PACT Reports New Data Highlighting Predictive Power of Machine Learning Approach Leveraging PACTImmune™ Database at Society for Immunotherapy of Cancer’s (SITC) 36th Annual Meeting

On November 15, 2021 PACT Pharma, Inc., a clinical-stage company developing transformational personalized neoTCR-T cell therapies for the eradication of solid tumors, reported that new data related to its PACTImmune Database were presented at the Society for Immunotherapy of Cancer (SITC) (Free SITC Whitepaper)’s (SITC) (Free SITC Whitepaper) 36th Annual Meeting (Press release, PACT Pharma, NOV 15, 2021, View Source [SID1234595650]). The results were featured in a poster presentation (#820) entitled, "Machine learning significantly improves neoantigen-HLA predictions utilizing > 26,000 data points from the PACTImmune Database," at the SITC (Free SITC Whitepaper) conference, which was held November 10-14, 2021.

Schedule your 30 min Free 1stOncology Demo!
Discover why more than 1,500 members use 1stOncology™ to excel in:

Early/Late Stage Pipeline Development - Target Scouting - Clinical Biomarkers - Indication Selection & Expansion - BD&L Contacts - Conference Reports - Combinatorial Drug Settings - Companion Diagnostics - Drug Repositioning - First-in-class Analysis - Competitive Analysis - Deals & Licensing

                  Schedule Your 30 min Free Demo!

The presented results reported findings from a study in which PACT applied machine learning to more than 26,000 manufactured polypeptides consisting of the initially predicted neoE peptide together with Beta-2-Microglobulin and the HLA heavy chain for 62 different HLA alleles. Data demonstrated that PACT’s approach significantly improved neoE-HLA predictions, resulting in a 22% improvement in success rates on prospective data as compared to the widely used netMHCpan4.1 predictions. Additionally, the presentation outlined key elements of PACT’s strategy for continued enhancements to its approach to further improve its predictive power.

"The PACTImmune Database enables us to tune and continue to learn from our platform and its growing data assets. Based on retrospective analysis we know that higher predicted neoE-HLA success corelates with more TCRs captured per patient. Ultimately, these improved predictions should give us more actionable neoTCR options for patients in our clinical trial," said Eric Stawiski, Vice President of Bioinformatics at PACT and presenter of the SITC (Free SITC Whitepaper) poster.

The abstract related to this presentation is available on the SITC (Free SITC Whitepaper) website and can be accessed at: View Source

About PACTImmune Database
PACT has developed a proprietary approach to validate predicted neoepitopes (neoEs) and their cognate T cell receptors (neoTCRs) by capturing neoepitope-specific T cells from peripheral blood. This neoTCR discovery and validation process is being applied in a clinical trial (NCT03970382) evaluating personalized neoTCR-T cell therapy to treat patients across eight solid tumor types. Extensive pre-, on- and post-treatment data related to this trial has been accumulated in the PACTImmune Database (PIDB) which represents a growing data asset for patient-specific tumor immunogenicity in solid tumors.