Phys Rev Lett. 2025 Mar 21;134(11):118402. doi: 10.1103/PhysRevLett.134.118402.

ABSTRACT

When cell sheets fold during development, their apical or basal surfaces constrict and cell shapes approach the geometric singularity in which these surfaces vanish. Here, we reveal the mechanical consequences of this geometric singularity for tissue folding in a minimal vertex model of an epithelial monolayer. In simulations of the buckling of the epithelium under compression and numerical solutions of the corresponding continuum model, we discover an "unbuckling" bifurcation: at large compression, the buckling amplitude can decrease with increasing compression. By asymptotic solution of the continuum equations, we reveal that this bifurcation comes with a large stiffening of the epithelium. Our results thus provide the mechanical basis for absorption of compressive stresses by tissue folds such as the cephalic furrow during germband extension in Drosophila.

PMID:40192356 | DOI:10.1103/PhysRevLett.134.118402

Elife. 2025 Apr 7;13:RP102819. doi: 10.7554/eLife.102819.

ABSTRACT

The formation of the mammalian brain requires regionalization and morphogenesis of the cranial neural plate, which transforms from an epithelial sheet into a closed tube that provides the structural foundation for neural patterning and circuit formation. Sonic hedgehog (SHH) signaling is important for cranial neural plate patterning and closure, but the transcriptional changes that give rise to the spatially regulated cell fates and behaviors that build the cranial neural tube have not been systematically analyzed. Here, we used single-cell RNA sequencing to generate an atlas of gene expression at six consecutive stages of cranial neural tube closure in the mouse embryo. Ordering transcriptional profiles relative to the major axes of gene expression predicted spatially regulated expression of 870 genes along the anterior-posterior and mediolateral axes of the cranial neural plate and reproduced known expression patterns with over 85% accuracy. Single-cell RNA sequencing of embryos with activated SHH signaling revealed distinct SHH-regulated transcriptional programs in the developing forebrain, midbrain, and hindbrain, suggesting a complex interplay between anterior-posterior and mediolateral patterning systems. These results define a spatiotemporally resolved map of gene expression during cranial neural tube closure and provide a resource for investigating the transcriptional events that drive early mammalian brain development.

PMID:40192104 | DOI:10.7554/eLife.102819

Aging Clin Exp Res. 2025 Apr 7;37(1):120. doi: 10.1007/s40520-025-03025-4.

ABSTRACT

BACKGROUND: Real-world data on adverse drug reactions (ADRs) associated with idarucizumab and andexanet alfa are limited.

AIM: This study aimed to assess the frequency, the characteristics and clinical and demographic factors associated with ADRs related to their use.

METHODS: This is a retrospective analysis of ADR reports collected in Vigibase® until May 31, 2023. Multivariable logistic regression estimated reporting odds ratios (RORs) for serious ADRs, death, and thromboembolic events according to demographical and clinical covariates.

RESULTS: A total of 1095 Individual Case Safety Reports (ICSRs) reporting idarucizumab (72%) or andexanet alfa (28%) as suspected/interacting agents were collected. Most of the subjects were males (44.5%), with a median age of 78 years, and exposed to only one suspected/interacting medication (73.6%). ADRs were defined as serious in 88.6% of cases, with a total of 614 (56.1%) fatal cases. Compared to patients without concomitant medications, probability of serious ADRs and death were both higher in those receiving ≥ 5 concomitant medications in the idarucizumab subgroup (ROR 4.04 and 1.66, respectively) and in those receiving 1-4 concomitant medications in the andexanet alfa subgroup (ROR 5.66 and 4.80, respectively). Moreover, the probability of thromboembolic events was significantly lower for subjects aged > 75 years (ROR for 75-84 years 0.55; ROR for ≥ 85 years 0.50).

DISCUSSION: In real-world, ADRs associated with idarucizumab and andexanet alfa use are generally serious, resulting in death in a high percentage of subjects.

CONCLUSION: Clinicians should pay particular attention when managing individuals needing these drugs, especially if vulnerable and requiring polytherapy.

PMID:40192996 | DOI:10.1007/s40520-025-03025-4

Oncol Res. 2025 Mar 19;33(4):919-935. doi: 10.32604/or.2024.054537. eCollection 2025.

