Welcome to the KnowEnG Platform !
KnowEnG enables knowledge-guided machine learning and graph mining analysis on genomic datasets using scalable cloud computation and exploration of results with interactive visualizations.
Researchers can upload their data in form of a spreadsheet and choose from several analysis pipelines. Each pipeline is a complex workflow involving algorithms for data processing and normalization, application of the core machine learning or statistical algorithms, as well as post-processing and visualization. Learn more about our current and future pipelines.
The knowledge-guided analyses use the KnowEnG Knowledge Network, which integrates many and varied public biological datasets of gene/protein interactions, relationships, and annotations. Explore information about the Knowledge Network and how it can be used in the KnowEnG platform pipelines here.
In this first public release, KnowEnG will be provided for free for researchers to explore the system. Learn more.
To get started immediately, check out our Quickstart Guide for examples using our three available analysis pipelines. Also, watch out for the release of additional Knowledge-Guided Pipelines that are currently in development.
For General Questions, email us at email@example.com
The KnowEnG Gene Set Characterization pipeline tests a gene set for enrichment against a large compendium of annotations. The GSC pipeline is now available on the Seven Bridges Cancer Genomics Cloud (SB-CGC) described using the Common Workflow Language (CWL). More pipelines will be available on SB-CGC in the near future.