Accurate Protein Identification Research Articles

Component-resolved diagnosis: enhancing precision diagnosis and clinical management of shellfish allergies

Shellfish, being one of the eight major food allergens, affects approximately 3% of the global population. The occurrence of shellfish allergy is not only related to the individual's immune system sensitivity but is also influenced by geographical environment, food availability, and dietary habits. Although crustaceans (such as shrimp, crab, and lobster) and mollusks (such as oysters, mussels, and squid) are collectively referred to as shellfish, they exhibit significant differences in biological evolution and the spectrum of allergenic molecules they contain, leading to various allergic reactions. Accurate identification of allergenic proteins is crucial for the diagnosis and management of shellfish allergies, with key allergenic protein families including tropomyosin, arginine kinase, and hemocyanin. Furthermore, due to the diversity of shellfish allergens and their cross-reactivity with dust mite and insect allergens, diagnosing and managing shellfish allergies is complex, especially concerning tropomyosin and arginine kinase protein families. Currently, there are no specific immunotherapy treatments for shellfish allergies, and clinical management primarily relies on avoiding allergens and using anti-allergy medications. This article thoroughly interprets the " Molecular Allergology User's Guide 2.0 (MAUG 2.0)" published by the European Academy of Allergy and Clinical Immunology (EAACI) and the latest research on shellfish allergies both domestically and internationally. It highlights the significant role of allergen component diagnostics in optimizing the diagnostic and treatment processes for shellfish allergies, effectively assisting clinicians in accurately identifying common allergens and cross-reactions, thereby providing patients with more personalized diagnosis and treatment plans.

Accurate Identification of Periplasmic Urea-binding Proteins by Structure- and Genome Context-assisted Functional Analysis

ABC transporters are ancient and ubiquitous nutrient transport systems in bacteria and play a central role in defining lifestyles. Periplasmic solute-binding proteins (SBPs) are components that deliver ligands to their translocation machinery. SBPs have diversified to bind a wide range of ligands with high specificity and affinity. However, accurate assignment of cognate ligands remains a challenging problem in SBPs. Urea metabolism plays an important role in the nitrogen cycle; anthropogenic sources account for more than half of global nitrogen fertilizer. We report identification of urea-binding proteins within a large SBP sequence family that encodes diverse functions. By combining genetic linkage between SBPs, ABC transporter components, enzymes or transcription factors, we accurately identified cognate ligands, as we verified experimentally by biophysical characterization of ligand binding and crystallographic determination of the urea complex of a thermostable urea-binding homolog. Using three-dimensional structure information, these functional assignments were extrapolated to other members in the sequence family lacking genetic linkage information, which revealed that only a fraction bind urea. Using the same combined approaches, we also inferred that other family members bind various short-chain amides, aliphatic amino acids (leucine, isoleucine, valine), γ-aminobutyrate, and as yet unknown ligands. Comparative structural analysis revealed structural adaptations that encode diversification in these SBPs. Systematic assignment of ligands to SBP sequence families is key to understanding bacterial lifestyles, and also provides a rich source of biosensors for clinical and environmental analysis, such as the thermostable urea-binding protein identified here.

PEL-PVP: Application of plant vacuolar protein discriminator based on PEFT ESM-2 and bilayer LSTM in an unbalanced dataset

Plant vacuoles, play a crucial role in maintaining cellular stability, adapting to environmental changes, and responding to external pressures. The accurate identification of vacuolar proteins (PVPs) is crucial for understanding the biosynthetic mechanisms of intracellular vacuoles and the adaptive mechanisms of plants. In order to more accurately identify vacuole proteins, this study developed a new predictive model PEL-PVP based on ESM-2. Through this study, the feasibility and effectiveness of using advanced pre-training models and fine-tuning techniques for bioinformatics tasks were demonstrated, providing new methods and ideas for plant vacuolar protein research. In addition, previous datasets for vacuolar proteins were balanced, but imbalance is more closely related to the actual situation. Therefore, this study constructed an imbalanced dataset UB-PVP from the UniProt database，helping the model better adapt to the complexity and uncertainty in real environments, thereby improving the model's generalization ability and practicality. The experimental results show that compared with existing recognition techniques, achieving significant improvements in multiple indicators, with 6.08 %, 13.51 %, 11.9 %, and 5 % improvements in ACC, SP, MCC, and AUC, respectively. The accuracy reaches 94.59 %, significantly higher than the previous best model GraphIdn. This provides an efficient and precise tool for the study of plant vacuole proteins.

