Esra Akbas - Research

Research Interests

Graph Mining and Compressing

Graph Machine Learning- GNN

Network Science

Text Mining

Bioinformatic, Biomedical applications

Selected Research Projects

Developing Novel Graph Neural Network Models

Recently, GNN models have become popular and successful in many different domains and real-world applications. However, there are still some challenges of the current models such as oversmothing, and application to large and complex graphs. We develop novel GNN models to overcome these drawbacks.

Graph Compressing for Expediting Graph Analysis

Overall objective of this project is to develop new graph processing methods based on graph compression that make the analysis of large graphs possible using existing solutions. The aim of graph compression is to create a smaller graph without losing any/much information about the graph and with preserving key network properties. The rationale underlying the proposed research is that the resultant compressed graph maintains the crucial information from the original large graph while eliminating redundant information. This will make it possible to analyze and visualize large graphs more efficiently with existing algorithms without losing their effectiveness.

Knowledge Discovery on Biomedical data

The goal of this project is to utilize applied machine learning to massive interaction data among biomedical entities like drugs, diseases, proteins and side effects. This project constructs different network structure from this biomedical relational data and also develop network-based learning methods to address critical problems in biology and medicine.

Sequence Classification

Sequence Data is very common in different domains including biological domains such as DNA, RNA. Different machine learning (ML) models have been employed to classify sequence data. The performance of ML classifiers primarily depends on selecting the best features. However, there is no explicit feature in sequence data, so designing an effective ML model for sequence classification is still challenging

As a solution to this challenge, we develop different models to represent sequence data as a graph and learn the representation of sequence and similarity between them

GNN models for Drug related problems

We are conducting multiple projects on DDI prediction using different graph-based techniques/methods. In one project, our method considers drugs and other biomedical entities like proteins, pathways, and side effects, for DDI prediction. We design a heterogeneous information network (HIN) to model relations between these entities. Afterward, we extract the rich semantic relationships among these entities using different meta-path-based topological features. An extensive set of features are fed to different classifiers for DDI prediction.

Link to this paper: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9562802

Biomedical knowledge mining on social networks

The overall objective of this project is to conduct biomedical knowledge mining to track public health issues on social networks. Dr. Akbas also focuses on developing novel graph and text mining methods to extrapolate useful information from social media data. Her goal is to combat different public health problems, such as opioid addiction and Covid-19, to help government officials and health administrators by providing timely and useful information.