ABSTRACT

OBJECTIVE: Prostate cancer (PCA) is the second most widespread cancer among men globally, with a rising mortality rate. Enzyme-responsive lipid nanoparticles (ERLNs) are promising vectors for the selective delivery of anticancer agents to tumor cells. The goal of this study is to fabricate ERLNs for dual delivery of gefitinib (GF) and simvastatin (SV) to PCA cells.

METHODS: ERLNs loaded with GF and SV (ERLNGFSV) were assembled using bottom-up and top-down techniques. Subsequently, these ERLN cargoes were coated with triacylglycerol, and phospholipids and capped with chitosan (CS). The ERLNGFSV, and CS engineered ERLNGFSV (CERLNGFSV) formulations were characterized for particle size (PS), zeta potential (ZP), and polydispersity index (PDI). The biocompatibility, and cytotoxicity of the plain and GF plus SV-loaded ERLN cargoes were assessed using erythrocytes and PC-3 cell line. Additionally, molecular docking simulations (MDS) were conducted to examine the influence of GF and SV on succinate dehydrogenase (SDH), glutathione peroxidase-4 (GPX-4), and 5α-reductase (5α-RD).

RESULTS: These results showed that plain, ERLNGFSV, and CERLNGFSV cargoes have a nanoscale size and homogeneous appearance. Moreover, ERLNGFSV and CERLNGFSV were biocompatible, with no detrimental effects on erythrocytes. Treatment with GF, SV, GF plus SV, ERLNGFSV, and CERLNGFSV significantly reduced the viability of PC-3 cells compared to control cells. Particularly, the blend of GF and SV, as well as ERLNGFSV and CERLNGFSV augmented PC-3 cell death. Also, treating PC-3 cells with free drugs, their combination, ERLNGFSV, and CERLNGFSV formulations elevated the percentage of apoptotic cells. MDS studies demonstrated that GF and SV interact with the active sites of SDH, GPX-4, and 5α-reductase.

CONCLUSIONS: This study concludes that SVGF combination and ERLNs loading induce particular delivery, and synergism on PC-3 death through action on multiple pathways involved in cell proliferation, and apoptosis, besides the interaction with SDH, GPX-4, and 5α-RD. Therefore, GFSV-loaded ERLN cargoes are a promising strategy for PCA treatment. In vivo studies are necessary to confirm these findings for clinical applications.

PMID:40191728 | PMC:PMC11964872 | DOI:10.32604/or.2024.054537

ACS Omega. 2025 Mar 20;10(12):12366-12374. doi: 10.1021/acsomega.4c11382. eCollection 2025 Apr 1.

ABSTRACT

The increasing prevalence of infections byCandida hemeulonii sensu stricto, particularly due to its resistance to standard antifungal therapies, represents a significant healthcare challenge. Traditional treatments often fail, emphasizing the need to explore alternative therapeutic strategies. Drug repurposing, which reevaluates existing drugs for new applications, offers a promising path. This study examines the potential of repurposing alexidine dihydrochloride as an antifungal agent againstC. hemeulonii sensu stricto. Minimum Inhibitory Concentration (MIC) and Minimum Fungicidal Concentration (MFC) values were established using broth microdilution methods. To further assess antifungal activity, different assays were conducted, including growth inhibition, biofilm inhibition, biofilm eradication, and cell damage. Checkerboard assays were employed to study the compound's fungicidal potential and interactions with other antifungals. Additional tests, sorbitol protection assay, efflux pump inhibition, cell membrane permeability assays, and nucleotide leakage were performed. In vivo efficacy and safety were evaluated inTenebrio molitor larvae. Alexidine demonstrated fungicidal activity againstC. hemeulonii sensu stricto, with an MIC of 0.5 μg/mL. Biofilm formation was significantly inhibited, with a reduction of 78.69%. Mechanistic studies revealed nucleotide leakage, indicating membrane impact, but no significant protein leakage was detected. In vivo, alexidine displayed a favorable safety profile, with no evidence of hemolysis or acute toxicity in the T. molitor model. These findings support alexidine as a strong candidate for antifungal drug repurposing, especially for treatingC. hemeulonii sensu stricto infections. Its efficacy in inhibiting growth and biofilm formation, combined with a positive safety profile, underscores its potential for clinical development as an antifungal therapy.

PMID:40191372 | PMC:PMC11966325 | DOI:10.1021/acsomega.4c11382

RSC Adv. 2025 Apr 4;15(14):10622-10633. doi: 10.1039/d4ra09055a. eCollection 2025 Apr 4.

