Pub Date : 2026-03-01Epub Date: 2026-01-30DOI: 10.1016/j.compbiomed.2026.111509
Yusuf Şeflekçi , Ahmet Efe Köseoğlu , Rabia Erdoğdu Sever , Elif Naz Işıksal , Filiz Özgül , Abdulilah Ece
Cat scratch disease (CSD), primarily caused by Bartonella henselae and Bartonella clarridgeiae, presents a global zoonotic concern, particularly in immunocompromised individuals. Conventional antibiotics offer limited protection, necessitating novel preventive strategies. Also, CSD is still one of the most prevalent infections brought on by Bartonella genus. The current study aimed at developing a multi-epitope peptide vaccine by targeting conserved antigenic proteins (Pap31, Omp43, and Omp89) from two Bartonella species utilizing immunoinformatics techniques. Comprehensive immunoinformatics analyses including antigenicity, allergenicity, solubility, and post-translational modification assessments were conducted. The selected epitopes with high antigenicity and non-allergenic, non-toxic properties were fused using appropriate linkers and an adjuvant. The vaccine construct was modeled in 3D, refined, and validated via Ramachandran and ERRAT analyses. Molecular docking followed by molecular dynamics simulations demonstrated strong interaction and structural stability with TLR2 receptor in a mimicked biological environment. Moreover, immune simulations showed strong stimulation of B and T cell responses, elevated IgM and IgG levels, and increased IFN-γ production. These preliminary in silico findings suggest a promising multi-epitope peptide vaccine candidate with a cross-protective potential against both B. henselae and B. clarridgeiae pathogens causing the zoonotic cat scratch disease in humans.
{"title":"Design and computational evaluation of a cross-protective multi-epitope vaccine candidate against Bartonella henselae and Bartonella clarridgeiae pathogens causing the zoonotic cat scratch disease in humans","authors":"Yusuf Şeflekçi , Ahmet Efe Köseoğlu , Rabia Erdoğdu Sever , Elif Naz Işıksal , Filiz Özgül , Abdulilah Ece","doi":"10.1016/j.compbiomed.2026.111509","DOIUrl":"10.1016/j.compbiomed.2026.111509","url":null,"abstract":"<div><div>Cat scratch disease (CSD), primarily caused by <em>Bartonella henselae</em> and <em>Bartonella clarridgeiae</em>, presents a global zoonotic concern, particularly in immunocompromised individuals. Conventional antibiotics offer limited protection, necessitating novel preventive strategies. Also, CSD is still one of the most prevalent infections brought on by <em>Bartonella</em> genus. The current study aimed at developing a multi-epitope peptide vaccine by targeting conserved antigenic proteins (Pap31, Omp43, and Omp89) from two <em>Bartonella</em> species utilizing immunoinformatics techniques. Comprehensive immunoinformatics analyses including antigenicity, allergenicity, solubility, and post-translational modification assessments were conducted. The selected epitopes with high antigenicity and non-allergenic, non-toxic properties were fused using appropriate linkers and an adjuvant. The vaccine construct was modeled in 3D, refined, and validated via Ramachandran and ERRAT analyses. Molecular docking followed by molecular dynamics simulations demonstrated strong interaction and structural stability with TLR2 receptor in a mimicked biological environment. Moreover, immune simulations showed strong stimulation of B and T cell responses, elevated IgM and IgG levels, and increased IFN-γ production. These preliminary <em>in silico</em> findings suggest a promising multi-epitope peptide vaccine candidate with a cross-protective potential against both <em>B. henselae</em> and <em>B. clarridgeiae</em> pathogens causing the zoonotic cat scratch disease in humans.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111509"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146071141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-02-11DOI: 10.1016/j.compbiomed.2026.111530
Komal Tanwar , Viney Kumar , Manish Dev Shrimali , Jai Prakash Tripathi
Misinformation about vaccination poses a significant public health threat by reducing vaccination rates and increasing disease burden. Understanding population heterogeneity can aid in recognizing and mitigating the effects of such misinformation, especially when vaccine effectiveness is low. Our research quantifies the impact of misinformation on vaccination uptake and explores its effects in heterogeneous versus homogeneous populations. We employed a dual approach combining compartmental modeling and complex network analysis to examine how various epidemiological parameters influence disease spread and vaccination behaviour. Our results indicate that misinformation significantly lowers vaccination rates, particularly in homogeneous populations, while heterogeneous populations demonstrate greater resilience. Among network topologies, small-world networks achieve higher vaccination rates under varying vaccine efficacies, whereas scale-free networks experience reduced vaccine coverage with higher misinformation amplification. Notably, cumulative infection remains independent of the disease transmission rate when the vaccine is partially effective. In small-world networks, cumulative infection shows high stochasticity across vaccination rates and misinformation parameters, while cumulative vaccination is highest with higher vaccination rates and lower misinformation coefficients. Public health efforts should prioritize addressing misinformation to control disease spread, particularly in homogeneous populations and scale-free networks, where its impact is more severe. Additionally, our model demonstrates strong performance on real-world contact networks, capturing how rapid misinformation spread and limited vaccine efficacy can severely hinder vaccination uptake and accelerate infection rates. Building resilience by fostering diverse community networks and promoting reliable vaccine information can boost vaccination rates. Furthermore, focusing public health campaigns on small-world networks may result in higher vaccine uptake, even when vaccine efficacy varies. These insights can help public health policymakers design effective vaccination strategies that consider population heterogeneity.
