Skip to content
View Kuanhao-Chao's full-sized avatar
🧬
🧬
53 followers · 19 following

Achievements

Achievement: YOLOAchievement: Arctic Code Vault ContributorAchievement: Pull SharkAchievement: Starstruck

Achievements

Achievement: YOLOAchievement: Arctic Code Vault ContributorAchievement: Pull SharkAchievement: Starstruck

Highlights

  • Pro

Block or report Kuanhao-Chao

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
Kuanhao-Chao/README.md

👋 Hi, I'm Kuan-Hao Chao

🎓 I'm currently a third-year Ph.D. Candidate in Computer Science at the Center for Computational Biology, Johns Hopkins University, working with Steven Salzberg and Mihaela Pertea. . My academic journey started in Electrical Engineering at National Taiwan University (NTU), shifting towards computer science in my final year at the College of Engineering & Computer Science at Australian National University (ANU) 🦘🐨


🧬 My research interest intersects deep learning with genomics and transcriptomics:

  • In transcriptional regulatory networks, my work uses sequence models to decode DNA patterns, aiming to uncover insights into how cis-regulatory DNA sequences and trans-regulators interact. I am developing a yeast large language model (LLM) to better understand the mechanisms of yeast gene expression regulation.
  • In splice site predictiong, I built a deep dilated residual convolutional neural network to decode the complexities of RNA splicing, alternative splicing, and the impact of genetic variants on cryptic splicing (Learn more).
  • In genome assembly, I assembled and annotated the first gapless Southern Chinese Han genome, Han1, using PacBio HiFi and Oxford Nanopore long reads, with T2T-CHM13 as a guide (Learn more).
  • In pangenome indexing, I applied new renaming heuristics and an SMT solver to make the Wheeler graph recognition problem computationally feasible (Learn more).
  • In genome annotation, I used graph-based methods to stitch together fragmented DNA and protein alignments, thereby assembling them into more accurate annotations. (Learn more).

💻 I am an advocate for open-source software, embracing the philosophy of “build what you need, use what you build”. I invite you to explore my NEWS page for the latest updates on my projects.

💬 Feel free to reach out to me for collaborations, discussions, or just to say hi! Coffee chat! ☕️

🔍 Discover more about my work on my personal website.

Pinned Loading

  1. OpenSpliceAI Public

    🤖 Open‑source deep-learning-based splice‑site predictor that decodes splicing patterns across species

    Python 8

  2. LiftOn Public

    🚀 LiftOn: Accurate annotation mapping for GFF/GTF across assemblies

    Python 92 5

  3. splam Public

    ✂️ Deep learning-based splice site predictor that improves spliced alignments

    C++ 48 2

  4. roblanf/sangeranalyseR Public

    functions to analyse sanger sequencing reads in R

    R 101 24

  5. Wheeler_Graph_Toolkit Public

    🔎 wheeler graph recognition algorithm, visualization and generation

    C++ 16

  6. Biobaby Public

    👶🏼🍼 a RPG game modified from a unity 2D game kit

    JavaScript 22 2