iSUMOK-PseAAC: prediction of lysine sumoylation sites using statistical moments and Chou's PseAAC

An intelligent model for prediction of abiotic stress-responsive microRNAs in plants using statistical moments based features and ensemble approaches

This study proposed an intelligent model for predicting abiotic stress-responsive microRNAs in plants. MicroRNAs (miRNAs) are short RNA molecules regulates the stress in genes. Experimental methods are costly and time-consuming, as compare to in-silico prediction. Addressing this gap, the study seeks to develop an efficient computational model for plant stress response prediction. The two benchmark datasets for MiRNA and Pre-MiRNA dataset have been acquired in this study. Four ensemble approaches such as bagging, boosting, stacking, and blending have been employed. Classifiers such as Random Forest (RF), Extra Trees (ET), Ada Boost (ADB), Light Gradient Boosting Machine (LGBM), and Support Vector Machine (SVM). Stacking and Blending employed all stated classifiers as base learners and Logistic Regression (LR) as Meta Classifier. There have been a total of four types of testing used, including independent set, self-consistency, cross-validation with 5 and 10 folds, and jackknife. This study has utilized evaluation metrics such as accuracy score, specificity, sensitivity, Mathew's correlation coefficient (MCC), and AUC. Our proposed methodology has outperformed existing state of the art study in both datasets based on independent set testing. The SVM-based approach has exhibited accuracy score of 0.659 for the MiRNA dataset, which is better than the previous study. The ET classifier has surpassed the accuracy of Pre-MiRNA dataset as compared to the existing benchmark study, achieving an impressive score of 0.67. The proposed method can be used in future research to predict abiotic stresses in plants.

FNeXter: A Multi-Scale Feature Fusion Network Based on ConvNeXt and Transformer for Retinal OCT Fluid Segmentation

The accurate segmentation and quantification of retinal fluid in Optical Coherence Tomography (OCT) images are crucial for the diagnosis and treatment of ophthalmic diseases such as age-related macular degeneration. However, the accurate segmentation of retinal fluid is challenging due to significant variations in the size, position, and shape of fluid, as well as their complex, curved boundaries. To address these challenges, we propose a novel multi-scale feature fusion attention network (FNeXter), based on ConvNeXt and Transformer, for OCT fluid segmentation. In FNeXter, we introduce a novel global multi-scale hybrid encoder module that integrates ConvNeXt, Transformer, and region-aware spatial attention. This module can capture long-range dependencies and non-local similarities while also focusing on local features. Moreover, this module possesses the spatial region-aware capabilities, enabling it to adaptively focus on the lesions regions. Additionally, we propose a novel self-adaptive multi-scale feature fusion attention module to enhance the skip connections between the encoder and the decoder. The inclusion of this module elevates the model's capacity to learn global features and multi-scale contextual information effectively. Finally, we conduct comprehensive experiments to evaluate the performance of the proposed FNeXter. Experimental results demonstrate that our proposed approach outperforms other state-of-the-art methods in the task of fluid segmentation.

Identification of 6-methyladenosine sites using novel feature encoding methods and ensemble models

N6-methyladenosine (6 mA) is the most common internal modification in eukaryotic mRNA. Mass spectrometry and site-directed mutagenesis, two of the most common conventional approaches, have been shown to be laborious and challenging. In recent years, there has been a rising interest in analyzing RNA sequences to systematically investigate mutated locations. Using novel methods for feature development, the current work aimed to identify 6 mA locations in RNA sequences. Following the generation of these novel features, they were used to train an ensemble of models using methods such as stacking, boosting, and bagging. The trained ensemble models were assessed using an independent test set and k-fold cross validation. When compared to baseline predictors, the suggested model performed better and showed improved ratings across the board for key measures of accuracy.

iSUMO-RsFPN: A predictor for identifying lysine SUMOylation sites based on multi-features and feature pyramid networks

SUMOylation is a protein post-translational modification that plays an essential role in cellular functions. For predicting SUMO sites, numerous researchers have proposed advanced methods based on ordinary machine learning algorithms. These reported methods have shown excellent predictive performance, but there is room for improvement. In this study, we constructed a novel deep neural network Residual Pyramid Network (RsFPN), and developed an ensemble deep learning predictor called iSUMO-RsFPN. Initially, three feature extraction methods were employed to extract features from samples. Following this, weak classifiers were trained based on RsFPN for each feature type. Ultimately, the weak classifiers were integrated to construct the final classifier. Moreover, the predictor underwent systematically testing on an independent test dataset, where the results demonstrated a significant improvement over the existing state-of-the-art predictors. The code of iSUMO-RsFPN is free and available at https://github.com/454170054/iSUMO-RsFPN.