{"title":"Unraveling vaccination behavior under misinformation in homogeneous and heterogeneous populations via integrated dynamical and network models","authors":"Komal Tanwar , Viney Kumar , Manish Dev Shrimali , Jai Prakash Tripathi","doi":"10.1016/j.compbiomed.2026.111530","DOIUrl":"10.1016/j.compbiomed.2026.111530","url":null,"abstract":"<div><div>Misinformation about vaccination poses a significant public health threat by reducing vaccination rates and increasing disease burden. Understanding population heterogeneity can aid in recognizing and mitigating the effects of such misinformation, especially when vaccine effectiveness is low. Our research quantifies the impact of misinformation on vaccination uptake and explores its effects in heterogeneous versus homogeneous populations. We employed a dual approach combining compartmental modeling and complex network analysis to examine how various epidemiological parameters influence disease spread and vaccination behaviour. Our results indicate that misinformation significantly lowers vaccination rates, particularly in homogeneous populations, while heterogeneous populations demonstrate greater resilience. Among network topologies, small-world networks achieve higher vaccination rates under varying vaccine efficacies, whereas scale-free networks experience reduced vaccine coverage with higher misinformation amplification. Notably, cumulative infection remains independent of the disease transmission rate when the vaccine is partially effective. In small-world networks, cumulative infection shows high stochasticity across vaccination rates and misinformation parameters, while cumulative vaccination is highest with higher vaccination rates and lower misinformation coefficients. Public health efforts should prioritize addressing misinformation to control disease spread, particularly in homogeneous populations and scale-free networks, where its impact is more severe. Additionally, our model demonstrates strong performance on real-world contact networks, capturing how rapid misinformation spread and limited vaccine efficacy can severely hinder vaccination uptake and accelerate infection rates. Building resilience by fostering diverse community networks and promoting reliable vaccine information can boost vaccination rates. Furthermore, focusing public health campaigns on small-world networks may result in higher vaccine uptake, even when vaccine efficacy varies. These insights can help public health policymakers design effective vaccination strategies that consider population heterogeneity.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111530"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146171749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-02-18DOI: 10.1016/j.compbiomed.2026.111554
Tahereh Zarei , M. Soltani , Cyrus Aghanajafi
This study investigates how cancer-induced alterations affect blood flow properties and the dynamics of a single leukocyte with modified mechanical characteristics, compared to a healthy leukocyte, within a venule. Simulations were performed using the ESPResSo package with the Object-in-Fluid (OIF) module. Cell mechanics were modeled with a spring-network membrane, and fluid–structure interactions were handled via force coupling. Base fluid parameters, including viscosity and hematocrit for breast cancer patients, were taken from experimental and clinical data reported in the literature, and the Navier–Stokes equations were solved under laminar flow at low Reynolds numbers.
