Indonesian Journal of Life Sciences

Comparative Analysis For CNN and MLP Models in Breast Cancer Diagnosis

Priscilla Natalie Nurtanio — 2026-03-31

Breast cancer remains one of the most common and deadly diseases affecting women worldwide, highlighting the importance of early and accurate diagnosis to improve treatment outcomes and survival rates. However, traditional mammography techniques often fall short, failing to detect up to 20% of cases, especially in women with dense breast tissue, which makes detection more difficult. In response to these limitations, this study explores the use of neural networks to enhance diagnostic accuracy in breast cancer detection, focusing on the Convolutional Neural Network (CNN) and Multilayer Perceptron (MLP). Utilizing the Wisconsin Diagnostic Breast Cancer (WDBC) dataset, a baseline CNN model is compared against an optimized CNN refined through hyperparameter tuning using randomized search, as well as two MLP models implemented via Keras and Scikit-learn, along with their optimized versions. Each model is evaluated using key classification metrics, including accuracy, precision, recall, F1-score, and AUC, with an emphasis on minimizing false negatives, as this is critical in medical diagnosis to avoid missed malignancies. The results indicate that the optimized CNN model achieved near-perfect scores across all metrics and demonstrated the best balance between training and testing data. Therefore, it outperforms the baseline CNN and MLP models in significantly reducing false negatives, showcasing the potential of a well-tuned CNN to enhance the automation and reliability of breast cancer diagnostic processes.

Structure-Based Computational Screening of Indonesian Spice-Derived Compounds Targeting the Neuropeptide Y1 Receptor

Blessari Tesalonika Woran — 2026-03-31

The neuropeptide Y1 receptor (NPY1R) is a promising therapeutic target for type 2 diabetes mellitus (T2DM) due to its role in regulating appetite and insulin secretion. Indonesian spices contain diverse bioactive compounds with potential metabolic effects, yet their interaction with NPY1R remains largely unexplored. This study aimed to identify potential natural allosteric modulators of NPY1R using structure-based virtual screening and pharmacokinetic analysis. A total of 17,356 compounds from the NCBI PubChem database were pre-filtered, yielding 860 ligands for blind molecular docking. Of these, 97 showed stronger predicted binding affinities than the reference antagonist BMS-193885. Further screening based on physicochemical properties, toxicity, and ADMET parameters identified six top candidates. Among them, cis-theaspirone demonstrated the most favorable profile, including binding to an allosteric pocket (–10.0 kcal/mol; RMSD 2.658 Å), high gastrointestinal absorption, blood–brain barrier permeability, and acceptable solubility. Molecular dynamics simulations over 50 ns confirmed stable ligand–receptor interactions. Overall, cis-theaspirone emerges as a potential NPY1R modulator, highlighting the promise of Indonesian spice-derived compounds for further investigation in metabolic disease research.

In-Silico Design of a PIN1/ABCC5-Targeted Multi-Epitope Vaccine for Nasopharyngeal Cancer

Putri Ashiila — 2026-03-31

Nasopharyngeal Carcinoma (NPC) is a rare malignancy. However, it is the fourth most common cancer affecting both sexes in Indonesia, and research on NPC remains limited. NPC is related to Epstein-Barr Virus (EBV) infection, making it a potential target for immunotherapy strategies. Developing a multi-epitope-based NPC vaccine targeting tumor-overexpressed antigens may evoke an immune response against cancer cells and benefit patients with advanced cancer stages or those resistant to treatment. Four cytotoxic (CTL) and one helper T-cell (HTL) epitopes from PIN1 were identified using NetMHCpan and NetMHCIIpan algorithms, respectively. Whereas from ABCC5, five CTL and four HTL epitopes were identified using the same algorithms. These epitopes were found to have good coverage across the Indonesian population, with population coverage analysis showing 99% coverage for human leukocyte antigen (HLA) Class I and 95% for HLA Class II. Having fulfilled other criteria such as immunogenicity, IFN-γ-inducing ability, and non-homology to human peptides, the epitopes were assembled into a vaccine construct together with E. coli and Bacillus as adjuvants and appropriate linkers. The construct was shown to have good physicochemical characteristics and the ability to induce CTL and HTL responses, which stem from the engagement of the vaccine with toll-like receptor 4 (TLR4) as revealed by docking simulations.