SumoPred-PLM: human SUMOylation and SUMO2/3 sites Prediction using Pre-trained Protein Language Model

SUMOylation is an essential post-translational modification system with the ability to regulate nearly all aspects of cellular physiology. Three major paralogues SUMO1, SUMO2 and SUMO3 form a covalent bond between the small ubiquitin-like modifier with lysine residues at consensus sites in protein substrates. Biochemical studies continue to identify unique biological functions for protein targets conjugated to SUMO1 versus the highly homologous SUMO2 and SUMO3 paralogues. Yet, the field has failed to harness contemporary AI approaches including pre-trained protein language models to fully expand and/or recognize the SUMOylated proteome. Herein, we present a novel, deep learning-based approach called SumoPred-PLM for human SUMOylation prediction with sensitivity, specificity, Matthew's correlation coefficient, and accuracy of 74.64%, 73.36%, 0.48% and 74.00%, respectively, on the CPLM 4.0 independent test dataset. In addition, this novel platform uses contextualized embeddings obtained from a pre-trained protein language model, ProtT5-XL-UniRef50 to identify SUMO2/3-specific conjugation sites. The results demonstrate that SumoPred-PLM is a powerful and unique computational tool to predict SUMOylation sites in proteins and accelerate discovery.

m1A-Ensem: accurate identification of 1-methyladenosine sites through ensemble models

BACKGROUND

1-methyladenosine (m1A) is a variant of methyladenosine that holds a methyl substituent in the 1st position having a prominent role in RNA stability and human metabolites.

OBJECTIVE

Traditional approaches, such as mass spectrometry and site-directed mutagenesis, proved to be time-consuming and complicated.

METHODOLOGY

The present research focused on the identification of m1A sites within RNA sequences using novel feature development mechanisms. The obtained features were used to train the ensemble models, including blending, boosting, and bagging. Independent testing and k-fold cross validation were then performed on the trained ensemble models.

RESULTS

The proposed model outperformed the preexisting predictors and revealed optimized scores based on major accuracy metrics.

CONCLUSION

For research purpose, a user-friendly webserver of the proposed model can be accessed through https://taseersuleman-m1a-ensem1.streamlit.app/ .

BBB-PEP-prediction: improved computational model for identification of blood-brain barrier peptides using blending position relative composition specific features and ensemble modeling

BBPs have the potential to facilitate the delivery of drugs to the brain, opening up new avenues for the development of treatments targeting diseases of the central nervous system (CNS). The obstacle faced in central nervous system disorders stems from the formidable task of traversing the blood-brain barrier (BBB) for pharmaceutical agents. Nearly 98% of small molecule-based drugs and nearly 100% of large molecule-based drugs encounter difficulties in successfully penetrating the BBB. This importance leads to identification of these peptides, can help in healthcare systems. In this study, we proposed an improved intelligent computational model BBB-PEP-Prediction for identification of BBB peptides. Position and statistical moments based features have been computed for acquired benchmark dataset. Four types of ensembles such as bagging, boosting, stacking and blending have been utilized in the methodology section. Bagging employed Random Forest (RF) and Extra Trees (ET), Boosting utilizes XGBoost (XGB) and Light Gradient Boosting Machine (LGBM). Stacking uses ET and XGB as base learners, blending exploited LGBM and RF as base learners, while Logistic Regression (LR) has been applied as Meta learner for stacking and blending. Three classifiers such as LGBM, XGB and ET have been optimized by using Randomized search CV. Four types of testing such as self-consistency, independent set, cross-validation with 5 and 10 folds and jackknife test have been employed. Evaluation metrics such as Accuracy (ACC), Specificity (SPE), Sensitivity (SEN), Mathew's correlation coefficient (MCC) have been utilized. The stacking of classifiers has shown best results in almost each testing. The stacking results for independent set testing exhibits accuracy, specificity, sensitivity and MCC score of 0.824, 0.911, 0.831 and 0.663 respectively. The proposed model BBB-PEP-Prediction shown superlative performance as compared to previous benchmark studies. The proposed system helps in future research and research community for in-silico identification of BBB peptides.

