Karthick Vasudevan; T Dhanushkumar; Sripad Rama Hebbar; Prasanna Kumar Selvam; Majji Rambabu; K. Anbarasu; Rohini Karunakaran · 2025 · Scientific Reports
Paper
Colorectal cancer (CRC) presents significant challenges due to limited targeted therapeutic options. This study integrates multi-omics analysis and AI to identify tumor antigens and immune gene targets for personalized immunotherapy. Using TCGA, differential expression and mutation analysis, we identified overexpressed and mutated genes in CRC. Among these, 62 neoantigens were shortlisted as potential tumor antigens. Survival analysis highlighted prognostic antigens, while their correlation with immune gene expression suggested these antigens could trigger immune activation. Three key neoantigens (TTK, EZH2, and KIF4A) emerged as promising candidates for immunotherapy. Based on immune gene activity, patients were categorized into three Immune Subtypes (IS). IS groups 1 and 2, characterized by high immune gene expression and immune activation markers, exhibited better survival outcomes, while IS 3, with low immune gene expression, showed poor survival and immune unresponsiveness. Neoantigen-based vaccines could potentially boost tumor recognition and improve survival for patients in immune-cold subtypes. Machine learning models like LightGBM, XGBoost, and XGBRF predicted optimal immune targets for vaccine design, validated through SHAP analysis. This study provides a machine learning- driven framework to identify tumor antigens and immune targets, offering a promising strategy for CRC immunotherapy tailored to immune subtype-specific responses.
Analysis
This study integrates multi-omics and AI to identify neoantigens and immune targets for personalized colorectal cancer vaccines, categorizing patients into immune subtypes to guide therapeutic strategies.
Discovery
Ruby Srivastava
Dariush Haghmorad; Majid Eslami; Niloufar Orooji; Iryna Halabitska; Iryna Kamyshna; Oleksandr Kamyshnyi; Valentyn Oksenych
Zachary Sethna; Pablo Guasp; Charlotte Reiche; Martina Milighetti; Nicholas Ceglia; Erin Patterson; Jayon Lihm; George C. Payne; Olga Lyudovyk; Luis A. Rojas; Nan Pang; Akihiro Ohmoto; Masataka Amisaki; Abderezak Zebboudj; Zagaa Odgerel; Emmanuel M. Bruno; Siqi Linsey Zhang; C. K. Cheng; Yuval Elhanati; Evelyna Derhovanessian; Luisa Manning; Felicitas Müller; Ina Rhee; Mahesh Yadav; Taha Merghoub; Jedd D. Wolchok; Olca Baştürk; Mithat Gönen; Andrew S. Epstein; Parisa Momtaz; Wungki Park; Ryan Sugarman; Anna M. Varghese; Elizabeth Won; Avni M. Desai; Alice C. Wei; Michael I. D’Angelica; T. Peter Kingham; Kevin C. Soares; William R. Jarnagin; Jeffrey A. Drebin; Eileen M. O’Reilly; Ira Mellman; Uğur Şahin; Özlem Türeci; Benjamin D. Greenbaum; Vinod P. Balachandran
David A. Braun; Giorgia Moranzoni; Vipheaviny Chea; Bradley A. McGregor; Eryn Blass; Chloe Ran Tu; Allison P. Vanasse; Cleo Forman; Juliet Forman; Alexander B. Afeyan; Nicholas Schindler; Yiwen Liu; Shuqiang Li; Jackson Southard; Steven L. Chang; Michelle S. Hirsch; Nicole R. LeBoeuf; Oriol Olive; Ambica Mehndiratta; Haley Greenslade; Keerthi Shetty; Susan Klaeger; Siranush Sarkizova; Christina B. Pedersen; Matthew Mossanen; Isabel Carulli; Anna Tarren; Joseph Duke-Cohan; Alexis A. Howard; J. Bryan Iorgulescu; Bohoon Shim; Jeremy M. Simon; Sabina Signoretti; Jon C. Aster; Liudmila Elagina; Steven A. Carr; Ignaty Leshchiner; Gad Getz; Stacey Gabriel; Nir Hacohen; Lars Rønn Olsen; Giacomo Oliveira; Donna Neuberg; Kenneth J. Livak; Sachet A. Shukla; Edward F. Fritsch; Catherine J. Wu; Derin B. Keskin; Patrick A. Ott; Toni K. Choueiri
Ting Fan; Congcong Xu; Jichuan Wu; Yihua Cai; WuQiang Cao; Haifa Shen; Mingna Zhang; Hanfei Zhu; Jingxian Yang; Zhounan Zhu; Xiaopin Ma; Jiale Ren; Lei Huang; Qianyun Li; Yuying Tang; Bo Yu; Chunxiu Chen; Mingcheng Xu; Qiuhe Wang; Zhuya Xu; Fengjia Chen; Shujing Liang; Zhixian Zhong; Anmbreen Jamroze; Dean G. Tang; Hangwen Li; Chunyan Dong
Fei Wang; Cai Guang; Yingchao Wang; Qiuyu Zhuang; Zhixiong Cai; Yingying Li; Shaodong Gao; Fang Li; Cuilin Zhang; Bixing Zhao; Xiaolong Liu
Source record