Data Resources

Data Consortia

Data consortia and related resources for ML training.

Consortium	Acronym / Affiliation	Website	URL	Description	Pricing / Membership Options	Comments
Genomics England (100,000 Genomes Project)	Genomics England	https://www.genomicsengland.co.uk	https://www.genomicsengland.co.uk	A UK initiative to sequence 100,000 genomes from NHS patients with rare diseases and cancers to advance research in genomics. Provides access to datasets for approved research purposes.	Membership is through approved research applications; no publicly listed pricing for general access.
The Cancer Genome Atlas (TCGA)	TCGA	https://www.cancer.gov/tcga	https://www.cancer.gov/tcga	A comprehensive project mapping genomic changes in over 30 types of cancer, used to improve understanding of cancer biology and treatment. Publicly accessible datasets for research.	Free access to datasets via public repositories (e.g., NCI GDC).
All of Us Research Program	All of Us	https://www.joinallofus.org	https://www.joinallofus.org	A U.S. NIH initiative aiming to build one of the largest, most diverse health databases to improve personalized medicine. Participants share health, genomic, and environmental data.	Free access, but requires registration and approval for data access.
ELIXIR	ELIXIR	https://www.elixir-europe.org	https://www.elixir-europe.org	A European intergovernmental organization that unites life science resources (tools, data, standards) for open access to drive research. Its network integrates national bioinformatics infrastructure.	Membership options for both academia and industry, with variable fees based on services.
Global Alliance for Genomics and Health (GA4GH)	GA4GH	https://www.ga4gh.org	https://www.ga4gh.org	An international effort developing frameworks and standards for sharing genomic and health-related data to accelerate research and medicine globally.	Free to participate; some projects or collaborations may involve fees.
Human Cell Atlas (HCA)	HCA	https://www.humancellatlas.org	https://www.humancellatlas.org	A global consortium creating a reference map of all human cells as a basis for understanding human health and disease. Provides access to cutting-edge datasets on cell types.	Free access to data, membership for collaboration opportunities.
The Structural Genomics Consortium (SGC)	SGC	https://www.thesgc.org	https://www.thesgc.org	A public-private partnership supporting the discovery of proteins linked to human disease by generating open-access 3D structures of proteins.	Free to access data and tools; industry participation may involve funding contributions or collaborations.
UK Biobank	UK Biobank	https://www.ukbiobank.ac.uk	https://www.ukbiobank.ac.uk	A large-scale biomedical database with genetic, health, and lifestyle information from 500,000 UK participants to advance medical research.	Researchers pay a fee to access data. Costs depend on the data type and scope of the research.
ENCODE (Encyclopedia of DNA Elements)	ENCODE	https://www.encodeproject.org	https://www.encodeproject.org	A collaborative project aimed at identifying all functional elements in the human genome. Provides large-scale datasets and analysis tools for understanding gene regulation.	Free public access to data.
Genetic Alliance Registry	Genetic Alliance	https://www.geneticalliance.org	https://www.geneticalliance.org	A consortium linking patient data registries to enable health research and drug discovery through shared data from rare disease patient communities.	Membership for patient organizations and research institutions, variable fees for participation.
Pistoia Alliance	Pistoia Alliance	https://www.pistoiaalliance.org	https://www.pistoiaalliance.org	A global, non-profit alliance focused on lowering barriers to innovation in life sciences R&D. Focus areas include digital transformation, AI, real-world data, and data interoperability.	Membership for organizations, fees vary by membership level and organization size.	May still have $250 individual membership. Offers many free virtual meetings on data topics.
Foundation for the National Institutes of Health Biomarkers Consortium (FNIH)	Biomarkers Consortium	https://fnih.org/what-we-do/biomarkers-consortium	https://fnih.org/what-we-do/biomarkers-consortium	Public-private partnership aiming to identify and qualify biomarkers for drug development and precision medicine across multiple diseases, particularly cancer and neurology.	Funding provided by partners; no general membership or pricing available publicly.
Critical Path Institute	C-Path	https://c-path.org	https://c-path.org	A non-profit accelerating drug development by creating data standards and public databases. Focuses heavily on biomarkers, clinical trial modeling, and regulatory science.	Primarily funded by grants and partnerships with sponsors; no general membership.
Biomarker Enterprise to Advance Personalized Medicine (BEAM)	BEAM	https://www.personalizedmedicinecoalition.org	https://www.personalizedmedicinecoalition.org	A collaboration that fosters biomarker discovery, development, and integration into clinical trials and treatments. Focuses on biomarker validation and standardization across the life sciences industry.	Operates under the Personalized Medicine Coalition, membership options vary for industry and academic institutions.
ERP Biomarkers	ERP Biomarkers	https://erpbiomarkers.org	https://erpbiomarkers.org	Focused on the identification and validation of electrophysiological (ERP) biomarkers, particularly for neuropsychiatric conditions, ERP Biomarkers seeks to improve biomarker-based approaches to drug development and diagnostics.	Research institutions and pharmaceutical companies can join for membership, with fees depending on organization type.
Accelerating Therapeutics for Opportunities in Medicine (ATOM)	ATOM	https://www.atomscience.org	https://www.atomscience.org	A public-private partnership using AI and high-performance computing to accelerate drug discovery and development, focusing on speeding the process from target identification to clinical candidate.	Collaborators are generally large institutions, and there is no public pricing; membership requires industry partnerships.	More of a government funded ai-drug discovery platform
MELLODDY Consortium	MELLODDY	https://www.melloddy.eu	https://www.melloddy.eu	A European project using AI and machine learning to leverage private datasets from pharmaceutical companies for drug discovery. The focus is on improving predictive modeling for preclinical and clinical success rates.	Funded by the European Union’s Horizon 2020 program and private industry collaborations; no public membership option.
AI4Health Consortium	AI4Health	https://www.ai4health.eu	https://www.ai4health.eu	A European initiative promoting the application of AI in healthcare and drug discovery. It integrates data, modeling, and AI solutions to address complex biomedical problems.	Funded by public and private partners; project-based participation, not an open membership consortium.
Open Reaction Database	ORD	https://docs.open-reaction-database.org/en/latest/	https://docs.open-reaction-database.org/en/latest/	open access chemical reaction database to support machine learning and related efforts in reaction prediction, chemical synthesis planning, and experiment design	Open source	Led by Conner Coley (MIT), moredetails here https://cen.acs.org/physical-chemistry/computational-chemistry/new-database-machine-learning-research/99/web/2021/11
Kaggle	Kaggle	https://www.kaggle.com	https://www.kaggle.com	Site to explore, analyze and share quality data sets. Incldues some synthetic data sets for training.
Google BigQuery	Google	https://cloud.google.com/bigquery/public-data	https://cloud.google.com/bigquery/public-data	Public data sets made available to the public through Google Cloud Public Dataset progeram.	Open to analyze or integrate into your tools.
Google Cloud Life Sciences Public Datasets	Google	https://cloud.google.com/life-sciences/docs/resources/public-datasets	https://cloud.google.com/life-sciences/docs/resources/public-datasets	A variety of public datasets you can access for free and integrate into your applications. Google hosts these datasets, providing public access (interactive or file access).
NAR Databases	Nucleic Acids Research	https://www.oxfordjournals.org/nar/database/c/	https://www.oxfordjournals.org/nar/database/c/	NAR annual db issue of molecular biology databases by cateogry. Over 1950 databases collected from 180 papers	Freely available on NAR web site.
			#REF!
Consortium	Acronym / Affiliation	Website	URL	Description	Pricing / Membership Options	Comments