Emerging trends in post-translational modification: Shedding light on Glioblastoma multiforme

Recent multi-omics studies, including proteomics, transcriptomics, genomics, and metabolomics have revealed the critical role of post-translational modifications (PTMs) in the progression and pathogenesis of Glioblastoma multiforme (GBM). Further, PTMs alter the oncogenic signaling events and offer a novel avenue in GBM therapeutics research through PTM enzymes as potential biomarkers for drug targeting. In addition, PTMs are critical regulators of chromatin architecture, gene expression, and tumor microenvironment (TME), that play a crucial function in tumorigenesis. Moreover, the implementation of artificial intelligence and machine learning algorithms enhances GBM therapeutics research through the identification of novel PTM enzymes and residues. Herein, we briefly explain the mechanism of protein modifications in GBM etiology, and in altering the biologics of GBM cells through chromatin remodeling, modulation of the TME, and signaling pathways. In addition, we highlighted the importance of PTM enzymes as therapeutic biomarkers and the role of artificial intelligence and machine learning in protein PTM prediction.

An application of topological data analysis in predicting sumoylation sites

Sumoylation is a reversible post-translational modification that regulates certain significant biochemical functions in proteins. The protein alterations caused by sumoylation are associated with the incidence of some human diseases. Therefore, identifying the sites of sumoylation in proteins may provide a direction for mechanistic research and drug development. Here, we propose a new computational approach for identifying sumoylation sites using an encoding method based on topological data analysis. The features of our model captured the key physical and biological properties of proteins at multiple scales. In a 10-fold cross validation, the outcomes of our model showed 96.45% of sensitivity (Sn), 94.65% of accuracy (Acc), 0.8946 of Matthew's correlation coefficient (MCC), and 0.99 of area under curve (AUC). The proposed predictor with only topological features achieves the best MCC and AUC in comparison to the other released methods. Our results suggest that topological information is an additional parameter that can assist in the prediction of sumoylation sites and provide a novel perspective for further research in protein sumoylation.

PseU-pred: An ensemble model for accurate identification of pseudouridine sites

Pseudouridine (ψ) is reported to occur frequently in all types of RNA. This uridine modification has been shown to be essential for processes such as RNA stability and stress response. Also, it is linked to a few human diseases, such as prostate cancer, anemia, etc. A few laboratory techniques, such as Pseudo-seq and N3-CMC-enriched Pseudouridine sequencing (CeU-Seq) are used for detecting ψ sites. However, these are laborious and drawn-out methods. The convenience of sequencing data has enabled the development of computationally intelligent models for improving ψ site identification methods. The proposed work provides a prediction model for the identification of ψ sites through popular ensemble methods such as stacking, bagging, and boosting. Features were obtained through a novel feature extraction mechanism with the assimilation of statistical moments, which were used to train ensemble models. The cross-validation test and independent set test were used to evaluate the precision of the trained models. The proposed model outperformed the preexisting predictors and revealed 87% accuracy, 0.90 specificity, 0.85 sensitivity, and a 0.75 Matthews correlation coefficient. A web server has been built and is available publicly for the researchers at https://taseersuleman-y-test-pseu-pred-c2wmtj.streamlit.app/.

A Framework for Prediction of Oncogenomic Progression Aiding Personalized Treatment of Gastric Cancer

