On December 17, 2020 Personalis, Inc. (Nasdaq: PSNL), a leader in advanced genomics for cancer, reported the launch of its Systematic HLA Epitope Ranking Pan Algorithm (SHERPA), the company’s proprietary, machine learning-based tool for the comprehensive identification and characterization of cancer neoantigens (Press release, Personalis, DEC 17, 2020, View Source [SID1234572999]). Integrated into the Personalis NeXT Platform, SHERPA enables the development of new neoantigen-based diagnostic biomarkers, such as the company’s proprietary Neoantigen Presentation Score (NEOPS), and novel personalized therapies.
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!
Data presented at the SITC (Free SITC Whitepaper) Annual Meeting in November 2020 showed SHERPA outperforming commonly used neoantigen binding prediction tools in clinical tumor samples. "With more accurate neoantigen presentation prediction, we are looking to enable a new generation of precision oncology applications," said Richard Chen, MD, Personalis CSO. "Trained on a proprietary immunopeptidomics dataset derived from engineered cell lines, SHERPA improves neoantigen presentation prediction compared to other in silico methods. With this advancement, SHERPA can enable more predictive biomarkers for cancer therapy as well as facilitate the development of neoantigen-targeting, personalized cancer therapies. Our recently-launched NEOPS is one example of a SHERPA-derived composite biomarker that has shown promise in predicting immunotherapy response in cancer patients."
While most conventional in silico methods generally only assess the potential MHC-binding affinity and stability of identified peptides, SHERPA goes a step further by incorporating features relating to the antigen processing machinery and RNA abundance to generate a presentation rank for each detected peptide. This serves to determine the relative likelihood of a given neoantigen being presented and undergoing immunosurveillance.
This launch represents the broader commercial release of SHERPA, which is currently being leveraged by Personalis’ preferred partner, Sarepta Therapeutics, to characterize immune response to precision genetic therapeutics in patients with rare diseases, demonstrating the applicability of this machine learning tool in disease areas beyond cancer.