/src-nice-ta/","tldr":"NICE technology appraisals say whether the NHS will pay, and why. They are the most transparent HTA record in the world."},{"id":"src-evaluate","kind":"collection","name":"Evaluate Vantage","route":"/collections/src-evaluate/","tldr":"Evaluate Vantage forecasts which drugs and modalities will matter commercially in the next decade."},{"id":"src-semantic-scholar","kind":"collection","name":"Semantic Scholar","route":"/collections/src-semantic-scholar/","tldr":"Semantic Scholar offers free literature search with machine-generated summaries and citation context."},{"id":"src-dimensions","kind":"collection","name":"Dimensions","route":"/collections/src-dimensions/","tldr":"Dimensions connects papers to the grants and trials behind them."},{"id":"tcia","kind":"collection","name":"The Cancer Imaging Archive (TCIA)","route":"/collections/tcia/","tldr":"The public archive of cancer scans that most radiology AI is trained and tested on."},{"id":"imaging-data-commons","kind":"collection","name":"NCI Imaging Data Commons (IDC)","route":"/collections/imaging-data-commons/","tldr":"The Imaging Data Commons is TCIA in the cloud, ready for large-scale model training."},{"id":"uk-biobank","kind":"collection","name":"UK Biobank","route":"/collections/uk-biobank/","tldr":"UK Biobank is the richest population cohort for linking genes, blood and imaging to who later develops cancer."},{"id":"all-of-us","kind":"collection","name":"All of Us Research Program","route":"/collections/all-of-us/","tldr":"America's answer to UK Biobank, built for diversity."},{"id":"flatiron-foundation-cgdb","kind":"collection","name":"Flatiron Health and Foundation Medicine Clinico-Genomic Database","route":"/collections/flatiron-foundation-cgdb/","tldr":"Real-world evidence at scale: what happened to patients with a given genomic profile on a given treatment."},{"id":"cdas-nlst-plco","kind":"collection","name":"NCI CDAS: NLST and PLCO screening trial data","route":"/collections/cdas-nlst-plco/","tldr":"NCI CDAS holds the lung screening trial images that trained Sybil and most lung-nodule AI."},{"id":"pathology-benchmarks","kind":"collection","name":"Pathology AI benchmarks (CAMELYON, PANDA, TCGA slide tasks)","route":"/collections/pathology-benchmarks/","tldr":"Pathology AI benchmarks are the open challenge datasets on which every pathology model is scored: CAMELYON16 and 17 for lymph node metastasis detection, PANDA for prostate grading with 11,000 biopsies, and TCGA slide-level tasks used to compare foundation models. Licences are mostly CC BY-NC-SA or set per challenge."},{"id":"tahoe-100m","kind":"collection","name":"Tahoe-100M","route":"/collections/tahoe-100m/","tldr":"Tahoe-100M is the biggest single-cell dataset ever released, built to teach AI how cancer cells respond to drugs."},{"id":"arc-virtual-cell-atlas","kind":"collection","name":"Arc Virtual Cell Atlas","route":"/collections/arc-virtual-cell-atlas/","tldr":"Arc's growing library of cell data, the fuel for virtual cell models."}]}