The results show that cancer-induced softening increases leukocyte deformability, enlarges the contact region, and enhances adhesion stability, thereby promoting prolonged wall attachment compared to a healthy leukocyte. Conversely, due to greater deformation and reduced cross-stream height, the cancer-affected leukocyte produces a weaker hydrodynamic obstruction, leading to a smaller reduction in peak flow velocity and a milder modification of wall shear rate. These findings indicate that cancer-driven biomechanical changes exert a dual effect on leukocyte–wall interactions, simultaneously facilitating adhesion while diminishing local hemodynamic perturbations. Overall, the study highlights the utility of OIF simulations for investigating leukocyte dynamics and hemodynamics in venules with cancer-affected blood flow.
{"title":"Effect of cancer-induced hemodynamic changes on single leukocyte dynamics in a venule using the Object-in-Fluid (OIF) module","authors":"Tahereh Zarei , M. Soltani , Cyrus Aghanajafi","doi":"10.1016/j.compbiomed.2026.111554","DOIUrl":"10.1016/j.compbiomed.2026.111554","url":null,"abstract":"<div><div>This study investigates how cancer-induced alterations affect blood flow properties and the dynamics of a single leukocyte with modified mechanical characteristics, compared to a healthy leukocyte, within a venule. Simulations were performed using the ESPResSo package with the Object-in-Fluid (OIF) module. Cell mechanics were modeled with a spring-network membrane, and fluid–structure interactions were handled via force coupling. Base fluid parameters, including viscosity and hematocrit for breast cancer patients, were taken from experimental and clinical data reported in the literature, and the Navier–Stokes equations were solved under laminar flow at low Reynolds numbers.</div><div>The results show that cancer-induced softening increases leukocyte deformability, enlarges the contact region, and enhances adhesion stability, thereby promoting prolonged wall attachment compared to a healthy leukocyte. Conversely, due to greater deformation and reduced cross-stream height, the cancer-affected leukocyte produces a weaker hydrodynamic obstruction, leading to a smaller reduction in peak flow velocity and a milder modification of wall shear rate. These findings indicate that cancer-driven biomechanical changes exert a dual effect on leukocyte–wall interactions, simultaneously facilitating adhesion while diminishing local hemodynamic perturbations. Overall, the study highlights the utility of OIF simulations for investigating leukocyte dynamics and hemodynamics in venules with cancer-affected blood flow.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111554"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146225726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-02-07DOI: 10.1016/j.compbiomed.2026.111533
Ammar Ahmed Pallikonda Latheef , Alberto Santamaria-Pang , Craig K. Jones , Haris I. Sair
Brain networks display hierarchical organization, a complexity that is challenging for deep learning models that are often flat classifiers and lack interpretability. To address this, we propose a novel architecture called the Emergent Language Symbolic Autoencoder (ELSA), a hierarchical symbolic autoencoder informed by weak supervision and an Emergent Language framework that learns to represent brain networks as interpretable symbolic sentences while simultaneously reconstructing the original data. Our framework's primary innovations are a set of hierarchically-aware loss functions and their application to modeling resting-state fMRI networks. By combining weak supervision from Independent Component Analysis (ICA) order with novel Progressive, Strict, and Containing Bias losses, we explicitly enforce a coarse-to-fine structure on the emergent language without requiring extensive manual labeling. We evaluated ELSA on data from the publicly available 1000 Functional Connectomes Project. The model generated sentences with clear hierarchical organization, where early symbols corresponded to broad parent networks and later symbols specified finer sub-networks. With the use of our proposed Progressive Strict loss function and containing bias penalty, the model's hierarchical consistency drastically improves compared to baseline, achieving near-perfect consistency at higher ICA orders and 43.5% at the challenging lowest order. The model also produces qualitatively superior visual progressions of the network reconstructions. By replacing opaque feature vectors with an interpretable symbolic language, ELSA provides a transparent, multi-level description of functional brain organization and offers a general framework for studying other hierarchically structured biomedical data.
