Prediction of protein secondary structure based on an improved channel attention and multiscale convolution module

Prediction of protein secondary structure by the improved TCN-BiLSTM-MHA model with knowledge distillation

Secondary structure prediction is a key step in understanding protein function and biological properties and is highly important in the fields of new drug development, disease treatment, bioengineering, etc. Accurately predicting the secondary structure of proteins helps to reveal how proteins are folded and how they function in cells. The application of deep learning models in protein structure prediction is particularly important because of their ability to process complex sequence information and extract meaningful patterns and features, thus significantly improving the accuracy and efficiency of prediction. In this study, a combined model integrating an improved temporal convolutional network (TCN), bidirectional long short-term memory (BiLSTM), and a multi-head attention (MHA) mechanism is proposed to enhance the accuracy of protein prediction in both eight-state and three-state structures. One-hot encoding features and word vector representations of physicochemical properties are incorporated. A significant emphasis is placed on knowledge distillation techniques utilizing the ProtT5 pretrained model, leading to performance improvements. The improved TCN, achieved through multiscale fusion and bidirectional operations, allows for better extraction of amino acid sequence features than traditional TCN models. The model demonstrated excellent prediction performance on multiple datasets. For the TS115, CB513 and PDB (2018-2020) datasets, the prediction accuracy of the eight-state structure of the six datasets in this paper reached 88.2%, 84.9%, and 95.3%, respectively, and the prediction accuracy of the three-state structure reached 91.3%, 90.3%, and 96.8%, respectively. This study not only improves the accuracy of protein secondary structure prediction but also provides an important tool for understanding protein structure and function, which is particularly applicable to resource-constrained contexts and provides a valuable tool for understanding protein structure and function.

Structural, functional, molecular docking analysis of a hypothetical protein from Talaromyces marneffei and its molecular dynamic simulation: an in-silico approach

Telaromyces marneffei (formerly Penicillium marneffei) is an endemic pathogenic fungus in Southern China and Southeast Asia. It can cause disease in patients with travel-related exposure to this organism and high morbidity and mortality in acquired immune deficiency syndrome (AIDS). In this study, we analyzed the structure and function of a hypothetical protein from T. marneffei using several bioinformatics tools and servers to unveil novel pharmacological targets and design a peptide vaccine against specific epitopes. A total of seven functional epitopes were screened on the protein, and 'STGVDMWSV' was the most antigenic, non-allergenic and non-toxic. Molecular docking showed stronger affinity between the CTL epitope 'STGVDMWSV' and the MHC I allele HLA-A*02:01, a higher docking score -234.98 kcal/mol, revealed stable interactions during a 100 ns molecular dynamic simulation. Overall, the results of this study revealed that this hypothetical protein is crucial for comprehending biochemical, physiological pathways and identifying novel therapeutic targets for human health. Communicated by Ramaswamy H. Sarma.

In Silico Vaccine Design and Expression of the Multi-Component Protein Candidate against the Toxoplasma gondii Parasite from MIC13, GRA1, and SAG1 Antigens

Background

We aimed to design a B and T cell recombinant protein vaccine of Toxoplasma gondii with in silico approach. MIC13 plays an important role in spreading the parasite in the host body. GRA1 causes the persistence of the parasite in the parasitophorous vacuole. SAG1 plays a role in host-cell adhesion and cell invasion.

Methods

Amino acid positions 73-272 from MIC13, 71-190 from GRA1, and 101-300 from SAG1 were selected and joined with linker A(EAAAK)A. The structures, antigenicity, allergenicity, physicochemical properties, as well as codon optimization and mRNA structure of this recombinant protein called MGS1, were predicted using bioinformatics servers. The designed structure was synthesized and then cloned in pET28a (+) plasmid and transformed into Escherichia coli BL21.

Results

The number of amino acids in this antigen was 555, and its antigenicity was estimated to be 0.6340. SDS-PAGE and Western blotting confirmed gene expression and successful production of the protein with a molecular weight of 59.56kDa. This protein will be used in our future studies as an anti-Toxoplasma vaccine candidate in animal models.

Conclusion

In silico methods are efficient for understanding information about proteins, selecting immunogenic epitopes, and finally producing recombinant proteins, as well as reducing the time and cost of vaccine design.

A Reliable Approach for Fabricating Tissue-Mimicking Phantoms with Designated Dielectric Properties from 16 MHz to 3 GHz

Tissue-mimicking dielectric phantoms are widely used to mimic the relative permittivity and conductivity of human tissues in various medical applications. The artificial material combinations determine the characterization of dialectic phantoms. However, a method that reliably determined the composition of artificial materials with designed values of dielectric properties and frequency is still lacking. In this work, we propose a method that easily determine the compositions of phantom to mimic the human tissues from 16 MHz to 3 GHz.

Few-shot segmentation with duplex network and attention augmented module

Establishing the relationship between a limited number of samples and segmented objects in diverse scenarios is the primary challenge in few-shot segmentation. However, many previous works overlooked the crucial support-query set interaction and the deeper information that needs to be explored. This oversight can lead to model failure when confronted with complex scenarios, such as ambiguous boundaries. To solve this problem, a duplex network that utilizes the suppression and focus concept is proposed to effectively suppress the background and focus on the foreground. Our network includes dynamic convolution to enhance the support-query interaction and a prototype match structure to fully extract information from support and query. The proposed model is called dynamic prototype mixture convolutional networks (DPMC). To minimize the impact of redundant information, we have incorporated a hybrid attentional module called double-layer attention augmented convolutional module (DAAConv) into DPMC. This module enables the network to concentrate more on foreground information. Our experiments on PASCAL-5i and COCO-20i datasets suggested that DPMC and DAAConv outperform traditional prototype-based methods by up to 5-8% on average.