DeepMHCII: A Novel Binding Core-Aware Deep Interaction Model for Accurate MHC II-peptide Binding Affinity Prediction

Computationally predicting MHC-peptide binding affinity is an important problem in immunological bioinformatics. Recent cutting-edge deep learning-based methods for this problem are unable to achieve satisfactory performance for MHC class II molecules. This is because such methods generate the input by simply concatenating the two given sequences: (the estimated binding core of) a peptide and (the pseudo sequence of) an MHC class II molecule, ignoring the biological knowledge behind the interactions of the two molecules. We thus propose a binding core-aware deep learning-based model, DeepMHCII, with binding interaction convolution layer (BICL), which allows integrating all potential binding cores (in a given peptide) and the MHC pseudo (binding) sequence, through modeling the interaction with multiple convolutional kernels. Extensive empirical experiments with four large-scale datasets demonstrate that DeepMHCII significantly outperformed four state-of-the-art methods under numerous settings, such as five-fold cross-validation, leave one molecule out, validation with independent testing sets, and binding core prediction. All these results with visualization of the predicted binding cores indicate the effectiveness and importance of properly modeling biological facts in deep learning for high performance and knowledge discovery. DeepMHCII is publicly available at https://weilab.sjtu.edu.cn/DeepMHCII/.

A Deep Learning Approach for NeoAG-Specific Prediction Considering Both HLA-Peptide Binding and Immunogenicity: Finding Neoantigens to Making T-Cell Products More Personal

[Background]: An emerging type of cancer treatment, known as cell immunotherapy, is gaining popularity over chemotherapy or other radia-tion therapy that causes mass destruction to our body. One favourable ap-proach in cell immunotherapy is the use of neoantigens as targets that help our body immune system identify the cancer cells from healthy cells. Neoan-tigens, which are non-autologous proteins with individual specificity, are generated by non-synonymous mutations in the tumor cell genome. Owing to its strong immunogenicity and lack of expression in normal tissues, it is now an important target for tumor immunotherapy. Neoantigens are some form of special protein fragments excreted as a by-product on the surface of cancer cells during the DNA mutation at the tumour. In cancer immunotherapies, certain neoantigens which exist only on cancer cells elicit our white blood cells (body's defender, anti-cancer T-cell) responses that fight the cancer cells while leaving healthy cells alone. Personalized cancer vaccines there-fore can be designed de novo for each individual patient, when the specific neoantigens are found to be relevant to his/her tumour. The vaccine which is usually coded in synthetic long peptides, RNA or DNA representing the neo-antigens trigger an immune response in the body to destroy the cancer cells (tumour). The specific neoantigens can be found by a complex process of biopsy and genome sequencing. Alternatively, modern technologies nowa-days tap on AI to predict the right neoantigen candidates using algorithms. However, determining the binding and non-binding of neoantigens on T-cell receptors (TCR) is a challenging computational task due to its very large search space. [Objective]: To enhance the efficiency and accuracy of traditional deep learning tools, for serving the same purpose of finding potential responsive-ness to immunotherapy through correctly predicted neoantigens. It is known that deep learning is possible to explore which novel neoantigens bind to T-cell receptors and which ones don't. The exploration may be technically ex-pensive and time-consuming since deep learning is an inherently computa-tional method. one can use putative neoantigen peptide sequences to guide personalized cancer vaccines design. [Methods]: These models all proceed through complex feature engineering, including feature extraction, dimension reduction and so on. In this study, we derived 4 features to facilitate prediction and classification of 4 HLA-peptide binding namely AAC and DC from the global sequence, and the LAAC and LDC from the local sequence information. Based on the patterns of sequence formation, a nested structure of bidirectional long-short term memory neural network called local information module is used to extract context-based features around every residue. Another bilstm network layer called global information module is introduced above local information module layer to integrate context-based features of all residues in the same HLA-peptide binding chain, thereby involving inter-residue relationships in the training process. introduced. [Results]: Finally, a more effective model is obtained by fusing the above two modules and 4 features matric, the method performs significantly better than previous prediction schemes, whose overall r-square increased to 0.0125 and 0.1064 on train and increased to 0.0782 and 0.2926 on test da-tasets. The RMSE for our proposed models trained decreased to approxi-mately 0.0745 and 1.1034, respectively, and decreased to 0.6712 and 1.6506 on test dataset. [Conclusion]: Our work has been actively refining a machine-learning model to improve neoantigen identification and predictions with the determinants for Neoantigen identification. The final experimental results show that our method is more effective than existing methods for predicting peptide types, which can help laboratory researchers to identify the type of novel HLA-peptide binding. Keywords: machine learning; Cancer Cell Immunology; HLA-peptide binding Neoantigen Prediction; HLA; Data Visualization; Novel Neoanti-gen and TCR Pairing Discovery; Vector representation

Mooring stone-like Arg 114 pulls diverse bulged peptides: first insight into African swine fever virus-derived T cell epitopes presented by swine MHC class I