ABSTRACT

Peroxisome proliferator-activated receptors (PPARs) are ligand-activated nuclear receptors with a crucial regulatory role in carbohydrate and lipid metabolism and are emerging druggable targets in "metabolic syndrome" (MetS) and cancers. However, there is a need to identify ligands that can activate specific PPAR subtypes, particularly PPARβ/δ, which is less studied compared with other PPAR isoforms (α and γ). Herein, using the drug-repurposing approach, the ZINC database of clinically approved drugs was screened to target the PPARβ/δ receptor through high-throughput-virtual-screening, followed by molecular docking and molecular dynamics (MD) simulation. The top-scoring ligands were subjected to drug-likeness analysis. The hit molecule was tested in an in vitro model of NAFLD (non-alcoholic fatty liver disease). The top five ligands with strong binding affinity towards PPARβ/δ were canagliflozin > empagliflozin > lumacaftor > eprosartan > dapagliflozin. RMSD/RMSF analysis demonstrated stable protein-ligand complexation (PLC) by the top-scoring ligands with PPARβ/δ. In silico ADMET prediction analysis revealed favorable pharmacokinetic profiles of these top five ligands. Canagliflozin showed significant (P < 0.001) dose-dependent decrease in lipid accumulation and the associated oxidative stress-inflammatory response, suggesting its promising anti-steatotic potential. These outcomes pave the way for further validation and development of PPAR activity-modulating therapeutics.

PMID:40190631 | PMC:PMC11970364 | DOI:10.1039/d4ra09055a

NAR Genom Bioinform. 2025 Apr 4;7(2):lqaf033. doi: 10.1093/nargab/lqaf033. eCollection 2025 Jun.

ABSTRACT

We describe FoundHaplo, an identity-by-descent algorithm that can be used to screen untyped disease-causing variants using single nucleotide polymorphism (SNP) array data. FoundHaplo leverages knowledge of shared disease haplotypes for inherited variants to identify those who share the disease haplotype and are, therefore, likely to carry the rare [minor allele frequency (MAF) ≤ 0.01%] variant. We performed a simulation study to evaluate the performance of FoundHaplo across 33 disease-harbouring loci. FoundHaplo was used to infer the presence of two rare (MAF ≤ 0.01%) pathogenic variants, SCN1B c.363C>G (p.Cys121Trp) and WWOX c.49G>A (p.E17K), which can cause mild dominant and severe recessive epilepsy, respectively, in the Epi25 cohort and the UK Biobank. FoundHaplo demonstrated substantially better sensitivity at inferring the presence of these rare variants than existing genome-wide imputation. FoundHaplo is a valuable screening tool for searching disease-causing variants with known founder effects using only SNP genotyping data. It is also applicable to nonhuman applications and nondisease-causing traits, including rare-variant drivers of quantitative traits. The FoundHaplo algorithm is available at https://github.com/bahlolab/FoundHaplo (DOI:10.5281/zenodo.8058286).

PMID:40191585 | PMC:PMC11970371 | DOI:10.1093/nargab/lqaf033

J Intern Med. 2025 Apr 6. doi: 10.1111/joim.20087. Online ahead of print.

ABSTRACT

BACKGROUND: Methotrexate (MTX) is the mainstay initial treatment of rheumatoid arthritis (RA), but individual response varies and remains difficult to predict. The role of genetics remains unclear, but studies suggest its importance.

METHODS: Incident RA patients starting MTX-monotherapy were identified through a large-scale Swedish register linkage. Demographic, clinical, medical, and drug history features were combined with fully imputed genotype data and used to train and evaluate multiple learning models to predict key MTX treatment outcomes.

RESULTS: Among 2432 patients, we consistently observed an estimated area under the curve (AUC) of ∼0.62, outperforming models trained on sex and age. The best performance was observed for EULAR primary response (AUC = 0.67), whereas models struggled the most with predicting discontinuation. Genetics provided negligible improvements to prediction quality.

CONCLUSIONS: Despite an extensive study population with broad multi-modal data, predicting MTX treatment outcomes remains a challenge. Common genetic variants added minimal predictive power over clinical features.

PMID:40190030 | DOI:10.1111/joim.20087

Hum Vaccin Immunother. 2025 Dec;21(1):2488557. doi: 10.1080/21645515.2025.2488557. Epub 2025 Apr 6.

