# Machine learning optimized autoimmune therapeutics with a focus on Type 1 Diabetes

> **NIH NIH R43** · THINK THERAPEUTICS, INC. · 2024 · $306,500

## Abstract

Project Summary
We propose to develop a new immunogenicity assay and machine learning based
framework for creating tolerization vaccines for autoimmune diseases with improved
population coverage. In collaboration with Harvard University and the University of
Massachusetts Chan Medical School Diabetes Center of Excellence we will develop a
new assay, the Multiplexed Multi-antigen Activation Assay (MMAA), to discover self-
antigens that are recognized by cytotoxic T cells in Type 1 Diabetes (T1D) (Aim 1). We
will use the self-antigens we have confirmed to design novel multi-epitope tolerization
vaccines and test the vaccines for their ability to expand CD4+ TReg cells in PBMCs from
T1D donors (Aim 2). We will utilize new machine learning methods to modify and select
vaccine epitopes to substantially improve tolerization vaccine population coverage. Our
products will be the resulting vaccines.

## Key facts

- **NIH application ID:** 10929966
- **Project number:** 5R43AI177185-02
- **Recipient organization:** THINK THERAPEUTICS, INC.
- **Principal Investigator:** David K Gifford
- **Activity code:** R43 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2024
- **Award amount:** $306,500
- **Award type:** 5
- **Project period:** 2023-09-15 → 2025-08-31

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10929966

## Citation

> US National Institutes of Health, RePORTER application 10929966, Machine learning optimized autoimmune therapeutics with a focus on Type 1 Diabetes (5R43AI177185-02). Retrieved via AI Analytics 2026-05-25 from https://api.ai-analytics.org/grant/nih/10929966. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*