Computational Biology and Chemistry最新文献

{"title":"Mechanistic insights into cardiovascular toxicity induced by polycyclic aromatic hydrocarbons using Benzo[a]pyrene (BaP) as an example","authors":"Haoyue Jia ,&nbsp;Hao Zhang ,&nbsp;Chengyan Guan ,&nbsp;Qiang Wan","doi":"10.1016/j.compbiolchem.2026.108877","DOIUrl":"10.1016/j.compbiolchem.2026.108877","url":null,"abstract":"<div><div>Environmental contamination has emerged as a critical global public health challenge. Among persistent organic pollutants, polycyclic aromatic hydrocarbons (PAHs) exhibit concerning bioaccumulation potential in aquatic and terrestrial ecosystems, with demonstrated cardiotoxic effects in humans. Nevertheless, the precise molecular pathogenesis of PAH-mediated cardiovascular damage requires further elucidation. This investigation adopts a multi-modal computational strategy integrating network toxicology with molecular docking to systematically characterize PAH-induced cardiovascular toxicity mechanisms. Comprehensive toxicity profiling was performed through ADMETlab 3.0 and ProTox3.0 platforms, while putative molecular targets were identified via SwissTargetPrediction, ChEMBL, SEA, and CTD repositories. Disease-relevant targets were curated from GeneCards and OMIM databases. Integrated analysis combining Venn diagram, protein-protein interaction (PPI) network, and Cytoscape 3.9.1 visualization identified critical common targets. Functional annotation using Metascape and DAVID elucidated the crucial associated biological processes, cellular compartments, and molecular functions. Pathway enrichment analysis identified dominant signaling pathways, primarily the PI3K-AKT and MAPK cascades, along with those involved in hemodynamic stress/atherogenesis and oncogenic networks. Molecular docking coupled with molecular dynamics simulations further confirmed robust and energetically favorable interactions between PAH compounds and core toxicity targets. Collectively, using BaP as a paradigm, this in-silico study demonstrates an integrative computational workflow to investigate PAH-induced cardiovascular toxicity, proposing candidate molecular targets and pathways, which exemplifies the utility of multi-level bioinformatics in generating hypotheses for toxicological evaluation.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108877"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145936780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational identification of potential MMP-2 inhibitors in cancer using machine learning, molecular docking, and dynamics simulations","authors":"Sohail Akhtar ,&nbsp;Ahmed Ibrahim ,&nbsp;Ahmed M.A. Abdalla ,&nbsp;Mohammad Aatif ,&nbsp;Rohit Kumar Singh Gautam ,&nbsp;Mohammad Aslam ,&nbsp;Danishuddin","doi":"10.1016/j.compbiolchem.2026.108919","DOIUrl":"10.1016/j.compbiolchem.2026.108919","url":null,"abstract":"<div><div>Matrix metalloproteinase-2 (MMP-2) is a zinc-dependent endopeptidase which plays a key role in the extracellular matrix-remodeling and cancer metastasis. Nevertheless, despite the vast number of attempts, MMP-2 selective and low-toxicity development is a problematic area because of the insufficient selectivity and the off-target effect of the previous candidates. This work demonstrated that an integrated machine learning-driven virtual screening pipeline can be used to discover better selectivity, and binding stability novel MMP-2 inhibitors. Various models of classification were trained with the help of a set of different molecular fingerprints, and random Forest and radial-basis-function Support Vector Model of classification showed the best predictive results (AUC &gt; 0.97, MCC &gt; 0.86). These models have been used to filter the Maybridge compound library resulting in the selection of the top-ranked ones. Molecular docking and subsequent ADMET profiling of the shortlisted seven potential compounds yielded a list of 1. Molecular dynamics simulations (100 ns) showed that GK03418 and RH00707 had stable binding conformations similar to that of the reference inhibitor. Free energy landscape mapping and principal component analysis was another method that proved thermodynamic stability of GK03418. The energetics of binding free-energy calculations with MM/PBSA and MM/GBSA showed positive results and the most promising inhibitor was GK03418. In general, this paper provides a computationally sound and scalable structure of the discovery of selective MMP-2 inhibitors that have future anticancer applicability.