{"title":"Emergent Language Symbolic Autoencoder (ELSA) with weak supervision to model hierarchical brain networks","authors":"Ammar Ahmed Pallikonda Latheef , Alberto Santamaria-Pang , Craig K. Jones , Haris I. Sair","doi":"10.1016/j.compbiomed.2026.111533","DOIUrl":"10.1016/j.compbiomed.2026.111533","url":null,"abstract":"<div><div>Brain networks display hierarchical organization, a complexity that is challenging for deep learning models that are often flat classifiers and lack interpretability. To address this, we propose a novel architecture called the Emergent Language Symbolic Autoencoder (ELSA), a hierarchical symbolic autoencoder informed by weak supervision and an Emergent Language framework that learns to represent brain networks as interpretable symbolic sentences while simultaneously reconstructing the original data. Our framework's primary innovations are a set of hierarchically-aware loss functions and their application to modeling resting-state fMRI networks. By combining weak supervision from Independent Component Analysis (ICA) order with novel Progressive, Strict, and Containing Bias losses, we explicitly enforce a coarse-to-fine structure on the emergent language without requiring extensive manual labeling. We evaluated ELSA on data from the publicly available 1000 Functional Connectomes Project. The model generated sentences with clear hierarchical organization, where early symbols corresponded to broad parent networks and later symbols specified finer sub-networks. With the use of our proposed Progressive Strict loss function and containing bias penalty, the model's hierarchical consistency drastically improves compared to baseline, achieving near-perfect consistency at higher ICA orders and 43.5% at the challenging lowest order. The model also produces qualitatively superior visual progressions of the network reconstructions. By replacing opaque feature vectors with an interpretable symbolic language, ELSA provides a transparent, multi-level description of functional brain organization and offers a general framework for studying other hierarchically structured biomedical data.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111533"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146141301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-02-02DOI: 10.1016/j.compbiomed.2026.111504
Leonardo Scabini , Kallil M. Zielinski , Marilia Fernandes , Ricardo T. Fares , Lucas C. Ribas , Rosana M. Kolb , Odemir M. Bruno
A complex network method is introduced for high-resolution hyperspectral image analysis and classification. The method is applied to detecting environmental pollution with the Jacaranda caroba plant species. Using confocal laser scanning microscopy (CLSM), detailed spectral data were captured from leaves exposed to different levels of potassium fluoride. Unlike most studies that focus on pixel- or patch-level classification, this work targets the classification of entire high-resolution hyperspectral images, requiring a method capable of capturing global spatial-spectral and texture relationships. Therefore, the limited number of samples and the high dimensionality of the hyperspectral data make conventional deep learning methods unsuitable, motivating the need for a robust and efficient alternative. To address this, we developed the hand-engineered technique named Directed Network of Angular Similarity (DNAS) which models the hyperspectral pixels as complex network vertices connected based on the angular similarity of their spectral bands. This technique allows for effective and efficient feature extraction, computing a compact image representation with only 36 descriptors. Coupled with a supervised classifier, our method achieves a classification accuracy of 92.6% when distinguishing Jacaranda caroba pollutant levels, surpassing both traditional and deep learning approaches. By leveraging the structural, spectral, and texture properties of hyperspectral data, the DNAS method provides a novel framework for detecting pollutant-induced changes in leaf structure, offering significant advantages in resource-limited scenarios. The results demonstrate the potential of Jacaranda caroba leaves, analyzed with this innovative technique, to serve as indicators of air quality.
{"title":"Complex networks for modeling texture and spectral features of hyperspectral images for environmental analysis","authors":"Leonardo Scabini , Kallil M. Zielinski , Marilia Fernandes , Ricardo T. Fares , Lucas C. Ribas , Rosana M. Kolb , Odemir M. Bruno","doi":"10.1016/j.compbiomed.2026.111504","DOIUrl":"10.1016/j.compbiomed.2026.111504","url":null,"abstract":"<div><div>A complex network method is introduced for high-resolution hyperspectral image analysis and classification. The method is applied to detecting environmental pollution with the <em>Jacaranda caroba</em> plant species. Using confocal laser scanning microscopy (CLSM), detailed spectral data were captured from leaves exposed to different levels of potassium fluoride. Unlike most studies that focus on pixel- or patch-level classification, this work targets the classification of entire high-resolution hyperspectral images, requiring a method capable of capturing global spatial-spectral and texture relationships. Therefore, the limited number of samples and the high dimensionality of the hyperspectral data make conventional deep learning methods unsuitable, motivating the need for a robust and efficient alternative. To address this, we developed the hand-engineered technique named Directed Network of Angular Similarity (DNAS) which models the hyperspectral pixels as complex network vertices connected based on the angular similarity of their spectral bands. This technique allows for effective and efficient feature extraction, computing a compact image representation with only 36 descriptors. Coupled with a supervised classifier, our method achieves a classification accuracy of 92.6% when distinguishing <em>Jacaranda caroba</em> pollutant levels, surpassing both traditional and deep learning approaches. By leveraging the structural, spectral, and texture properties of hyperspectral data, the DNAS method provides a novel framework for detecting pollutant-induced changes in leaf structure, offering significant advantages in resource-limited scenarios. The results demonstrate the potential of <em>Jacaranda caroba</em> leaves, analyzed with this innovative technique, to serve as indicators of air quality.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111504"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146112360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-02-10DOI: 10.1016/j.compbiomed.2026.111549
Krish Chaudhary , Narendra N. Khanna , Pankaj K. Jain , Rajesh Singh , Laura E. Mantella , Amer M. Johri , Gavino Faa , Mohamed Abbas , John R. Laird , Mustafa Al-Maini , Esma R. Isenovic , Luca Saba , Jasjit S. Suri
Background and motivation
Classifying diseases like heart problems using gene expression data depends on selecting important genes. Traditional machine learning (ML) often uses simple feature selection (FS) techniques, which can limit accuracy. In our research, we combine deep learning (DL) with gene-focused methods like differential expression analysis (DEA) to improve classification performance significantly.
