liveBook · Manning

Support vector regression

As explained in Build AI Drug Discovery Pipelines

SVR is support vector regression, a supervised regression method that fits a function using support vectors and an epsilon-insensitive loss.

Support vector regression (SVR) is a supervised regression method that finds a hyperplane while allowing a margin of error around predicted values. Its epsilon-insensitive loss ignores small errors, making it useful for noisy experimental solubility labels. section 4.3.3 section 4.5

For descriptor-based molecular data, SVR remains linear in its feature space but can represent nonlinear relationships after feature expansion. This makes it a practical option for small-to-medium datasets with engineered molecular descriptors. section 4.3.3

A practical SVR workflow includes:

  • Create molecular descriptors, optionally expand them with PolynomialFeatures, and scale the resulting features. section 4.4.3
  • Train with a regularized estimator such as SGDRegressor using epsilon-insensitive loss, a learning-rate schedule, and optional early stopping. section 4.3.3
  • Tune regularization, polynomial degree, and epsilon-tube width, then inspect validation curves for underfitting and overfitting. section 4.4.3
  • Compare test-set RMSE with meaningful baselines rather than interpreting the score alone. section 4.3.3

Molecular solubility prediction

An SVR model trained on engineered molecular descriptors achieved a validation RMSE of 1.3791. The selected model reached a test RMSE of 1.2783, outperforming the ESOL baseline at 1.3787 and the y-scrambled baseline at 2.4585. Its pipeline combined median imputation, degree-two polynomial features, standardization, L2 regularization, epsilon-insensitive loss, inverse-scaled learning, and early stopping. section 4.3.3

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains epsilon-tube behavior, preprocessing, optimization, hyperparameter effects, bias-variance trade-offs, and baseline evaluation.
Examples
Uses molecular descriptors, degree-two polynomial features, solubility RMSE, ESOL, y-scrambled labels, and learning or validation curves.
What it assumes
Assumes basic regression and molecular-descriptor concepts while developing model selection, preprocessing, and validation practices.
What you can do after
Build it from scratch, tune its preprocessing and hyperparameters, and evaluate generalization against solubility baselines.
How it connects
Connects SVR with linear regression, ridge regression, Lasso regression, RANSAC, polynomial features, regularization, and bias-variance trade-offs.

Also explained in

Compare how 2 books explain support vector regression →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.