Summary of project PR001000
This data is available at the NIH Common Fund's National Metabolomics Data Repository (NMDR) website, the Metabolomics Workbench, https://www.metabolomicsworkbench.org, where it has been assigned Project ID PR001000. The data can be accessed directly via it's Project DOI: 10.21228/M8F982 This work is supported by NIH grant, U2C- DK119886.
See: https://www.metabolomicsworkbench.org/about/howtocite.php
| Project ID: | PR001000 |
| Project DOI: | doi: 10.21228/M8F982 |
| Project Title: | Predicting T Cell Quality During Manufacturing Through an AI-based Integrative Multi-omics Analytical Platform |
| Project Summary: | Large-scale, reproducible manufacturing of therapeutic cells with consistent high quality is vital for translation to clinically effective and widely accessible cell-therapies for patients. However, the biological and logistical complexity of manufacturing a living product, including challenges associated with their inherent variability as well as uncertainties of process parameters, currently make it difficult to achieve predictable cell-product quality. Using a degradable microscaffold-based T cell manufacturing process as an example, we developed an Artificial Intelligence (AI)-driven experimental-computational platform to identify a multivariate set of critical process parameters (CPPs) and critical quality attributes (CQAs) from heterogeneous, high dimensional, time-dependent multi-omics data, measurable during early stages of manufacturing and that are predictive of end-of-manufacturing product quality. Sequential, Design-of-Experiment (DOE)-based studies, coupled with a set of agnostic machine-learning framework, was used to extract multiple feature combinations from Day 4 to 6 media assessment, that were highly predictive (R2>90%) of the end-product phenotypes, specifically the total live CD4+ and CD8+ naïve and central memory T cells (CD63L+CCR7+ cells), and the CD4+/CD8+ T cell ratio. This generalizable workflow and computational platform could be broadly applied to any cell-therapy manufacturing process to identify multivariate early CQAs and CPPs that are predictable of final product quality. |
| Institute: | University of Georgia;Georgia Institute of Technology;University of Puerto Rico Mayaguez |
| Last Name: | Colonna |
| First Name: | Maxwell |
| Address: | 315 Riverbend Rd, Athens, Georgia, 30602, USA |
| Email: | maxwellbaca@uga.edu |
| Phone: | 7065420257 |
| Funding Source: | NSF EEC-1648035 |
| Publications: | Predicting T Cell Quality During Manufacturing Through an AI-based Integrative Multi-omics Analytical Platform |
| Contributors: | Valerie Odeh-Couvertier, Nathan J. Dwarshuis, Maxwell B. Colonna, Bruce L. Levine, Arthur S. Edison, Theresa Kotanchek, Krishnendu Roy, and Wandaliz Torres-Garcia |
Summary of all studies in project PR001000
| Study ID | Study Title | Species | Institute | Analysis(* : Contains Untargted data) | Release Date | Version | Samples | Download(* : Contains raw data) |
|---|---|---|---|---|---|---|---|---|
| ST001476 | Design of Experiments for Maximizing T cell endpoints | Homo sapiens | University of Georgia | NMR* | 2020-09-10 | 1 | 235 | Uploaded data (586M)* |
