| _version_ | 1866902000584622080 |
|---|---|
| author | Al-sahly, Wafa |
| author_facet | Al-sahly, Wafa |
| contents | <p><strong>We have 3 datasets </strong></p> <p>The first one, from GEO with accession no. GSE75299, is https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE75299.</p> <p>The second one, also from GEO with accession no. GSE65185, is at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi.</p> <p>The third one, from EGA with study ID EGAD00001001306, is at https://ega-archive.org/datasets/EGAD00001001306.</p> <p><strong>purpose of the study</strong></p> <p>Develop a machine learning framework for predicting treatment response in cutaneous melanoma patients by integrating and harmonising raw RNA-seq data from multiple independent studies.</p> <p><strong>Methods, Software and version</strong></p> <p>nf-core RNA-seq pipeline by nextflow (Feature count)</p> <p>R code (DEGs), ML, DL, Feature selection, Figures, validation</p> <p> </p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17632979 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Cross-Study Harmonization and Machine Learning Pipeline for Predicting Melanoma Treatment Response Al-sahly, Wafa <p><strong>We have 3 datasets </strong></p> <p>The first one, from GEO with accession no. GSE75299, is https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE75299.</p> <p>The second one, also from GEO with accession no. GSE65185, is at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi.</p> <p>The third one, from EGA with study ID EGAD00001001306, is at https://ega-archive.org/datasets/EGAD00001001306.</p> <p><strong>purpose of the study</strong></p> <p>Develop a machine learning framework for predicting treatment response in cutaneous melanoma patients by integrating and harmonising raw RNA-seq data from multiple independent studies.</p> <p><strong>Methods, Software and version</strong></p> <p>nf-core RNA-seq pipeline by nextflow (Feature count)</p> <p>R code (DEGs), ML, DL, Feature selection, Figures, validation</p> <p> </p> |
| title | Cross-Study Harmonization and Machine Learning Pipeline for Predicting Melanoma Treatment Response |
| url | https://doi.org/10.5281/zenodo.17632979 |