Resources

DEEPAligner (Deep Encoded Epigenetic Pathway Aligner),
is a novel alignment method that finds functionally consistent and topologically sound alignments of epigenetic signatures from pathway networks. A deep embedding framework is used to obtain epigenetic signatures from pathways which are then aligned for functional consistency and local topological similarity.

Publication:
Visakh R and K A Abdul Nazeer, “DEEPAligner: Deep encoding of pathways to align epigenetic signatures”, Computational Biology and Chemistry (Elsevier), Vol. 72, February 2018, pp. 87-95.


The inlcuded R package (dkmpp_0.1.0.tar.gz) contains an implementation of ‘Density K-Means++’ algorithm – a density based deterministic variant of the K-Means clustering algorithm.

The algorithm systematically finds out a set of inital centroids which belong to dense regions in feature space and which are adequately separated.

Publication:
N. Nidheesh, K.A. Abdul Nazeer, P.M. Ameer, An enhanced deterministic K-Means clustering algorithm for cancer subtype prediction from gene expression data, Computers in Biology and Medicine 91C (2017) pp. 213-221. https://doi.org/10.1016/j.compbiomed.2017.10.014


The model classifies cancer-related lncRNAs to Oncogenic or Tumour Suppressive. The interaction data of lncRNAs with proteins and lncRNA coexpression are the input. The interaction data are mapped to the objects and links of a Heterogeneous Information Network (HIN). The feature set for the classifier is constructed by mining the topological features of HIN. The key concept in feature set construction is metapath.

Publication: P.V. Sunil Kumar; M. Manju; G. Gopakumar, ” Function prediction of cancer-related LncRNAs using heterogeneous information network model“,  International Journal of Data Mining and Bioinformatics (IJDMB), Vol. 21, No. 4, 2018.


The model predicts lncRNA-disease associations and lncRNA-pathway association by mapping existing lncRNA-disease associations to an HIN (Heterogeneous Information Network). The feature set for the classifier that performs the prediction is constructed from a new meta-path based parameter Association Index.

Publication:  P V Sunil Kumar, G Gopakumar, Inferring Disease and Pathway Associations of Long Non Coding RNAs using Heterogeneous Information Network Model, Journal of Bioinformatics and Computational Biology, DOI: 10.1142/S0219720019500203