A novel clinical metaproteomics workflow enables bioinformatic analysis of host-microbe dynamics in disease.

Clinical metaproteomics has immense potential to offer functional insights into the microbiome and its contributions to human disease. However, there are numerous challenges in the metaproteomic analysis of clinical samples, including handling of very large protein sequence databases for sensitive and accurate peptide and protein identification from mass spectrometry data, as well as taxonomic and functional annotation of quantified peptides and proteins to enable interpretation of results. To address these challenges, we have developed a novel clinical metaproteomics workflow that provides customized bioinformatic identification, verification, quantification, and taxonomic and functional annotation. This bioinformatic workflow is implemented in the Galaxy ecosystem and has been used to characterize diverse clinical sample types, such as nasopharyngeal swabs and bronchoalveolar lavage fluid. Here, we demonstrate its effectiveness and availability for use by the research community via analysis of residual fluid from cervical swabs.

Model fusion for predicting unconventional proteins secreted by exosomes using deep learning.

Unconventional secretory proteins (USPs) are vital for cell-to-cell communication and are necessary for proper physiological processes. Unlike classical proteins that follow the conventional secretory pathway via the Golgi apparatus, these proteins are released using unconventional pathways. The primary modes of secretion for USPs are exosomes and ectosomes, which originate from the endoplasmic reticulum. Accurate and rapid identification of exosome-mediated secretory proteins is crucial for gaining valuable insights into the regulation of non-classical protein secretion and intercellular communication, as well as for the advancement of novel therapeutic approaches. Although computational methods based on amino acid sequence prediction exist for predicting unconventional proteins secreted by exosomes (UPSEs), they suffer from significant limitations in terms of algorithmic accuracy. In this study, we propose a novel approach to predict UPSEs by combining multiple deep learning models that incorporate both protein sequences and evolutionary information. Our approach utilizes a convolutional neural network (CNN) to extract protein sequence information, while various densely connected neural networks (DNNs) are employed to capture evolutionary conservation patterns.By combining six distinct deep learning models, we have created a superior framework that surpasses previous approaches, achieving an ACC score of 77.46% and an MCC score of 0.5406 on an independent test dataset.

An Efficient Deep Learning Approach for DNA-Binding Proteins Classification from Primary Sequences

As the number of identified proteins has expanded, the accurate identification of proteins has become a significant challenge in the field of biology. Various computational methods, such as Support Vector Machine (SVM), K-nearest neighbors (KNN), and convolutional neural network (CNN), have been proposed to recognize deoxyribonucleic acid (DNA)-binding proteins solely based on amino acid sequences. However, these methods do not consider the contextual information within amino acid sequences, limiting their ability to adequately capture sequence features. In this study, we propose a novel approach to identify DNA-binding proteins by integrating a CNN with bidirectional long-short-term memory (LSTM) and gated recurrent unit (GRU) as (CNN-BiLG). The CNN-BiLG model can explore the potential contextual relationships of amino acid sequences and obtain more features than traditional models. Our experimental results demonstrate a validation set prediction accuracy of 94% for the proposed CNN-BiLG, surpassing the accuracy of machine learning models and deep learning models. Furthermore, our model is both effective and efficient, exhibiting commendable classification accuracy based on comparative analysis.

DeepPLM_mCNN: An approach for enhancing ion channel and ion transporter recognition by multi-window CNN based on features from pre-trained language models

