Mostofa Rafid Uddin

I am a doctoral student in the CPCB Ph.D. Program in Carnegie Mellon University School of Computer Science, working with Dr. Min Xu. I am also a Center for Machine Learning and Health (CMLH) Fellow in Digital Health Innovation. My research interests include un/self-supervised learning, Representation Learning, Bioinformatics, 3D Computer Vision, Object detection and segmentation, Probabilistic graphical models, and Deep generative models.

My PhD thesis involves developing unsupervised algorithms for generative modelling of subcellular structure morphology from 2D and 3D microscopic images. Before joining my PhD, I graduated with B.Sc.Engg. in Computer Science and Engineering from Bangladesh University of Engineering and Technology(BUET) and later worked as a lecturer. During that time, I worked with Dr. Md. Shamsuzzoha Bayzid on leveraging machine translation for protein structure prediction.

Click here to download my full CV.

News
  • Received Outstanding Research Accomplishment Award from my PhD Program!!
  • Serving as a reviewer for ECCV 2024, NeurIPS 2024.
  • Received the prestigious CMLH fellowship in digital health for 2023!
  • Serving as a PC member in AAAI 2024!
  • Our consortium project on BrCa tumor landscape got provisionally accepted at Nat Cancer!!
  • Served as a Reviewer/PC member at ICCV 2023 and AAAI 2023!
  • First authored work "Harmony: A Generic Unsupervised Approach for Disentangling Semantic Content From Parameterized Transformations" got accepted at CVPR 2022!
  • Two co-authored papers on macromolecule recovery from subtomograms got accepted at ICIP 2022!
  • Worked as reviewer for ECCV 2022!
  • Worked as reviewer for CVPR 2022!

Publications

Please refer to my Google Scholar page for an up-to-date list with citations.

Published/Accepted Papers
  1. Mostofa Rafid Uddin, Gregory Howe, Xiangrui Zeng, and Min Xu. Harmony: A Generic Unsupervised Approach for Disentangling Semantic Content From Parameterized Transformations In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 20646-20655. [News link]

  2. Mostofa Rafid Uddin, Sazan Mahbub, Md Saifur Rahman, Md Shamsuzzoha Bayzid. SAINT: Self-Attention Augmented Inception-Inside-Inception Network Improves Protein Secondary Structure Prediction . Bioinformatics , Volume 36, Issue 17, 2020, Pages 4599-4608.

  3. Sayali Onkar, Jian Cui, Carly Cardello, Anthony Cillo, Mostofa Rafid Uddin, April Sagan, Marion Joy, Hatice Osmanbeyoglu, Katherine Pogue- Geile, Priscilla McAuliffe, Peter Lucas, Adrian Lee, Tullia Bruno, Steffi Oesterreich, and Dario Vignali. Immune landscape in invasive ductal and lobular breast cancer reveals a divergent macrophage-driven microenvironment Nature Cancer. 2023. 4(4), 516-534.

  4. Hmrishav Bandyopadhyay, Zihao Deng, Leiting Ding, Sinuo Liu, Mostofa Rafid Uddin, Xiangrui Zeng, Sima Behpour, Min Xu. Cryo-shift: Reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization. Bioinformatics , Volume 38, Issue 4, 2022, Pages 977–984.

  5. Najibul Sarker, Zaber Hakim, Ali Dabouei, Mostofa Rafid Uddin, Zachary Freyberg, Andrew Macwilliams, Joshua Kangas, Min Xu. Detecting Anomalies from Liquid Transfer Videos in Automated Laboratory Setting. Frontiers in Molecular Biosciences . 2023.

  6. Tarun Gupta, Xuehai He, Mostofa Rafid Uddin, Xiangrui Zeng, Andrew Zhou, Jing Zhang, Zachary Freyberg, Min Xu. Self-supervised learning for macromolecular structure classification based on cryo-electron tomograms. Frontiers in Physiology

  7. Xiangrui Zeng, Ziqian Lin, Mostofa Rafid Uddin, Bo Zhou, Chao Cheng, Jing Zhang, Zachary Freyberg, Min Xu. Structure Detection in 3D Cellular Cryo-electron Tomograms by Reconstructing 2D Annotated Tilt-series. Journal of Computational Biology, 2022. .

