Computational Biology and Chemistry最新文献

{"title":"Advancing Alzheimer’s therapeutics via in silico strategies: Tideglusib based multi-target analogues","authors":"Samanta Gambhir,&nbsp;Manjinder Singh","doi":"10.1016/j.compbiolchem.2025.108685","DOIUrl":"10.1016/j.compbiolchem.2025.108685","url":null,"abstract":"<div><div>Alzheimer’s disease is an advanced neurodegenerative illness that disturbs cognitive behavior. Multiple factors are responsible for the etiology of Alzheimer’s disease and one of the cores neuropathologic finding is generation of hyper-phosphorylated tau. GSK-3β or Glycogen synthase kinase-3β a kinase leads to the hyperphosphorylation of tau protein at multiple sites and aggregates into neurofibrillary tangles in AD patient’s brain. Tideglusib is a drug which is under second phase of clinical trial (NCT01350362), impedes the GSK-3β at therapeutically concentration that has been established through various <em>in silico</em> techniques like scaffold morphing, pharmacokinetic, molecular docking and dynamic simulations studies. The Tideglusib based analogues showed good interactions with the catalytic dyed residue (Cys199) of GSK-3β GSK-3β, the main amino acid responsible for its tau hyperphosphorylation activity. Also, the designed analogues of Tideglusib are analyzed for its Multi targeting potential with three main receptors (GSK-3β, AChE, BACE) through molecular docking and molecular dynamic simulation approaches. SG-09 stands out with the best binding affinity and the stable ligand-protein interaction analogues in the time interval of 100 ns can be used as Multitargeting drug with further <em>in silico, in vitro and in vivo</em> clinical evaluation. This design strategy could thus reap considerable clinical and economic rewards.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"120 ","pages":"Article 108685"},"PeriodicalIF":3.1,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099400","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":"Unlocking the anticancer role of alpha-phellandrene via TRPM4 channel modulation in lung cancer","authors":"Akanksha Singh ,&nbsp;Shristi Modanwal ,&nbsp;Abha Meena ,&nbsp;Nidhi Mishra","doi":"10.1016/j.compbiolchem.2025.108688","DOIUrl":"10.1016/j.compbiolchem.2025.108688","url":null,"abstract":"<div><div>Lung cancer remains one of the leading causes of death worldwide, and in major cases accounts for non-small cell lung cancer (NSCLC). Recent advances in targeted therapy have greatly improved treatment outcomes by concentrating on specific genes, proteins, and signaling pathways in tumors, providing a precise treatment method that causes less damage to healthy cells. In the context of targeted therapy, one more target biomarker has been identified, ion channels, which have been considered diverse regulators in the progression of lung cancer. Transient receptor potential (TRP) channels have captivated tremendous appreciation as promising drug targets over the past few years. Importantly, TRPM, a family of TRP that are key regulators of calcium homeostasis, have emerged as promising therapeutic targets due to their overexpression in various cancers, including lung cancer, as well as their involvement in tumor progression, metastasis, and apoptosis resistance. This study investigates the potential of naturally occurring monoterpenes as TRPM channel modulators using an <em>in silico</em> approach. Fifteen monoterpenes were selected and evaluated for their pharmacokinetic properties (ADMET), drug-likeness, and molecular docking study against TRPM2, TRPM4, TRPM5, TRPM7, and TRPM8 isoforms. Alpha-Phellandrene showed significant binding affinity toward TRPM4 (-6.0 kcal/mol) and notably shared key binding residues (ARG960, TYR964, GLU978, GLN976, PRO975, GLN973, LEU968) with the standard inhibitor 9-Phenanthrol, indicating its potential as a natural mimic. Molecular dynamics (MD) simulations further validated the structural stability of the TRPM4–alpha–phellandrene complex over 100 ns. Research findings suggested alpha-phellandrene as a promising candidate for developing TRPM4-targeted therapies in lung cancer.