PCP-ML can be used to create a quick, stand-alone feature generation program or used in conjunction with other libraries. The left side of the figure illustrates how PCP-ML can be used to create feature files which are then fed into existing ML tools (e.g., SVMlight) to generate a final prediction. In this case, PCP-ML is used to create a feature file that becomes the input to an existing machine learning tool, and this tool makes the final prediction. The right side of the figure shows PCP-ML packaged with other machine learning libraries for a complete, custom solution for protein prediction tasks. In this case, one program will read the input and generate the predictions. The round boxes represent libraries or packages and the labelled boxes represent programs or scripts.