Loading
Ridge regression is linear regression with a penalty that shrinks coefficients, which keeps it stable when there are more genes than samples; a multilayer perceptron is the simplest neural network, a few fully connected layers.
Ridge regression estimates multiple-regression coefficients when the variables are highly correlated, by adding an L2 penalty (Wikipedia); with twenty thousand correlated genes and a few hundred samples it is the natural per-drug or per-outcome head on top of principal components. A multilayer perceptron is a feedforward network of fully connected layers with non-linear activations (Wikipedia), the usual encoder in autoencoders and the usual non-linear baseline; when it does not beat ridge, the non-linearity is not buying anything.
Shares Drug-response baselines and frameworks: mean-drug floor, LightGBM, DrEval, IMPROVE, DeepTTA, Logistic regression and nearest-centroid classifiers, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Linear probe, Principal component analysis (PCA) as a feature compressor, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Loss functions: cross-entropy and mean squared error, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Loss functions: cross-entropy and mean squared error, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Drug-response baselines and frameworks: mean-drug floor, LightGBM, DrEval, IMPROVE, DeepTTA, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Drug-response baselines and frameworks: mean-drug floor, LightGBM, DrEval, IMPROVE, DeepTTA, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Principal component analysis (PCA) as a feature compressor, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Principal component analysis (PCA) as a feature compressor, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.