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"120 ","pages":"Article 108688"},"PeriodicalIF":3.1,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145152190","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":"Morpholine-modified thiosemicarbazones and thiazolidin-4-ones against Alzheimer’s key enzymes: From synthesis to inhibition","authors":"Yeliz Demir ,&nbsp;Halil Şenol ,&nbsp;Orhan Uluçay ,&nbsp;Şeyma Ateşoğlu S. ,&nbsp;Feyzi Sinan Tokalı","doi":"10.1016/j.compbiolchem.2025.108683","DOIUrl":"10.1016/j.compbiolchem.2025.108683","url":null,"abstract":"<div><div>Inhibition of acetylcholinesterase (AChE) and butyrylcholinesterase (BChE) is a key therapeutic approach in the management of Alzheimer’s disease and other neurodegenerative disorders. A novel series of phenolic Mannich base-derived thiosemicarbazones and their cyclized thiazolidin-4-one analogs incorporating morpholine moieties were synthesized and characterized. Enzyme inhibition kinetics were evaluated against AChE and BChE, with cytotoxicity assessed on the BEAS-2B cell line. The most potent inhibitors were further examined via molecular docking, MM-GBSA binding free energy decomposition, and 250 ns molecular dynamics (MD) simulations to elucidate their binding mechanisms and stability. Compounds <strong>12</strong> (AChE, <em>K</em>_i = 32.83 ± 4.45 nM) and <strong>6</strong> (BChE, <em>K</em>_i = 30.13 ± 5.78 nM) exhibited the highest inhibitory activities without notable cytotoxicity at their effective concentrations. Kinetic analyses revealed competitive inhibition. Computational studies demonstrated that morpholine tertiary amine groups played a pivotal role in anchoring the ligands via persistent cation–π and hydrogen-bond interactions with key active site residues. <em>In silico</em> ADME analysis indicated that most of the synthesized compounds possess favorable pharmacokinetic properties. This combined <em>in vitro</em> and <em>in silico</em> study identifies compounds <strong>6</strong> and <strong>12</strong> as promising lead structures for cholinesterase inhibition, highlighting the critical contribution of tertiary amine moieties to binding affinity and selectivity.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"120 ","pages":"Article 108683"},"PeriodicalIF":3.1,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145088499","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":"Design, synthesis, and computational evaluation of ester prodrugs of isoguvacine as potential antiseizure medications","authors":"Yan Hong Ng ,&nbsp;Muhamad Imam Muhajir ,&nbsp;Khairul Azreena Bakar ,&nbsp;Rani Maharani ,&nbsp;Unang Supratman ,&nbsp;Jalifah Latip ,&nbsp;Murni Nazira Sarian ,&nbsp;Su Datt Lam ,&nbsp;Shevin Rizal Feroz","doi":"10.1016/j.compbiolchem.2025.108678","DOIUrl":"10.1016/j.compbiolchem.2025.108678","url":null,"abstract":"<div><div>Epilepsy, a neurological disorder affecting millions worldwide, has driven the development of various antiseizure medications (ASMs). Isoguvacine (IGV), a potent and selective agonist of the GABA_A receptor (GABA_AR), has shown potential in the treatment of epilepsy and other neurological disorders. However, its low blood-brain barrier permeability impairs its ability to act effectively within the central nervous system. To address this limitation, two novel ester derivatives of IGV, <strong>E7</strong> and <strong>E14</strong>, were synthesized via Steglich esterification and evaluated through an integrated computational framework comprising density functional theory (DFT) calculations, molecular docking, molecular dynamics (MD) simulations, and <em>in silico</em> ADMET predictions. DFT analysis revealed that esterification significantly modified the electronic properties of IGV, with <strong>E14</strong> exhibiting the highest polarizability (225.895 ų) and smallest energy gap (–0.155 eV), indicative of enhanced reactivity. Molecular docking demonstrated that GABA (–8.46 kcal/mol) and IGV (–8.35 kcal/mol) exhibit similar binding affinity and complex stability with GABA_AR, supporting the reliability of our computational approach. MD simulations further confirmed the stability of these complexes, where lower RMSD, RMSF, and Rg values indicated that binding of GABA and IGV did not induce significant conformational changes in the overall receptor structure. Moreover, the derivatives were projected to exhibit optimal intestinal absorption (&gt;90%), oral bioavailability, as well as favorable safety profiles with minimal interaction risks and non-carcinogenic properties. Collectively, these <em>in silico</em> findings highlight the potential of ester prodrug design to overcome the central pharmacokinetic limitations of IGV, with <strong>E14</strong> emerging as the most promising ASM candidate for further experimental development in epilepsy therapy. Beyond identifying therapeutic advantages of <strong>E14</strong>, this study also underscores the broader value of integrated computational approaches as powerful and predictive tools in early-stage drug discovery for neurological disorders.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"120 ","pages":"Article 108678"},"PeriodicalIF":3.