1
|
Shah AA, Daud A, Bukhari A, Alshemaimri B, Ahsan M, Younis R. DEL-Thyroid: deep ensemble learning framework for detection of thyroid cancer progression through genomic mutation. BMC Med Inform Decis Mak 2024; 24:198. [PMID: 39039464 DOI: 10.1186/s12911-024-02604-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2024] [Accepted: 07/10/2024] [Indexed: 07/24/2024] Open
Abstract
Genes, expressed as sequences of nucleotides, are susceptible to mutations, some of which can lead to cancer. Machine learning and deep learning methods have emerged as vital tools in identifying mutations associated with cancer. Thyroid cancer ranks as the 5th most prevalent cancer in the USA, with thousands diagnosed annually. This paper presents an ensemble learning model leveraging deep learning techniques such as Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Bi-directional LSTM (Bi-LSTM) to detect thyroid cancer mutations early. The model is trained on a dataset sourced from asia.ensembl.org and IntOGen.org, consisting of 633 samples with 969 mutations across 41 genes, collected from individuals of various demographics. Feature extraction encompasses techniques including Hahn moments, central moments, raw moments, and various matrix-based methods. Evaluation employs three testing methods: self-consistency test (SCT), independent set test (IST), and 10-fold cross-validation test (10-FCVT). The proposed ensemble learning model demonstrates promising performance, achieving 96% accuracy in the independent set test (IST). Statistical measures such as training accuracy, testing accuracy, recall, sensitivity, specificity, Mathew's Correlation Coefficient (MCC), loss, training accuracy, F1 Score, and Cohen's kappa are utilized for comprehensive evaluation.
Collapse
Affiliation(s)
- Asghar Ali Shah
- Center of Excellence in Artificial Intelligence (CoE-AI), Department of Computer Science, Bahria University, Islamabad, 04408, Pakistan
| | - Ali Daud
- Faculty of Resilience, Rabdan Academy, Abu Dhabi, United Arab Emirates.
| | - Amal Bukhari
- Department of Information Systems and Technology, Collage of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi Arabia
| | - Bader Alshemaimri
- Software Engineering Department, College of Computing and Information Sciences, King Saud University, Riyadh, Saudi Arabia
| | - Muhammad Ahsan
- Department of Computer Science, University of Alabama at Birmingham, 1402 10th Avenue S, Birmingham, AL, 35294, USA
| | - Rehmana Younis
- College of Letters and Sciences, Graduate Student of Robotics Engineering, Columbus State University, Columbus, USA
| |
Collapse
|
2
|
Suleman MT, Alturise F, Alkhalifah T, Khan YD. m1A-Ensem: accurate identification of 1-methyladenosine sites through ensemble models. BioData Min 2024; 17:4. [PMID: 38360720 PMCID: PMC10868122 DOI: 10.1186/s13040-023-00353-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Accepted: 12/31/2023] [Indexed: 02/17/2024] Open
Abstract
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/ .
Collapse
Affiliation(s)
- Muhammad Taseer Suleman
- Department of Computer Science, School of Systems and Technology, University of Management and Technology, Lahore, 54770, Pakistan
| | - Fahad Alturise
- Department of Computer, College of Science and Arts in Ar Rass, Qassim University, Ar Rass, Qassim, Saudi Arabia.
| | - Tamim Alkhalifah
- Department of Computer, College of Science and Arts in Ar Rass, Qassim University, Ar Rass, Qassim, Saudi Arabia
| | - Yaser Daanial Khan
- Department of Computer Science, School of Systems and Technology, University of Management and Technology, Lahore, 54770, Pakistan
| |
Collapse
|
3
|
Alotaibi FM, Khan YD. A Framework for Prediction of Oncogenomic Progression Aiding Personalized Treatment of Gastric Cancer. Diagnostics (Basel) 2023; 13:2291. [PMID: 37443684 DOI: 10.3390/diagnostics13132291] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2023] [Revised: 06/05/2023] [Accepted: 06/13/2023] [Indexed: 07/15/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Fahad M Alotaibi
- Department of Information System, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia
| | - Yaser Daanial Khan
- Department of Computer Science, University of Management and Technology, Lahore 54770, Pakistan
| |
Collapse
|
4
|
Tu J, Hu L, Mohammed KJ, Le BN, Chen P, Ali E, Ali HE, Sun L. Application of logistic regression, support vector machine and random forest on the effects of titanium dioxide nanoparticles using macroalgae in treatment of certain risk factors associated with kidney injuries. ENVIRONMENTAL RESEARCH 2023; 220:115167. [PMID: 36584853 DOI: 10.1016/j.envres.2022.115167] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/14/2022] [Revised: 12/16/2022] [Accepted: 12/25/2022] [Indexed: 06/17/2023]
Abstract
The use of titanium dioxide (TiO2) nanoparticles in many biological and technical domains is on the rise. There hasn't been much research on the toxicity of titanium dioxide nanoparticles in biological systems, despite their ubiquitous usage. In the current investigation, samples were exposed to various dosages of TiO2 nanoparticles for 4 days, 1 month, and 2 months following treatment. ICP-AES was used to dose TiO2 into the tissues, and the results showed that the kidney had a significant TiO2 buildup. On the other hand, apoptosis of renal tubular cells is one of the most frequent cellular processes contributing to kidney disease (KD). Nevertheless, the impact of macroalgal seaweed extract on KD remains undetermined. In this work, machine learning (ML) approaches have been applied to develop prediction algorithms for acute kidney injury (AKI) by use of titanium dioxide and macroalgae in hospitalized patients. Fifty patients with (AKI) and 50 patients (non-AKI group) have been admitted and considered. Regarding demographic data, and laboratory test data as input parameters, support vector machine (SVM), and random forest (RF) are utilized to build models of AKI prediction and compared to the predictive performance of logistic regression (LR). Due to its strong antioxidant and anti-inflammatory powers, the current research ruled out the potential of using G. oblongata red macro algae as a source for a variety of products for medicinal uses. Despite a high and fast processing of algorithms, logistic regression showed lower overfitting in comparison to SVM, and Random Forest. The dataset is subjected to algorithms, and the categorization of potential risk variables yields the best results. AKI samples showed significant organ defects than non-AKI ones. Multivariate LR indicated that lymphocyte, and myoglobin (MB) ≥ 1000 ng/ml were independent risk parameters for AKI samples. Also, GCS score (95% CI 1.4-8.3 P = 0.014) were the risk parameters for 60-day mortality in samples with AKI. Also, 90-day mortality in AKI patients was significantly high (P < 0.0001). In compared to the control group, there were no appreciable changes in the kidney/body weight ratio or body weight increases. Total thiol levels in kidney homogenate significantly decreased, and histopathological analysis confirmed these biochemical alterations. According to the results, oral TiO2 NP treatment may cause kidney damage in experimental samples.
