Search

Membrane proteins play a crucial role in various cellular processes and are essential components of cell membranes. Computational methods have emerged as a powerful tool for studying membrane proteins due to their complex structures and properties that make them difficult to analyze experimentally. Traditional features for protein sequence analysis based on amino acid types, composition, and pair composition have limitations in capturing higher-order sequence patterns. Recently, multiple sequence alignment (MSA) and pre-trained language models (PLMs) have been used to generate features from protein sequences. However, the significant computational resources required for MSA-based features generation can be a major bottleneck for many applications. Several methods and tools have been developed to accelerate the generation of MSAs and reduce their computational cost, including heuristics and approximate algorithms. Additionally, the use of PLMs such as BERT has shown great potential in generating informative embeddings for protein sequence analysis. In this review, we provide an overview of traditional and more recent methods for generating features from protein sequences, with a particular focus on MSAs and PLMs. We highlight the advantages and limitations of these approaches and discuss the methods and tools developed to address the computational challenges associated with features generation. Overall, the advancements in computational methods and tools provide a promising avenue for gaining deeper insights into the function and properties of membrane proteins, which can have significant implications in drug discovery and personalized medicine., (© 2023 Wiley-VCH GmbH.)

Background: Epithelial ovarian cancer is a highly lethal gynecological malignancy. Accurate and cost-effective predictive tools to estimate the prognosis of patients with epithelial ovarian cancer before treatment are currently lacking., Objective: The purpose of this study was to evaluate the prognostic significance of pretreatment serum levels of carcinoembryonic antigen (CEA) and carbohydrate antigen-125 (CA-125) in primary epithelial ovarian cancer., Methods: Between 2008 and 2016, 326 patients with a diagnosis of primary epithelial ovarian cancer were retrospectively reviewed. We attempted to identify an optimal cut-off value of CEA to predict survival using ROC curve analysis. Cox regression univariate and multivariate analyses were used to evaluate prognostic factors., Results: The optimal cut-off value of CEA was 2.6 ng/mL. In univariate and multivariate analyses, FIGO stage and pretreatment CA-125 and CEA levels significantly predicted progression-free and overall survival. The 5-year progression-free survival rate for patients with both a CEA level < 2.6 ng/mL and CA-125 level < 35 U/mL was 84%, compared to only 33% for the patients with higher levels of both markers (p< 0.001). The 5-year cancer specific survival rate was 94% in those with a CEA level < 2.6 ng/mL and CA-125 level < 35 U/mL, and only 39% for those with higher levels of both markers (p< 0.001)., Conclusions: In addition to traditional prognostic factors, a pretreatment serum CEA level ⩾ 2.6 ng/mL and CA-125 level ⩾ 35 U/mL were also independent prognostic factors for epithelial ovarian cancer. Patients with an elevated CEA and/or CA-125 level before treatment should be considered to be at high-risk of recurrence and death.

Membrane proteins, the most important drug targets, account for around 30% of total proteins encoded by the genome of living organisms. An important role of these proteins is to bind adenosine triphosphate (ATP), facilitating crucial biological processes such as metabolism and cell signaling. There are several reports elucidating ATP-binding sites within proteins. However, such studies on membrane proteins are limited. Our prediction tool, DeepATP, combines evolutionary information in the form of Position Specific Scoring Matrix and two-dimensional Convolutional Neural Network to predict ATP-binding sites in membrane proteins with an MCC of 0.89 and an AUC of 99%. Compared to recently published ATP-binding site predictors and classifiers that use traditional machine learning algorithms, our approach performs significantly better. We suggest this method as a reliable tool for biologists for ATP-binding site prediction in membrane proteins., (Copyright © 2019 Elsevier Inc. All rights reserved.)

Objective: To investigate the expression of secreted frizzled-related protein 1 (SFRP1), β-catenin and E-cadherin in colorectal carcinoma and its clinicopathological significance., Methods: The expression of SFRP1, β-catenin and E-cadherin mRNA and protein in tumor and pericancerous tissue samples from 60 cases of colorectal cancer was assayed by reverse-transcription PCR and immunohistochemistry, respectively. The correlation of their expression with clinicopathological factors of colorectal cancer was analyzed., Results: In 52/60 cases the relative mRNA expression of SFRP1 in cancer tissue and pericancerous tissue was 0.4837±0.1532 and 0.7170 ±0.1830; for β-catenin was 0.9293± 0.3705 and 0.6469±0.3166; and for E-cadherin was 0.5556±0.2535 and 0.9422±0.2372 (P<0.01), respectively. SFRP1 mRNA expression was associated with lymphatic metastasis (P<0.05). The positive rate of SFRP1 in colorectal cancer was 31.67% (19/60), and was significantly lower than that in pericancerous colorectal mucosa (75.00%, 45/60). No relationship between SFRP1 protein expression and clinical pathology was found. Abnormal expression rates of β-catenin and E-cadherin in colorectal cancer were 75.00% (45/60) and 58.33% (35/60), respectively, which were significantly higher than that in pericancerous colorectal mucosa (1.67% and 6.67%), respectively. Abnormal β-catenin and E-cadherin expression was associated with tumor differentiation, lymphatic metastasis and Duke's staging. SFRP1 protein expression was negatively correlated with β-catenin and E-cadherin expression (r=-0.517, -0.442, Ps<0.01)., Conclusion: Down-regulation of SFRP1 in colorectal cancer may cause abnormal Wnt signaling and induce abnormal β-catenin and E-cadherin expression, indicating that SFRP1 might be involved in the development and progression of colorectal cancer, and could be a novel therapeutic target for colorectal cancer.

