Article Per Year (5 Year)
p-Index From 2021 - 2026
0.882
P-Index
This Author published in this journals
All Journal Heca Journal of Applied Sciences Malacca Pharmaceutics Journal of Educational Management and Learning Grimsa Journal of Science Engineering and Technology
Teuku Rizky Noviandy
Department of Information Systems, Faculty of Engineering, Universitas Abulyatama, Aceh Besar 23372, Indonesia
Agriculture, Biological Sciences & Forestry Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Earth & Planetary Sciences Education Engineering Health Professions Immunology & microbiology Languange, Linguistic, Communication & Media Mathematics Medicine & Pharmacology Physics Other

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Fine-Tuning ChemBERTa for Predicting Activity of AXL Kinase Inhibitors in Oncogenic Target Modeling Teuku Rizky Noviandy; Ghazi Mauer Idroes; Mohsina Patwekar; Rinaldi Idroes
Grimsa Journal of Science Engineering and Technology Vol. 3 No. 2 (2025): October 2025
Publisher : Graha Primera Saintifika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61975/gjset.v3i2.98

Abstract

The development of selective kinase inhibitors remains a key objective in cancer drug discovery, where predictive computational models can significantly accelerate the identification of leads. In this study, we investigate the fine-tuning strategies of the transformer-based ChemBERTa model for quantitative structure–activity relationship (QSAR) modeling of AXL receptor tyrosine kinase inhibitors, an important therapeutic target implicated in tumor progression and metastasis. A dataset of AXL inhibitors was curated from the ChEMBL database. Three fine-tuning configurations, namely baseline, full fine-tune, and aggressive, were implemented to examine the influence of learning rate, weight decay, and the number of frozen transformer layers on model performance. Models were evaluated using accuracy, precision, recall, F1-score, and calibration metrics. Results showed that both the full fine-tune and aggressive configurations outperformed the baseline model, achieving higher precision and F1-scores while maintaining robust recall. The aggressive configuration achieved the most balanced performance, with improved calibration and the lowest expected calibration error, indicating reliable probabilistic predictions. Overall, this study highlights that controlled fine-tuning of ChemBERTa significantly enhances predictive performance and confidence estimation in QSAR modeling, offering valuable insights for optimizing transformer-based chemical language models in kinase-targeted drug discovery.
Comparative Analysis of Ensemble Machine Learning Models for QSAR-Based Prediction of Anticoagulant Activity in Thrombotic Disorders Teuku Rizky Noviandy; Rahmat Sufri; Ryan Setiawan; Anisah Anisah
Heca Journal of Applied Sciences Vol. 4 No. 1 (2026): March 2026
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/hjas.v4i1.393

Abstract

Thrombotic disorders remain a major cause of global morbidity and mortality, with dysregulation of blood coagulation pathways playing a central role in disease progression. In particular, Thrombin is a key therapeutic target for anticoagulant drug development, making accurate prediction of inhibitory activity highly relevant for accelerating discovery efforts. Despite advances in computational drug discovery, there is still a need for systematic evaluation of machine learning approaches for QSAR-based prediction of anticoagulant activity. Many existing studies focus on single models or lack consistent comparison frameworks, limiting insights into the relative performance of different ensemble techniques. To address this gap, this study explores the application of multiple ensemble machine learning methods, including Random Forest, XGBoost, Gradient Boosting, and Extra Trees, combined with hyperparameter optimization using random search. The main objective of this work is to conduct a comparative analysis of these ensemble models to predict pIC50 values for thrombin inhibitors using molecular descriptors derived from chemical structures. The results show that the Extra Trees model achieved the best overall performance, with an R2 of 0.697, RMSE of 0.851, and MAE of 0.615 after tuning. Additionally, Gradient Boosting and XGBoost demonstrated significant improvement following hyperparameter optimization, highlighting the importance of model tuning in QSAR tasks. Overall, the study confirms that ensemble learning methods yield reliable, accurate predictions of anticoagulant activity, with Extra Trees emerging as the most effective approach for this dataset.
A Data-Driven Classification of Student Productivity Based on Academic Performance, Lifestyle Patterns, and Digital Habits Teuku Rizky Noviandy; Hizir Sofyan; Yosza Dasril; Rinaldi Idroes
Journal of Educational Management and Learning Vol. 4 No. 1 (2026): May 2026
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/jeml.v4i1.433

