ABSTRACT
Major histocompatibility complex I (MHC-I) molecules have the characteristic of de-homogeneity which can be recognized by CD8+T cells and plays an important role in antigen delivery. The loss or downregulation of the MHC-I may prevent the immune-mediated reaction. Some tumors may use the mechanism to become invisible in the immune system, causing MHC-I-based immunotherapy to be essential for cancer treatment. To raise the accuracy of targeted immunotherapy, precise and robust prediction of MHC-I affinity can be indispensable. Although traditional experimental methods focused on the comparison of mass spectrometry and flow cytometry to determine the sequence information, experimental technology was expensive and inefficient. Due to the weakness of second-generation sequencing, small-length sequences such as MHC-I may face a high risk of base deletion and mismatch. While machine learning and deep learning methods are mainly based on data mining and statistical inference, without costing too much on biological experiments. In addition, these models have robust generalization ability and accurate performances in several classification and regression tasks, offering confidential results of MHC affinity prediction. In this thesis, we considered 25 biological and sequence features including amino acid (AA) residues, hybrid orbital theory, and 3D physical structure. These computed properties in higher dimensions were further deduced by the specific feature selection algorithm. The final feature maps were integrated into a features matrix (9 x 25), regarded as a large labeled dataset. 222,875 samples were divided into training (178,300 samples) and testing datasets (44,575 samples). With this high-quantity feature matrix, we build several machine learning and deep learning models. Using MSE as the assessment, Bi-LSTM gained the best performance in both training dataset and testing dataset (Training_MSE: 0.0517; Testing_MSE: 0.0594) which was better than the SVM (Training_MSE: 0.0759; Testing_MSE: 0.0757) and DNN (Training_MSE: 0.0736; Testing_MSE: 0.0735). Our results mentions that the Bi-LSTM model may have a robust and stable ability in MHC-I affinity prediction, which can improve the study of bioinformatic study and increase the development of sequence prediction.
- Sullivan RJ, Atkins MB, Kirkwood JM, Agarwala SS, Clark JI, Ernstoff MS, Fecher L, Gajewski TF, Gastman B, Lawson DH, Lutzky J, McDermott DF, Margolin KA, Mehnert JM, Pavlick AC, Richards JM, Rubin KM, Sharfman W, Silverstein S, Slingluff CL Jr, Sondak VK, Tarhini AA, Thompson JA, Urba WJ, White RL, Whitman ED, Hodi FS, Kaufman HL. An update on the Society for Immunotherapy of Cancer consensus statement on tumor immunotherapy for the treatment of cutaneous melanoma: version 2.0. J Immunother Cancer. 2018 May 30;6(1):44. doi: 10.1186/s40425-018-0362-6Google Scholar
- Morrison AH, Byrne KT, Vonderheide RH. Immunotherapy and Prevention of Pancreatic Cancer. Trends Cancer. 2018 Jun;4(6):418-428. doi: 10.1016/j.trecan.2018.04.001Google Scholar
- Yoon JS, Song BG, Lee JH, Lee HY, Kim SW, Chang Y, Lee YB, Cho EJ, Yu SJ, Sinn DH, Kim YJ, Lee JH, Yoon JH. Adjuvant cytokine-induced killer cell immunotherapy for hepatocellular carcinoma: a propensity score-matched analysis of real-world data. BMC Cancer. 2019 May 31;19(1):523. doi: 10.1186/s12885-019-5740-zGoogle Scholar
- Vonderheide RH, Bayne LJ. Inflammatory networks and immune surveillance of pancreatic carcinoma. Curr Opin Immunol. 2013 Apr;25(2):200-5. doi: 10.1016/j.coi.2013.01.006Google Scholar
- Chan HP, Samala RK, Hadjiiski LM, Zhou C. Deep Learning in Medical Image Analysis. Adv Exp Med Biol. 2020;1213:3-21. doi: 10.1007/978-3-030-33128-3_1Google Scholar
