Skip to content
View bracealround's full-sized avatar
76 followers · 240 following
  • University of Central Florida
  • Orlando, USA

Block or report bracealround

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
bracealround/README.md

Hi, I'm Sourav Saha 👋

Ph.D. in Computer Science · University of Central Florida
Genome Language Models · Bioinformatics · NLP · LLMs

profile views Website LinkedIn Google Scholar Email Kaggle Codeforces

🧬 About Me

I'm a Ph.D. student in the Computational Biology & Machine Learning Lab at UCF, where I apply language modeling techniques to biological sequences — particularly genome language models for understanding RNA regulatory elements.

  • 🎓 Passed my PhD Qualifying Review (March 2026)
  • 🔬 Currently working on genome LMs for polyadenylation site prediction and diffusion language models in proteomics, with applications in drug discovery and cancer research
  • 📄 First author of PolyA-GLM (CSBJ, 2025) — a framework for de novo polyA site discovery
  • 🧪 Maintain tools for alternative splicing and polyadenylation analysis (survey published in Experimental & Molecular Medicine, IF 12.8)
  • 🌏 Previously: ML Engineer at Reve Systems building Bangla NLP systems, and Lecturer at UAP, Bangladesh
  • 🤝 Co-organized the first Violence-Inciting Text Detection shared task at BLP @ EMNLP 2023 (27 teams)
  • 📫 Reach me at saha.sourav@ucf.edu

📚 Selected Publications

🧬 Bioinformatics & Genome Language Models

  • PolyA-GLM: A Comprehensive Framework for De Novo Polyadenylation Site Prediction Using Genome Language Models Computational and Structural Biotechnology Journal (Elsevier, Q1, IF 5.2), 2025 · First author
  • Computational Methods for Alternative Polyadenylation and Splicing in Post-Transcriptional Gene Regulation Experimental & Molecular Medicine (Nature Publishing Group, Q1, IF 12.8), 2025 · Second author

📝 NLP, LLMs & Responsible AI

  • BnPC: A Gold Standard Corpus for Paraphrase Detection in Bangla — BUCC @ LREC-COLING 2024 · First author
  • Vio-Lens: Annotated Social Network Posts Leading to Communal Violence — BLP @ EMNLP 2023 · First author · 31 citations
  • BLP Shared Task 1: Violence-Inciting Text Detection — BLP @ EMNLP 2023 · First author · 19 citations
  • Data, Annotation, and Meaning-Making: Faith-Based Communal Violence — ACM FAccT 2024 · Co-author · 16 citations
  • garNER at SemEval-2023 Task 2: Knowledge Augmentation for Multilingual NER — SemEval @ ACL 2023 · Equal contribution

📖 Full list on Google Scholar →

🤝 Professional Service

  • 🔍 Reviewer — ISMB 2025, 2026
  • 🧑‍⚖️ Program Committee & Reviewer — 2nd Workshop on Bangla Language Processing, IJCNLP-AACL 2025
  • 🎯 Shared Task Organizer — Violence-Inciting Text Detection, BLP @ EMNLP 2023
  • 👨‍🏫 Programming Team Coach — University of Asia Pacific (2024)
  • 🏆 Top 10 in 10 tracks — SemEval 2023 Task 2 (Team garNER)

🛠️ Tech Stack

📈 GitHub Stats

streak stats

trophies

"Can the same architectures that decode human language also decode the language of life?"

Pinned Loading

  1. Result_Processing_System_RPS Result_Processing_System_RPS Public

    This is a web application called Result Processing System (RPS), created using Django and bootstrap framework with SQLite database.

    CSS 2 1

  2. Design_Pattern_Codes Design_Pattern_Codes Public

    These are different design pattern codes implemented by me for Software Engineering And Design Pattern Course

    Java 2

  3. ImageManipulation-Detection-with-Different-Datasets ImageManipulation-Detection-with-Different-Datasets Public

    This Ml based project runs and compares a deep-learning model on 3 different publically available dataset

    Jupyter Notebook 1

  4. Emedichineproject Emedichineproject Public

    It is an Android project which is used for purchasing and distributing medicine orders.

    Java

  5. blp-workshop/blp_task1 blp-workshop/blp_task1 Public

    3 2

  6. Zero-Few-Shot-Result-Violence-Detection-Using-LLMs Zero-Few-Shot-Result-Violence-Detection-Using-LLMs Public

    Python