A tale of solving two computational challenges in protein science: neoantigen prediction and protein structure prediction

Combining diffusion and transformer models for enhanced promoter synthesis and strength prediction in deep learning

In the field of synthetic biology, the engineering of synthetic promoters that outperform their natural counterparts is of paramount importance, which can optimize the expression of exogenous genes, enhance the efficiency of metabolic pathways, and possess substantial commercial value. Research indicates that some synthetic promoters have higher transcriptional activity compared to strong natural promoters. However, with the exponential increase in complexity due to the 4n potential combinations in a promoter sequence of length n, identifying effective synthetic promoters remains a formidable challenge. Deep learning models, by adaptively learning from extensive data sets, have become instrumental in analyzing biological data. This study introduces a diffusion model-based approach for designing promoters viable in model bacteria such as Escherichia coli and cyanobacteria. This model proficiently assimilates and utilizes inherent biological features from natural promoter sequences to engineer synthetic variants. Additionally, we employed a transformer model to evaluate the efficacy of these synthetic promoters, aiming at screening those with high performance. The experimental findings suggest that the synthetic promoters by the diffusion model not only share key biological features with their natural counterparts but also demonstrate greater similarity to natural promoters than those generated by a variational autoencoder. In predicting promoter strength, the transformer model demonstrated improved performance over the convolutional neural network. Finally, we developed an integrated platform for generating promoters and predicting their strength.

IMPORTANCE

We demonstrated that diffusion models are superior in accomplishing the promoter synthesis task compared to other state-of-the-art deep learning models. The effectiveness of our method was validated using data sets of Escherichia coli and cyanobacteria promoters, showing more stable and prompt convergence and more natural-like promoters than the variational autoencoder model. We extracted sequence information, dimer information, and position information from promoters and combined them with a transformer model to predict promoter strength. Our prediction results were more accurate than those obtained with a convolutional neural network model. Our in silico experiments systematically introduced mutations in promoter sequences and explored their contribution to promoter strength, highlighting the depth of learning in our model.

NovoBoard: A Comprehensive Framework for Evaluating the False Discovery Rate and Accuracy of De Novo Peptide Sequencing

De novo peptide sequencing is one of the most fundamental research areas in mass spectrometry-based proteomics. Many methods have often been evaluated using a couple of simple metrics that do not fully reflect their overall performance. Moreover, there has not been an established method to estimate the false discovery rate (FDR) of de novo peptide-spectrum matches. Here we propose NovoBoard, a comprehensive framework to evaluate the performance of de novo peptide-sequencing methods. The framework consists of diverse benchmark datasets (including tryptic, nontryptic, immunopeptidomics, and different species) and a standard set of accuracy metrics to evaluate the fragment ions, amino acids, and peptides of the de novo results. More importantly, a new approach is designed to evaluate de novo peptide-sequencing methods on target-decoy spectra and to estimate and validate their FDRs. Our FDR estimation provides valuable information to assess the reliability of new peptides identified by de novo sequencing tools, especially when no ground-truth information is available to evaluate their accuracy. The FDR estimation can also be used to evaluate the capability of de novo peptide sequencing tools to distinguish between de novo peptide-spectrum matches and random matches. Our results thoroughly reveal the strengths and weaknesses of different de novo peptide-sequencing methods and how their performances depend on specific applications and the types of data.

Targeting Tumor Heterogeneity with Neoantigen-Based Cancer Vaccines

Neoantigen-based cancer vaccines have emerged as a promising immunotherapeutic approach to treat cancer. Nevertheless, the high degree of heterogeneity in tumors poses a significant hurdle for developing a vaccine that targets the therapeutically relevant neoantigens capable of effectively stimulating an immune response as each tumor contains numerous unique putative neoantigens. Understanding the complexities of tumor heterogeneity is crucial for the development of personalized neoantigen-based vaccines, which hold the potential to revolutionize cancer treatment and improve patient outcomes. In this review, we discuss recent advancements in the design of neoantigen-based cancer vaccines emphasizing the identification, validation, formulation, and targeting of neoantigens while addressing the challenges posed by tumor heterogeneity. The review highlights the application of cutting-edge approaches, such as single-cell sequencing and artificial intelligence to identify immunogenic neoantigens, while outlining current limitations and proposing future research directions to develop effective neoantigen-based vaccines.

Structural and Dynamic-Based Characterization of the Recognition Patterns of E7 and TRP-2 Epitopes by MHC Class I Receptors through Computational Approaches

A detailed comprehension of MHC-epitope recognition is essential for the design and development of new antigens that could be effectively used in immunotherapy. Yet, the high variability of the peptide together with the large abundance of MHC variants binding makes the process highly specific and large-scale characterizations extremely challenging by standard experimental techniques. Taking advantage of the striking predictive accuracy of AlphaFold, we report a structural and dynamic-based strategy to gain insights into the molecular basis that drives the recognition and interaction of MHC class I in the immune response triggered by pathogens and/or tumor-derived peptides. Here, we investigated at the atomic level the recognition of E7 and TRP-2 epitopes to their known receptors, thus offering a structural explanation for the different binding preferences of the studied receptors for specific residues in certain positions of the antigen sequences. Moreover, our analysis provides clues on the determinants that dictate the affinity of the same epitope with different receptors. Collectively, the data here presented indicate the reliability of the approach that can be straightforwardly extended to a large number of related systems.