Accurate classification of membrane proteins like ion channels and transporters is critical for elucidating cellular processes and drug development. We present DeepPLM_mCNN, a novel framework combining Pretrained Language Models (PLMs) and multi-window convolutional neural networks (mCNNs) for effective classification of membrane proteins into ion channels and ion transporters. Our approach extracts informative features from protein sequences by utilizing various PLMs, including TAPE, ProtT5_XL_U50, ESM-1b, ESM-2_480, and ESM-2_1280. These PLM-derived features are then input into a mCNN architecture to learn conserved motifs important for classification. When evaluated on ion transporters, our best performing model utilizing ProtT5 achieved 90% sensitivity, 95.8% specificity, and 95.4% overall accuracy. For ion channels, we obtained 88.3% sensitivity, 95.7% specificity, and 95.2% overall accuracy using ESM-1b features. Our proposed DeepPLM_mCNN framework demonstrates significant improvements over previous methods on unseen test data. This study illustrates the potential of combining PLMs and deep learning for accurate computational identification of membrane proteins from sequence data alone. Our findings have important implications for membrane protein research and drug development targeting ion channels and transporters. The data and source codes in this study are publicly available at the following link: https://github.com/s1129108/DeepPLM_mCNN.

Joint micrograph denoising and protein localization in cryo-electron microscopy

Abstract Cryo-electron microscopy (cryo-EM) is an imaging technique that allows the visualization of proteins and macromolecular complexes at near-atomic resolution. The low electron doses used to prevent radiation damage to the biological samples result in images where the power of noise is 100 times stronger than that of the signal. Accurate identification of proteins from these low signal-to-noise ratio (SNR) images is a critical task, as the detected positions serve as inputs for the downstream 3D structure determination process. Current methods either fail to identify all true positives or result in many false positives, especially when analyzing images from smaller-sized proteins that exhibit extremely low contrast, or require manual labeling that can take days to complete. Acknowledging the fact that accurate protein identification is dependent upon the visual interpretability of micrographs, we propose a framework that can perform denoising and detection in a joint manner and enable particle localization under extremely low SNR conditions using self-supervised denoising and particle identification from sparsely annotated data. We validate our approach on three challenging single-particle cryo-EM datasets and projection images from one cryo-electron tomography dataset with extremely low SNR, showing that it outperforms existing state-of-the-art methods used for cryo-EM image analysis by a significant margin. We also evaluate the performance of our algorithm under decreasing SNR conditions and show that our method is more robust to noise than competing methods.

Improving Antifreeze Proteins Prediction with Protein Language Models and Hybrid Feature Extraction Networks.

Accurate identification of antifreeze proteins (AFPs) is crucial in developing biomimetic synthetic anti-icing materials and low-temperature organ preservation materials. Although numerous machine learning-based methods have been proposed for AFPs prediction, the complex and diverse nature of AFPs limits the prediction performance of existing methods. In this study, we propose AFP-Deep, a new deep learning method to predict antifreeze proteins by integrating embedding from protein sequences with pre-trained protein language models and evolutionary contexts with hybrid feature extraction networks. The experimental results demonstrated that the main advantage of AFP-Deep is its utilization of pre-trained protein language models, which can extract discriminative global contextual features from protein sequences. Additionally, the hybrid deep neural networks designed for protein language models and evolutionary context feature extraction enhance the correlation between embeddings and antifreeze pattern. The performance evaluation results show that AFP-Deep achieves superior performance compared to state-of-the-art models on benchmark datasets, achieving an AUPRC of 0.724 and 0.924, respectively.

Machine learning-based antioxidant protein identification model: Progress and evaluation.

Efficient and accurate identification of antioxidant proteins is of great significance. In recent years, many models for identifying antioxidant proteins have been proposed, but the low sensitivity and high dimensionality of the models are common problems. The generalization ability of the model needs to be improved. Researchers have tried different feature extraction algorithms and feature selection algorithms to obtain the most effective feature combination and have chosen more appropriate classification algorithms and tools to improve model performance. In this article, we systematically reviewed the data set of the most frequently used antioxidant proteins and the method selection for each step of model establishment and discussed the characteristics of each method. We have conducted a detailed analysis of recent research and believe that the practical ability and efficiency of model application can be improved by reducing model dimensions. The key to improving the performance of antioxidant protein recognition models in the future may lie in feature selection, so this paper also focuses on the combination of feature extraction and selection steps in the analysis of the model building process.