The Physicochemical Properties, Antioxidant Potential, and Skin Penetration of Pterostilbene-Loaded NLCs

Elaine Louise — 2026-03-31

Pterostilbene is a naturally occurring polyphenolic compound known for its antioxidant activity and potential use in topical skin care formulations. However, its poor water solubility and limited skin penetration reduce its therapeutic effectiveness. In this study, pterostilbene-loaded nanostructured lipid carriers (PT-NLCs) were developed and evaluated as a topical delivery system to enhance its stability and dermal performance. The PT-NLCs showed a mean particle size of 78–99 nm (88.57 ± 10.60 nm), a polydispersity index of 0.284, and an encapsulation efficiency of 99.98%, indicating a stable nanosystem. The NLC formulation increased apparent water solubility by over 5,000-fold and improved skin penetration by approximately 360% compared with raw pterostilbene. PT-NLCs also demonstrated enhanced antioxidant activity, with about a 34% increase in radical scavenging capacity in the DPPH assay and improved protection of skin cells against oxidative stress while maintaining good cytocompatibility. These findings demonstrate that NLC-based encapsulation effectively improves the solubility, dermal penetration, and antioxidant efficacy of pterostilbene, highlighting its potential as a promising ingredient for topical skin treatment applications.

Integrated Network Pharmacology and Molecular Docking Identify Neuroprotective Candidates from Nicotiana tabacum L. Against Alzheimer’s Disease

Daffa Rizal Dzulfaqaar Alauddin — 2026-03-31

The neuroprotective potential of compounds from Nicotiana tabacum L. against Alzheimer’s disease was evaluated using network pharmacology, molecular docking, and ADME profiling. 25 compounds were screened, and the intersection of predicted targets with Alzheimer’s disease associated proteins yielded 90 overlapping proteins. Network topology using Degree prioritized three hub targets, IL-1β (Degree: 37), GSK3β (Degree: 25), and AChE (Degree: 19). Docking in YASARA against IL-1β (5R8Q), GSK3β (5K5N), and AChE (4EY7) produced binding energy ranges of -6.673 to -8.680, -9.769 to -10.614, and -10.349 to -12.275 kcal/mol, respectively. The β-amyrin ranked best among test ligands for IL-1β at -6.885 kcal/mol and for GSK3β at -10.178 kcal/mol, while citrostadienol ranked best for AChE at -10.881 kcal/mol. Dual-target profiles supported 28-Isofucosterol for GSK3β and AchE, and gramisterol for IL-1β and AChE. BOILED Egg analysis supported BBB-oriented prioritization of candidates with TPSA <79 Å², while highly lipophilic sterol-type leads indicate formulation-dependent developability. Overall, Nicotiana tabacum L. provides non-nicotine sterol and triterpenoid scaffolds as multi-target chemotypes spanning inflammation, kinase signaling, and cholinergic dysfunction in Alzheimer’s disease.

The F-11 Sensory Neuron Model: A Scalable In Vitro Platform for Neuropathic Pain and Drug Screening

Tommy Alfandy Nazwar — 2026-03-31

Neuropathic pain remains a major therapeutic challenge, largely due to the translational disconnect between preclinical animal models and clinical efficacy in humans. This review critically evaluates the differentiated F-11 cell line, a hybridoma of mouse neuroblastoma and rat embryonic dorsal root ganglion (DRG) neurons, as a scalable, reproducible, and physiologically relevant in vitro platform for neuropathic pain research and analgesic drug screening. A detailed analysis of differentiation strategies highlights the critical interplay of neurotrophic factors (notably NGF), intracellular signaling modulators (such as cAMP elevators), and extracellular matrix cues in driving neuronal maturation. Functional validation via calcium imaging and electrophysiology confirms capsaicin responsiveness and action potential generation, mirroring native nociceptors. Its compatibility with medium-to-high-throughput screening and mechanistic studies including investigation of silent nociceptor sensitization in chronic pain conditions along with emerging applications in neuropathy models, makes it a valuable tool for de-risking drug candidates before animal studies.