Membrane proteins perform diverse functions in living organisms such as transporters, receptors and channels. The functions of membrane proteins have been investigated with several computational approaches, such as developing databases, analyzing the structure-function relationship and establishing algorithms to discriminate different type of membrane proteins. However, compilation of bioinformatics resources for the functions of membrane proteins is not well documented compared with their structural aspects. In this comprehensive review, we elaborately focus on three aspects of membrane protein functions: (i) databases for different types of membrane proteins based on their functions including transporters, receptors and ion channels, annotated functional data for genomes, as well as functionally important amino acid residues in membrane proteins obtained from experimental data, (ii) analysis of membrane protein functions based on their structures, motifs, amino acid properties and other features and (iii) algorithms for discriminating different types of membrane proteins and annotating them in genomic sequences. In addition, we provide a list of online resources for the databases and web servers for functional annotation of membrane proteins.

Discriminating outer membrane proteins (OMPs) from other folding types of globular and membrane proteins is an important task both for identifying OMPs from genomic sequences and for the successful prediction of their secondary and tertiary structures. We have developed a method based on radial basis function networks and position specific scoring matrix (PSSM) profiles generated by PSI-BLAST and non-redundant protein database. Our approach with PSSM profiles has correctly predicted the OMPs with a cross-validated accuracy of 96.4% in a set of 1251 proteins, which contain 206 OMPs, 667 globular proteins and 378 alpha-helical inner membrane proteins. Furthermore, we applied our method on a dataset containing 114 OMPs, 187 TMH proteins and 195 globular proteins obtained with less than 20% sequence identity and obtained the cross-validated accuracy of 95%. This accuracy of discriminating OMPs is higher than other methods in the literature and our method could be used as an effective tool for dissecting OMPs from genomic sequences. We have developed a prediction server, TMBETADISC-RBF, which is available at http://rbf.bioinfo.tw/~sachen/OMP.html.

• Integration of pre-trained protein language models with multi-window CNNs for secondary active transporter identification. • Pre-trained language model embeddings capture informative sequence patterns compared to one-hot encodings or evolutionary profiles. • Pre-trained language model embeddings with 128 filters and multi-window CNN achieved 86% sensitivity, 99% specificity, and 98% accuracy. Secondary active transporters play pivotal roles in regulating ion and molecule transport across cell membranes, with implications in diseases like cancer. However, studying transporters via biochemical experiments poses challenges. We propose an effective computational approach to identify secondary active transporters from membrane protein sequences using pre-trained language models and deep learning neural networks. Our dataset comprised 290 secondary active transporters and 5,420 other membrane proteins from UniProt. Three types of features were extracted - one-hot encodings, position-specific scoring matrix profiles, and contextual embeddings from the ProtTrans language model. A multi-window convolutional neural network architecture scanned the ProtTrans embeddings using varying window sizes to capture multi-scale sequence patterns. The proposed model combining ProtTrans embeddings and multi-window convolutional neural networks achieved 86% sensitivity, 99% specificity and 98% overall accuracy in identifying secondary active transporters, outperforming conventional machine learning approaches. This work demonstrates the promise of integrating pre-trained language models like ProtTrans with multi-scale deep neural networks to effectively interpret transporter sequences for functional analysis. Our approach enables more accurate computational identification of secondary active transporters, advancing membrane protein research. [ABSTRACT FROM AUTHOR]

In cellular transportation mechanisms, the movement of ions across the cell membrane and its proper control are important for cells, especially for life processes. Ion transporters/pumps and ion channel proteins work as border guards controlling the incessant traffic of ions across cell membranes. We revisited the study of classification of transporters and ion channels from membrane proteins with a more efficient deep learning approach. Specifically, we applied multi‐window scanning filters of convolutional neural networks on almost full‐length position‐specific scoring matrices for extracting useful information. In this way, we were able to retain important evolutionary information of the proteins. Our experiment results show that a convolutional neural network with a minimum number of convolutional layers can be enough to extract the conserved information of proteins which leads to higher performance. Our best prediction models were obtained after examining different data imbalanced handling techniques, and different protein encoding methods. We also showed that our models were superior to traditional deep learning approaches on the same datasets as well as other machine learning classification algorithms. [ABSTRACT FROM AUTHOR]