African swine fever virus (ASFV) is the causative agent of African swine fever (ASF), which is a devastating pig disease threatening the global pork industry. However, currently no commercial vaccines are available. During the immune response, major histocompatibility complex (MHC) class I molecules select viral peptide epitopes and present them to host cytotoxic T lymphocytes, thereby playing critical roles in eliminating viral infections. Here we screened peptides derived from ASFV and determined the molecular basis of ASFV-derived peptides presented by the swine leukocyte antigen (SLA)-1*0101. We found that peptide binding in SLA-1*0101 differs from the traditional mammalian binding patterns. Unlike the typical B and F pockets used by the common MHC-I molecule, SLA-1*0101 uses the D and F pockets as major peptide anchor pockets. Furthermore, the conformationally stable Arg 114 residue located in the peptide-binding groove (PBG) was highly selective for the peptides. Arg 114 draws negatively charged residues at positions P5 to P7 of the peptides, which led to multiple bulged conformations of different peptides binding to SLA-1*0101 and creating diversity for T cells receptor docking. Thus, the solid Arg 114 residue acts as a “mooring stone” and pulls the peptides into the PBG of SLA-1*0101. Notably, the T cells recognition and activation of p72-derived peptides were verified by SLA-1*0101 tetramer-based flow cytometry in peripheral blood mononuclear cells (PBMCs) of the donor pigs. These results refresh our understanding of MHC I molecular anchor peptides, and provide new insights into vaccine development for the prevention and control of ASF. IMPORTANCE The spread of African swine fever virus (ASFV) has caused enormous losses to the pork industry worldwide. Here, a series of ASFV-derived peptides were identified, which could bind to swine leukocyte antigen SLA-1*0101, a prevalent SLA allele among Yorkshire pigs. The crystal structure of four ASFV-derived peptides and one foot-and-mouth disease virus (FMDV)-derived peptide complexed with SLA-1*0101 revealed an unusual peptide anchoring mode of SLA-1*0101 with D and F pockets as anchoring pockets. Negatively-charged residues are preferred within the middle portion of SLA-1*0101-binding peptides. Notably, we determined an unexpected role of Arg 114 of SLA-1*0101 as a “mooring stone” which pulls the peptide anchoring into the PBG in diverse “M” or “n” shaped conformation. Furthermore, T cells from donor pigs could activate through the recognition of ASFV-derived peptides. Our study sheds light on the uncommon presentation of ASFV peptides by swine MHC I and benefits the development of ASF vaccines.

The proposed promiscuity value of an HLA can vary significantly depending on the source data used

ABSTRACTImmune checkpoint blockade, a form of immunotherapy, mobilizes a patient’s own immune system against cancer cells by releasing some of the natural brakes on T cells. Although our understanding of this process is evolving, it is thought that a patient response to immunotherapy requires tumor presentation of neoantigens to T cells and patients whose tumors present a wider array of neoantigens are more likely to derive benefit from immune checkpoint blockade1–4. Manczinger et al.5 recently reported findings that would appear contrarian to this notion in that they suggested patients with HLA alleles which bind more diverse peptides (higher promiscuity) are less likely to respond to immunotherapy. To estimate HLA promiscuity they looked at the HLA-peptide binding repertoires for class I alleles contained in the IEDB6, and obtained consistent results when performing robustness checks and subsequent analyses. Here we show that the proposed HLA promiscuity values can vary significantly across source data types and individual experiments.

Domain Analysis and Motif Matcher (DAMM): A Program to Predict Selectivity Determinants in Monosiga brevicollis PDZ Domains Using Human PDZ Data

Choanoflagellates are single-celled eukaryotes with complex signaling pathways. They are considered the closest non-metazoan ancestors to mammals and other metazoans and form multicellular-like states called rosettes. The choanoflagellate Monosiga brevicollis contains over 150 PDZ domains, an important peptide-binding domain in all three domains of life (Archaea, Bacteria, and Eukarya). Therefore, an understanding of PDZ domain signaling pathways in choanoflagellates may provide insight into the origins of multicellularity. PDZ domains recognize the C-terminus of target proteins and regulate signaling and trafficking pathways, as well as cellular adhesion. Here, we developed a computational software suite, Domain Analysis and Motif Matcher (DAMM), that analyzes peptide-binding cleft sequence identity as compared with human PDZ domains and that can be used in combination with literature searches of known human PDZ-interacting sequences to predict target specificity in choanoflagellate PDZ domains. We used this program, protein biochemistry, fluorescence polarization, and structural analyses to characterize the specificity of A9UPE9_MONBE, a M. brevicollis PDZ domain-containing protein with no homology to any metazoan protein, finding that its PDZ domain is most similar to those of the DLG family. We then identified two endogenous sequences that bind A9UPE9 PDZ with <100 μM affinity, a value commonly considered the threshold for cellular PDZ–peptide interactions. Taken together, this approach can be used to predict cellular targets of previously uncharacterized PDZ domains in choanoflagellates and other organisms. Our data contribute to investigations into choanoflagellate signaling and how it informs metazoan evolution.