Construing recombinant ZFP160 from Aspergillus terreus as pterin deaminase enzyme

Pterin deaminase stands as a metalloenzyme and exhibits both antitumor and anticancer activities. Therefore, this study aimed to explore the molecular function of zinc finger protein-160 (zfp160) from Aspergillus terreus with its enzyme mechanism in detail. Subsequently, preliminary molecular docking studies on zfp160 from A. terreus were done. Next, the cloning and expression of zfp160 protein were carried out. Following, protein expression was induced and purified through nickel NTA column with imidazole gradient elution. Through the Mascot search engine tool, the expressed protein of MALDI-TOF was confirmed by 32 kDa bands of SDS-PAGE. Furthermore, its enzymatic characterization and biochemical categorization were also explored. The optimum conditions for enzyme were determined to be pH 8, temperature 35°C, km 50 μm with folic acid as substrate, and Vmax of 24.16 (IU/mL). Further, in silico analysis tried to explore the interactions and binding affinity of various substrates to the modeled pterin deaminase from A. terreus. Our results revealed the binding mode of different substrate molecules with pterin deaminase using the approximate scoring functions that possibly correlate with actual experimental binding affinities. Following this, molecular dynamic simulations provided the in-depth knowledge on deciphering functional mechanisms of pterin deaminase over other drugs.

Computational Methods in Immunology and Vaccinology: Design and Development of Antibodies and Immunogens

The design of new biomolecules able to harness immune mechanisms for the treatment of diseases is a prime challenge for computational and simulative approaches. For instance, in recent years, antibodies have emerged as an important class of therapeutics against a spectrum of pathologies. In cancer, immune-inspired approaches are witnessing a surge thanks to a better understanding of tumor-associated antigens and the mechanisms of their engagement or evasion from the human immune system. Here, we provide a summary of the main state-of-the-art computational approaches that are used to design antibodies and antigens, and in parallel, we review key methodologies for epitope identification for both B- and T-cell mediated responses. A special focus is devoted to the description of structure- and physics-based models, privileged over purely sequence-based approaches. We discuss the implications of novel methods in engineering biomolecules with tailored immunological properties for possible therapeutic uses. Finally, we highlight the extraordinary challenges and opportunities presented by the possible integration of structure- and physics-based methods with emerging Artificial Intelligence technologies for the prediction and design of novel antigens, epitopes, and antibodies.

iTCep: a deep learning framework for identification of T cell epitopes by harnessing fusion features

Neoantigens recognized by cytotoxic T cells are effective targets for tumor-specific immune responses for personalized cancer immunotherapy. Quite a few neoantigen identification pipelines and computational strategies have been developed to improve the accuracy of the peptide selection process. However, these methods mainly consider the neoantigen end and ignore the interaction between peptide-TCR and the preference of each residue in TCRs, resulting in the filtered peptides often fail to truly elicit an immune response. Here, we propose a novel encoding approach for peptide-TCR representation. Subsequently, a deep learning framework, namely iTCep, was developed to predict the interactions between peptides and TCRs using fusion features derived from a feature-level fusion strategy. The iTCep achieved high predictive performance with AUC up to 0.96 on the testing dataset and above 0.86 on independent datasets, presenting better prediction performance compared with other predictors. Our results provided strong evidence that model iTCep can be a reliable and robust method for predicting TCR binding specificities of given antigen peptides. One can access the iTCep through a user-friendly web server at http://biostatistics.online/iTCep/, which supports prediction modes of peptide-TCR pairs and peptide-only. A stand-alone software program for T cell epitope prediction is also available for convenient installing at https://github.com/kbvstmd/iTCep/.

AttnTAP: A Dual-input Framework Incorporating the Attention Mechanism for Accurately Predicting TCR-peptide Binding

T-cell receptors (TCRs) are formed by random recombination of genomic precursor elements, some of which mediate the recognition of cancer-associated antigens. Due to the complicated process of T-cell immune response and limited biological empirical evidence, the practical strategy for identifying TCRs and their recognized peptides is the computational prediction from population and/or individual TCR repertoires. In recent years, several machine/deep learning-based approaches have been proposed for TCR-peptide binding prediction. However, the predictive performances of these methods can be further improved by overcoming several significant flaws in neural network design. The interrelationship between amino acids in TCRs is critical for TCR antigen recognition, which was not properly considered by the existing methods. They also did not pay more attention to the amino acids that play a significant role in antigen-binding specificity. Moreover, complex networks tended to increase the risk of overfitting and computational costs. In this study, we developed a dual-input deep learning framework, named AttnTAP, to improve the TCR-peptide binding prediction. It used the bi-directional long short-term memory model for robust feature extraction of TCR sequences, which considered the interrelationships between amino acids and their precursors and postcursors. We also introduced the attention mechanism to give amino acids different weights and pay more attention to the contributing ones. In addition, we used the multilayer perceptron model instead of complex networks to extract peptide features to reduce overfitting and computational costs. AttnTAP achieved high areas under the curves (AUCs) in TCR-peptide binding prediction on both balanced and unbalanced datasets (higher than 0.838 on McPAS-TCR and 0.908 on VDJdb). Furthermore, it had the highest average AUCs in TPP-I and TPP-II tasks compared with the other five popular models (TPP-I: 0.84 on McPAS-TCR and 0.894 on VDJdb; TPP-II: 0.837 on McPAS-TCR and 0.893 on VDJdb). In conclusion, AttnTAP is a reasonable and practical framework for predicting TCR-peptide binding, which can accelerate identifying neoantigens and activated T cells for immunotherapy to meet urgent clinical needs.