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145082734","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":"Design and synthesis of tunable schiff base complexes from bis-(2-oxoindolin-3-ylidene)anthracene-9,10-dione: Integrated structural, biological, and molecular modeling insights","authors":"Ahmed M. Abu-Dief ,&nbsp;Eida S. Al-Farraj ,&nbsp;Mohamed Abdel-Hameed ,&nbsp;Nadiyah Alahmadi ,&nbsp;Maher Fathalla ,&nbsp;Abdullah Yahya Abdullah Alzahrani ,&nbsp;Mashael A. Alghamdi ,&nbsp;Aly Abdou","doi":"10.1016/j.compbiolchem.2025.108682","DOIUrl":"10.1016/j.compbiolchem.2025.108682","url":null,"abstract":"<div><div>Three novel compounds, each featuring a tetra-dentate ligand known as 1-((2-oxoindolin-3-ylidene)amino)-2-((2-oxoindolin-3-ylidene)amino)anthracene-9,10-dione (BIA), have been successfully synthesized. These molecules exhibit the unique characteristic of forming complexes with Cu(II), Ru(III), and VO(II) metal ions, resulting in distinct metal-organic structures.Structural characterization was performed using elemental analysis, magnetic properties measurement, FT-IR spectroscopy, and electronic spectroscopy. Moreover, the stoichiometry in solution was determined through both continuous variation and molar ratio analysis. These analyses have shown that the copper and ruthenium complexes exhibit an octahedral geometric configuration. Conversely, the vanadyl (VO) complex demonstrates a distinct square pyramidal structure.Density functional theory (DFT) computations were employed to confirm the geometrical configurations of the prepared complexes. The synthesized <strong>BIA</strong> ligand and its corresponding metal complexes were assessed for their <em>in vitro</em> antimicrobial. The results indicated that the RuBIA complex emerged as the most efficacious agent against both bacterial and fungal growth, outperforming established medications like Ofloxacin and Fluconazole as standard drugs with sequence<strong>BIA &lt; VOBIA &lt; CuBIA &lt;RuBIA</strong>complex.Additionally, the study evaluated the in vitro cytotoxicity of the synthesized compounds against Hep-G2, MCF-7, and HCT-116 cancer cell lines. The results suggested that the <strong>RuBIA</strong> complex had the highest potency (IC50 =3.42–6.45 <strong>µg/µl)</strong>, followed by <strong>CuBIA</strong>(IC50 =4.42–7.85 <strong>µg/µl)</strong>, and <strong>VOBIA</strong>(IC50 =5.72–8.35 <strong>µg/µl)</strong>, indicating their potential as promising anticancer agents. The DPPH radical scavenging activity was also assessed, and all complexes displayed greater efficacy than Ascorbic acid. Investigations employing molecular docking methodologies were undertaken to discern the interaction mechanisms of the aforementioned complexes. The findings revealed that the incorporation of metal ions substantially bolstered the molecular affinities, with the sequence of binding potency as follows: RuBIA&gt; CuBIA &gt; VOBIA complex&gt;BIA ligand.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"120 ","pages":"Article 108682"},"PeriodicalIF":3.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145076783","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":"Effectiveness of artificial intelligence in classification of connective tissue diseases in patients with anti-nuclear antibody (ANA) positivity","authors":"Burcu Bosnalı ,&nbsp;Erdinç Türk ,&nbsp;Tahir Saygın Öğüt ,&nbsp;Mert Ünal ,&nbsp;Taner Danışman ,&nbsp;Hatice Yazısız ,&nbsp;Funda Erbasan ,&nbsp;Mustafa Ender Terzioğlu ,&nbsp;Veli Yazisiz","doi":"10.1016/j.compbiolchem.2025.108679","DOIUrl":"10.1016/j.compbiolchem.2025.108679","url":null,"abstract":"<div><h3>Objectives</h3><div>The study aimed to investigate the classification performance of artificial intelligence (AI) in diagnosing connective tissue diseases(CTD). This was done by analyzing laboratory data, including additional markers, in patients who tested positive for antinuclear antibody(ANA).</div></div><div><h3>Material/Methods</h3><div>The research included 663 ANA-positive patients. An automated machine learning approach, specifically Auto-Weka, was used to classify these patients based on 75 features, including age, sex, and various laboratory tests.</div></div><div><h3>Results</h3><div>The Bayes Network achieved the highest overall performance with 93.1 % accuracy, 77.7 % sensitivity, and 96.0 % specificity in the classification of all patients. The most successful models were <em>Locally Weighted Learning</em> for systemic lupus erythematosus(SLE), with an accuracy of 93.4 %; <em>Logistic Model Trees</em> for primary Sjogren's syndrome(pSS), with an accuracy of 91.4 %; <em>AdaBoostM</em> for rheumatoid arthritis(RA), with an accuracy of 95.2 %; and <em>Sequential Minimal Optimization</em> for systemic sclerosis(SSc), with an accuracy of 92.0 %. Sensitivity and specificity rates for SLE, pSS, RA and SSc were found to be 69.4 %, 72.0 %, 78.5 %, 75.3 % and 98.7 %, 96.2 %, 98.9 %, 94.9 %, respectively. The area under the ROC curve in the general distribution of the groups was 95.6 %, the highest value in distinguishing was 99.1 % for RA and the lowest was 85.1 % for SSc. The most predictive markers identified were hematocrit for SLE, anti-SSA for pSS, rheumatoid factor for RA, and anti-centromere B positivity for SSc.