Method
We thoroughly and rigorously evaluated ML and DL classifiers using two gene expression datasets (GSE36961 and GSE57345). We tested four hypotheses using feature selection methods such as chi-square, DEA. We applied principal component analysis (PCA) to reduce the number of features. To ensure the reliability of our findings, we applied k-fold cross-validation, hyperparameter tuning, block effect analysis, and assessed data augmentation and generalization. Statistical tests, including paired t-test and Mann–Whitney U test, and Wilcoxon signed-rank test were performed to compare model performances rigorously.
Results
Our experiments on two gene expression datasets (GSE36961, GSE57345) not only confirmed all four hypotheses (H1, H2, H3, and H4) but also revealed significant performance improvements. For H1, without FS, DL outperformed ML models by a substantial margin. For H2, with FS, DL outperformed ML models by a significant percentage. In H3, ML with FS improved over ML without FS by a considerable margin. For H4, DL with FS outperformed DL without FS by a noticeable percentage. Among FS methods, DEA consistently yielded the best results for both ML and DL, further underlining the significance of our findings.
Conclusions
Combining DL with biological feature selection, especially DEA, improves gene expression classification and enables gene ranking and biomarker identification. This integrative approach balances modeling power with biological relevance, providing a reproducible framework for robust biomarker-based classification.
{"title":"Identification of high-risk genes and classification of acute myocardial infarction patients utilizing deep learning in a restricted cohort","authors":"Krish Chaudhary , Narendra N. Khanna , Pankaj K. Jain , Rajesh Singh , Laura E. Mantella , Amer M. Johri , Gavino Faa , Mohamed Abbas , John R. Laird , Mustafa Al-Maini , Esma R. Isenovic , Luca Saba , Jasjit S. Suri","doi":"10.1016/j.compbiomed.2026.111549","DOIUrl":"10.1016/j.compbiomed.2026.111549","url":null,"abstract":"<div><h3>Background and motivation</h3><div>Classifying diseases like heart problems using gene expression data depends on selecting important genes. Traditional machine learning (ML) often uses simple feature selection (FS) techniques, which can limit accuracy. In our research, we combine deep learning (DL) with gene-focused methods like differential expression analysis (DEA) to improve classification performance significantly.</div></div><div><h3>Method</h3><div>We thoroughly and rigorously evaluated ML and DL classifiers using two gene expression datasets (GSE36961 and GSE57345). We tested four hypotheses using feature selection methods such as chi-square, DEA. We applied principal component analysis (PCA) to reduce the number of features. To ensure the reliability of our findings, we applied k-fold cross-validation, hyperparameter tuning, block effect analysis, and assessed data augmentation and generalization. Statistical tests, including paired <em>t</em>-test and Mann–Whitney <em>U</em> test, and Wilcoxon signed-rank test were performed to compare model performances rigorously.</div></div><div><h3>Results</h3><div>Our experiments on two gene expression datasets (GSE36961, GSE57345) not only confirmed all four hypotheses (H1, H2, H3, and H4) but also revealed significant performance improvements. For H1, without FS, DL outperformed ML models by a substantial margin. For H2, with FS, DL outperformed ML models by a significant percentage. In H3, ML with FS improved over ML without FS by a considerable margin. For H4, DL with FS outperformed DL without FS by a noticeable percentage. Among FS methods, DEA consistently yielded the best results for both ML and DL, further underlining the significance of our findings.</div></div><div><h3>Conclusions</h3><div>Combining DL with biological feature selection, especially DEA, improves gene expression classification and enables gene ranking and biomarker identification. This integrative approach balances modeling power with biological relevance, providing a reproducible framework for robust biomarker-based classification.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111549"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146164633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-01-31DOI: 10.1016/j.compbiomed.2026.111520
Mahmoud A. Senousy , Olfat G. Shaker , Raghda Abdel-Sattar , Abdullah A. Gibriel