Mutations in genes can alter their DNA patterns, and by recognizing these mutations, many carcinomas can be diagnosed in the progression stages. The human body contains many hidden and enigmatic features that humankind has not yet fully understood. A total of 7539 neoplasm cases were reported from 1 January 2021 to 31 December 2021. Of these, 3156 were seen in males (41.9%) and 4383 (58.1%) in female patients. Several machine learning and deep learning frameworks are already implemented to detect mutations, but these techniques lack generalized datasets and need to be optimized for better results. Deep learning-based neural networks provide the computational power to calculate the complex structures of gastric carcinoma-driven gene mutations. This study proposes deep learning approaches such as long and short-term memory, gated recurrent units and bi-LSTM to help in identifying the progression of gastric carcinoma in an optimized manner. This study includes 61 carcinogenic driver genes whose mutations can cause gastric cancer. The mutation information was downloaded from intOGen.org and normal gene sequences were downloaded from asia.ensembl.org, as explained in the data collection section. The proposed deep learning models are validated using the self-consistency test (SCT), 10-fold cross-validation test (FCVT), and independent set test (IST); the IST prediction metrics of accuracy, sensitivity, specificity, MCC and AUC of LSTM, Bi-LSTM, and GRU are 97.18%, 98.35%, 96.01%, 0.94, 0.98; 99.46%, 98.93%, 100%, 0.989, 1.00; 99.46%, 98.93%, 100%, 0.989 and 1.00, respectively.

Ensemble Learning for Hormone Binding Protein Prediction: A Promising Approach for Early Diagnosis of Thyroid Hormone Disorders in Serum

Hormone-binding proteins (HBPs) are specific carrier proteins that bind to a given hormone. A soluble carrier hormone binding protein (HBP), which can interact non-covalently and specifically with growth hormone, modulates or inhibits hormone signaling. HBP is essential for the growth of life, despite still being poorly understood. Several diseases, according to some data, are caused by HBPs that express themselves abnormally. Accurate identification of these molecules is the first step in investigating the roles of HBPs and understanding their biological mechanisms. For a better understanding of cell development and cellular mechanisms, accurate HBP determination from a given protein sequence is essential. Using traditional biochemical experiments, it is difficult to correctly separate HBPs from an increasing number of proteins because of the high experimental costs and lengthy experiment periods. The abundance of protein sequence data that has been gathered in the post-genomic era necessitates a computational method that is automated and enables quick and accurate identification of putative HBPs within a large number of candidate proteins. A brand-new machine-learning-based predictor is suggested as the HBP identification method. To produce the desirable feature set for the method proposed, statistical moment-based features and amino acids were combined, and the random forest was used to train the feature set. During 5-fold cross validation experiments, the suggested method achieved 94.37% accuracy and 0.9438 F1-scores, respectively, demonstrating the importance of the Hahn moment-based features.

iDHU-Ensem: Identification of dihydrouridine sites through ensemble learning models

Background

Dihydrouridine (D) is one of the most significant uridine modifications that have a prominent occurrence in eukaryotes. The folding and conformational flexibility of transfer RNA (tRNA) can be attained through this modification.

Objective

The modification also triggers lung cancer in humans. The identification of D sites was carried out through conventional laboratory methods; however, those were costly and time-consuming. The readiness of RNA sequences helps in the identification of D sites through computationally intelligent models. However, the most challenging part is turning these biological sequences into distinct vectors.

Methods

The current research proposed novel feature extraction mechanisms and the identification of D sites in tRNA sequences using ensemble models. The ensemble models were then subjected to evaluation using k-fold cross-validation and independent testing.

Results

The results revealed that the stacking ensemble model outperformed all the ensemble models by revealing 0.98 accuracy, 0.98 specificity, 0.97 sensitivity, and 0.92 Matthews Correlation Coefficient. The proposed model, iDHU-Ensem, was also compared with pre-existing predictors using an independent test. The accuracy scores have shown that the proposed model in this research study performed better than the available predictors.

Conclusion

The current research contributed towards the enhancement of D site identification capabilities through computationally intelligent methods. A web-based server, iDHU-Ensem, was also made available for the researchers at https://taseersuleman-idhu-ensem-idhu-ensem.streamlit.app/.