Effectiveness of Mesenchymal Stem Cells and Their Derivatives in Modulating Oxidative Stress in Neurodegenerative Diseases: A Structured Narrative Review

Niken Rahmah Ghanny — 2026-03-31

Background: Oxidative stress plays a critical role in the development and progression of neurodegenerative diseases such as Parkinson’s disease (PD), Alzheimer’s disease (AD), and amyotrophic lateral sclerosis (ALS). Mesenchymal stem cells (MSCs) and their derivatives have emerged as promising therapeutic strategies due to their antioxidant, anti-inflammatory, and neuroprotective properties. Objective: This review evaluated the effectiveness of MSC-based interventions in modulating oxidative stress in neurodegenerative disease models. Methods: A structured narrative review search was conducted following PRISMA 2020 guidelines using PubMed and Scopus databases for studies published between 2020 and 2025, with the last search in December 2025. Results: 33 studies met the inclusion criteria, primarily involving Parkinson’s and Alzheimer’s disease models. Overall, MSC-based therapies reduced oxidative stress markers, enhanced antioxidant defenses, activated the Nrf2/HO-1 pathway, improved mitochondrial function, and reduced neuroinflammation in experimental neurodegenerative disease models.

Smartphone Use and Musculoskeletal Disorders: A Systematic Review of Epidemiological Evidence and Potential on Inflammatory Mechanisms

Nurul Afifah Hijami — 2026-03-31

Smartphone use among adults has increased and often involves prolonged exposure with sustained non-neutral neck posture. Epidemiological studies report a high prevalence of neck and shoulder pain among frequent users. Biomechanical loading of the cervical spine is considered a main mechanism, while inflammatory processes have been proposed as an additional pathway. This systematic review evaluated the association between smartphone use and musculoskeletal complaints, focusing on inflammatory biomarkers as a potential biological mechanism.

The review followed PRISMA 2020 guidelines. Searches were conducted in PubMed and ScienceDirect for peer-reviewed studies published between 2018 and 2025. Eligible studies included adults aged 18 years or older who reported smartphone use exceeding 2 to 3 hours per day. Exposure was commonly assessed using self-report questionnaires or structured surveys. Studies examining neck or shoulder outcomes, posture, or inflammatory biomarkers were included. Observational studies, randomized controlled trials, and ergonomic interventions were eligible.

Thirty studies met the inclusion criteria. Most reported significant associations between prolonged smartphone use, sustained neck flexion, and musculoskeletal pain in the neck and shoulders. Prevalence ranged from moderate to high among students and workers with a daily use of 3 to 9 hours. No included study directly measured inflammatory biomarkers in general smartphone users. Related evidence indicates elevated IL-6 and C-reactive protein in sedentary populations with high device exposure.

Potential Use of WT1 as a Diagnostic and Therapeutic Marker of Acute Myeloid Leukemia: A Review

Almitra Rindiarti — 2026-03-31

Acute myeloid leukemia (AML) is a heterogeneous malignancy characterized by uncontrolled proliferation and impaired hematopoietic differentiation of myeloid lineage with rapid disease progression. Among the various biomarkers studied, Wilms’ tumor 1 (WT1) is a widely expressed gene in AML, making it an attractive biomarker candidate for diagnosis and minimal residual disease (MRD) monitoring. This review evaluates the potential of WT1 as an effective diagnostic biomarker and the current detection methods, highlighting the advantages and limitations of the current gold standard, RT-qPCR, and exploring potential alternative approaches, such as ELISA and antibody-based flow cytometry, for its clinical applicability. Using public gene datasets, bioinformatic analysis further supports WT1’s overexpression in AML, though with varying levels across subtypes, suggesting its potential as part of a multimodal diagnostic plan rather than a standalone marker. Beyond diagnostics, WT1 is also a promising therapeutic target, with peptide and dendritic cell vaccines, as well as TCR-engineered T cells, demonstrating encouraging clinical outcomes. Next-generation strategies, including CAR-T cells, bispecific T-cell engagers, and mRNA vaccines, are advancing preclinical and early clinical studies. Together, these findings highlight WT1 as both a biomarker and a therapeutic target, with future integration into precision medicine likely to improve AML detection, risk stratification, and treatment.