Project description:RNAseq FASTq files of 181 bulk pre-treatment and 14 post-treatment tumors from GO30140 Ph1b group A and F and 177 bulk pre-treatment tumors of IMbrave150 PhIII
Project description:In this publication, researchers investigated the intricate relationship between breast cancers and their microenvironment, specifically focusing on predicting treatment responses using multi-omic machine learning model. They collected diverse data types including clinical, genomic, transcriptomic, and digital pathology profiles from pre-treatment biopsies of breast tumors. Leveraging this comprehensive multi-omic dataset, the team developed ensemble machine learning models using different algorithms (Logistic Regression, SVM and Random Forest). These predictive models identifies patients likely to achieve a pathological complete response (pCR) to therapy, showcasing their potential to enhance treatment selection.
Please note that the authors also have an interactive dashboard to apply the fully-integrated NAT response model on new (or any desired) data. The user can find its link in their GitHub repository: https://github.com/micrisor/NAT-ML
For more information and clarification, please refer to the ReadMe_NAT-ML document in the files section.
Project description:RNAseq fastq files from 611 bulk pre-treatment tumors from two indications: metastatic urothelial bladder cancer patients (IMvigor210) and metastatic renal cell carcinoma (IMmotion150)
Project description:The inactive X chromosome’s (Xi) physical territory is microscopically devoid of transcriptional hallmarks and enriched in silencing-associated modifications. How these microscopic signatures relate to specific Xi sequence is unknown. This study reports the profiling of Xi gene expression and chromatin states at high-resolution via allele-specific sequencing in F1 hybrid mouse trophoblast stem cells (TSCs). Datasets provided include those generated from strand-specific RNA-Seq, ChIP-Seq, FAIRE-Seq, and DNase-Seq protocols. Included for each dataset are FASTQ files, BED alignments and WIG files with coordinates relative to UCSC genome build mm9, and _snp files that report the location of all SNP-overlapping reads.