Machine learning-based model for accurate identification of druggable proteins using light extreme gradient boosting

The identification of druggable proteins (DPs) is significant for the development of new drugs, personalized medicine, understanding of disease mechanisms, drug repurposing, and economic benefits. By identifying new druggable targets, researchers can develop new therapies for a range of diseases, leading to better patient outcomes. Identification of DPs by machine learning strategies is more efficient and cost-effective than conventional methods. In this study, a computational predictor, namely Drug-LXGB, is introduced to enhance the identification of DPs. Features are discovered by composition, transition, and distribution (CTD), composition of K-spaced amino acid pair (CKSAAP), pseudo-position-specific scoring matrix (PsePSSM), and a novel descriptor, called multi-block pseudo amino acid composition (MB-PseAAC). The dimensions of CTD, CKSAAP, PsePSSM, and MB-PseAAC are integrated and utilized the sequential forward selection as feature selection algorithm. The best characteristics are provided by random forest, extreme gradient boosting, and light eXtreme gradient boosting (LXGB). The predictive analysis of these learning methods is measured via 10-fold cross-validation. The LXGB-based model secures the highest results than other existing predictors. Our novel protocol will perform an active role in designing novel drugs and would be fruitful to explore the potential target. This study will help better to capture a more universal view of a potential target. Communicated by Ramaswamy H. Sarma

High Accuracy Protein Identification: Fusion of Solid-State Nanopore Sensing and Machine Learning.

Proteins are arguably one of the most important class of biomarkers for health diagnostic purposes. Label-free solid-state nanopore sensing is a versatile technique for sensing and analyzing biomolecules such as proteins at single-molecule level. While molecular-level information on size, shape, and charge of proteins can be assessed by nanopores, the identification of proteins with comparable sizes remains a challenge. Here, solid-state nanopore sensing is combined with machine learning to address this challenge. The translocations of four similarly sized proteins is assessed using amplifiers with bandwidths (BWs) of 100kHz and 10MHz, the highest bandwidth reported for protein sensing, using nanopores fabricated in <10nm thick silicon nitride membranes. F-values of up to 65.9% and 83.2% (without clustering of the protein signals) are achieved with 100kHz and 10MHz BW measurements, respectively, for identification of the four proteins. The accuracy of protein identification is further enhanced by classifying the signals into different clusters based on signal attributes, with F-value and specificity of up to 88.7% and 96.4%, respectively, for combinations of four proteins. The combined use of high bandwidth instruments, advanced clustering and machine learning methods allows label-free identification of proteins with high accuracy.

Dynamic Changes in Proteome during Yak Oocyte Maturation Analyzed Using iTRAQ Technology

The aim of this study was to investigate protein regulation at different time points during the in vitro maturation of yak oocytes. Yak oocytes at GV, MI, and MII stages were collected during in vitro maturation, and differential proteomics sequencing was performed using iTRAQ technology. GO functional classification indicated that the differential proteins were closely associated with biological processes such as “metabolic processes”, and molecular events such as “binding” molecular-function-related categories were active. KOG analysis showed that energy-metabolism-related activities were vigorous during oocyte development from the GV phase to MI phase, and genetic material preparation activities were more active when oocytes developed from the MI stage to MII stage. KEGG pathway analysis showed that the PPAR metabolic pathway, Hippo signaling pathway, and ECM–receptor interaction and metabolic pathway were enriched from the GV to the MI stages. The PI3K-Akt, TGF-β, and phagosome pathways were enriched from the MI stage to the MII stage. These results indicate that transient dynamic changes occurred in the proteome during the maturation of yak oocytes, and the physiological functions mediated by these were also different. The accurate identification of the differential proteins in the three stages of GV, MI, and MII was helpful in further analyzing the molecular regulatory mechanism of yak oocyte maturation.

Digerati – A multipath parallel hybrid deep learning framework for the identification of mycobacterial PE/PPE proteins

The genome of Mycobacterium tuberculosis contains a relatively high percentage (10%) of genes that are poorly characterised because of their highly repetitive nature and high GC content. Some of these genes encode proteins of the PE/PPE family, which are thought to be involved in host-pathogen interactions, virulence, and disease pathogenicity. Members of this family are genetically divergent and challenging to both identify and classify using conventional computational tools. Thus, advanced in silico methods are needed to identify proteins of this family for subsequent functional annotation efficiently. In this study, we developed the first deep learning-based approach, termed Digerati, for the rapid and accurate identification of PE and PPE family proteins. Digerati was built upon a multipath parallel hybrid deep learning framework, which equips multi-layer convolutional neural networks with bidirectional, long short-term memory, equipped with a self-attention module to effectively learn the higher-order feature representations of PE/PPE proteins. Empirical studies demonstrated that Digerati achieved a significantly better performance (∼18–20%) than alignment-based approaches, including BLASTP, PHMMER, and HHsuite, in both prediction accuracy and speed. Digerati is anticipated to facilitate community-wide efforts to conduct high-throughput identification and analysis of PE/PPE family members. The webserver and source codes of Digerati are publicly available at http://web.unimelb-bioinfortools.cloud.edu.au/Digerati/.

