Computational Biology and Chemistry最新文献

{"title":"DeeppestNet: An end-to-end framework for high-performance crop pest recognition","authors":"K.S. Guruprakash ,&nbsp;P. Siva Karthik ,&nbsp;A. Ramachandran ,&nbsp;K. Gayathri","doi":"10.1016/j.compbiolchem.2026.108916","DOIUrl":"10.1016/j.compbiolchem.2026.108916","url":null,"abstract":"<div><div>Accurate and efficient crop-pest identification is essential for sustainable agriculture. However, noisy background regions make it difficult to accurately identify crop pests since they obstruct the feature extraction process. Furthermore, pest recognition remains challenging due to limited data and algorithmic complexity. DeeppestNet, a graph pyramid attention-based Bidirectional Long Short-Term Memory (GPA-BiLSTM) model, is proposed as a solution to this problem. In order to improve the recognition process, the Contrast adaptive limited histogram equalization (CLAHE) approach is first used to increase the image quality. Rich feature maps of fine-grained feature regions are intended to be provided by the adaptive pyramid attention module with a cross stage partial (AP-CSP) backbone network. In order to acquire multi-scale spatial features and improve recognition skills through graphical relations, a multi-level pyramid structure is also provided. Graph-based BiLSTM (G-BiLSTM) is used for the final classification, and the Grey Wolf-Salp Swarm Optimization (GW-SSO) technique is used to improve the accuracy. Robust multi-dimensional structural features are extracted with spatial and temporal dependencies when combining G-BiLSTM with a CNN backbone. Additionally, the integration of GW and SSO improves the performance by assuring high precision, fast convergence and balance exploration, exploitation strategies are achieved. The IP-102 dataset is used to assess the proposed pest detection method utilizing evaluation measures like f-measure, recall, precision, and so on. DeeppestNet has achieved 4.6 % higher accuracy than EfficientNet. The experimental outcomes demonstrate that the proposed method performs better than the greatest advanced Deep Learning (DL) algorithms. The proposed method is accurate, efficient, and computationally efficient in comparison to other methods.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108916"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074197","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":"R-loop-driven molecular subtypes reveal prognostic and immunogenomic features in uterine corpus endometrial carcinoma","authors":"Hui Liu,&nbsp;Yuanting Lai","doi":"10.1016/j.compbiolchem.2026.108947","DOIUrl":"10.1016/j.compbiolchem.2026.108947","url":null,"abstract":"<div><h3>Background</h3><div>R-loops are three-stranded nucleic acid structures implicated in genome instability and cancer progression. However, the prognostic significance and mechanistic role of R-loops in uterine corpus endometrial carcinoma (UCEC) remain poorly understood.</div></div><div><h3>Methods</h3><div>Transcriptomic, clinical, mutational, and spatial data for UCEC were obtained from The Cancer Genome Atlas (TCGA) and public databases. Multiomics analyses, including prognostic modeling, survival analyses, differential expression analyses, copy number variation (CNV) profiling, somatic mutation comparisons, single-cell transcriptomics, spatial transcriptomics, and immune-related pathway exploration, were conducted to elucidate the biological implications of R-loop genes, matrix-specific CSDE1, and the associated SPP1 pathway. In vivo and in vitro functional experiments were conducted to evaluate the role of CSDE1 in UCEC.</div></div><div><h3>Results</h3><div>Elevated R-loop activity was associated with advanced clinical stage, high tumor grade, and poor survival outcomes in patients with UCEC. A robust prognostic model based on R-loop genes achieved high predictive accuracy across multiple datasets. Low-risk patients had higher tumor mutation burdens and distinct mutational profiles, whereas high-risk patients had more chromosomal instability and more CNV events. CSDE1 emerged as the top predictive gene, displaying fibroblast-specific expression and copy number-driven upregulation. Single-cell and spatial transcriptomics revealed that CSDE1⁺ fibroblasts actively communicated with immune cells via the SPP1 pathway and were spatially enriched in malignant, fibroblast-dense regions. High CSDE1 expression correlated with the activation of oncogenic pathways and the suppression of multiple steps in the cancer–immunity cycle. Furthermore, CSDE1 promoted the proliferation and migration of UCEC cells in vitro and in vivo by reducing R-loop accumulation and DNA damage.</div></div><div><h3>Conclusion</h3><div>R-loop activity and CSDE1 expression define a clinically relevant molecular program in UCEC that integrates genomic instability, immunosuppression, and stromal remodeling. These findings provide a basis for stratified prognosis and potential therapeutic targeting in endometrial cancer, suggesting that CSDE1 may be a promising new therapeutic target for the treatment of UCEC in the future.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108947"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146185183","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":"MYB: A potential therapeutic target in triple-negative breast cancer based on the PI3K/AKT signaling pathway","authors":"Ziyu Zhuang,&nbsp;Jiayi Hu,&nbsp;Hongbo Yu,&nbsp;Yu Xie","doi":"10.1016/j.compbiolchem.2026.108938","DOIUrl":"10.1016/j.compbiolchem.2026.108938","url":null,"abstract":"<div><h3>Background</h3><div>Compared to non-triple-negative breast cancer (Non-TNBC), triple-negative breast cancer (TNBC) exhibits significantly poorer prognosis. Previous research has confirmed that the PI3K/AKT pathway is closely associated with prognosis in breast cancer patients. Yet, it remains unclear whether this pathway is implicated in the prognostic differences observed between TNBC and Non-TNBC.</div></div><div><h3>Methods</h3><div>After downloading raw transcriptomic datasets from the GEO database and removing batch effects, we performed an integrated analysis to delineate how key genes drive the poor prognosis of TNBC. Functional enrichment, machine-learning-based feature selection, immune-cell infiltration profiling, drug-sensitivity screening, single-cell RNA sequencing and spatial transcriptomics were successively applied. Molecular-docking simulations were finally conducted to evaluate the binding affinity of MYB toward bioactive compounds derived from the Taohong Siwu Decoction.</div></div><div><h3>Results</h3><div>Across 113 algorithm combinations, MYB plays the most critical role in distinguishing TNBC from Non-TNBC. The constructed prognostic model confirms the significant association between MYB expression and patient outcomes. Immune cell infiltration, drug sensitivity, single-cell data analysis and spatial transcriptome revealed the specific mechanisms through which MYB influences patient prognosis. Molecular docking experiments demonstrate strong binding between key components in Taohong Siwu Decoction and MYB.</div></div><div><h3>Conclusion</h3><div>Based on multi-omics analysis, our findings indicate that the PI3K/AKT pathway is a key factor contributing to the significant prognostic disparity between TNBC and Non-TNBC. Within this pathway, the MYB gene emerges as a potential therapeutic target. This discovery provides a potential basis for future research exploring MYB as a therapeutic target for TNBC patients.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108938"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146159607","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":"Predicting curcumin release kinetics from nanocarriers using a physics-informed machine learning framework","authors":"Sonia Fathi-karkan ,&nbsp;Abbas Rahdar","doi":"10.1016/j.compbiolchem.2026.108907","DOIUrl":"10.1016/j.compbiolchem.2026.108907","url":null,"abstract":"<div><h3>Background</h3><div>Curcumin nanoformulations display highly heterogeneous release behaviors, yet the field lacks an integrated framework capable of predicting kinetics across diverse material classes. However, the diffusion parameters governing these systems have remained previously unresolved due to inconsistent experimental conditions and limited datasets.</div></div><div><h3>Aim</h3><div>Here we establish a physics-informed machine-learning framework that predicts curcumin release kinetics with unprecedented physical consistency across heterogeneous nanocarriers.</div></div><div><h3>Methods</h3><div>A curated dataset of 75 formulations was encoded using 13 physicochemical descriptors, and release kinetics were parameterized using a two-component diffusion model. A Physics-Informed Neural Network incorporating explicit monotonicity and non-negativity constraints was trained and benchmarked against Random Forest, XGBoost, and a multilayer neural network. External validation used 31 independent formulations.</div></div><div><h3>Results</h3><div>The model demonstrated 0.92 R², 2.15 MSE, and 98 % physical consistency, exceeding baseline methods by up to 1.6-fold. External validation achieved 0.885 R² and mean absolute errors &lt; 0.08 across release-time distributions. Design-space mapping uncovered previously inaccessible parameter regions associated with rapid, balanced, and sustained-release profiles. Application-specific performance analyses showed 0.87–0.91 R², mean absolute error 2.10–4.30 h, and physical consistency 94–98 %.</div></div><div><h3>Conclusions</h3><div>This framework resolves key kinetic parameters across diverse nanocarriers with high fidelity and provides a new foundation for data-driven formulation engineering. The approach enables predictive optimization of curcumin delivery systems and opens the door to automated design of controlled-release nanomedicines.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108907"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146034878","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":"Multiscale computational modeling integrated with in vitro evaluation of green-synthesized 2,3-dihydroquinazolin-4(1 H)-ones targeting U87 glioblastoma cells","authors":"Sathiaseelan Perumal ,&nbsp;Perumal Muthuraja ,&nbsp;Venkatesan Muthukumar ,&nbsp;Paramasivam Manisankar ,&nbsp;Viswanathan Subramanian","doi":"10.1016/j.compbiolchem.2026.108929","DOIUrl":"10.1016/j.compbiolchem.2026.108929","url":null,"abstract":"<div><div>Glioblastoma multiforme (GBM) is a highly aggressive brain tumour with limited therapeutic options, largely owing to the poor blood–brain barrier (BBB) permeability of current drugs. Quinazolinone derivatives represent an important class of heterocycles with diverse pharmacological potential; however, their activity against U87 glioblastoma cells has not been previously reported. In this study, a series of 2,3-dihydroquinazolin-4(1 H)-one derivatives (DHQs) were synthesised through a sustainable PEG-400-mediated multicomponent protocol performed in a sealed tube, providing an efficient and environmentally benign route to access this pharmacologically important scaffold. To identify potential glioblastoma inhibitors, a multiscale computational pipeline integrating DFT descriptors, ADME screening, molecular docking, molecular dynamics (MD) simulations, MM/GBSA, principal component analysis (PCA), and free energy landscape (FEL) calculations was employed. Among the synthesised molecules, compound <strong>1h</strong> emerged as the most promising candidate, exhibiting the highest binding affinity towards EGFR (−9.11 kcal mol⁻¹) and favourable CNS-relevant physicochemical properties. MD simulations confirmed the structural stability of the <strong>1h–3POZ</strong> complex for over 100 ns, as supported by low RMSD values, restricted residue fluctuations, and a stable free-energy profile. Experimental validation using the MTT assay on U87 glioblastoma cells demonstrated that compound <strong>1h</strong> exhibited potent cytotoxicity (IC₅₀ = 16.57 ± 0.90μM), significantly outperforming temozolomide. Overall, this study presents the first integrated green-synthetic and computational-experimental evaluation of DHQs against U87 cells, highlighting compound <strong>1h</strong> as a promising lead for glioblastoma drug discovery.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108929"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074081","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":"Dual inhibition of AChE and GSK-3β by flavonoids of Bergenia ciliata: Molecular dynamics insights into anti-Alzheimer’s activity","authors":"James H. Zothantluanga ,&nbsp;Bharath Kumar Chagaleti ,&nbsp;Dhritiman Roy ,&nbsp;Mohnad Abdalla ,&nbsp;Amr Ahmed El-Arabey ,&nbsp;Nada F. Alahmady ,&nbsp;Niraj Kumar Jha","doi":"10.1016/j.compbiolchem.2026.108908","DOIUrl":"10.1016/j.compbiolchem.2026.108908","url":null,"abstract":"<div><div>Alzheimer's disease (AD) is one of the most prevalent neurodegenerative disorders and is also responsible for more than half of all dementia cases. In our ongoing efforts to identify promising phytocompounds as potential modulators of AD-related molecular targets, we studied 53 phytocompounds from <em>Bergenia ciliata</em>, a medicinal plant known for its <em>in vivo</em> anti-Alzheimer activity. Acetylcholinesterase (AChE), GSK-3β, and β-site amyloid precursor protein cleaving enzyme (BACE1) were the target proteins. Molecular docking and 100 ns molecular dynamics (MD) simulations revealed that 3-O-galloylcatechin and 3-O-galloylepicatechin showed favorable interactions with AChE and GSK-3β, as they were able to outperform the positive controls in all of the studied parameters. However, the MM-GBSA binding free energy calculations revealed that only 3-O-galloylepicatechin, but not 3-O-galloylcatechin, outperformed the positive control of GSK-3β. Density functional theory (DFT) studies revealed that 3-O-galloylcatechin and 3-O-galloylepicatechin were stable and chemically reactive at the active sites of AChE and GSK-3β. The <em>in-silico</em> findings suggest that the observed <em>in-vivo</em> anti-Alzheimer activity of <em>B. ciliata</em> may be partly associated with the favorable molecular interactions of 3-O-galloylcatechin and 3-O-galloylepicatechin with AChE and GSK-3β. The current findings highlight the structural and mechanistic relevance of <em>B. ciliata</em> phytocompounds in modulating AD–associated targets. Based on the current findings, medicinal plants that contain 3-O-galloylcatechin and 3-O-galloylepicatechin may also be screened for their interactions with AD–related molecular targets.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108908"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145974172","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 first passage time study of bacterial eradication under the influence of antibacterial agents","authors":"Nafisa Siddiqui ,&nbsp;Shivangi Chourasia ,&nbsp;Aishani Ghosal ,&nbsp;Rati Sharma","doi":"10.1016/j.compbiolchem.2026.108889","DOIUrl":"10.1016/j.compbiolchem.2026.108889","url":null,"abstract":"<div><div>Studies concerning bacterial eradication have become important in the light of growing antibiotic resistance observed around the world. Hence, it is important to develop and optimize new strategies and discover alternatives for treatment against drug resistant bacteria. Considering this, we apply the method of first passage time (FPT) to theoretically scrutinize the bacterial population dynamics in the presence of antibacterial agents. First, we demonstrate that the extinction time for bacterial population in the presence of antibiotics can be lowered by reducing the growth rate of bacteria. Next, we examine the antibacterial role of silver nano-particles (AgNPs) against the pathogenic bacteria <em>Escherichia coli</em>. We find that in comparison to antibiotics, the same concentration of AgNPs require more time for complete clearance of the bacterial population. Therefore, in order to reduce this extinction time, we investigate the combined effect of AgNP and Ampicillin. Our results suggest that AgNP combined with Ampicillin can be a substitute in tackling resistance against <em>E. coli</em>.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108889"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145974165","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 network pharmacology and bioassays to unveil the antidiabetic mechanism of Mukia maderasapatana-mediated selenium nanoparticles","authors":"R. Sowmya,&nbsp;S. Karthick Raja Namasivayam,&nbsp;G.S. Amrish Varshan,&nbsp;Krithika Shree Sivasuriyan","doi":"10.1016/j.compbiolchem.2026.108901","DOIUrl":"10.1016/j.compbiolchem.2026.108901","url":null,"abstract":"<div><div>Diabetes mellitus remains a major global health challenge, necessitating the development of alternative therapeutic strategies with improved efficacy and safety. The present proof-of-concept study reports, a comparative evaluation of <em>Mukia maderasapatana</em>-mediated biogenic selenium nanoparticles (SeNPs), chemically synthesized SeNPs, and a chitosan–starch–selenium nanocomposite (SeNC) for antidiabetic potential. Biogenic SeNPs were successfully synthesized and stabilized by phytochemicals from <em>M. maderasapatana</em>, resulting in smaller particle size and greater colloidal stability compared to chemogenic formulations. In vitro assays demonstrated that biogenic SeNPs exhibited markedly greater inhibitory activity against α-amylase (IC₅₀: 60 µg/mL) and α-glucosidase (IC₅₀: 80 µg/mL) compared to chemogenic SeNPs and SeNC (IC₅₀: 120 µg/mL for both enzymes). Strong antioxidant activity was also observed, with biogenic SeNPs showing the highest DPPH and ABTS radical scavenging effects (up to 87 % inhibition at 140 µg/mL). Molecular docking identified chitosan, squalene, and dihydroxanthin as the most potent ligands, displaying high binding affinities across key diabetic targets, including α-amylase (−11.0 kcal/mol), α-glucosidase (−12.2 kcal/mol), glycogen phosphorylase (−11.7 kcal/mol), and PTP1B (−12.1 kcal/mol). Organ-specific docking further confirmed favorable safety profiles with strong yet non-toxic binding to CYP3A4, HSA, CA-II, and PPAR-γ. Collectively, these findings highlight Mukia-derived biogenic SeNPs as a promising therapeutic candidate with enhanced enzyme inhibitory, antioxidant, and molecular-targeting capabilities, establishing a foundational proof-of-concept for their development as antidiabetic nanomedicine.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108901"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145974170","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":"Evaluation of lawsone as a potential inhibitor of Staphylococcus aureus efflux pump mediated drugs resistance: An in-vitro and in-silico study","authors":"Bochra Kouidhi ,&nbsp;Ehab Mostafa Mohamed Ali ,&nbsp;Tarek Zmantar ,&nbsp;Sihem Bayar ,&nbsp;Abdelsattar M. Omar ,&nbsp;Salman Bakr Hosawi ,&nbsp;Hisham N. Altayeb ,&nbsp;Imran Kazmi ,&nbsp;Mustafa Zeyadi ,&nbsp;Kamel Chaieb","doi":"10.1016/j.compbiolchem.2026.108922","DOIUrl":"10.1016/j.compbiolchem.2026.108922","url":null,"abstract":"<div><div><em>Staphylococcus aureus</em> (<em>S. aureus</em>) is a causative agent of a wide range of infections such as staphylococcal scalded skin syndrome, toxic shock syndrome, necrotizing pneumonia, endocarditis, and osteomyelitis, posing a significant challenge in clinical management. This study explores the antibacterial potential of lawsone on <em>S. aureus</em> using experimental and computational methods. The minimum inhibitory concentration (MIC) of lawsone (alone and in combination with erythromycin, tetracycline, norfloxacin and ciprofloxacin) on 8 clinical multi-drug resistant <em>S. aureus</em> was evaluated in vitro. The ability of lawsone to modulate antibiotic susceptibility was also determined. Molecular docking was carried out to investigate the binding affinities between lawsone and five efflux pumps (EPP) (NorA, NorB, MsrA, SepA, and MefA) and a ribosomal protection protein (TetM) implicated in <em>S. aureus</em> drug resistance. Furthermore, molecular dynamics simulations (MDS) were performed to assess the stability of the protein-ligand complexes throughout the 100 ns simulation period. In addition, the physicochemical properties, drug-likeness, and toxicity of the lawsone were predicted. Lawsone showed synergistic effects with erythromycin, tetracycline, norfloxacin, and ciprofloxacin, as indicated by the modulation factors (MF) ranging from 2 to &gt; 16. Notably, the strain SA383 showed MF values of &gt; 8 for two antibiotics (ciprofloxacin and erythromycin), and &gt; 16 for norfloxacin. Molecular docking revealed strong binding affinities between lawsone and the evaluated <em>S. aureus</em> drug resistant proteins. The MDS confirmed the stability of the lawsone-protein complexes over 100 ns simulation period, supporting its potential as an efflux pump inhibitor (EPI). ADMET profiling of lawsone demonstrated favorable drug-likeness, pharmacokinetics, and low toxicity. Lawsone does not inhibit major cytochrome P450 enzymes. Toxicity predictions also showed no significant risks of carcinogenicity or immunotoxicity, but potential mutagenicity and nephrotoxicity which require further study. Lawsone also exhibits no predicted activity on androgen receptors, aromatase, or GABA receptors, indicating minimal hormonal disruption. These findings highlight lawsone as a promising candidate for the development of a new EPI candidate, particularly against antibiotic-resistant <em>S. aureus</em>.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108922"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146069498","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":"Developing a trustworthy and explainable framework for classifying skin lesions through transfer learning and attention mechanisms","authors":"Ali M. Duhaim ,&nbsp;Noor S. Baqer ,&nbsp;Mohammed A. Fadhel","doi":"10.1016/j.compbiolchem.2026.108914","DOIUrl":"10.1016/j.compbiolchem.2026.108914","url":null,"abstract":"<div><div>Detection of high precision skin lesions, especially melanoma, are still a major challenge in medical imagination due to their close visual equality and lack of reliably labeled datasets. In this study, we introduce a deep learning sketch aimed at balancing clinical accuracy with clinical interpretation. The workflow starts with a series of preprosaresing steps: removing hair from dermoscopic images, correction with the cow and separating the wound area using a U-NET segmentation model. On top of that, a skilled-B4 network was properly set and increased with a competition block meditation module (CBAM) to focus the model on clinically important properties. In order to further strengthen performance, this spine was integrated into a dress with its –201 and Renex −50, where predictions are added through a soft poll. The model output was interpreted by the use of character comb and lime, which provides visual clarification of areas affecting the final decision. The training was held on him10000 datasets and valid against ISIC-2019 and pH, which demonstrated the contour's ability to generalize in different wound categories. The model reached 98.95 % accuracy, 98.7 % balanced accuracy and 99.6 % sensitivity to melanoma, improvement in recent benchmarks. By combining efficiency, interpretation and design of privacy and inconvenience, the framework gives a realistic step towards safe and reliable integration of AI units into dermatology practice.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"122 ","pages":"Article 108914"},"PeriodicalIF":3.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146035277","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}