</div></div><div><h3>Conclusion</h3><div>AI models are highly successful in classifying ANA-positive patients with great accuracy. AI-based approaches have the potential to assist clinicians in diagnosing autoimmune diseases by providing more accurate and faster results.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"120 ","pages":"Article 108679"},"PeriodicalIF":3.1,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145044459","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":"Exploring biological research hotspots through a novel bibliometric approach","authors":"Shan Chen ,&nbsp;Junsha Wang ,&nbsp;Xinyu Huang ,&nbsp;Kailin Chen ,&nbsp;Limei Fu ,&nbsp;Yuanzhao Ding","doi":"10.1016/j.compbiolchem.2025.108680","DOIUrl":"10.1016/j.compbiolchem.2025.108680","url":null,"abstract":"<div><div>Biological research is a crucial field of study, profoundly impacting every aspect of human life. The objective of this study is to utilize an innovative bibliometric analysis method to understand current research hotspots and future trends in biology. This novel bibliometric analysis method, based on the R programming language, offers a completely different approach than traditional VOSviewer, providing a more in-depth analysis. Based on the bibliometric analysis results, this paper also proposes potential future developments, namely, integrating big data with machine learning. By integrating existing data into large databases and then training models, this approach can provide deep insights and accurate predictions for the future.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"120 ","pages":"Article 108680"},"PeriodicalIF":3.1,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145044460","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":"Improvement of an eye disease detection model by using the denoising diffusion implicit model","authors":"Ping-Huan Kuo ,&nbsp;Eirene Du ,&nbsp;Chiou-Jye Huang ,&nbsp;Wei-Chuan Lan ,&nbsp;Shu-Hung Chou ,&nbsp;Ting-Chun Yao ,&nbsp;Chao-Chung Peng","doi":"10.1016/j.compbiolchem.2025.108677","DOIUrl":"10.1016/j.compbiolchem.2025.108677","url":null,"abstract":"<div><div>With rapid developments in artificial intelligence (AI), the discussion about and applications of generative AI have increased substantially. Generative AI has extensive and valuable applications in many industrial and medical fields and is a possible solution for industries that struggle to collect large quantities of data. The present study evaluated the use of generative AI in eye disease prediction. Because retinal images are difficult to acquire, this study used a generative AI model [i.e., the denoising diffusion implicit model (DDIM)] to conduct data augmentation, thereby improving the accuracy of a convolutional neural network (CNN) model developed for eye disease detection. This study adopted the DDIM primarily for its high inference speed and ability to consistently generate high-quality samples in a limited number of steps, making it suitable for tasks that require high-quality medical images. With the increasing prevalence of electronic products, the number of patients with retinopathy or optic neuropathy is increasing annually, and patients are experiencing these diseases at increasingly younger ages. Moreover, eye diseases such as glaucoma and macular degeneration are becoming increasingly common in modern society. The developed CNN model exhibited a 3 % higher accuracy when it was trained using the data generated by the DDIM than when it was trained without these data. This CNN model can screen eye disease symptoms early to enable patients to receive timely treatment, thereby mitigating the risk and consequences of eye diseases. The results of this study indicate that the training data generated using the DDIM can enhance the accuracy of early eye disease detection.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"120 ","pages":"Article 108677"},"PeriodicalIF":3.1,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145088553","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":"Rational design, biological and in-silico evaluation of quinoline-chalcone hybrids: A new series of antimicrobial and anticancer agents","authors":"Ilker Kiliccioglu ,&nbsp;Ahmad Badreddin Musatat ,&nbsp;Gorkem Dulger ,&nbsp;Alparslan Atahan ,&nbsp;Basaran Dulger ,&nbsp;Mustafa Zengin","doi":"10.1016/j.compbiolchem.2025.108675","DOIUrl":"10.1016/j.compbiolchem.2025.108675","url":null,"abstract":"<div><div>This study investigates the synthesis, antimicrobial, anticancer, and in silico properties of novel quinoline-chalcone hybrids (<strong>nQCa-l</strong>), which were synthesized and characterized. Their antimicrobial activity revealed broad-spectrum efficacy, with compound 2QC-h demonstrating superior potency compared to several standard antibiotics and antifungals. The anticancer potential was assessed against gastrointestinal system cancer cell lines (AGS, HepG2, HCT116), where 2QC-h emerged as the most potent antiproliferative agent, often surpassing oxaliplatin in efficacy, particularly in AGS gastric cancer cells. Mechanistic studies have demonstrated that 2QC-h synergistically induces apoptosis and inhibits epithelial-mesenchymal transition (EMT) in AGS cells through the intrinsic mitochondrial pathway, thereby enhancing the anticancer effect of oxaliplatin. Crucially, 2QC-h exhibited selective cytotoxicity towards gastrointestinal system cancer cells (AGS cells: 4.85 ± 0.22 µg/mL and 2.66 ± 0.58 µg/mL, HCT116 cells: 6.61 ± 0.29 µg/mL and 2.39 ± 0.57 µg/mL, and HepG2 cells: 9.14 ± 0.49 µg/mL and 6.15 ± 0.27 µg/mL for 24 h and 48 h, respectively) and minimal morphological effects on healthy HUVEC cells. Computational studies, including DFT analysis, MEP, RDG, ELF, LOL, and ALIE, provided comprehensive insights into the electronic structure, reactivity, and non-covalent interactions, elucidating the structure-activity relationships (SAR). Molecular docking simulations identified VEGFR-2 and EGFR as the preferential targets for these derivatives, with nanomolar binding affinities, which correlated strongly with experimental cytotoxic potencies. ADME highlighted favorable drug-likeness properties while identifying areas for further optimization. Overall, this research establishes quinoline-chalcone hybrids as promising multi-target therapeutic agents with significant potential for developing novel antimicrobial and anticancer drugs.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"120 ","pages":"Article 108675"},"PeriodicalIF":3.1,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145044462","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":"Diagnosis of leukemia using microarray analysis based on Hidden Markov Model and Random Convolutional Kernel Transform","authors":"Sareh Baqeri Matak ,&nbsp;Elham Askari ,&nbsp;Sara Motamed","doi":"10.1016/j.compbiolchem.2025.108676","DOIUrl":"10.1016/j.compbiolchem.2025.108676","url":null,"abstract":"<div><h3>Introduction</h3><div>Leukemia is one of the most prevalent cancers worldwide, and early detection is critical for effective treatment. Microarray data is a key tool in this process, given the vast number of genes involved, which makes the analysis complex and time-consuming. Identifying relevant genes is a crucial step in disease diagnosis.</div></div><div><h3>Material and methods</h3><div>This study aims to improve the diagnostic accuracy of various leukemia types by using microarray data in combination with advanced deep learning techniques. The proposed model begins with selecting essential features and sequences relevant to diagnosis. These data sequences are processed using a Generative Adversarial Network (GAN) with a U-Net architecture to generate synthetic data. Both the synthetic and original data are then labeled for analysis. Feature ranking is conducted using a Hidden Markov Model (HMM), followed by classification using the Random Convolutional Kernel Transformation (ROCKET) approach. This process ultimately predicts five leukemia categories within the sample.</div></div><div><h3>Results</h3><div>The results demonstrate that the proposed model achieves a high classification accuracy of 99.26 %, outperforming existing methods.</div></div><div><h3>Conclusion</h3><div>This research highlights the importance of leveraging DNA alterations associated with genetic mutations to improve leukemia diagnostics, emphasizing the potential for early detection and intervention. In simpler terms, identifying DNA modifications across the genome can help predict an individual's likelihood of developing leukemia. Detecting these changes can significantly aid in diagnosis.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"120 ","pages":"Article 108676"},"PeriodicalIF":3.1,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145044463","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}