ABSTRACT

It is estimated that 40-50% of severe asthma has an atopic basis, representing a clinical challenge and a significant economic burden for healthcare systems. The most effective treatment has emerged with the use of biologic therapies such as omalizumab; however, the rate of therapy switching due to loss of efficacy is high, which has a negative impact on the healthcare system. The aim was to evaluate the influence of genetic polymorphisms as predictors of omalizumab survival. We conducted a retrospective observational cohort study of 110 patients with uncontrolled severe allergic asthma treated with omalizumab in a tertiary hospital. We analyzed FCER1A (rs2251746, rs2427837), FCER1B (rs1441586, rs573790, rs1054485, rs569108), C3 (rs2230199), FCGR2A (rs1801274), FCGR2B (rs3219018, rs1050501), FCGR3A (rs10127939, rs396991), IL1RL1 (rs1420101, rs17026974, rs1921622) and GATA2 (rs4857855) by real-time PCR using Taqman probes. Drug survival was defined as the time from initiation to discontinuation of omalizumab. Cox regression analysis adjusted for the presence of respiratory disease, GERD, SAHS and years with asthma showed that the SNPs FCER1B rs573790 - CT (p < .001; HR = 3.38; CI95% = 1.66-6.87), FCGR3A rs10127939-AC (p = .018; HR = 3.85; CI95% = 1.25-11.81) and FCGR3A rs396991-CC (p = .020; HR = 2.23; CI95% = 1.14-4.38) were the independent variables associated with worse survival in patients diagnosed with asthma. A trend toward statistical significance was also found between and FCGR3A rs10127939-CC (p = .080; HR = 0.13; CI95% = 0.01-1.28) and longer drug survival. The results of this study demonstrate the potential influence of the polymorphisms studied on omalizumab survival and the clinical benefit that could be achieved by defining predictive biomarkers of drug survival.

PMID:40189906 | DOI:10.1080/21645515.2025.2488557

Eur J Clin Invest. 2025 Apr;55 Suppl 1:e70002. doi: 10.1111/eci.70002.

ABSTRACT

BACKGROUND: Recent advancements in deep learning (DL), a subset of artificial intelligence, have shown the potential to automate and improve disease recognition, phenotyping and prediction of disease onset and outcomes by analysing various sources of medical data. The electrocardiogram (ECG) is a valuable tool for diagnosing and monitoring cardiovascular conditions.

METHODS: The implementation of DL in ECG analysis has been used to detect and predict rhythm abnormalities and conduction abnormalities, ischemic and structural heart diseases, with performance comparable to physicians. However, despite promising development of DL algorithms for automatic ECG analysis, the integration of DL-based ECG analysis and deployment of medical devices incorporating these algorithms into routine clinical practice remains limited.

RESULTS: This narrative review highlights the applications of DL in 12-lead ECG analysis. Furthermore, we review randomized controlled trials that assess the clinical effectiveness of these DL tools. Finally, it addresses different key barriers to widespread implementation in clinical practice, including regulatory hurdles, algorithm transparency and data privacy concerns.

CONCLUSIONS: By outlining both the progress and the obstacles in this field, this review aims to provide insights into how DL could shape the future of ECG analysis and enhance cardiovascular care in daily clinical practice.

PMID:40191935 | DOI:10.1111/eci.70002

Eur J Clin Invest. 2025 Apr;55 Suppl 1:e14370. doi: 10.1111/eci.14370.

ABSTRACT

BACKGROUND: The management of cardiotoxicity related to cancer therapies has emerged as a significant clinical challenge, prompting the rapid growth of cardio-oncology. As cancer treatments become more complex, there is an increasing need to enhance diagnostic and therapeutic strategies for managing their cardiovascular side effects.

OBJECTIVE: This review investigates the potential of artificial intelligence (AI) to revolutionize cardio-oncology by integrating diverse data sources to address the challenges of cardiotoxicity management.

METHODS: We explore applications of AI in cardio-oncology, focusing on its ability to leverage multiple data sources, including electronic health records, electrocardiograms, imaging modalities, wearable sensors, and circulating serum biomarkers.

RESULTS: AI has demonstrated significant potential in improving risk stratification and longitudinal monitoring of cardiotoxicity. By optimizing the use of electrocardiograms, non-invasive imaging, and circulating biomarkers, AI facilitates earlier detection, better prediction of outcomes, and more personalized therapeutic interventions. These advancements are poised to enhance patient outcomes and streamline clinical decision-making.