Optimizing the Production of gp145, an HIV-1 Envelope Glycoprotein Vaccine Candidate and Its Encapsulation in Guanosine Microparticles.

We have developed a pipeline to express, purify, and characterize HIV envelope protein (Env) gp145 from Chinese hamster ovary cells, to accelerate the production of a promising vaccine candidate. First in shake flasks, then in bioreactors, we optimized the growth conditions. By adjusting the pH to 6.8, we increased expression levels to 101 mg/L in a 50 L bioreactor, nearly twice the previously reported titer value. A battery of analytical methods was developed in accordance with current good manufacturing practices to ensure a quality biopharmaceutical. Imaged capillary isoelectric focusing verified proper glycosylation of gp145; dynamic light scattering confirmed the trimeric arrangement; and bio-layer interferometry and circular dichroism analysis demonstrated native-like properties (i.e., antibody binding and secondary structure). MALDI-TOF mass spectrometry was used as a multi-attribute platform for accurate mass determination, glycans analysis, and protein identification. Our robust analysis demonstrates that our gp145 product is very similar to a reference standard and emphasizes the importance of accurate characterization of a highly heterogeneous immunogen for the development of an effective vaccine. Finally, we present a novel guanosine microparticle with gp145 encapsulated and displayed on its surface. The unique properties of our gp145 microparticle make it amenable to use in future preclinical and clinical trials.

A Cosine-Similarity-Based Deconvolution Method for Analyzing Data-Independent Acquisition Mass Spectrometry Data

Although data-independent acquisition (DIA) has the ability to identify and quantify all peptides in a sample, highly complex mixed mass spectra present difficulties for accurate peptide and protein identification. Additionally, the correspondence between the precursor and its fragments is broken, making it challenging to perform peptide identification directly using conventional DDA search engines. In this paper, we propose a cosine-similarity-based deconvolution method: CorrDIA. This is achieved by reconstructing the correspondence between precursor and fragment ions based on the consistency of extracted ion chromatograms (XICs). A deisotope peak cluster operation is added and centered on the MS/MS spectrum to improve the accuracy of spectrum interpretation and increase the number of identified peptides. The resulting MS/MS spectra can be identified using any data-dependent acquisition (DDA) sequencing software. The experimental results demonstrate that the number of peptide results increased by 12 percent and 21 percent respectively, and the repetition rate decreased by 12 percent. This reduces mass spectra complexity and difficulties in mass spectra analysis without the need for any mass spectra libraries.

Isolation, Genomic, and Proteomic Characterization of a Novel Neotropical Strain of Bacillus thuringiensis with Mosquitocidal Activities

The combination of genomic and proteomic analyses is a useful tool for the study of novel Bacillus thuringiensis (Bt) strains, as these approaches allow the accurate identification of pesticidal proteins and virulence factors produced. Here, we isolated and evaluated the potential of a novel Neotropical Bt strain (TOD651) for controlling larvae of Aedes aegypti and Culex quinquefasciatus mosquitoes. Aiming for the full comprehension of the TOD651 larvicidal potential, we further evaluated the whole TOD651 genome and conducted the proteomic analysis of the TOD651 spore–crystal mixtures. Our results showed that Bt TOD651 similarly killed both A. aegypti (0.011 µg/mL) and C. quinquefasciatus (0.023 µg/mL) larvae, exhibiting similar potency to the commercial Bt strain. The genome sequence revealed that Bt TOD651 harbors cry11Aa3, cry10Aa4, cry4Aa4, cry4Ba5, cyt1Aa5, cyt1Ca1, cyt2Ba13, mpp60Aa3, and mpp60Ba3. The proteomic analysis revealed no expression of Mpp60Aa3, while all the other pesticidal proteins were expressed (Cry4Ba5 was more abundant than Cyt1Aa5). The expression of the Mppe showed the major proportions between proteases. The virulent factor neutral protease B and spore coat proteins were also expressed. The expression of relevant pesticidal proteins (e.g., Cry, Cyt, Mpp, and other pathogenic factors), whose actions can occur in a synergic relation, indicates that the biocontrol using Bt TOD651 may contribute to delaying the selection of resistant individuals.