- Wang J, Chen S, Liang H, Zhao Y, Xu Z, Xiao W, Zhang T, Ji R, Chen T, Xiong B, Chen F, Yang J, Lou H. Fully Automatic Classification of Brain Atrophy on NCCT Images in Cerebral Small Vessel Disease: A Pilot Study Using Deep Learning Models. Front Neurol. 2022 Mar 24;13:846348. doi: 10.3389/fneur.2022.846348Google Scholar
- Kido S, Hirano Y, Mabu S. Deep Learning for Pulmonary Image Analysis: Classification, Detection, and Segmentation. Adv Exp Med Biol. 2020;1213:47-58. doi: 10.1007/978-3-030-33128-3_3Google Scholar
- Tung CW, Ho SY. POPI: predicting immunogenicity of MHC class I binding peptides by mining informative physicochemical properties. Bioinformatics. 2007 Apr 15;23(8):942-9. doi: 10.1093/bioinformatics/btm061Google Scholar
- Liu Z, Cui Y, Xiong Z, Nasiri A, Zhang A, Hu J. DeepSeqPan, a novel deep convolutional neural network model for pan-specific class I HLA-peptide binding affinity prediction. Sci Rep. 2019 Jan 28;9(1):794. doi: 10.1038/s41598-018-37214-1Google Scholar
- Antonio Gulli , Amita Kapoor , Sujit Pal (2019).Deep Learning with TensorFlow 2 and Keras – Second Edition. WOW! eBook. ISBN-10: 1838823417Google Scholar
- Zhao T, Cheng L, Zang T, Hu Y. Peptide-Major Histocompatibility Complex Class I Binding Prediction Based on Deep Learning With Novel Feature. Front Genet. 2019 Nov 28;10:1191. doi: 10.3389/fgene.2019.01191Google Scholar
- Rammensee HG, Falk K, Rötzschke O. Peptides naturally presented by MHC class I molecules. Annu Rev Immunol. 1993;11:213-44. doi: 10.1146/annurev.iy.11.040193.001241Google Scholar
- Hobohm U, Meyerhans A. A pattern search method for putative anchor residues in T cell epitopes. Eur J Immunol. 1993 Jun;23(6):1271-6. doi: 10.1002/eji.1830230612Google Scholar
- Nielsen M, Lund O, Buus S, Lundegaard C. MHC class II epitope predictive algorithms. Immunology. 2010 Jul;130(3):319-28. doi: 10.1111/j.1365-2567.2010.03268.xGoogle Scholar
- Cheng T, Zhao Y, Li X, Lin F, Xu Y, Zhang X, Li Y, Wang R, Lai L. Computation of octanol-water partition coefficients by guiding an additive model with knowledge. J Chem Inf Model. 2007 Nov-Dec;47(6):2140-8. doi: 10.1021/ci700257yGoogle Scholar
- Ertl P, Rohde B, Selzer P. Fast calculation of molecular polar surface area as a sum of fragment-based contributions and its application to the prediction of drug transport properties. J Med Chem. 2000 Oct 5;43(20):3714-7. doi: 10.1021/jm000942eGoogle Scholar
Recommendations
Identification and evaluation of immunogenic MHC-I and MHC-II binding peptides from Mycobacterium tuberculosis
AbstractDue to several limitations of the only available BCG vaccine, to generate adequate protective immune responses, it is important to develop potent and cost-effective vaccines against tuberculosis (TB). In this study, we have used an immune-...
Highlights- 5 proteins namely ECCB1, ECCD1, ECCE1, TB 31.7 and MyCP1 were predicted as the most antigenic proteins.
- Best predicted peptides were found to be present in the MtbTB31.7 (Rv2623).
- Simulation studies showed significantly less ...
Polymorphism in the ligand binding domain of rage alters its binding affinity towards Aβ42 peptides: an in-silico study
The study was aimed to understand the influence of RAGE polymorphism G82S, R48Q, R77C on the binding affinity to Aβ42 peptides through an in-silico approach. The structure of RAGE ectodomain 3CJJ was docked with three forms of Aβ42 [monomeric: apolar ...
Quantitative prediction of MHC-II binding affinity using particle swarm optimization
Objective: Helper T-cell epitopes (Th epitopes) are the basic units which activate helper T-cell's immune response, and they are helpful for understanding the immune mechanism and developing vaccines. Peptide and major histocompatibility complex class ...
Comments