Early diagnosis, tumor staging, and prognosis remain formidable challenges in colorectal cancer (CRC). N6-methyladenosine (m6A) RNA methylation-related genes have evolved as crucial epitranscriptomic factors in CRC pathogenesis; however, their landscape of clinical applications is unexplored. We investigated the circulating expression signature of m6A regulators and their downstream target SOX2, their predictive potential for early CRC diagnosis, and correlations with tumor-related data. The study included overall 300 subjects divided into test and validation sets. Most serum m6A regulators showed upregulation in adenomatous polyps (AP) and CRC patients versus healthy controls in the test set. Serum METTL3, WTAP, and YTHDF1 mRNA expression was higher; METTL14 was not significantly altered, while YTHDC2 and ALKBH5 expression was lower in CRC than AP patients. The downstream m6A target SOX2 mRNA and protein levels were concomitantly upregulated in CRC, but not AP patients. A panel of m6A-related genes (WTAP, YTHDF1, YTHDC2, and SOX2 mRNA and protein levels) showed excellent accuracy (AUC = 0.991) that surpassed individual markers in predicting CRC among non-CRC counterparts (healthy controls + AP) in the test set. Using these markers, we developed a simple prediction nomogram for easier application. The diagnostic accuracy of the predictive model and the nomogram was confirmed in the validation set. Among CRC patients, METTL14 expression and SOX2 protein were positively correlated with CEA. YTHDC2 was correlated with tumor location. Negative correlations were recorded between METTL14 and lymph node (LN) metastasis and ALKBH5 with tumor stage, LN, and distant metastasis. Conclusively, serum m6A-related genes are differently expressed in AP and CRC and are promising biomarkers for early CRC detection. We developed a novel predictive panel of serum m6A-related genes that could empower CRC screening and early diagnosis. METTL14, ALKBH5, YTHDC2 expression, and SOX2 protein correlate with tumor-related data and are candidates for CRC prognosis.
{"title":"N6-methyladenosine RNA methylation regulators and their target SOX2 as circulating biomarkers of colorectal cancer: Insights towards early diagnosis and staging","authors":"Mahmoud A. Senousy , Olfat G. Shaker , Raghda Abdel-Sattar , Abdullah A. Gibriel","doi":"10.1016/j.compbiomed.2026.111520","DOIUrl":"10.1016/j.compbiomed.2026.111520","url":null,"abstract":"<div><div>Early diagnosis, tumor staging, and prognosis remain formidable challenges in colorectal cancer (CRC). N<sup>6</sup>-methyladenosine (m<sup>6</sup>A) RNA methylation-related genes have evolved as crucial epitranscriptomic factors in CRC pathogenesis; however, their landscape of clinical applications is unexplored. We investigated the circulating expression signature of m<sup>6</sup>A regulators and their downstream target SOX2, their predictive potential for early CRC diagnosis, and correlations with tumor-related data. The study included overall 300 subjects divided into test and validation sets. Most serum m<sup>6</sup>A regulators showed upregulation in adenomatous polyps (AP) and CRC patients versus healthy controls in the test set. Serum METTL3, WTAP, and YTHDF1 mRNA expression was higher; METTL14 was not significantly altered, while YTHDC2 and ALKBH5 expression was lower in CRC than AP patients. The downstream m<sup>6</sup>A target SOX2 mRNA and protein levels were concomitantly upregulated in CRC, but not AP patients. A panel of m<sup>6</sup>A-related genes (WTAP, YTHDF1, YTHDC2, and SOX2 mRNA and protein levels) showed excellent accuracy (AUC = 0.991) that surpassed individual markers in predicting CRC among non-CRC counterparts (healthy controls + AP) in the test set. Using these markers, we developed a simple prediction nomogram for easier application. The diagnostic accuracy of the predictive model and the nomogram was confirmed in the validation set. Among CRC patients, METTL14 expression and SOX2 protein were positively correlated with CEA. YTHDC2 was correlated with tumor location. Negative correlations were recorded between METTL14 and lymph node (LN) metastasis and ALKBH5 with tumor stage, LN, and distant metastasis. Conclusively, serum m<sup>6</sup>A-related genes are differently expressed in AP and CRC and are promising biomarkers for early CRC detection. We developed a novel predictive panel of serum m<sup>6</sup>A-related genes that could empower CRC screening and early diagnosis. METTL14, ALKBH5, YTHDC2 expression, and SOX2 protein correlate with tumor-related data and are candidates for CRC prognosis.