The movement of ions across the cell membrane is an essential for many biological processes. This study is focused on ion channels and ion transporters (pumps) as types of border guards control the incessant traffic of ions across cell membranes. Ion channels and ion transporters function to regulate membrane potential and electrical signaling and play important roles in cell proliferation, migration, apoptosis, and differentiation. In their behaviors, it is found that ion channels differ significantly from ion transporters. Therefore, a method for automatically classifying ion transporters and ion channels from membrane proteins is proposed by training deep neural networks and using the position‐specific scoring matrix profile as an input. The key of novelty is the three‐stage approach, in which five techniques for data normalization are used; next three imbalanced data techniques are applied to the minority classes and then, six classifiers are compared with the proposed method. © 2019 Wiley Periodicals, Inc. This article presents a deep learning approach using convolutional neural networks and position‐specific scoring matrix profiles of protein sequences to classify ion transporters and ion channels from membrane proteins. The proposed technique describes a new predictor capable of increasing the performance of classification using an efficient combination of feature normalization techniques and imbalanced data set techniques. The results show that the proposed method can capture the hidden patterns information more accurate in the feature sets. [ABSTRACT FROM AUTHOR]

Graphical abstract Highlights • An advanced technique for discriminating membrane transport proteins in different classes and families. • The performance is improved with post translational modification information and position specific scoring matrices. • Our method performs better than other methods and published works. • A powerful model to help biologists understanding better the function of transport proteins. • A basis for further research could use PTM information to improve bioinformatics problems. Abstract Transporters involved in the cellular entry and exit of ions or molecules throughout the membrane proteins and thereby play an essential role in recognizing the immune system and energy transducers. According to their relevance in proteomics, numerous studies have been conducted to analyze the transporters; especially the discrimination of their classes and subfamilies. We realized that post translational modification information had a critical role in the process of transport proteins. Therefore, in this study, we aim to incorporate post translational information with radial basis function networks to improve the predictive performance of transport proteins in major classes (channels/pores, electrochemical transporters, and active transporters) and six different families (α-type channels, β-barrel porins, pore-forming toxins, porters, P P bond hydrolysis-driven transporters, and oxidoreduction-driven transporters). The experiment results by using PSSM profiles combined with PTM information could classify the transporters into three classes and six families with five-fold cross-validation accuracy of 87.6% and 92.5%, respectively. For the independent dataset of 444 proteins, the performance with post translational modification attained the accuracy of 82.13% and 89.34% for classifying three classes and six families, respectively. Compared with the other methods and previous works, our result shows that the predictive performance is better with the accuracy improvement by 12%. We suggest that our study could become a robust model for biologists to discriminate transport proteins with high performance and understand better the function of transport proteins. Further, the contributions of this study could be fundamental for further research that can use PTM information to enhance numerous computational biology problems. [ABSTRACT FROM AUTHOR]

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. [Display omitted] • Novel Integration: Integrating ProtTrans and ESM1b boosts ion channel and transporter protein identification. • Diverse Convolution: Filters across 4-64 residues capture local and global motifs for nuanced structure recognition. • State-of-the-Art: Achieves 95.20% accuracy for ion channels and 95.41% for transporters, setting new standards. • Explainable Framework: Multi-window CNN and pre-trained features offer insights into discriminative protein features. [ABSTRACT FROM AUTHOR]

[Display omitted] • Active transport mechanisms regulate ions or small molecules across a cell membrane. • Primary and secondary active transport utilize energy to move the substances. • Proposed Support Vector Machine and Bidirectional Encoder Representations from Transformers embeddings to represent proteins. • Capture multiple meanings for the same amino acid to reveal the importance of specific residues. • Developed a method to classify proteins to a type of active transporters using pre-trained contextual embeddings. Primary and secondary active transport are two types of active transport that involve using energy to move the substances. Active transport mechanisms do use proteins to assist in transport and play essential roles to regulate the traffic of ions or small molecules across a cell membrane against the concentration gradient. In this study, the two main types of proteins involved in such transport are classified from transmembrane transport proteins. We propose a Support Vector Machine (SVM) with contextualized word embeddings from Bidirectional Encoder Representations from Transformers (BERT) to represent protein sequences. BERT is a powerful model in transfer learning, a deep learning language representation model developed by Google and one of the highest performing pre-trained model for Natural Language Processing (NLP) tasks. The idea of transfer learning with pre-trained model from BERT is applied to extract fixed feature vectors from the hidden layers and learn contextual relations between amino acids in the protein sequence. Therefore, the contextualized word representations of proteins are introduced to effectively model complex structures of amino acids in the sequence and the variations of these amino acids in the context. By generating context information, we capture multiple meanings for the same amino acid to reveal the importance of specific residues in the protein sequence. The performance of the proposed method is evaluated using five-fold cross-validation and independent test. The proposed method achieves an accuracy of 85.44 %, 88.74 % and 92.84 % for Class-1, Class-2, and Class-3, respectively. Experimental results show that this approach can outperform from other feature extraction methods using context information, effectively classify two types of active transport and improve the overall performance. [ABSTRACT FROM AUTHOR]