Table 1.

Comprehensive omics database resources for building AI models.

Name	Main features	Web link
CGHub	Overall data repository; enormous data	https://cghub.ucsc.edu/
TCGA	Comprehensive database; enormous data	https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga
CCLE	Comprehensive database; enormous data	https://sites.broadinstitute.org/ccle
EGA	Overall data repository; enormous data	https://ega-archive.org/
ICGC	Comprehensive genomics data	https://dcc.icgc.org/
DepMap	High data quality; visualization	https://depmap.org/portal/
SomamiR	Correlation between cancer somatic mutation and miRNA	https://compbio.uthsc.edu/SomamiR/
COSMIC	largest and most comprehensive somatic mutation database; regularly-updated	https://cancer.sanger.ac.uk/cosmic
MethyCancer	integrated data of DNA methylation, cancer-related gene, mutation and cancer information	http://methycancer.psych.ac.cn/
CTRP	connecting sensitivity to cancer feature	https://portals.broadinstitute.org/ctrp/
gCSI	Large amount of transcriptomics data	https://pharmacodb.pmgenomics.ca/datasets/4
GDSC	Drug response data; genomics markers of drug sensitivity; update irregularly	https://www.cancerrxgene.org/
NCI60	Large amount of drug data and genomics data	https://discover.nci.nih.gov/cellminer/loadDownload.do https://dtp.cancer.gov/databases_tools/bulk_data.htm
canSAR	Comprehensive database; discovery drug	https://cansarblack.icr.ac.uk/
cBioPortal	Large amount of available data	https://www.cbioportal.org/datasets
UCSC	Synthetical genomics information	https://genome.ucsc.edu/
dbNSFP	Predictive data	http://bib.oxfordjournals.org/
NONCODE	database dedicated to non-coding RNAs	http://www.noncode.org/
CSD	The positive and negative training sets	http://bib.oxfordjournals.org/
TCIA	A great quantity of medical related image data sets	https://www.tcia.at/home
MSKCC	Cancer mutation databases	http://www.cbioportal.org/
ARCHS4	comprehensive processed mRNA expression data	https://maayanlab.cloud/archs4/