Skip to content
View lhallee's full-sized avatar

Block or report lhallee

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
lhallee/README.md

“Somewhere in the semantics of natural language and the ambiguity of our understanding in reality leaves truth as one of the great mysteries”

Introduction

Hi, I’m @lhallee!

My name is Logan Hallee, a scientist working on computational protein modeling through the lens of machine learning. Most notably, I am the the Chief Scientific Officer and Founder of Synthyra, a Public Benefit LLC which functions as a research org for protein science. I am also a PhD Candidate in Bioinformatics at the University of Delaware in the (Gleghorn Lab), where my research is focused on (you guessed it) protein modeling with transformer neural networks. On the side I run a fun blog called Minds and Molecules which touches on philosophical ideas I find facinating.

You can find my CV here

Research Highlights

SYNTERACT

Tetris For Proteins

  • Collaborated with Stephen Wolfram & other mentors at the Wolfram Winter School.
  • Developed “Tetris For Proteins” – a shape-based metric emulating lock-and-key enzyme-substrate interactions.
  • Generates hypotheses on protein aggregation likelihood.

Annotation Vocabulary

  • Invented the Annotation Vocabulary, a unique set of integers mapped to popular protein and gene ontologies.
  • Enables state-of-the-art protein annotation and generation models when paired with its own token embedding.

Codon Usage Bias

  • Codon usage bias is highlighted as a key biological phenomenon and valuable feature for machine learning in Nature Scientific Reports.
  • Our models show codon usage with a powerful phylogenetic association
  • Introduced cdsBERT, showcasing cost-effective ways to enhance biological relevance in protein language models via a codon vocabulary.

Mixture of Experts Extension

  • Invented a Mixture of Experts extension for scalable transformer networks adept at sentence similarity tasks.
  • Future networks with N experts could perform like N independently trained networks, offering significant time and computational savings in semantic retrieval systems.
  • In review.

Computer Vision in Biology

  • Collaborates on lab projects involving deep learning for reconstructing 3D organs from 2D Z-stacks.
  • Informs morphometric and pharmacokinetic studies to further understanding of organ structure and function.

Additional Projects & Publications


Socials / Websites

Contact

Research related queries - [email protected]

Business related queries - [email protected]


Last Updated: April 2025

Pinned Loading

  1. Gleghorn-Lab/AnnotationVocabulary Gleghorn-Lab/AnnotationVocabulary Public

    Jupyter Notebook 7

  2. Gleghorn-Lab/Mixture-of-Experts-Sentence-Similarity Gleghorn-Lab/Mixture-of-Experts-Sentence-Similarity Public

    Python 14

  3. Multi_Head_Mixture_of_Experts__MH-MOE Multi_Head_Mixture_of_Experts__MH-MOE Public

    Python 24 5

  4. featureranker featureranker Public

    Python package for feature ranking

    Jupyter Notebook 6

  5. ProteinVecHuggingface ProteinVecHuggingface Public

    Python 2

  6. CUF-ORF CUF-ORF Public

    CUF Classification and ORF Identification

    Jupyter Notebook