Publish Date : 26th December, 2017

It is a pleasure to let you know that UIU BSCSE students Farshid Ryhan and Sajid Ahmed have got their first journal paper accepted in Scientific Reports Journal, a reputed journal with impact factor 4.8 (5 years) and ranked 5 in the relevant discipline and published by Nature Publishing Group. This work was done under the supervision of Dr. Dewan Md. Farid and Dr. Swakkhar Shatabda and an extension or application of their BSCSE thesis work. Their paper is titled ” iDTI-ESBoost: Identification of Drug Target Interaction Using Evolutionary and Structural Features with Boosting“.

In this work, they proposed and developed a method that will predict whether a drug will interact with a target protein or not. They have shown the effectiveness of their method on real datasets of enzymes, nr, etc target proteins and drugs. We hope this method will be helpful in drug discovery related field. Professor Sohel Rahman, CSE, BUET, Dr Abdollah Dehzangi, Morgan State University, United States and Dr Zaynab Mousavian, Tehran University, Iran jointly supervised the project with us. We are very happy to share this success of our students. Both of them are currently working as instructor in the CSE department.

Link to the published article:

Here is an abstract of the paper:

Prediction of new drug-target interactions is critically important as it can lead the researchers to find new uses for old drugs and to disclose their therapeutic profiles or side effects. However, experimental prediction of drug-target interactions is expensive and time-consuming. As a result, computational methods for prediction of new drug-target interactions have gained a tremendous interest in recent times. Here we present iDTI-ESBoost, a prediction model for identification of drug-target interactions using evolutionary and structural features. Our proposed method uses a novel data balancing and boosting technique to predict drug-target interaction. On standard gold datasets, iDTI-ESBoost outperforms the state-of-the-art methods in terms of area under receiver operating characteristic (auROC) curve and area under precision recall (auPR) curve. This is significant as auPR curves are argued as suitable metric for comparison for imbalanced datasets similar to the one studied here. Our reported results show the effectiveness of the classifier, balancing methods and the novel features incorporated in iDTI-ESBoost. We believe the excellent performance of iDTI-ESBoost both in terms of auROC and auPR would motivate the researchers and practitioners to use it to predict drug-target interactions. To facilitate that, iDTI-ESBoost is implemented and made publicly available at:
http://farshidrayhan.pythonanywhere.com/iDTI-ESBoost/.

Share This: