Skip to main content

Engagements tagged slurm

Developing an automated microscopy analysis pipeline
South Dakota Mines

The goal is to build a complete pipeline that automates the preprocessing, analysis, and visualization of microscopy data. The pipeline is as follows: Scheduled transfer Microscope -> OSN bucket -> Computation on Bridges-2 GPU: preprocessing with petakit5D (deskew/decon/rotation) -> Segmentation using our refined SAM2 model -> isosurface generation and analysis using u-unwrap3D -> compression/packing of volumetric data into webp and DRACO GLTF for visualization on web viewers. At each stage the intermediate will be stored on the OSN bucket. This will leverage ACCESS allocation BIO240051: Cloud storage and compute for volumetric fluorescence movies

Status: In Review
Re-engineering Lilly’s KisunlaTM into a novel antibody targeting IL13RA2 against GBM using AI-driven macromolecular modeling
Atrium Health Levine Cancer
  • Summary and objectives of the proposed experiments: 
  1. An initial research-based Ab (scFv47, discovered by our collaborator Dr. Balyasnikova) model, modeling Ab-Ag (IL13RA2 against GBM) protein complex, and identifying the binding sites (epitopes) using ROSETTA and AlphaFold2 multimer tools.
  2. Graft the CDRs of scFv (single-chain variable fragment) of antibody or Bispecific T cell engagers (BTEs) onto the template Ab, the framework of Lilly's Kisunla™ Ab drug.
  3. Modify, improve, and optimize the overall or full antibody protein structures using AI-driven macromolecule modeling (AlphaFold3).
  4. Explore single nucleotide polymorphism (SNP), pathogenic genetic variants and N-glycosylation of IL13RA2 (target) protein domain interacting with the Ab candidates among the patient population using ROSETTA software packages.
Status: In Progress