RCCC_Pred: A Novel Method for Sequence-Based Identification of Renal Clear Cell Carcinoma Genes through DNA Mutations and a Blend of Features

To save lives from cancer, it is very crucial to diagnose it at its early stages. One solution to early diagnosis lies in the identification of the cancer driver genes and their mutations. Such diagnostics can substantially minimize the mortality rate of this deadly disease. However, concurrently, the identification of cancer driver gene mutation through experimental mechanisms could be an expensive, slow, and laborious job. The advancement of computational strategies that could help in the early prediction of cancer growth effectively and accurately is thus highly needed towards early diagnoses and a decrease in the mortality rates due to this disease. Herein, we aim to predict clear cell renal carcinoma (RCCC) at the level of the genes, using the genomic sequences. The dataset was taken from IntOgen Cancer Mutations Browser and all genes' standard DNA sequences were taken from the NCBI database. Using cancer-associated information of mutation from INTOGEN, the benchmark dataset was generated by creating the mutations in original sequences. After extensive feature extraction, the dataset was used to train ANN+ Hist Gradient boosting that could perform the classification of RCCC genes, other cancer-associated genes, and non-cancerous/unknown (non-tumor driver) genes. Through an independent dataset test, the accuracy observed was 83%, whereas the 10-fold cross-validation and Jackknife validation yielded 98% and 100% accurate results, respectively. The proposed predictor RCCC_Pred is able to identify RCCC genes with high accuracy and efficiency and can help scientists/researchers easily predict and diagnose cancer at its early stages.

Evaluation of deep learning techniques for identification of sarcoma-causing carcinogenic mutations

The abnormal growth of human healthy cells is called cancer. One of the major types of cancer is sarcoma, mostly found in human bones and soft tissue cells. It commonly occurs in children. According to a survey of the United States of America, there are more than 17,000 sarcoma patients registered each year which is 15% of all cancer cases. Recognition of cancer at its early stage saves many lives. The proposed study developed a framework for the early detection of human sarcoma cancer using deep learning Recurrent Neural Network (RNN) algorithms. The DNA of a human cell is made up of 25,000 to 30,000 genes. Each gene is represented by sequences of nucleotides. The nucleotides in a sequence of a driver gene can change which is termed as mutations. Some mutations can cause cancer. There are seven types of a gene whose mutation causes sarcoma cancer. The study uses the dataset which has been taken from more than 134 samples and includes 141 mutations in 8 driver genes. On these gene sequences RNN algorithms Long and Short-Term Memory (LSTM), Gated Recurrent Units and Bi-directional LSTM (Bi-LSTM) are used for training. Rigorous testing techniques such as Self-consistency testing, independent set testing, 10-fold cross-validation test are applied for the validation of results. These validation techniques yield several metrics such as Area Under the Curve (AUC), sensitivity, specificity, Mathew's correlation coefficient, loss, and accuracy. The proposed algorithm exhibits an accuracy of 99.6% with an AUC value of 1.00.

A machine learning technique for identifying DNA enhancer regions utilizing CIS-regulatory element patterns

Enhancers regulate gene expression, by playing a crucial role in the synthesis of RNAs and proteins. They do not directly encode proteins or RNA molecules. In order to control gene expression, it is important to predict enhancers and their potency. Given their distance from the target gene, lack of common motifs, and tissue/cell specificity, enhancer regions are thought to be difficult to predict in DNA sequences. Recently, a number of bioinformatics tools were created to distinguish enhancers from other regulatory components and to pinpoint their advantages. However, because the quality of its prediction method needs to be improved, its practical application value must also be improved. Based on nucleotide composition and statistical moment-based features, the current study suggests a novel method for identifying enhancers and non-enhancers and evaluating their strength. The proposed study outperformed state-of-the-art techniques using fivefold and tenfold cross-validation in terms of accuracy. The accuracy from the current study results in 86.5% and 72.3% in enhancer site and its strength prediction respectively. The results of the suggested methodology point to the potential for more efficient and successful outcomes when statistical moment-based features are used. The current study's source code is available to the research community at https://github.com/csbioinfopk/enpred.

ResSUMO: A Deep Learning Architecture Based on Residual Structure for Prediction of Lysine SUMOylation Sites

Lysine SUMOylation plays an essential role in various biological functions. Several approaches integrating various algorithms have been developed for predicting SUMOylation sites based on a limited dataset. Recently, the number of identified SUMOylation sites has significantly increased due to investigation at the proteomics scale. We collected modification data and found the reported approaches had poor performance using our collected data. Therefore, it is essential to explore the characteristics of this modification and construct prediction models with improved performance based on an enlarged dataset. In this study, we constructed and compared 16 classifiers by integrating four different algorithms and four encoding features selected from 11 sequence-based or physicochemical features. We found that the convolution neural network (CNN) model integrated with residue structure, dubbed ResSUMO, performed favorably when compared with the traditional machine learning and CNN models in both cross-validation and independent tests. The area under the receiver operating characteristic (ROC) curve for ResSUMO was around 0.80, superior to that of the reported predictors. We also found that increasing the depth of neural networks in the CNN models did not improve prediction performance due to the degradation problem, but the residual structure could be included to optimize the neural networks and improve performance. This indicates that residual neural networks have the potential to be broadly applied in the prediction of other types of modification sites with great effectiveness and robustness. Furthermore, the online ResSUMO service is freely accessible.

