98%
921
2 minutes
20
Interleukin-2 (IL-2) based immunotherapy has been approved for treating certain types of cancer, as IL-2 plays a crucial role in regulating the immune system. In this study, we developed a method for predicting IL-2-inducing peptides. Our method was trained, tested, and validated on a main dataset containing 6,574 experimentally validated Major histocompatibility complex (MHC) binders, including 3,429 IL-2-inducing and 3,145 non-inducing peptides. A primary analysis of IL-2 inducing and non-inducing peptides revealed that certain residues, such as alanine and leucine, are more abundant in IL-2-inducing peptides. Initially, we developed alignment-based methods, which demonstrated high precision but limited coverage. Subsequently, we developed artificial intelligence-based models, including machine learning (ML), deep learning (DL), and large language models (LLM), to predict IL-2-inducing peptides. Our Extra Tree-based model, developed using dipeptide composition and peptide length, achieved a maximum AUC of 0.82. Finally, we constructed ensemble models that combined artificial intelligence and alignment-based methods. Our best ensemble model, which integrates the Extra Tree-based model with MERCI, achieved the highest AUC of 0.84 and an MCC of 0.51 on the main dataset. One limitation of the main dataset is that both IL-2-inducing and non-inducing peptides are MHC binders. To address this limitation, we created two additional datasets: Alternate Dataset 1, consisting of 3,429 IL-2-inducing peptides and 3,429 non-inducing peptides (MHC non-binders), and Alternate Dataset 2, consisting of 3,429 IL-2-inducing peptides and 3,439 non-inducing peptides (MHC binders + MHC non-binders). Our best ensemble model achieved AUCs of 0.9 and 0.8 with MCCs of 0.61 and 0.44 on Alternate Datasets 1 and 2, respectively. To assist the scientific community, we have integrated the best models from this study into a standalone software and web server, IL2pred, which enables users to predict, scan, and design IL-2-inducing peptides ( https://webs.iiitd.edu.in/raghava/il2pred/ ).
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12267595 | PMC |
http://dx.doi.org/10.1038/s41598-025-08388-2 | DOI Listing |
Sci Rep
July 2025
Department of Computational Biology, Indraprastha Institute of Information Technology, A-302 (R&D Block), Okhla Industrial Estate, Phase III, (Near Govind Puri Metro Station), New Delhi, 110020, India.
Interleukin-2 (IL-2) based immunotherapy has been approved for treating certain types of cancer, as IL-2 plays a crucial role in regulating the immune system. In this study, we developed a method for predicting IL-2-inducing peptides. Our method was trained, tested, and validated on a main dataset containing 6,574 experimentally validated Major histocompatibility complex (MHC) binders, including 3,429 IL-2-inducing and 3,145 non-inducing peptides.
View Article and Find Full Text PDFBiomolecules
December 2024
Molecular Oncology Laboratory, Cell Differentiation and Cancer Research Unit, UMIEZ Campus II FES Zaragoza, National Autonomous University of Mexico, Mexico City 09230, Mexico.
Cervical cancer is a global health problem; therapies focused on eliminating tumour cells and strengthening different immunotherapies are in development. However, it has been observed that cervical tumour cells can evade cell death mechanisms and generate immune system molecules to promote their proliferation and metastasis. In this context, we analysed the role of the IL-2 and CD95 pathways, essential molecules in activating the immune system and eliminating tumour cells.
View Article and Find Full Text PDFMar Drugs
December 2022
Student Research Committee, Shiraz University of Medical Sciences, Shiraz 71345-1583, Iran.
Complex pathological diseases, such as cancer, infection, and Alzheimer's, need to be targeted by multipronged curative. Various omics technologies, with a high rate of data generation, demand artificial intelligence to translate these data into druggable targets. In this study, 82 marine venomous animal species were retrieved, and 3505 cryptic cell-penetrating peptides (CPPs) were identified in their toxins.
View Article and Find Full Text PDFJ Hepatol
May 2017
Institute of Molecular Immunology and Experimental Oncology, Klinikum München rechts der Isar, Technische Universität München, Germany. Electronic address:
Background & Aims: Liver sinusoidal endothelial cells (LSECs) are prominent liver-resident antigen (cross-)presenting cells. LSEC cross-priming of naïve CD8 T cells does not require CD4 T cell help in contrast to priming by dendritic cells (DC) but leads to the formation of memory T cells that is preceded by transient Granzyme B (GzmB) expression. Here we provide evidence for a so far unrecognized CD4 T helper cell function in LSEC-induced CD8 T cell activation.
View Article and Find Full Text PDFJ Immunol
July 2016
Sorbonne Universités, Université Pierre et Marie Curie, Université Paris 6, UMRS 959, I, F-75013 Paris, France; INSERM, UMRS 959, I, F-75013 Paris, France; and Service de Biothérapies et Centre d'Investigation Clinique en Biothérapie, Groupe Hospitalier Pitié Salpêtrière, Assistance Publique
Regulatory T cells (Tregs) are pivotal for maintenance of immune self-tolerance and also regulate immune responses to exogenous Ags, including allergens. Both decreased Treg number and function have been reported in allergic patients, offering new therapeutic perspectives. We previously demonstrated that Tregs can be selectively expanded and activated by low doses of IL-2 (ld-IL-2) inducing immunoregulation without immunosuppression and established its protective effect in autoimmune diseases.
View Article and Find Full Text PDF