  8. Tianyang Wang, Bo Li, Jing Zhang, Xiangrui Zeng, Mostofa Rafid Uddin, Wei Wu, Min Xu. Deep Active Learning for Cryo-Electron Tomography Classification. International Conference on Image Processing (ICIP), 2022.

Teaching Experiences

Carnegie Mellon University- GTA

  • CMU02-620 Machine Learning for Scientists : A graduate level machine Learning course designed for Masters students in automated science and computational biology in SCS.
  • CMU02-740 Bioimage Informatics : A graduate level course on biological image processing designed for Masters students in automated science and computational biology in SCS.
January 2022 - May 2022

East West University- Lecturer

  • CSE498 Social and Professional Issues in Computing
  • CSE103 Structured Programming
  • CSE101 Computer Fundamentals
  • CSE350 Data Communications
  • CSE106 Discrete Mathematics
January 2019 - 2020

Awards & Honors

  • CMLH Fellowshiop in Digital Health 2023
  • news
  • Deans List Award and University Merit Scholarship
  • 1st Place - Poster Presentation, International Conference on Networking, Systems and Security (4th NSysS 2017) pdf
  • 1st Place - Hackathon for environmental migrants in Bangladesh arranged by Wageningen University, Netherlands. report
  • 2nd Place - Bracathon 2017 by BRAC
  • 3rd Place - National Hackathon 2016 by ICT Division.
  • 3rd Place - BUET Website Design Competition by IICT, BUET

Activities & Workshop

Mini-Projects

Design of Phase-separated Protein Sequences using Adaptive Sampling and Active Learning

Skills: Probabilistic Graphical Models, Protein Design, Optimization.

We address the problem of in silico protein design with a high propensity for liquid-liquid phase separation (LLPS) and droplet formation. Recently, there has been a surge in computational protein design methods that exhibit certain functions or structures. Moreover, no current method explicitly addresses the problem of computationally designing proteins with a high propensity for phase separation. To this end, we, for the first time, developed an adaptive sampling-based approach for in silico phase-separation protein design. Our method consists of multiple components, including a relaxed “energy" based sequence generator, a biochemical condition-aware attention-neural network-based surrogate model, a Bayesian acquisition function, and its optimizer. We demonstrate that our pipeline effectively generates in silico proteins with a high propensity for droplet formation in LLPS experiments, which outperforms other design methods.

Project is available here.

Edge prediction: Predicting Edge in Academic Citation Networks

Skills: Machine Learning, Graph Neural Networks.

This project attempts to assess the performance of various methods for predicting the citation of academic articles. Many researchers have sought to predict the future citation of new articles, and this interest has resulted in researchers using various machine learning methods for prediction. Our work asks a slightly different but related question. Given an article, how likely is it to cite another particular article? For our specific task, we found that sophisticated graph structure-based model does not achieve very promising performance. To this end, we developed an intelligent and novel feature engineering pipeline that could generate highly accurate predictions with relatively simpler models. We achieved around 95% F1 score with random forest classifier with our engineered features, which largely outperformed the graph neural network-based model.

Pytorch Autograd Implementation of OpenMM local energy minimizer

Tools : Pytorch, OpenMM

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.

Project is available here.

Predicting age from lung single cell data

In this project, we have analyzed the scRNA-seq data for 28 control patients to predict biological age from them. We tested with different machine learning approaches along with popular feature extraction methods and reported the results.This project was done as a lab rotation work with Prof. Ziv Bar-Joseph.

Project is available here.

Bangla to English Machine Translation Using Seq2seq Model with Attention Mechanism

Tools : Keras library (Tensorflow Backend), Python, Skills: Neural Machine Translation, Protein Structure Prediction.

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.

Project is available here.

Posture Corrector using Arduino

Tools : Arduino, Android, Bluetooth Module

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.

<


Contact

7513 Gates and Hillman Centers
Carnegie Mellon University
5000 Forbes Avenue
Pittsburgh, PA 15213, USA

mru AT andrew DOT cmu DOT edu, rafid DOT uddin95 AT gmail DOT com