License Genomic & Clinical Oncology Datasets for AI/ML
Whole-genome, whole-exome and targeted-panel sequencing linked to pathology, radiology and EMR — one accredited source, one patient population.
Genomic & Clinical Data for Oncology AI
Shaip’s genomic and clinical data comes from a single NABL-accredited laboratory (ISO 15189 scope) with a consistent sequencing and reporting pipeline and known provenance, covering an Indian / South Asian oncology population that is markedly under-represented in the public reference sets most AI models are trained on today.
Sequence data is linkable to structured clinical annotation — diagnosis, staging, pathology, treatment and, where available, outcomes — and can be delivered as a fully linked longitudinal patient journey across the full care episode. GRCh38 is the reference build; GRCh37 remap, OMOP CDM, FHIR and Phenopackets are available on request.
| Dataset Type | Volume | Geography | Format |
|---|---|---|---|
| Dataset TypeLongitudinal Patient JourneyLinked genomic + pathology + radiology + EMR + outcomes | Volume50K+ patients | GeographyIndia | FormatLinked relational export; OMOP CDM / FHIR / Phenopackets on request |
| Dataset TypeRadiology Reports + Paired ImagingCT, MRI, PET-CT, X-ray, USG, Mammography | Volume50K+ patients | GeographyIndia | FormatDe-identified DICOM, text/HL7 reports, NIfTI on request |
| Dataset TypeTargeted NGS (50-gene hotspot panel)Tissue + ctDNA | Volume30K+ patients | GeographyIndia (South Asian) | FormatFASTQ, BAM, annotated VCF, report |
| Dataset TypeWhole-Genome Sequencing (Oncology)Germline + somatic, tumour/normal paired | Volume11.9K patients | GeographyIndia (South Asian) | FormatFASTQ, BAM/CRAM, VCF/gVCF, MAF, CNV/SV |
| Dataset TypeWhole-Exome Sequencing (Oncology)Germline + somatic, tumour/normal paired | Volume9.8K patients | GeographyIndia (South Asian) | FormatFASTQ, BAM/CRAM, VCF/gVCF, MAF |
| Dataset TypeComprehensive Oncology Genomic Profiling1000-gene panel, tissue + liquid biopsy | Volume5K+ patients | GeographyIndia (South Asian) | FormatFASTQ, BAM/CRAM, annotated VCF, PDF/JSON report |
| Dataset TypeElectronic Medical RecordsCoded (ICD-10, LOINC, RxNorm) + free-text clinical notes | Volume- | GeographyIndia | FormatCSV/Parquet; HL7 FHIR / OMOP CDM on request |
We deal with all types of Data Licensing i.e., text, audio, video, or image. The datasets consist of Medical datasets for ML: Physician Dictation Dataset, Physician Clinical Notes, Medical Conversation Dataset, Medical Transcription Dataset, Doctor-Patient Conversation, Medical Text Data, Medical Images – CT Scan, MRI, Ultra Sound (collected basis custom requirements).
Can’t find what you are looking for?
New off-the-shelf medical datasets are being collected across all data types
Contact us now to let go of your healthcare training data collection worries
