MOTIVATION: The binding of a peptide antigen to a Class I major histocompatibility complex (MHC) protein is part of a key process that lets the immune system recognize an infected cell or a cancer cell. This mechanism enabled the development of peptide-based vaccines that can activate the patient's immune response to treat cancers. Hence, the ability of accurately predict peptide-MHC binding is an essential component for prioritizing the best peptides for each patient. However, peptide-MHC binding experimental data for many MHC alleles are still lacking, which limited the accuracy of existing prediction models. RESULTS: In this study, we presented an improved version of MHCSeqNet that utilized sub-word-level peptide features, a 3D structure embedding for MHC alleles, and an expanded training dataset to achieve better generalizability on MHC alleles with small amounts of data. Visualization of MHC allele embeddings confirms that the model was able to group alleles with similar binding specificity, including those with no peptide ligand in the training dataset. Furthermore, an external evaluation suggests that MHCSeqNet2 can improve the prioritization of T cell epitopes for MHC alleles with small amount of training data. AVAILABILITY AND IMPLEMENTATION: The source code and installation instruction for MHCSeqNet2 are available at https://github.com/cmb-chula/MHCSeqNet2.

Set prediction tasks require the matching between predicted set and ground truth set in order to propagate the gradient signal. Recent works have performed this matching in the original feature space thus requiring predefined distance functions. We propose a method for learning the distance function by performing the matching in the latent space learned from encoding networks. This method enables the use of teacher forcing which was not possible previously since matching in the feature space must be computed after the entire output sequence is generated. Nonetheless, a naive implementation of latent set prediction might not converge due to permutation instability. To address this problem, we provide sufficient conditions for permutation stability which begets an algorithm to improve the overall model convergence. Experiments on several set prediction tasks, including image captioning and object detection, demonstrate the effectiveness of our method.

MOTIVATION: MHC-peptide binding prediction has been widely used for understanding the immune response of individuals or populations, each carrying different MHC molecules as well as for the development of immunotherapeutics. The results from MHC-peptide binding prediction tools are mostly reported as a predicted binding affinity (IC50) and the percentile rank score, and global thresholds e.g. IC50 value < 500 nM or percentile rank < 2% are generally recommended for distinguishing binding peptides from non-binding peptides. However, it is difficult to evaluate statistically the probability of an individual peptide binding prediction to be true or false solely considering predicted scores. Therefore, statistics describing the overall global false discovery rate (FDR) and local FDR, also called posterior error probability (PEP) are required to give statistical context to the natively produced scores. RESULT: We have developed an algorithm and code implementation, called MHCVision, for estimation of FDR and PEP values for the predicted results of MHC-peptide binding prediction from the NetMHCpan tool. MHCVision performs parameter estimation using a modified expectation maximization framework for a two-component beta mixture model, representing the distribution of true and false scores of the predicted dataset. We can then estimate the PEP of an individual peptide's predicted score, and conversely the probability that it is true. We demonstrate that the use of global FDR and PEP estimation can provide a better trade-off between sensitivity and precision over using currently recommended thresholds from tools. AVAILABILITY AND IMPLEMENTATION: https://github.com/PGB-LIV/MHCVision. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Immunotherapy is an emerging approach in cancer treatment that activates the host immune system to destroy cancer cells expressing unique peptide signatures (neoepitopes). Administrations of cancer-specific neoepitopes in the form of synthetic peptide vaccine have been proven effective in both mouse models and human patients. Because only a tiny fraction of cancer-specific neoepitopes actually elicits immune response, selection of potent, immunogenic neoepitopes remains a challenging step in cancer vaccine development. A basic approach for immunogenicity prediction is based on the premise that effective neoepitope should bind with the Major Histocompatibility Complex (MHC) with high affinity. RESULTS: In this study, we developed MHCSeqNet, an open-source deep learning model, which not only outperforms state-of-the-art predictors on both MHC binding affinity and MHC ligand peptidome datasets but also exhibits promising generalization to unseen MHC class I alleles. MHCSeqNet employed neural network architectures developed for natural language processing to model amino acid sequence representations of MHC allele and epitope peptide as sentences with amino acids as individual words. This consideration allows MHCSeqNet to accept new MHC alleles as well as peptides of any length. CONCLUSIONS: The improved performance and the flexibility offered by MHCSeqNet should make it a valuable tool for screening effective neoepitopes in cancer vaccine development.

The primary, secondary, and tertiary structures of spectrin are reasonably well defined, but the structural basis for the known dramatic molecular shape change, whereby the molecular length can increase three-fold, is not understood. In this study, we combine previously reported biochemical and high-resolution crystallographic data with structural mass spectroscopy and electron microscopic data to derive a detailed, experimentally-supported quaternary structure of the spectrin heterotetramer. In addition to explaining spectrin's physiological resting length of ~55-65 nm, our model provides a mechanism by which spectrin is able to undergo a seamless three-fold extension while remaining a linear filament, an experimentally observed property. According to the proposed model, spectrin's quaternary structure and mechanism of extension is similar to a Chinese Finger Trap: at shorter molecular lengths spectrin is a hollow cylinder that extends by increasing the pitch of each spectrin repeat, which decreases the internal diameter. We validated our model with electron microscopy, which demonstrated that, as predicted, spectrin is hollow at its biological resting length of ~55-65 nm. The model is further supported by zero-length chemical crosslink data indicative of an approximately 90 degree bend between adjacent spectrin repeats. The domain-domain interactions in our model are entirely consistent with those present in the prototypical linear antiparallel heterotetramer as well as recently reported inter-strand chemical crosslinks. The model is consistent with all known physical properties of spectrin, and upon full extension our Chinese Finger Trap Model reduces to the ~180-200 nm molecular model currently in common use.

Pleiotropy refers to the phenomenon in which a single gene controls several distinct, and seemingly unrelated, phenotypic effects. We use C. elegans early embryogenesis as a model to conduct systematic studies of pleiotropy. We analyze high-throughput RNA interference (RNAi) data from C. elegans and identify "phenotypic signatures", which are sets of cellular defects indicative of certain biological functions. By matching phenotypic profiles to our identified signatures, we assign genes with complex phenotypic profiles to multiple functional classes. Overall, we observe that pleiotropy occurs extensively among genes involved in early embryogenesis, and a small proportion of these genes are highly pleiotropic. We hypothesize that genes involved in early embryogenesis are organized into partially overlapping functional modules, and that pleiotropic genes represent "connectors" between these modules. In support of this hypothesis, we find that highly pleiotropic genes tend to reside in central positions in protein-protein interaction networks, suggesting that pleiotropic genes act as connecting points between different protein complexes or pathways.