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108919"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational exploration of squalene analog 4,4′diapophytofluene as a potential anti-aging phytotherapeutic","authors":"Madhurima Dutta ,&nbsp;Anjan Hazra ,&nbsp;Suparna Mandal Biswas","doi":"10.1016/j.compbiolchem.2026.108945","DOIUrl":"10.1016/j.compbiolchem.2026.108945","url":null,"abstract":"<div><div>Cellular senescence is a complex biological process characterized by several unique features including cell-cycle arrest, macromolecular damage, secretory phenotypes (SASPs), and deregulated metabolism. These factors are essential for understanding their impact on aging and diseases. Extensive studies on various biochemical pathways associated with mammalian aging have identified SIRT-1, Bcl-xL, Hsp-90, MDM-2, AMPK and mTOR as some key regulatory proteins. So, preserving the functions of these proteins could potentially decelerate the aging process. A previous study had demonstrated that 4,4′-diapophytofluene (4,4′-DPE), a squalene analog extracted from the pentane fraction of <em>Cocos nucifera</em> leaves was more effective than squalene in suppressing senescence induction in WI38 and HaCaT cells. In the present study, high-throughput virtual screening was performed to evaluate the interaction between 4,4′-DPE and six aforementioned aging regulators, further validating its role as a natural senotherapeutic along with squalene and some well-known anti-aging botanicals (quercetin, curcumin, resveratrol, metformin, and fisetin). In molecular docking studies, 4,4′-DPE revealed stronger binding affinity (ΔG) with SIRT-1, Bcl-xL, Hsp-90, MDM-2, and mTOR, except for AMPK protein, compared to quercetin, curcumin, resveratrol, and fisetin. The MM/PBSA and FEL plots of molecular dynamics simulation of 100 ns production had also highlighted 4,4′-DPE maintained thermodynamically stable and favourable interactions with binding pockets of five proteins, supported by persistent van der Waals and hydrophobic contacts with minimal structural deviations. Furthermore, the ADMET studies confirmed 4,4′-DPE as a clinically safe bioactive compound, facilitating it to become a novel senotherapeutic/anti-aging agent for pharmaceuticals and dermatological products.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108945"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146168557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systems biology approach to programmed cell death in prostate cancer: Biomarker discovery and therapeutic potential of DL-PDMP","authors":"Elif Kubat Oktem ,&nbsp;Muhammed Yasar Bener ,&nbsp;Ummuhan Demir","doi":"10.1016/j.compbiolchem.2026.108912","DOIUrl":"10.1016/j.compbiolchem.2026.108912","url":null,"abstract":"<div><div>Prostatic adenocarcinoma (PRAD) is among the most common malignancies in men and is characterized by considerable genetic and epigenetic heterogeneity. Despite advances in diagnosis and treatment, options for advanced and refractory prostate cancer remain limited, which adversely affects patient prognosis. This project aims to identify diagnostic and prognostic biomarkers associated with programmed cell death (PCD) mechanisms in prostate cancer and to reposition existing drugs that target these biomarkers. Using RNA-seq and clinical data from The Cancer Genome Atlas (TCGA), differential gene expression, ROC curve, and survival analyses identified six candidate biomarkers with strong diagnostic and prognostic significance. Three small molecules – DL-PDMP, clobetasol propionate, and metoclopramide hydrochloride – capable of reversing gene expression profiles were selected for in vitro assays in a drug repositioning analysis conducted using the L1000CDS2 platform. Among these, DL-PDMP was prioritized because of its low IC₅₀ value and low toxicity to normal prostate epithelial cells. Furthermore, DL-PDMP has been shown to induce apoptosis and suppress colony formation. These findings suggest that targeting PCD-associated biomarkers is a promising strategy for prostate cancer treatment, making DL-PDMP a strong candidate for further preclinical studies.