The Support Vector Machine (SVM) Calculator accepts gene expression values from log2 normalized microarray data and copy number values as integers. It can also accept qRT-PCR data, but equal width binning is necessary for comparison to the training set. The SVMs were trained on a set of 49 cell lines for the paclitaxel sensitivity calculator and 44 for the gemcitabine sensitivity calculator. Subsequently, SVMs for doxorubicin, epirubicin, methotrexate, tamoxifen and 5-fluorouracil were built using 84 breast cancer patient data from METABRIC, treated with either chemotherapy or both chemo- and hormone therapy. Additional models were built for cisplatin, carboplatin and oxaliplatin, based on 39, 46 and 47 breast cancer patients respectively. After you input expression and/or copy number data, the calculator will return the score - the distance from the SVM hyperplane - and the prediction for whether the cell line or patient is sensitive or resistant.
Based on Genomic signatures for paclitaxel and gemcitabine resistance in breast cancer derived by machine learning. Stephanie N. Dorman, Katherina Baranova, Joan H.M. Knoll, Brad L. Urquhart, Gabriella Mariani, Maria Luisa Carcangiu, Peter K. Rogan (published in Molecular Oncology, 2015). READ PAPER HERE
Predicting Outcomes of Hormone and Chemotherapy in the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) Study by Biochemically-inspired Machine Learning. Iman Rezaeian, Eliseos J. Mucaki, Katherina Baranova, Huy Q. Pham, Dimo Angelov, Alioune Ngom, Luis Rueda, Peter K. Rogan (published in F1000 Research, 2016). READ PAPER HERE
Predicting Response to Platin Chemotherapy Agents with Biochemically-inspired Machine Learning. Eliseos J. Mucaki, Jonathan Z.L. Zhao, Daniel J. Lizotte, and Peter K. Rogan. Signal Transduct Target Ther. 2019. Jan 11;4:1. READ PAPER HERE
Multigene signatures of responses to chemotherapy derived by biochemically-inspired machine learning. Peter K. Rogan. Mol Genet Metab. 128 (2019): 45-52. READ PAPER HERE