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111520"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146099554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We propose a novel medical image classification method that integrates dual-model weight selection with self-knowledge distillation (SKD). In real-world medical settings, deploying large-scale models is often limited by computational resource constraints, which pose significant challenges for their practical implementation. Thus, developing lightweight models that achieve comparable performance to large-scale models while maintaining computational efficiency is crucial. To address this, we employ a dual-model weight selection strategy that initializes two lightweight models with weights derived from a large pretrained model, enabling effective knowledge transfer. Next, SKD is applied to these selected models, allowing the use of a broad range of initial weight configurations without imposing additional excessive computational cost, followed by fine-tuning for the target classification tasks. By combining dual-model weight selection with self-knowledge distillation, our method overcomes the limitations of conventional approaches, which often fail to retain critical information in compact models. Extensive experiments on publicly available datasets—chest X-ray images, lung computed tomography scans, and brain magnetic resonance imaging scans—demonstrate the superior performance and robustness of our approach compared to existing methods.
{"title":"Dual-model weight selection and self-knowledge distillation for medical image classification","authors":"Ayaka Tsutsumi , Guang Li , Ren Togo , Takahiro Ogawa , Satoshi Kondo , Miki Haseyama","doi":"10.1016/j.compbiomed.2026.111510","DOIUrl":"10.1016/j.compbiomed.2026.111510","url":null,"abstract":"<div><div>We propose a novel medical image classification method that integrates dual-model weight selection with self-knowledge distillation (SKD). In real-world medical settings, deploying large-scale models is often limited by computational resource constraints, which pose significant challenges for their practical implementation. Thus, developing lightweight models that achieve comparable performance to large-scale models while maintaining computational efficiency is crucial. To address this, we employ a dual-model weight selection strategy that initializes two lightweight models with weights derived from a large pretrained model, enabling effective knowledge transfer. Next, SKD is applied to these selected models, allowing the use of a broad range of initial weight configurations without imposing additional excessive computational cost, followed by fine-tuning for the target classification tasks. By combining dual-model weight selection with self-knowledge distillation, our method overcomes the limitations of conventional approaches, which often fail to retain critical information in compact models. Extensive experiments on publicly available datasets—chest X-ray images, lung computed tomography scans, and brain magnetic resonance imaging scans—demonstrate the superior performance and robustness of our approach compared to existing methods.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111510"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146118234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-02-16DOI: 10.1016/j.compbiomed.2026.111470
Zaibunnisa L.H. Malik, Pooja Raundale
Motor impairments affect approximately 86.9% of children with Autism Spectrum Disorder (ASD), often persisting into adolescence and increasing the risk of Developmental Coordination Disorder (DCD). Despite their prevalence, only 31.6% of affected individuals receive physical therapy, underscoring a critical gap in early intervention. Traditional methods for diagnosing Fine Motor Deficits (FMD) are often time-consuming and costly, necessitating the adoption of data-driven approaches. This study introduces a machine learning framework for the rapid and reliable prediction of fine motor impairments in adolescents with ASD. By integrating EEG-based neurophysiological signals, behavioral assessments, and motor coordination tests, the study evaluates five classification models—Logistic Regression, Support Vector Machine, K-Nearest Neighbors, Random Forest, and Neural Network. Among these, Logistic Regression achieved the highest accuracy (95.84%), demonstrating strong predictive power for identifying fine motor deficits. The proposed framework enhances the efficiency of FMD screening and provides an interpretable model for potential clinical use in early ASD diagnosis.
