DNA motifs are short (5-20 bp) recurring patterns that represent binding sites for regulatory proteins such as Transcription Factors (TF).
These motifs along with the genes make up the gene regulation machinery in a living organism. Searching for these small patterns in large genomic data (up to billion bp) is very challenging. Further, these motifs may work in collaboration with one or more other motifs, and it is a computationally expensive task to find various permutations with a biological function.
We built an Artificial Neural Network (ANN) model to predict the co-occurrence of motifs from given instances of a TF binding motif. Then we grouped co-located motif instances into clusters, also known as Co-Regulatory Clusters (CRCs). Multiple features based on DNA shape, DNA composition, and protein-protein interaction (PPI) were calculated to study the biophysical characteristics of co-occurring motifs.
We applied this model to locate collaborative TF binding sites in the data generated through ChIP-Seq experiments with 89% accuracy.
⁍ Search for Co-Regulatory Clusters annotated from known ChIP-Seq datasets from 231 human TFs
⁍ Enter one or more gene and motif names to query from our database
⁍ Search for Novel Co-Regulatory Clusters predicted from our model without any known protein-pretein interactions
⁍ Enter one or more gene and motif names to query from our database where every CRC has an associated CRC score