LBCEPred: a machine learning model to predict linear B-cell epitopes

B-cell epitopes have the capability to recognize and attach to the surface of antigen receptors to stimulate the immune system against pathogens. Identification of B-cell epitopes from antigens has a great significance in several biomedical and biotechnological applications, provides support in the development of therapeutics, design and development of an epitope-based vaccine and antibody production. However, the identification of epitopes with experimental mapping approaches is a challenging job and usually requires extensive laboratory efforts. However, considerable efforts have been placed for the identification of epitopes using computational methods in the recent past but deprived of considerable achievements. In this study, we present LBCEPred, a python-based web-tool (http://lbcepred.pythonanywhere.com/), build with random forest classifier and statistical moment-based descriptors to predict the B-cell epitopes from the protein sequences. LBECPred outperforms all sequence-based available models that are currently in use for the B-cell epitopes prediction, with 0.868 accuracy value and 0.934 area under the curve. Moreover, the prediction performance of proposed models compared to other state-of-the-art models is 56.3% higher on average for Mathews Correlation Coefficient. LBCEPred is easy to use tool even for novice users and has also shown the models stability and reliability, thus we believe in its significant contribution to the research community and the area of bioinformatics.

A comprehensive tool for accurate identification of methyl-Glutamine sites

Methylation is a biochemical process involved in nearly all of the human body functions. Glutamine is considered an indispensable amino acid that is susceptible to methylation via post-translational modification (PTM). Modern research has proved that methylation plays a momentous role in the progression of most types of cancers. Therefore, there is a need for an effective method to predict glutamine sites vulnerable to methylation accurately and inexpensively. The motive of this study is the formulation of an accurate method that could predict such sites with high accuracy. Various computationally intelligent classifiers were employed for their formulation and evaluation. Rigorous validations prove that deep learning performs best as compared to other classifiers. The accuracy (ACC) and the area under the receiver operating curve (AUC) obtained by 10-fold cross-validation was 0.962 and 0.981, while with the jackknife testing, it was 0.968 and 0.980, respectively. From these results, it is concluded that the proposed methodology works sufficiently well for the prediction of methyl-glutamine sites. The webserver's code, developed for the prediction of methyl-glutamine sites, is freely available at https://github.com/s20181080001/WebServer.git. The code can easily be set up by any intermediate-level Python user.

iTAGPred: A Two-Level Prediction Model for Identification of Angiogenesis and Tumor Angiogenesis Biomarkers

A crucial biological process called angiogenesis plays a vital role in migration, growth, and wound healing of endothelial cells and other processes that are controlled by chemical signals. Angiogenesis is the process that controls the growth of blood vessels within tissues while angiogenesis proteins play a significant role in the proper working of this process. The balancing of these signals is necessary for the proper working of angiogenesis. Unbalancing of these signals increases blood vessel formation, which causes abnormal growth or several diseases including cancer. The proposed work focuses on developing a two-layered prediction model using different classifiers like random forest (RF), neural network, and support vector machine. The first level performs in silico identification of angiogenesis proteins based on the primary structure. In the case the protein is an angiogenesis protein, then the second level predicts whether the protein is linked with tumor angiogenesis or not. The performance of the model is evaluated through various validation techniques. The model was evaluated using k-fold cross-validation, independent, self-consistency, and jackknife testing. The overall accuracy using an RF classifier for angiogenesis at the first level was 97.8% and for tumor angiogenesis at the second level was 99.5%, ANN showed 94.1% accuracy for angiogenesis and 79.9% for tumor angiogenesis, and the accuracy of SVM for angiogenesis was 78.8% and for tumor angiogenesis was 65.19%.