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108912"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146034879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the performance of physics-informed neural networks for tumor growth prediction under noisy and sparse data conditions","authors":"Nicolás Murúa ,&nbsp;Aníbal Coronel ,&nbsp;Gastón Márquez","doi":"10.1016/j.compbiolchem.2026.108915","DOIUrl":"10.1016/j.compbiolchem.2026.108915","url":null,"abstract":"<div><div>Cancer presents multiple challenges for its study, which is why mathematical models have become essential tools to understand its dynamics and reduce reliance on costly biological experiments. This investigation explores the use of Physics-Informed Neural Networks (PINNs) to approximate and predict cancer progression based on a simplified ordinary differential system mathematical model, which describes the interactions among tumor, normal, and immune cells. Synthetic data are generated using the implicit Euler method, incorporating noise to simulate real clinical measurements. The study evaluates how the amount of data, temporal spacing, and noise level affect the network’s performance. Results show that having at least 40 days of data enables accurate predictions in most evaluated scenarios. A comparative analysis with a Multi-Layer Perceptron (MLP) and a Least Squares (LS) approach using RK45 demonstrated that the PINN is significantly more robust for learning and predicting future dynamics, especially under limited or noisy data conditions. The inclusion of the physical loss allowed the model to extrapolate beyond the observed domain, although it did not fully compensate for data scarcity. Accurately modeling the immune cell population proved particularly challenging. These findings help identify the limitations and obstacles that such techniques must overcome to be effectively applied in real-world clinical settings, ultimately supporting data-driven medical decision-making through robust, model-based predictions.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108915"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146032000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Boolean network-based identification of optimal drug combinations for prostate cancer","authors":"Pranabesh Bhattacharjee ,&nbsp;Addanki Pratap Kumar ,&nbsp;Aniruddha Datta","doi":"10.1016/j.compbiolchem.2026.108898","DOIUrl":"10.1016/j.compbiolchem.2026.108898","url":null,"abstract":"<div><div>Prostate cancer is one of the most common cancers among men in the United States and is a leading cause of cancer-related deaths and the second most common cancer in men worldwide. In this study, we used a Boolean network model to analyze prostate cancer signaling pathways and to identify optimal drug combinations for precision therapy. By integrating publicly available biological signaling pathway data with recent research findings, we developed a comprehensive model that represents protein-protein interactions, gene mutations, and pathway dysregulation. Faults induced by mutations were modeled using the “stuck at 0” or “stuck at 1” fault paradigms, capturing the impact of genetic alterations on pathway behavior. The model was simulated across various drug combinations to determine which therapies could most effectively alleviate the aberrant signaling caused by specific mutations. To quantify therapeutic efficacy, we calculated a Size Difference (SD) score, a metric analogous to Hamming distance, measuring the deviation from normal, for each drug combination and fault scenario. The results revealed that drug combinations involving Berberine, Docetaxel, Olaparib, and Enzalutamide showed promising prediction efficacy (more than 90 %), indicating higher therapeutic potential. A distinguishing feature of this work is that, in addition to the standard prostate cancer drugs, we have included Berberine, a non-toxic natural compound with beneficial effects. These computational findings provide a framework for future experimental and clinical validation, which is necessary to confirm the therapeutic relevance of the predicted drug combinations.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108898"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145999827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ginsenoside Rb1 as a multi-target modulator in heart failure: Mechanistic insights into extracellular remodeling and transcriptional pathways from network pharmacology, molecular dynamics, and binding free energy analyses","authors":"Qiang Yin ,&nbsp;Ying Liu ,&nbsp;Ibrahim Kehinde ,&nbsp;Mahmoud Soliman ,&nbsp;Baobao Bai","doi":"10.1016/j.compbiolchem.2026.108902","DOIUrl":"10.1016/j.compbiolchem.2026.108902","url":null,"abstract":"<div><h3>Background</h3><div>Heart failure is a leading global health burden, often driven by Angiotensin II (Ang II)–induced processes such as inflammation, fibrosis, and extracellular matrix remodeling. These mechanisms involve multiple protein hubs, making single-target drugs insufficient. Natural products such as Ginsenoside Rb1, a major bioactive constituent of <em>Panax ginseng</em>, have emerged as promising multi-target agents, though their mechanistic roles in cardiovascular protection remain incompletely defined.