Table 1.
Current database resources that could be used for building AI models for therapy prediction.
| Name | Main Features | Web Link |
|---|---|---|
| CGHub | Cancer genomics data repository | https://docs.gdc.cancer.gov/Encyclopedia/pages/Cancer_Genomics_Hub/ (accessed on 2 September 2024) |
| TCGA | Comprehensive database of cancer patients’ genomic, epigenomic, transcriptomic, and proteomic data. | https://www.cancer.gov/ccg/research/genome-sequencing/tcga (accessed on 2 September 2024) |
| CCLE | Comprehensive genetic database of cancer cell lines | https://sites.broadinstitute.org/ccle (accessed on 2 September 2024) |
| EGA | European genetic, phenotypic, and clinical data repository | https://ega-archive.org/ (accessed on 2 September 2024) |
| DepMap | High data quality visualization tool | https://depmap.org/portal/ (accessed on 2 September 2024) |
| SomamiR | Cancer somatic mutation and miRNA correlation | https://compbio.uthsc.edu/SomamiR/ (accessed on 2 September 2024) |
| COSMIC | Comprehensive somatic mutation database | https://cancer.sanger.ac.uk/cosmic (accessed on 2 September 2024) |
| MethyCancer | DNA methylations, cancer-related genes, and mutations in correlation with additional cancer information | http://methycancer.psych.ac.cn/ (accessed on 2 September 2024) |
| CTRP | connecting genetic, cellular features, lineage to cancer cell-lines sensitivity to small molecules | https://portals.broadinstitute.org/ctrp/ (accessed on 2 September 2024) |
| gCSI | Large number of transcriptomics data | https://pharmacodb.pmgenomics.ca/datasets/4 (accessed on 2 September 2024) |
| GDSC | Drug response, including genomics markers of drug sensitivity | https://www.cancerrxgene.org/ (accessed on 2 September 2024) |
| NCI60 | Large number of drug and genomics data |
https://discover.nci.nih.gov/cellminer/loadDownload.do (accessed on 2 September 2024) https://dtp.cancer.gov/databases_tools/bulk_data.htm (accessed on 2 September 2024) |
| canSAR | Comprehensive drug discovery database | https://cansarblack.icr.ac.uk/ (accessed on 2 September 2024) |
| cBioPortal | Large database of cancer genomics data | https://www.cbioportal.org/datasets (accessed on 2 September 2024) |
| UCSC | Synthetical genomics information | https://genome.ucsc.edu/ (accessed on 2 September 2024) |
| dbNSFP | Non-synonymous single-nucleotide variants | https://sites.google.com/site/jpopgen/dbNSFP (accessed on 2 September 2024) |
| NONCODE | Non-coding RNAs database | http://www.noncode.org/ (accessed on 2 September 2024) |
| TCIA | Comprehensive immunogenomic data from the NGS of 20 solid tumors from TCGA | https://www.tcia.at/home (accessed on 2 September 2024) |
| ARCHS4 | Comprehensive RNA-Sequenced data from human and mouse | https://maayanlab.cloud/archs4/ (accessed on 2 September 2024) |