I have been involved in research and development since 2010. I have contributed to various projects and the outcome has been published in prestigious fully refereed venues.
We developed a novel paradigm to integrate data from three major sources in order to predict novel therapeutic drug indications. Microarray data, biomedical text mining data, and gene interaction data have been all integrated to predict ranked lists of genes based on their relevance to a particular drug or disease molecular action. These ranked lists of genes have finally been used as a raw material for building a disease-drug connectivity map. We reported 13% sensitivity improvement in comparison with using microarray or text mining data independently. Our paradigm is able to predict many clinically validated disease-drug associations that could not be captured using microarray or text mining data independently.
This work has been published in the Journal of Bioinformatics and Computational Biology which is directly related to the scope of the work done and hence the paper will reach a wider reader group.
Multi-scale Community Finder (MCF) is a tool to profile network communities (i.e., clusters of nodes) with the control of community sizes. The controlling parameter is referred to as the scale of the network community profile. MCF is able to find communities in all major types of networks including directed, signed, bipartite, and multi-slice networks. The fast computation promotes the practicability of the tool for large-scaled analysis (e.g., protein-protein interaction and gene co-expression networks). MCF is distributed as an open-source C++ package for academic use.
This significant contribution to the research community has been published in the Computer Methods and Programs in Biomedicine journal which is directly related to the theme of the work.
We proposed a novel approach which uses a well-known clustering algorithm k-means and a database indexing structure B+-tree to facilitate retrieving relevant images in an efficient and effective way. Cluster validity analysis indexes combined with majority voting are employed to verify the appropriate number of clusters. While searching for similar images, we consider images from the closest cluster and from other nearby clusters. We introduced two new parameters named cG and cS to determine the distance range to be searched in each cluster. We used Daubechies wavelet for extracting the feature vectors of images. The reported test results demonstrate how using data mining techniques could improve the efficiency of CBIR without sacrificing much from the overall accuracy.
This work was published in Knowledge-Based Systems, which is a premier journal in computer science with high impact factor.
We developed a robust framework that tackles this problem by considering both web log data and web structure data to suggest a more compact structure that could satisfy a larger user group. The study assumes the trend recorded so far in the web log reflects well the anticipated behavior of the users in the future. We separately analyze web log and web structure data using three techniques, namely clustering, frequent pattern mining and network analysis. The final outcome from the two stages is reflected on to one of the six models, namely the network of pages to report linking pages by the most appropriate connections.
This has been published in the International Journal of Business Intelligence and Data Mining which has a wide reader group in this domain.
We propose a link prediction model which is capable of predicting both links that might exist and links that may disappear in the future. The model has been successfully applied in two different though very related domains, namely health care and gene expression networks. The former application concentrates on physicians and their interactions while the second application covers genes and their interactions. We have tested our model using different classifiers and the reported results are encouraging. We compared our approach with the internal links approach and we concluded that our approach performs very well in both bipartite and non-bipartite graphs.
This work was published in the Network Modeling Analysis in Health Informatics and Bioinformatics journal which is the only journal in the literature that covers directly the intersection of network analysis, health informatics and bioinformatics.