KUALA LUMPUR, Oct 20 (Bernama) -- Biotechnology company ImmunoScape has published new peer-reviewed research that demonstrates the use of machine learning to predict the virus specificity of human T-cells.
Led by ImmunoScape Scientist Michael Fehlings, and published in the scientific journal, Cell Reports, the research could have profound implications for the use of machine learning in the discovery and development of T-cell based immunotherapies.
This study opens novel avenues to address the challenges of finding T-cell receptors (TCRs) that can be transformed into therapeutics against different diseases and indications.
The company has built a discovery engine that offers 360-degree views of lab-validated data from millions of T cells, which serves as the foundation for its machine learning platform.
“Our proprietary multi-omics database includes an unparalleled set of T-cell phenotypes and corresponding TCRs against viral, cancer and other antigens and builds the foundation for our computational models.
“Our mission is to harness the power of machine learning to accelerate the discovery of cancer-specific T cells while expanding access to more effective therapeutics,” said ImmunoScape co-founder and chief executive officer, Choon-Peng Ng in a statement.
The findings include identification of unique phenotypes of T cells specific for different virus antigens; inference of phenotypic signatures from virus-specific T cells via machine learning; and utilisation of machine learning to predict antigen specificity from T-cell phenotypes.
ImmunoScape developed and trained machine learning models to identify and learn common phenotypic signatures inherent to T cells specific for different antigen categories in the study.
With the validation of its platform, ImmunoScape will expand the use of machine learning to identify tumour-specific TCRs to support its pipeline for the development of novel TCR-based therapeutics against solid tumours.
-- BERNAMA
No comments:
Post a Comment