Figure 2:

Workflow for model selection and parameter fitting. The diagram shows how the data were used to train and validate each model. The performance of each model was assessed by a patient-holdout cross-validation, where the tumor and healthy samples from the same patient were excluded for validation. Data from the remaining N-1 patients were used to fit the model. For each model, between 100,000 and 375,000 initial sets of weights were generated. To save compute cycles, only models with good or better performance were run a large number of times. Each set of weights was used for exhaustive leave-one-out cross-validation over all N patients. Each run of cross-validation with each set of initial weights was run for 2,500 iterations of gradient optimization. The best fit to the N-1 training samples from among all runs was used to evaluate the excluded validation data.