I am a Lecturer in the Department of Computer Science and Engineering in Bangladesh University of Engineering and Technology (BUET). I received my Bachelors (B.Sc.) in Computer Science and Engineering from the same university. I am expected to join the Electrical Engineering and Computer Science (EECS) department of Massachusetts Institute of Technology (MIT) as a graduate student in Fall 2022. My research interests broadly lies in:
designing efficient and scalable computational models for solving real biological problems.
analyzing and finding insights in genomics / proteomics / bioimage data using various algorithmic and learning approaches.
designing powerful and robust vision architectures for biomedical image segmentation and analysis.
application of machine learning in computational biology and bioinformatics
Apart from my academic activities, I like to travel to new places. I have visited three countries till now and it's in my bucket list to increase the number to fifty before I turn 50. I like to hangout with my friends and family in my off-time and sing a few songs whenever I can.
B.Sc. in CSE (2016 - 2021) (Ranked 3rd in class)
Bangaldesh University of Engineering and Technology
Species tree estimation is frequently based on phylogenomic approaches that use multiple genes from throughout the genome. However, for a combination of reasons (ranging from sampling biases to more biological causes, as in gene birth and loss), gene trees are often incomplete, meaning that not all species of interest have a common set of genes. Incomplete gene trees can potentially impact the accuracy of phylogenomic inference. We, for the first time, introduce the problem of imputing the quartet distribution induced by a set of incomplete gene trees, which involves adding the missing quartets back to the quartet distribution. We present QT-GILD, an automated and specially tailored unsupervised deep learning technique, accompanied by cues from natural language processing (NLP), which learns the quartet distribution in a given set of incomplete gene trees and generates a complete set of quartets accordingly. QT-GILD is a general-purpose technique needing no explicit modeling of the subject system or reasons for missing data or gene tree heterogeneity. Experimental studies on a collection of simulated and empirical data sets suggest that QT-GILD can effectively impute the quartet distribution, which results in a dramatic improvement in the species tree accuracy. Remarkably, QT-GILD not only imputes the missing quartets but it can also account for gene tree estimation error. Therefore, QT-GILD advances the state-of-the-art in species tree estimation from gene trees in the face of missing data. QT-GILD is freely available in open source form at this link .
Covid-19 pandemic, caused by the SARS-CoV-2 genome sequence of coronavirus, has affected millions of people all over the world and taken thousands of lives. It is of utmost importance that the character of this deadly virus be studied and its nature is analyzed. We present here an analysis pipeline comprising a classification exercise to identify the virulence of the genome sequences and extraction of important features from its genetic material that is used subsequently to predict mutation at those interesting sites using deep learning techniques. We have classified the SARS-CoV-2 genome sequences with high accuracy and predicted the mutations in the sites of Interest. In a nutshell, we have prepared an analysis pipeline for hCov genome sequences leveraging the power of machine intelligence and uncovered what remained apparently shrouded by raw data. The All the codes and data (except for the Genome Sequences) of our pipeline can be found at this link
This study leveraged the phylogenetic analysis of more than 10,000 genome sequences of novel coronavirus (SARS-CoV-2) from 67 countries. Due to the requirement of high-end computational power for phylogenetic analysis, we leverage a fast yet highly accurate alignment-free method to develop the phylogenetic tree out of all the strains of novel coronavirus. K-Means clustering and PCA-based dimension reduction technique were used to identify a representative strain from each location. The resulting phylogenetic tree was able to highlight evolutionary relationships of SARS-CoV-2 genome and, subsequently, linked to the interpretation of facts and figures across the globe for the spread of COVID-19. Our analysis revealed that the geographical boundaries could not be explained by the phylogenetic analysis of novel coronavirus as it placed different countries from Asia, Europe and the USA in very close proximity in the tree. Instead, the commute of people from one country to another is the key to the spread of COVID-19. We believe our study will support the policymakers to contain the spread of COVID-19 globally.
Worked as the Vice-Chairperson of IEEE Computer Society, BUET Student Branch.
Worked as the General Secretary of Murchhona, BUET which is the central cultural club of BUET.
Participated in reviewing and creating digital content for the National ICT books as a team member of CSE, BUET.
Worked as the chief co-ordinator of BUET System Analysis, Design and Development community (BSADD).
Actively worked as an organizer of BUET CSE FEST 2016, 2018, 2019, 2020.
Actively worked as an volunteer of TEDxBUET 2016.