KNIME Extensions: A modular, highly configurable framework for easy workflow automation and data analysis
Using the popular open-source KNIME interface, researchers can easily assemble individual "nodes" into a complete workflow — from structure preparation and selection to a validated predictive model. Expediting a wide variety of common tasks, Schrödinger KNIME Extensions are an indispensable tool for modeling and cheminformatics.
The Advantages of Workflow Automation
Real world research seldom involves a single question being answered by means of a single operation, and the fields of molecular modeling and cheminformatics are no exception. While researchers can create custom scripts to automate common procedures, this solution is less than ideal when projects demand rapid workflow prototyping, interactive data analysis, and robust, appropriately validated models. By no coincidence, these are exactly the conditions for which Schrödinger KNIME Extensions are best suited — together with the open-source KNIME interface, Schrödinger KNIME Extensions are designed to provide a powerful means for researchers to easily develop, validate, and deploy multi-step computational workflows.
KNIME has established itself as the leading open-source data pipelining tool, and provides an ideal platform for researchers looking for a way to combine best-of-breed technologies from commercial software, academic programs, and in-house code. Independent of the Schrödinger Extensions, KNIME already incorporates over 100 processing nodes for data manipulation and mining, including the complete set of analysis models from the well-known Weka data-mining environment. Additionally, it includes plug-ins that run R-scripts, giving users access to a vast library of statistical routines. Visualization of results is made possible by means of KNIME nodes that support interactive use of scatter plots, parallel coordinates, and more.
The Schrödinger nodes build upon the existing KNIME infrastructure, nearly doubling the number of available nodes, and provide access to a wealth of ligand- and structure-based tools from the Schrödinger Suite. Glide, Prime, Phase, MacroModel, Jaguar, and other programs and utilities have Schrödinger nodes that enable core functionality; please see the Features table to the right for examples.
Above, a close-up on several nodes of a KNIME workflow that uses Schrödinger Extensions. The drag-and-drop interface of the KNIME platform makes it simple and intuitive to create new workflows, while annotation allow researchers and collaborators to easily understand each node's purpose. [Click image to enlarge]
Complex workflows can be constructed to bring molecules through a series of different programs that compute energetic and structural properties, which can then easily be combined to build models and improve the accuracy of predictions. Additionally, Schrödinger KNIME Extensions are distributed with a number of pre-configured workflows that enable a variety of sophisticated experiments.
KNIME’s open architecture allows custom nodes and data types to be developed and integrated into KNIME with a very moderate amount of effort, thus enabling the incorporation of in-house applications and third-party software. KNIME’s extensible nature, combined with its easy-to-use interface and the power of Schrödinger software, make Schrödinger KNIME Extensions a powerful platform for workflow automation, model building, and data analysis.
To download free KNIME workflows for use with Schrödinger software, please visit our KNIME Workflows page.