This project is based on Gene expression dataset from Kaggle. Here Molecular Classification of Cancer by Gene Expression monitoring Dataset is done. This dataset comes from a proof-of-concept study published in 1999 by Golub et al. It showed how new cases of cancer could be classified by gene expression monitoring (via DNA microarray) and thereby provided a general approach for identifying new cancer classes and assigning tumors to known classes. These data were used to classify patients with acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL). Golub et al "Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression Monitoring" -> There are two datasets containing the initial (training, 38 samples) and independent (test, 34 samples) datasets used in the paper. These datasets contain measurements corresponding to ALL and AML samples from Bone Marrow and Peripheral Blood. Intensity values have been re-scaled such that overall intensities for each chip are equivalent. --------------------------------------- Results: --------------------------------------- SVM (Support Vector Machine): Accuracy of training set = 100& Accuracy of test set = 89% Random Forest Classifier: Accuracy of training set = 100& Accuracy of test set = 94% ANN (Artificial Neural Network): Accuracy of training set = 100& Accuracy of test set = 100%
KungWanyi/Classification_of_Cancer_by_Gene_Expression_Dataset
This project is based on Gene expression dataset from Kaggle. Here Molecular Classification of Cancer by Gene Expression monitoring Dataset is done. This dataset comes from a proof-of-concept study published in 1999 by Golub et al. It showed how new cases of cancer could be classified by gene expression monitoring (via DNA microarray) and thereby provided a general approach for identifying new cancer classes and assigning tumors to known classes. These data were used to classify patients with acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL).
Jupyter Notebook