Aptamer-Based Targeted Protein Degradation.

The selective removal of misfolded, aggregated, or aberrantly overexpressed protein plays an essential role in maintaining protein-dominated biological processes. In parallel, the precise knockout of abnormal proteins is inseparable from the accurate identification of proteins within complex environments. Guided by these precepts, small molecules, or antibodies, are commonly used as protein recognition tools for developing targeted protein degradation (TPD) technology. Indeed, TPD has shown tremendous prospects in chronic diseases, rare diseases, cancer research, and other fields. Meanwhile, aptamers are short RNA or DNA oligonucleotides that can bind to target proteins with high specificity and strong affinity. Accordingly, aptamers are actively used in designing and constructing TPD technology. In this perspective, we provide a brief introduction to TPD technology in its current progress, and we summarize its application challenges. Recent advances in aptamer-based TPD technology are reviewed, together with corresponding challenges and outlooks.

Visualizing DNA Damage Repair Proteins in Patient-Derived Ovarian Cancer Organoids via Immunofluorescence Assays.

Immunofluorescence is one of the most widely used techniques to visualize target antigens with high sensitivity and specificity, allowing for the accurate identification and localization of proteins, glycans, and small molecules. While this technique is well-established in two-dimensional (2D) cell culture, less is known about its use in three-dimensional (3D) cell models. Ovarian cancer organoids are 3D tumor models that recapitulate tumor cell clonal heterogeneity, the tumor microenvironment, and cell-cell and cell-matrix interactions. Thus, they are superior to cell lines for the evaluation of drug sensitivity and functional biomarkers. Therefore, the ability to utilize immunofluorescence on primary ovarian cancer organoids is extremely beneficial in understanding the biology of this cancer. The current study describes the technique of immunofluorescence to detect DNA damage repair proteins in high-grade serous patient-derived ovarian cancer organoids (PDOs). After exposing the PDOs to ionizing radiation, immunofluorescence is performed on intact organoids to evaluate nuclear proteins as foci. Images are collected using z-stack imaging on confocal microscopy and analyzed using automated foci counting software. The described methods allow for the analysis of temporal and special recruitment of DNA damage repair proteins and colocalization of these proteins with cell-cycle markers.

Single-molecule identification of folded proteins from nanopore ionic current signatures.

Single-molecule protein sequencing would provide unprecedented insights into cellular processes and the diseases that arise from protein misfunction. Recently, nanopores have emerged as a platform for fast label-free analyte detection guided by the ionic current blockades generated from single molecules translocating under an applied electric field. The major bottleneck to nanopore protein sequencing is the need to distinguish twenty proteinogenic amino acids accurately at every single residue. Here, we demonstrate a proof-of-principle proteome characterization system that relies on ionic current signatures produced by complete translocation of natively folded proteins through an array of nanopores. Using the steric exclusion model, we computed the ionic current spectra for all structurally known proteins, initially excluding all membrane proteins, proteins containing partially-disordered domains, and multimeric protein assemblies - about 4000 proteins in total. For each protein, we computationally simulated a fluid driven tumbling through a nanopore by calculating current for 5000 randomly chosen orientations that changes the effective cross-section and thus modulates current. Ionic current signatures of proteins with varying molecular weight clearly differed by the magnitude of blockades confirming the steric exclusion origin of the current. Interestingly, proteins with similar molecular weight also showed a varied range of mean blockade currents due to changing current signatures originating from the protein shape. Using a support vector machine learning algorithm trained on our data set, we were able to theoretically distinguish the weight and shape of the 4000 chosen proteins to near perfect accuracy, in the absence of instrumentation noise. We then theoretically introduced a thermal noise source into our simulated ionic current recordings to demonstrate the minimum requirements of an experimental system that would permit accurate protein identification from a single molecule translocation.