A new approach for determining SARS-CoV-2 epitopes using machine learning-based in silico methods

Cihan, Pınar; Ozger, Zeynep Banu

doi:10.1016/j.compbiolchem.2022.107688

Cited by 15 publications

(6 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In another study, a Bayesian neural network was used for this task and was able to achieve an accuracy of 85% [63]. It can be seen from Table 9 that the random forest model developed in [43] was able to make good predictions, although there is a need for improvement in the model's performance. In all the methods used previously, to the best of our knowledge, none have attempted the transfer learning strategy that was used in this study.…”

Section: Discussionmentioning

confidence: 99%

“…The data consisted of ten features, both structural and chemical. The protein sequences and peptide sequences were in categorical form but were later converted to numerical form using their sequence lengths so that each protein sequence or peptide sequence would have a value that corresponded to the number of its categorical letters, while chou_fasman (beta turn), kolaskar_tongaonkar (antigenicity), Parker (hydrophobicity), Emini (relative surface accessibility), stability, isoelectric_point, aromaticity, and hydrophobicity were numerical, as previously described in [43]; see Figure 1 for the data distribution. The SARS-CoV-2 dataset lacked label information and comprised 20,312 peptides isolated from the virus' spike protein.…”

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Accelerating SARS-CoV-2 Vaccine Development: Leveraging Novel Hybrid Deep Learning Models and Bioinformatics Analysis for Epitope Selection and Classification

Ameen¹,

Mostafa

Ozsahin

et al. 2023

Processes

View full text Add to dashboard Cite

It is essential to use highly antigenic epitope areas, since the development of peptide vaccines heavily relies on the precise design of epitope regions that can elicit a strong immune response. Choosing epitope regions experimentally for the production of the SARS-CoV-2 vaccine can be time-consuming, costly, and labor-intensive. Scientists have created in silico prediction techniques based on machine learning to find these regions, to cut down the number of candidate epitopes that might be tested in experiments, and, as a result, to lessen the time-consuming process of their mapping. However, the tools and approaches involved continue to have low accuracy. In this work, we propose a hybrid deep learning model based on a convolutional neural network (CNN) and long short-term memory (LSTM) for the classification of peptides into epitopes or non-epitopes. Numerous transfer learning strategies were utilized, and the fine-tuned method gave the best result, with an AUC of 0.979, an f1 score of 0.902, and 95.1% accuracy, which was far better than the performance of the model trained from scratch. The experimental results obtained show that this model has superior performance when compared to other methods trained on IEDB datasets. Using bioinformatics tools such as ToxinPred, VaxiJen, and AllerTop2.0, the toxicities, antigenicities, and allergenicities, respectively, of the predicted epitopes were determined. In silico cloning and codon optimization were used to successfully express the vaccine in E. coli. This work will help scientists choose the best epitope for the development of the COVID-19 vaccine, reducing cost and labor and thereby accelerating vaccine production.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Accelerating SARS-CoV-2 Vaccine Development: Leveraging Novel Hybrid Deep Learning Models and Bioinformatics Analysis for Epitope Selection and Classification

Ameen¹,

Mostafa

Ozsahin

et al. 2023

Processes

View full text Add to dashboard Cite

show abstract

“…Expanding the dataset to include data from other ICUs within the same institution could help address this limitation. Fourth, balancing a dataset using methods, such as SMOTE (Synthetic Minority Over-sampling Technique) [ 41 ], can improve the performance of a machine learning model in minority class prediction by creating synthetic samples by interpolating between existing minority class samples and then increasing the number of minority class samples in the training dataset. Fifth, the study did not use more complex modeling techniques, such as recurrent neural networks or transformers, which have built-in temporal dynamics functionality, due to the desire to use smaller computational units and maintain interpretability of features.…”

Section: Discussionmentioning

confidence: 99%

Prediction of Acid-Base and Potassium Imbalances in Intensive Care Patients Using Machine Learning Techniques

et al. 2023

View full text Add to dashboard Cite

Acid–base disorders occur when the body’s normal pH is out of balance. They can be caused by problems with kidney or respiratory function or by an excess of acids or bases that the body cannot properly eliminate. Acid–base and potassium imbalances are mechanistically linked because acid–base imbalances can alter the transport of potassium. Both acid–base and potassium imbalances are common in critically ill patients. This study investigated machine learning models for predicting the occurrence of acid–base and potassium imbalances in intensive care patients. We used an institutional dataset of 1089 patients with 87 variables, including vital signs, general appearance, and laboratory results. Gradient boosting (GB) was able to predict nine clinical conditions related to acid–base and potassium imbalances: mortality (AUROC = 0.9822), hypocapnia (AUROC = 0.7524), hypercapnia (AUROC = 0.8228), hypokalemia (AUROC = 0.9191), hyperkalemia (AUROC = 0.9565), respiratory acidosis (AUROC = 0.8125), respiratory alkalosis (AUROC = 0.7685), metabolic acidosis (AUROC = 0.8682), and metabolic alkalosis (AUROC = 0.8284). Some predictions remained relatively robust even when the prediction window was increased. Additionally, the decision-making process was made more interpretable and transparent through the use of SHAP analysis. Overall, the results suggest that machine learning could be a useful tool to gain insight into the condition of intensive care patients and assist in the management of acid–base and potassium imbalances.

show abstract

“…In this study, accuracy, precision, recall, and F1 score metrics were used to evaluate the classification performance of the RNN methods. The formulas for these metrics are provided below [9,10]:…”

Section: B Performance Metricsmentioning

confidence: 99%

Effect of Parameter Selection on Heart Attack Risk Prediction in an RNN Model

Cihan

2023

ICAENS

View full text Add to dashboard Cite

Heart attack has become a significant public health issue worldwide, and effective prediction methods, along with early diagnosis, are crucial for the prevention and treatment of this disease. Various machine learning and deep learning techniques have been employed in the literature to predict the risk of heart attack. In this study, the evaluation of heart attack risk was conducted using the Recurrent Neural Network (RNN) classification method with different parameters. By considering various parameters that affect the performance of the RNN model, the impact of proper parameter selection on classification accuracy was investigated. During the data preprocessing stage, the data was appropriately standardized, and 5-fold cross-validation was performed. Eleven RNN models were compared by altering different parameters such as the number of units, the number of training cycles, batch size, dropout rate, activation function, and number of units in the dense layer. The classification performance was evaluated using metrics such as accuracy, precision, recall, and F1 score. The results demonstrate that parameter selection influences the performance of the RNN classification model and that performance improvements can be achieved with appropriate parameter selections.

show abstract

A new approach for determining SARS-CoV-2 epitopes using machine learning-based in silico methods

Cited by 15 publications

References 61 publications

Accelerating SARS-CoV-2 Vaccine Development: Leveraging Novel Hybrid Deep Learning Models and Bioinformatics Analysis for Epitope Selection and Classification

Accelerating SARS-CoV-2 Vaccine Development: Leveraging Novel Hybrid Deep Learning Models and Bioinformatics Analysis for Epitope Selection and Classification

Prediction of Acid-Base and Potassium Imbalances in Intensive Care Patients Using Machine Learning Techniques

Effect of Parameter Selection on Heart Attack Risk Prediction in an RNN Model

Contact Info

Product

Resources

About