{"title":"Predicting fine motor deficit in autism by measuring brain activities and characterizing motor impairments","authors":"Zaibunnisa L.H. Malik, Pooja Raundale","doi":"10.1016/j.compbiomed.2026.111470","DOIUrl":"10.1016/j.compbiomed.2026.111470","url":null,"abstract":"<div><div>Motor impairments affect approximately 86.9% of children with Autism Spectrum Disorder (ASD), often persisting into adolescence and increasing the risk of Developmental Coordination Disorder (DCD). Despite their prevalence, only 31.6% of affected individuals receive physical therapy, underscoring a critical gap in early intervention. Traditional methods for diagnosing Fine Motor Deficits (FMD) are often time-consuming and costly, necessitating the adoption of data-driven approaches. This study introduces a machine learning framework for the rapid and reliable prediction of fine motor impairments in adolescents with ASD. By integrating EEG-based neurophysiological signals, behavioral assessments, and motor coordination tests, the study evaluates five classification models—Logistic Regression, Support Vector Machine, K-Nearest Neighbors, Random Forest, and Neural Network. Among these, Logistic Regression achieved the highest accuracy (95.84%), demonstrating strong predictive power for identifying fine motor deficits. The proposed framework enhances the efficiency of FMD screening and provides an interpretable model for potential clinical use in early ASD diagnosis.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111470"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146212409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-03-01Epub Date: 2026-02-18DOI: 10.1016/j.compbiomed.2026.111545
Shafigh Ashrafi, Hedieh Sajedi
The StitchNet framework introduced a paradigm shift in Neural Architecture Search (NAS) by proposing the construction of neural networks from pre-trained fragments. This approach reduces computational costs and enables task-specific model creation without retraining entire networks. Building on this foundation, our study evaluates the practical application of StitchNet in constructing neural networks tailored to medical image classification tasks. Specifically, we assess its performance on a dataset of retinal images classified into three categories: healthy, dry, and wet AMD (Age-Related Macular Degeneration), namely drusen and choroidal neovascularization (CNV). By employing fragments from five pre-trained networks and integrating techniques such as recurrent neural networks (RNNs) and autoencoders, we aim to validate and enhance StitchNet's capabilities. Our findings demonstrate that while StitchNet achieves competitive accuracy with reduced computational overhead, incorporating domain-specific optimizations further improves its adaptability and efficiency. So, the developed network outperforms a scientist-designed network by 6%. In the next phase, we will explore ways to improve the algorithm's efficiency and minimize the data required for processing. Fully reproducible code here: https://github.com/ShafighAshrafi/stitchnet.
{"title":"Task-specific neural networks for medical imaging using pretrained fragments","authors":"Shafigh Ashrafi, Hedieh Sajedi","doi":"10.1016/j.compbiomed.2026.111545","DOIUrl":"10.1016/j.compbiomed.2026.111545","url":null,"abstract":"<div><div>The StitchNet framework introduced a paradigm shift in Neural Architecture Search (NAS) by proposing the construction of neural networks from pre-trained fragments. This approach reduces computational costs and enables task-specific model creation without retraining entire networks. Building on this foundation, our study evaluates the practical application of StitchNet in constructing neural networks tailored to medical image classification tasks. Specifically, we assess its performance on a dataset of retinal images classified into three categories: healthy, dry, and wet AMD (Age-Related Macular Degeneration), namely drusen and choroidal neovascularization (CNV). By employing fragments from five pre-trained networks and integrating techniques such as recurrent neural networks (RNNs) and autoencoders, we aim to validate and enhance StitchNet's capabilities. Our findings demonstrate that while StitchNet achieves competitive accuracy with reduced computational overhead, incorporating domain-specific optimizations further improves its adaptability and efficiency. So, the developed network outperforms a scientist-designed network by 6%. In the next phase, we will explore ways to improve the algorithm's efficiency and minimize the data required for processing. Fully reproducible code here: <span><span>https://github.com/ShafighAshrafi/stitchnet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"204 ","pages":"Article 111545"},"PeriodicalIF":6.3,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146225809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号