Abstract

Student productivity is influenced by various factors, including academic habits, lifestyle characteristics, and digital distraction behaviors. The increasing use of digital technologies, such as smartphones, social media, and online gaming, has created new challenges for maintaining student focus and academic performance. Therefore, understanding and predicting student productivity levels is important for supporting effective educational management and student success. This study aims to classify student productivity levels using machine learning techniques based on academic, behavioral, and digital distraction variables. The study utilized the Student Productivity & Digital Distraction Dataset obtained from Kaggle, consisting of 20,000 student records. The productivity score was transformed into five productivity categories, namely very low, low, medium, high, and very high productivity. Four machine learning algorithms, including Decision Tree (DT), and K-Nearest Neighbors (KNN), Gradient Boosting (GB), and Random Forest (RF) were evaluated using accuracy, precision, recall, F1-score, and confusion matrix analysis. The results showed that RF achieved the best performance with an accuracy of 81.15%, precision of 81.35%, recall of 81.15%, and F1-score of 81.23%, outperforming GB, DT, and KNN. The findings indicate that ensemble learning methods are more effective in modeling the complex relationships among academic habits, lifestyle factors, digital distraction, and student productivity. Furthermore, the study demonstrates the potential of machine learning as a decision-support tool for educational management, enabling the identification of students with different productivity levels and supporting data-driven interventions to improve academic outcomes.
Online Gaming, Digital Entertainment, and Academic Performance among Students: A Review Teuku Rizky Noviandy; Rinaldi Idroes
Journal of Educational Management and Learning Vol. 4 No. 1 (2026): May 2026
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/jeml.v4i1.434

Abstract

Online gaming and digital entertainment have become increasingly integrated into students’ daily lives through smartphones, computers, gaming platforms, video streaming, and social media. This review paper examines the relationship between online gaming, digital entertainment, and academic performance among students. The discussion highlights that digital entertainment can produce both positive and negative effects depending on duration, timing, content type, self-regulation, and learning context. Moderate and purposeful use may support cognitive skills, social interaction, motivation, and digital literacy. In contrast, excessive or problematic use may contribute to distraction, reduced study time, poor sleep quality, lower learning engagement, and weaker academic outcomes. Quantitative findings from previous studies show that many students engage frequently in online gaming and digital entertainment, including long weekly gaming time, mobile gaming as a major source of entertainment, and frequent social media checking. Overall, the reviewed literature suggests that the relationship between digital entertainment and academic performance is conditional rather than absolute. Healthy digital habits, effective time management, and guidance from parents, teachers, and educational institutions are important to help students balance entertainment and academic responsibilities.
QSAR Modeling of Beta-2 Adrenergic Receptor Ligands Using Molecular Descriptor–Based Machine Learning Teuku Rizky Noviandy; Mohsina Patwekar; Rinaldi Idroes
Malacca Pharmaceutics Vol. 4 No. 1 (2026): March 2026
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/mp.v4i1.394

Abstract

The Beta-2 Adrenergic Receptor (ADRB2) is a well-characterized G protein–coupled receptor widely studied in pharmacology and drug discovery. In this study, quantitative structure–activity relationship (QSAR) models were developed using molecular descriptor–based machine learning approaches to predict the activity of ADRB2 ligands. A curated dataset of 745 compounds with experimentally determined IC₅₀ values was obtained from the ChEMBL database. Two-dimensional molecular descriptors were calculated and preprocessed to remove low-variance and highly correlated features, resulting in a refined feature set for model development. The dataset was categorized into active and inactive compounds and divided into training and testing subsets. Four machine learning algorithms. Logistic Regression, Support Vector Machine, Gradient Boosting, and Random Forest were implemented and evaluated using accuracy, precision, recall, F1-score, and ROC-AUC metrics. Among the models, Random Forest achieved the best performance, with an accuracy of 89.26%, F1-score of 89.87%, and AUC of 0.926, followed by Gradient Boosting with an accuracy of 87.92% and AUC of 0.922. Analysis of physicochemical descriptors indicated that hydrogen-bond donor capacity (nHD) shows a statistically significant association with variations in compound activity toward ADRB2, while lipophilicity (LogP) and hydrogen-bond acceptor count (nHA) do not exhibit statistically significant differences between activity classes. Overall, the results demonstrate that molecular descriptor–based machine learning models, particularly ensemble methods, provide an effective framework for predicting ADRB2-related compound activity and support the prioritization of candidate molecules in computational drug discovery.
Co-Authors Anisah Anisah Ghazi Mauer Idroes Hizir Sofyan Mohsina Patwekar Rahmat Sufri Rinaldi Idroes Ryan Setiawan Yosza Dasril