I am a graduate student in the CPCB Ph.D. Program in Carnegie Mellon University School of Computer Science, working with Dr. Min Xu. Prior to this, I received my B.Sc.Engg. in Computer Science and Engineering from Bangladesh University of Engineering and Technology(BUET) and later worked as a lecturer. I completed my undergrad thesis under the supervision of Dr. Md. Shamsuzzoha Bayzid. My research interest lies broadly in application of machine learning and computer vision in computational biology and bioinformatics. Specifically, I like to map the problems in computational biology to popular machine learning and vision problems and come up with new efficient algorithms.
Currently I am working on representation learning for imaging data and its applications in bioimage informatics, more specifically, electron tomography images. Previously, I have worked on structural bioinformatics, specifically, protein folding.
Apart from academic activities, I like to travel-meet different types of people and taste different types of foods. In my free times, I like to make outings with my friends and family.
In this work, we present SAINT, a highly accurate and fast method for protein Q8 structure prediction, which incorporates self-attention mechanism (a concept from natural language processing) with the Deep Inception-Inside-Inception (Deep3I) network in order to effectively capture both the short-range and long-range dependencies among the amino acid residues. SAINT offers a more interpretable framework than the typical black-box deep neural network methods. We report, on an extensive evaluation study, the performance of SAINT in comparison with the existing best methods on a collection of recent benchmark dataset, namely TEST2016, TEST2018, CASP12 and CASP13. We have made SAINT freely available at this link.
The propitious developments in molecular biology and next generation sequencing have enabled the possibility for DNA storage technologies. However, the full application and power of our genomic revolution have not been fully utilized in clinical medicine given a lack of transition from research to real world clinical practice. This has identified an increasing need for an operating system which allows for the transition from research to clinical use. We present eMED-DNA, an in silico operating system for archiving and managing all forms of electronic health records (EHRs) within one’s own copy of the sequenced genome to aid in the application and integration of genomic medicine within real world clinical practice. We incorporated an efficient and sophisticated in-DNA file management system for the lossless management of EHRs within a genome. This represents the first in silico integrative system which would bring closer the utopian ideal for integrating genotypic data with phenotypic clinical data for future medical practice.
Worked as a moderator of East West University Electronics, Programming and Robotics Club. (Jan 2020- Dec 2020)
Designed and developed a responsive website for International Conference on Networking, Systems and Security(NSysS) jointly with Ajoy Das, under supervision of Dr. Rifat Shahriyar. Website Link.
Participated in a workshop on ``Reverse Engineering" arranged by ICT Division, Bangladesh Government. A team consisting of 18 members from CSE, BUET was provided with the opportunity to attend this workshop. The workshop was conducted by Dr. Desmond Devendran.
Participated in reviewing National ICT books as a team member of CSE, BUET.
Actively worked as an organizer of BUET CSE FEST 2018.
In this project, we implemented the openmm local energy minimizer (that is used to minimize the free energy of protein in protein dynamics) using pytorch. We extended the autograd mechanics of pytorch for a custom backpropagation where in the forward pass the energy is calculated and in the backward pass, each atom's coordinate is updated according to the energy gradients. This work was done under supervision of Prof. David Koes.
In this term project, we did an experiment on Neural Machine Translation(NMT) for Bangla to English Translation. We used a moderate size dataset containing 4379 sentence translations from English to Bangla. We used seq2seq encoder-decoder model containing Word2Vec and LSTMs with and without attention for small epochs. With finely tuned hyperparameters, we observed that using Bahdanau's attention with the vanilla encoder-decoder model improves the BLEU score for Bangla to English translation.
In this work, we developed a posture corrector android application that can detect unusual bending of the user. The application is connected with a wearable device containing Arduino and flex sensor. A user wearing a dress containing the device gets a notification in his application if he bends in a way that is harmful to his posture. Later a small physical motor was also introduced with the device that will force the user to correct his posture in case he doesn't has his phone nearby. However, the work was done for term project purpose and not commercially deployable.
In this term project, a cross-platform application was developed for travelers inside Bangladesh. Using the app, anyone can easily find the popular tourist places in Bangladesh, see user reviews and available accommodations nearby the place, view the places with high risks and get suggestions on how to avoid them. The project was deployed using AngularJs framework Ionic for frontend and a Python Django server for backend; the communication between frontend and backend was established using a REST API.
In this term project, an android game named glowhockey was deployed in a board containing 4 LED matrices. The gamers could use the gyro sensor in their hands to move the glowing hockey sticks in the board. The sensors and LED matrix were governed by an ATMega32 microprocessor which was programmed in C.
In this sophomore project, an application named FoodiesDhaka was developed using JavaFX and MySQL. In this application, the app users are provided with a choice of restaurants according to different areas in Dhaka city and they can see the user reviews and ratings for the restaurants. They can also suggest adding new restaurants in the list that can be further reviewed and checked by the admin side. The communication is done using Java Networking. However, the whole project was done in the localhost for term project purpose and is not deployable commercially.