</div></div><div><h3>Methods</h3><div>A combined strategy of network pharmacology, protein–protein interaction analysis, molecular docking, molecular dynamics (MD) simulations, and MM/GBSA binding free energy calculations was employed. Hub proteins associated with Ang II–mediated heart failure were identified, followed by docking and MM/GBSA analyses to compare the binding affinity of Rb1 against reference drugs (Losartan, Enalapril, and Carvedilol). Protein–ligand interaction maps, hydrophobicity profiling, and electrostatic potential (ESP) analyses were used to elucidate binding mechanisms.</div></div><div><h3>Results</h3><div>Five hub proteins—MMP9, FN1, JUN, FGF2, and STAT3—were identified as central to Ang II–driven remodeling, inflammation, and transcriptional regulation. MM/GBSA analyses revealed consistently favorable ΔG_bind values for Rb1, including −36.40 kcal/mol (FN1), −35.30 kcal/mol (STAT3), and −33.70 kcal/mol (JUN), which were comparable to or exceeded those of the reference drugs. In contrast, Rb1 showed moderate affinity at MMP9 (−31.80 kcal/mol) and FGF2 (−30.70 kcal/mol). Interaction plots demonstrated that the amphipathic nature of Rb1, with a bulky hydrophobic backbone and multiple polar hydroxyl groups, enabled multidentate hydrogen bonding, van der Waals stabilization, and π-alkyl interactions across diverse binding pockets. Hydrophobicity and ESP mapping further confirmed that Rb1 adapts effectively to both hydrophobic and polar microenvironments, explaining its broader multi-target binding capacity compared to the more structurally restricted reference drugs.</div></div><div><h3>Conclusion</h3><div>This study highlights Ginsenoside Rb1 as a promising polypharmacological candidate for heart failure, showing strong and adaptable binding to multiple Ang II–related targets.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108902"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146035276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Thyroid hormone signaling causally influences pancreatic disease risk: Evidence from Mendelian randomization and multi-omics integration","authors":"Xuejiao Wu ,&nbsp;Zilin Yang","doi":"10.1016/j.compbiolchem.2026.108897","DOIUrl":"10.1016/j.compbiolchem.2026.108897","url":null,"abstract":"<div><div>The relationship between thyroid function and pancreatic disease has been observed clinically, yet causality remains unestablished. We applied bidirectional Mendelian randomization using genetic instruments from genome-wide association studies encompassing over 500,000 individuals to determine causal relationships. We demonstrate that genetic liability to hypothyroidism substantially protects against acute pancreatitis (odds ratio 0.37, 95 % CI 0.17–0.80). Genetically elevated basal metabolic rate increases acute pancreatitis risk (OR 1.16) while decreasing chronic pancreatitis risk (OR 0.77), revealing divergent pathophysiological mechanisms. No causal relationship exists between thyroid function and pancreatic cancer. To elucidate underlying mechanisms, we performed multi-omics analysis including bulk RNA sequencing from 172 pancreatic adenocarcinomas, single-cell RNA sequencing from acute pancreatitis (32,830 cells), chronic pancreatitis (30,426 cells), and pancreatic cancer (95,751 cells), and GeoMx spatial transcriptomics (253 regions). High metabolic gene expression predicts favorable cancer survival (hazard ratio 0.52, P = 0.0015). Single-cell analysis reveals myeloid-specific metabolic gene downregulation in chronic pancreatitis and 31-fold upregulation of the thyroid hormone-inactivating enzyme DIO3 in tumor epithelial cells. Spatial transcriptomics demonstrates that PPARGC1A downregulation occurs in preneoplastic lesions before malignant transformation. These findings establish thyroid function as a causal determinant of pancreatitis susceptibility, identify cell type-specific mechanisms including local thyroid hormone inactivation and metabolic reprogramming, and demonstrate that patient-derived organoids better preserve prognostically favorable metabolic phenotypes than cell lines. Thyroid function represents a potentially modifiable risk factor for inflammatory pancreatic disease.