Lazada

XtalPi to Present the Latest Progress of Its AI Cancer Vaccine Design Platform at AACR 2024

BEIJING and HONG KONG, March 28, 2024 /PRNewswire/ — XtalPi, a leading global technology company in integrating artificial intelligence (AI) and robotics to advance the discovery of groundbreaking medicine and innovative materials, today announced it will present a poster showcasing the latest accomplishments of its AI-powered platform for designing cancer vaccines at the 2024 American Association for Cancer Research (AACR) Annual Meeting. The meeting will take place from 5th – 10th April 2024 in San Diego, California, and XtalPi’s poster will be included in the online Proceedings of the AACR.

“We are excited to share the progress from our joint research initiative with CK Life Sciences, which leverages the innovative approach from our peptide R&D platform to design cancer vaccines with enhanced efficacy. Together, we are committed to overcoming conventional limitations in creating new therapeutics and deploying cutting-edge technologies to benefit patients worldwide,” said Dr. Lipeng Lai, Co-founder and Chief Innovation Officer at XtalPi.

POSTER PRESENTATION DETAILS

Abstract 3525: Towards the efficient design of shared neoantigen peptide cancer vaccines using artificial intelligence

Authors: Genwei Zhang, Jiewen Du, Xiangrui Gao, Tianyuan Wang, Zhenghui Wang, Qingxia Zhang, Tongren Liu, Dong Chen, Ruohan Zhu, Yalong Zhao, Samson Li, Melvin Toh, Lipeng Lai

Session Date and Time: Monday, April 8(th), 1:30 PM – 5:00 PM Pacific Standard Time

The accurate prediction of immunogenicity of cancer vaccines remains elusive. We developed new models that predict the probability of a given peptide derived from the protein of interest to be presented by MHC-I or MHC-II.

For MHC-I antigen presentation model development, over 17 million entries in the dataset were collected from published literature and available databases, such as IEDB, with peptide lengths ranging from 8 to 11. The peptides were restricted to 150 unique MHC-I alleles. Similarly, ~4 million entries with peptide lengths ranging from 13 to 21 were collected for MHC-II antigen presentation model development, and the peptides were restricted to 19 unique MHC-II alleles. To develop advanced antigen presentation models, a language model was chosen as the backbone network, and contrastive learning was used to better discriminate the peptide-MHC match versus mismatch. Overall, both MHC-I and MHC-II presentation models were constructed with about 30 million parameters.

To validate algorithm prediction accuracy and peptide immunogenicity, 28 predicted patentable peptides derived from mutated TP53 protein were synthesized and their binding to respective common HLA alleles was validated using surface plasmon resonance. We found that over 80% of the peptides displayed binding affinities stronger than the positive control, suggesting that AI significantly improves the design of neoantigen peptide vaccines. Our developed AI models surpassed the performance of state-of-the-art prediction algorithms, the latest versions of NetMHCpan and MixMHCpred, for both MHC-I and MHC-II antigen presentation.

DETAILS ON XTALPI PEPTIDE R&D PLATFORM

XtalPi Innovation Center based in Beijing has established a fully integrated peptide R&D platform that combines dry-lab design with wet-lab validation and optimization to advance the rapid development of peptides for nutraceuticals, cosmetics, and pharmaceuticals.

The peptide R&D platform can carry out high-precision AI peptide design and has successfully built data-driven design processes for both linear and cyclic peptides. It is also equipped for automated synthesis, automated cleavage, and purification of peptides, as well as high-resolution mass spectrometry analysis and sequence identification.

In addition, XtalPi has established high-throughput one-bead-one-compound (OBOC)-based screening workflows for peptide and mRNA-encoded peptide libraries, which provide one-pot molecule screening of millions and trillions of molecules respectively. Its library screening enables rapid identification and improvement of peptide candidates’ affinities. The seamless integration of dry and wet lab capabilities significantly shortens the peptide discovery and optimization cycles, leading to a higher experimental success rate.

About XtalPi

XtalPi is an innovative technology company powered by artificial intelligence (AI) and robotics. Founded in 2015 on the MIT campus, XtalPi is dedicated to driving intelligent and digital transformation in the life science and new materials industries. With tightly interwoven quantum physics, AI, cloud computing, and large-scale clusters of robotic workstations, XtalPi offers a range of technology solutions, services, and products to accelerate and empower innovation for biopharmaceutical and new materials companies worldwide.

 

View original content to download multimedia: Read More