Sequence based model using deep neural network and hybrid features for identification of 5-hydroxymethylcytosine modification
Abstract RNA modifications are pivotal in the development of newly synthesized structures, showcasing a vast array of alterations across various RNA classes. Among these, 5-hydroxymethylcytosine (5HMC) stands out, playing a crucial role in gene regulation and epigenetic changes, yet its detection th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-59777-y |
| _version_ | 1797199497666756608 |
|---|---|
| author | Salman Khan Islam Uddin Mukhtaj Khan Nadeem Iqbal Huda M. Alshanbari Bakhtiyar Ahmad Dost Muhammad Khan |
| author_facet | Salman Khan Islam Uddin Mukhtaj Khan Nadeem Iqbal Huda M. Alshanbari Bakhtiyar Ahmad Dost Muhammad Khan |
| author_sort | Salman Khan |
| collection | DOAJ |
| description | Abstract RNA modifications are pivotal in the development of newly synthesized structures, showcasing a vast array of alterations across various RNA classes. Among these, 5-hydroxymethylcytosine (5HMC) stands out, playing a crucial role in gene regulation and epigenetic changes, yet its detection through conventional methods proves cumbersome and costly. To address this, we propose Deep5HMC, a robust learning model leveraging machine learning algorithms and discriminative feature extraction techniques for accurate 5HMC sample identification. Our approach integrates seven feature extraction methods and various machine learning algorithms, including Random Forest, Naive Bayes, Decision Tree, and Support Vector Machine. Through K-fold cross-validation, our model achieved a notable 84.07% accuracy rate, surpassing previous models by 7.59%, signifying its potential in early cancer and cardiovascular disease diagnosis. This study underscores the promise of Deep5HMC in offering insights for improved medical assessment and treatment protocols, marking a significant advancement in RNA modification analysis. |
| first_indexed | 2024-04-24T07:16:42Z |
| format | Article |
| id | doaj.art-c6b0432aabe84f068bb55f1143f4979b |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T07:16:42Z |
| publishDate | 2024-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-c6b0432aabe84f068bb55f1143f4979b2024-04-21T11:17:56ZengNature PortfolioScientific Reports2045-23222024-04-0114111210.1038/s41598-024-59777-ySequence based model using deep neural network and hybrid features for identification of 5-hydroxymethylcytosine modificationSalman Khan0Islam Uddin1Mukhtaj Khan2Nadeem Iqbal3Huda M. Alshanbari4Bakhtiyar Ahmad5Dost Muhammad Khan6Department of Computer Science, Abdul Wali Khan University MardanDepartment of Computer Science, Abdul Wali Khan University MardanDepartment of Information Technology, The University of HaripurDepartment of Computer Science, Abdul Wali Khan University MardanDepartment of Mathematical Sciences, College of Science, Princess Nourah bint Abdulrahman UniversityHigher Education Department AfghanistanDepartment of Statistics, Abdul Wali Khan University MardanAbstract RNA modifications are pivotal in the development of newly synthesized structures, showcasing a vast array of alterations across various RNA classes. Among these, 5-hydroxymethylcytosine (5HMC) stands out, playing a crucial role in gene regulation and epigenetic changes, yet its detection through conventional methods proves cumbersome and costly. To address this, we propose Deep5HMC, a robust learning model leveraging machine learning algorithms and discriminative feature extraction techniques for accurate 5HMC sample identification. Our approach integrates seven feature extraction methods and various machine learning algorithms, including Random Forest, Naive Bayes, Decision Tree, and Support Vector Machine. Through K-fold cross-validation, our model achieved a notable 84.07% accuracy rate, surpassing previous models by 7.59%, signifying its potential in early cancer and cardiovascular disease diagnosis. This study underscores the promise of Deep5HMC in offering insights for improved medical assessment and treatment protocols, marking a significant advancement in RNA modification analysis.https://doi.org/10.1038/s41598-024-59777-y5-HydroxymethylcytosineRNACancerDiabetesCardiovascularDeep learning |
| spellingShingle | Salman Khan Islam Uddin Mukhtaj Khan Nadeem Iqbal Huda M. Alshanbari Bakhtiyar Ahmad Dost Muhammad Khan Sequence based model using deep neural network and hybrid features for identification of 5-hydroxymethylcytosine modification Scientific Reports 5-Hydroxymethylcytosine RNA Cancer Diabetes Cardiovascular Deep learning |
| title | Sequence based model using deep neural network and hybrid features for identification of 5-hydroxymethylcytosine modification |
| title_full | Sequence based model using deep neural network and hybrid features for identification of 5-hydroxymethylcytosine modification |
| title_fullStr | Sequence based model using deep neural network and hybrid features for identification of 5-hydroxymethylcytosine modification |
| title_full_unstemmed | Sequence based model using deep neural network and hybrid features for identification of 5-hydroxymethylcytosine modification |
| title_short | Sequence based model using deep neural network and hybrid features for identification of 5-hydroxymethylcytosine modification |
| title_sort | sequence based model using deep neural network and hybrid features for identification of 5 hydroxymethylcytosine modification |
| topic | 5-Hydroxymethylcytosine RNA Cancer Diabetes Cardiovascular Deep learning |
| url | https://doi.org/10.1038/s41598-024-59777-y |
| work_keys_str_mv | AT salmankhan sequencebasedmodelusingdeepneuralnetworkandhybridfeaturesforidentificationof5hydroxymethylcytosinemodification AT islamuddin sequencebasedmodelusingdeepneuralnetworkandhybridfeaturesforidentificationof5hydroxymethylcytosinemodification AT mukhtajkhan sequencebasedmodelusingdeepneuralnetworkandhybridfeaturesforidentificationof5hydroxymethylcytosinemodification AT nadeemiqbal sequencebasedmodelusingdeepneuralnetworkandhybridfeaturesforidentificationof5hydroxymethylcytosinemodification AT hudamalshanbari sequencebasedmodelusingdeepneuralnetworkandhybridfeaturesforidentificationof5hydroxymethylcytosinemodification AT bakhtiyarahmad sequencebasedmodelusingdeepneuralnetworkandhybridfeaturesforidentificationof5hydroxymethylcytosinemodification AT dostmuhammadkhan sequencebasedmodelusingdeepneuralnetworkandhybridfeaturesforidentificationof5hydroxymethylcytosinemodification |