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108897"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146020906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DisSubFormer: A subgraph transformer model for disease subgraph representation and comorbidity prediction","authors":"Ashwag Altayyar,&nbsp;Li Liao","doi":"10.1016/j.compbiolchem.2026.108935","DOIUrl":"10.1016/j.compbiolchem.2026.108935","url":null,"abstract":"<div><div>Disease comorbidity—the co-occurrence of multiple diseases in the same individual—is increasingly prevalent and poses major clinical and biological challenges. Computational approaches for studying disease relationships and predicting comorbidity have evolved from overlap-based similarity measures to molecular network modeling and graph deep learning. However, existing methods often (i) learn global or subgraph-based disease embeddings without modeling the topology of fragmented disease subgraphs in a comorbidity-adaptive manner, or (ii) incorporate Gene Ontology (GO) information in ways that underutilize GO’s hierarchical ancestry and deeper functional abstractions. In this work, we propose DisSubFormer, a subgraph Transformer model for disease subgraph representation learning and comorbidity prediction. We first learn unified protein representations by integrating structural patterns from a PPI network with GO-aware functional information, explicitly incorporating GO’s hierarchical ancestry. We next sample biologically informed anchor patches in a property-aware manner to prioritize disease-relevant regions of the PPI network, replacing full-graph attention with subgraph-to-subgraph attention between disease subgraphs and these anchor patches to improve scalability and relevance. Specifically, DisSubFormer introduces a learnable multi-head attention mechanism where each head attends over a distinct anchor-patch type, with head-specific relational terms to capture complementary positional, neighborhood, and structural properties within fragmented disease subgraphs for comorbidity prediction. Experiments on a benchmark comorbidity dataset demonstrate that DisSubFormer consistently outperforms state-of-the-art methods, achieving an AUROC of 0.97.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108935"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146144430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Chronic kidney disease detection using XceptionNet with Harmonic Addax Optimization","authors":"Suruchi Gaurav Dedgaonkar ,&nbsp;Geeta S Navale ,&nbsp;Priya Shelke ,&nbsp;Amol Vishwanath Dhumane","doi":"10.1016/j.compbiolchem.2026.108921","DOIUrl":"10.1016/j.compbiolchem.2026.108921","url":null,"abstract":"<div><div>Chronic Kidney Disease (CKD) refers to a persistent and progressive impairment of kidney function occurring over a prolonged duration. Impaired kidney filtration can lead to the accumulation of waste products and excess fluid in the bloodstream, contributing to the development of secondary medical conditions. CKD leads to high blood pressure, glomerulonephritis, diabetes, and polycystic kidney disease. However, early detection of CKD is significant for decreasing complications and preventing kidney failure. However, generalization and class imbalance issues complicate the detection process. In order to improve CKD detection and resolve current limitations, an optimized deep learning approach is presented in this paper. This paper proposes a CKD detection framework that integrates XceptionNet with the Harmonic Addax Optimization Algorithm (HAOA). First, the chronic kidney dataset is provided as input and undergoes sigmoid normalization to ensure proper data scaling and structural consistency. Next, feature fusion is performed by a Deep Belief Network (DBN) with a Soergel metric. Then, data augmentation is performed utilizing the Synthetic Minority Overlapping Technique (SMOTE). At last, CKD detection is done using Xception with HAOA. Here, HAOA is developed by combining Harmonic analysis and the Addax Optimization Algorithm (AOA). The performance of the proposed Xception with the HAOA method is analyzed by the CKD dataset 1, CKD dataset 2, and the Risk Factor Prediction of CKD Dataset. It also achieves a good True Positive Rate (TPR) value of 94.679 %, True Negative Rate (TNR) of 92.777 %, and accuracy of 93.667 %, a precision of 92.258 %, and an F1-score of 93.453 %. The proposed model serves as an effective tool for early CKD diagnosis, reducing the risk of kidney failure and improving potential outcomes.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108921"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}