Collapse
Affiliation(s)
- Jianxin Tu
- Department of Rheumatology and Immunology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Lingzhen Hu
- Department of Rheumatology and Immunology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Khidhair Jasim Mohammed
- Air Conditioning and Refrigeration Techniques Engineering Department, Al-Mustaqbal University College, Babylon 51001, Iraq
| | - Binh Nguyen Le
- Institute of Research and Development, Duy Tan University, Da Nang, VietNam; School of Engineering & Technology, Duy Tan University, Da Nang, VietNam.
| | - Peirong Chen
- Department of Rheumatology and Immunology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Elimam Ali
- Department of Civil Engineering, College of Engineering in Al-Kharj, Prince Sattam Bin Abdulaziz University, Al-Kharj, 11942, Saudi Arabia
| | - H Elhosiny Ali
- Advanced Functional Materials & Optoelectronic Laboratory (AFMOL), Department of Physics, Faculty of Science, King Khalid University, P.O. Box 9004, Abha 61413, Saudi Arabia; Research Center for Advanced Materials Science (RCAMS), King Khalid University, P.O. Box 9004, Abha 61413, Saudi Arabia; Physics Department, Faculty of Science, Zagazig University, Zagazig 44519, Egypt
| | - Li Sun
- Department of Rheumatology and Immunology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China.
| |
Collapse
|
5
|
Deep learning ensemble 2D CNN approach towards the detection of lung cancer. Sci Rep 2023; 13:2987. [PMID: 36807576 PMCID: PMC9941084 DOI: 10.1038/s41598-023-29656-z] [Citation(s) in RCA: 17] [Impact Index Per Article: 17.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2022] [Accepted: 02/08/2023] [Indexed: 02/22/2023] Open
Abstract
In recent times, deep learning has emerged as a great resource to help research in medical sciences. A lot of work has been done with the help of computer science to expose and predict different diseases in human beings. This research uses the Deep Learning algorithm Convolutional Neural Network (CNN) to detect a Lung Nodule, which can be cancerous, from different CT Scan images given to the model. For this work, an Ensemble approach has been developed to address the issue of Lung Nodule Detection. Instead of using only one Deep Learning model, we combined the performance of two or more CNNs so they could perform and predict the outcome with more accuracy. The LUNA 16 Grand challenge dataset has been utilized, which is available online on their website. The dataset consists of a CT scan with annotations that better understand the data and information about each CT scan. Deep Learning works the same way our brain neurons work; therefore, deep learning is based on Artificial Neural Networks. An extensive CT scan dataset is collected to train the deep learning model. CNNs are prepared using the data set to classify cancerous and non-cancerous images. A set of training, validation, and testing datasets is developed, which is used by our Deep Ensemble 2D CNN. Deep Ensemble 2D CNN consists of three different CNNs with different layers, kernels, and pooling techniques. Our Deep Ensemble 2D CNN gave us a great result with 95% combined accuracy, which is higher than the baseline method.
Collapse
|
6
|
Suleman MT, Alturise F, Alkhalifah T, Khan YD. iDHU-Ensem: Identification of dihydrouridine sites through ensemble learning models. Digit Health 2023; 9:20552076231165963. [PMID: 37009307 PMCID: PMC10064468 DOI: 10.1177/20552076231165963] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2022] [Accepted: 03/09/2023] [Indexed: 04/04/2023] Open
Abstract
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/.
Collapse
Affiliation(s)
- Muhammad Taseer Suleman
- Department of Computer Science, School of systems and technology, University of Management and Technology, Lahore, Pakistan
| | - Fahad Alturise
- Department of Computer, College of Science and Arts in Ar Rass, Qassim University, Ar Rass, Qassim, Saudi Arabia
- Fahad Alturise, Department of Computer, College of Science and Arts in Ar Rass, Qassim University, Ar Rass, Qassim, Saudi Arabia.
| | - Tamim Alkhalifah
- Department of Computer, College of Science and Arts in Ar Rass, Qassim University, Ar Rass, Qassim, Saudi Arabia
| | - Yaser Daanial Khan
- Department of Computer Science, School of systems and technology, University of Management and Technology, Lahore, Pakistan
| |
Collapse
|