CONCLUSIONS: AI represents a transformative opportunity in cardio-oncology by advancing diagnostic and therapeutic capabilities. However, successful implementation requires addressing practical challenges such as data integration, model interpretability, and clinician training. Continued collaboration between clinicians and AI developers will be essential to fully integrate AI into routine clinical workflows.

PMID:40191923 | DOI:10.1111/eci.14370

ACS Nano. 2025 Apr 7. doi: 10.1021/acsnano.5c02004. Online ahead of print.

ABSTRACT

Swimming kinematics and macroscale mechanical testing have shown that the vertebral column of sharks acts as a biological spring, storing and releasing energy during locomotion. Using synchrotron X-ray nanotomography and deep-learning image segmentation, we studied the ultrastructure and deformation mechanism of mineralized shark vertebrae from Carcharhinus limbatus (Blacktip shark). The vertebral centrum con regions: the corpus calcareum, a hypermineralized double cone, and the intermediale, blocks of mineralized cartilage interspersed by unmineralized arches. At the micron scale, mineralized cartilage has previously been described as a 3D network of interconnected mineral plates that vary in thickness and spacing. The corpus calcareum consists of stacked, interconnected, curved mineralized planes permeated by a network of organic occlusions. The mineral network in the intermedialia resembles trabecular bone, including thicker struts in the direction opposite to the predominant biological strain. We characterized collagenous fiber elements winding around lacunar spaces in the intermedialia, and we hypothesize the swirling arrangement and elasticity of the fibers to be distributing stress. With little permanent deformation detected in mineralized structures, it is likely that the soft organic matrix is crucial for absorbing energy through deformation, irreversible damage, and viscoelastic behavior. In the corpus calcareum, cracks typically terminate toward thick struts along the mineral planes, resembling the microscale crack deflection and arrest mechanism found in other staggered biocomposites, such as nacre or bone. Using transmission electron microscopy (TEM), we observed preferentially oriented, needlelike bioapatite crystallites and d-band patterns of collagen type-II fibrils resulting from intrafibrillar mineralization.

PMID:40191917 | DOI:10.1021/acsnano.5c02004

Front Aging Neurosci. 2025 Mar 21;17:1532470. doi: 10.3389/fnagi.2025.1532470. eCollection 2025.

ABSTRACT

Conventional computer-aided diagnostic techniques for Alzheimer's disease (AD) predominantly rely on magnetic resonance imaging (MRI) in isolation. Genetic imaging methods, by establishing the link between genes and brain structures in disease progression, facilitate early prediction of AD development. While deep learning methods based on MRI have demonstrated promising results for early AD diagnosis, the limited dataset size has led most AD studies to lean on statistical approaches within the realm of imaging genetics. Existing deep-learning approaches typically utilize pre-defined regions of interest and risk variants from known susceptibility genes, employing relatively straightforward feature fusion methods that fail to fully capture the relationship between images and genes. To address these limitations, we proposed a multi-modal deep learning classification network based on MRI and single nucleotide polymorphism (SNP) data for AD diagnosis and mild cognitive impairment (MCI) progression prediction. Our model leveraged a convolutional neural network (CNN) to extract whole-brain structural features, a Transformer network to capture genetic features, and employed a cross-transformer-based network for comprehensive feature fusion. Furthermore, we incorporated an attention-map-based interpretability method to analyze and elucidate the structural and risk variants associated with AD and their interrelationships. The proposed model was trained and evaluated using 1,541 subjects from the ADNI database. Experimental results underscored the superior performance of our model in effectively integrating and leveraging information from both modalities, thus enhancing the accuracy of AD diagnosis and prediction.

PMID:40191788 | PMC:PMC11968703 | DOI:10.3389/fnagi.2025.1532470

J Med Signals Sens. 2025 Feb 28;15:6. doi: 10.4103/jmss.jmss_46_24. eCollection 2025.

ABSTRACT

BACKGROUND: Gastroesophageal reflux disease (GERD) is a prevalent digestive disorder that impacts millions of individuals globally. Multichannel intraluminal impedance-pH (MII-pH) monitoring represents a novel technique and currently stands as the gold standard for diagnosing GERD. Accurately characterizing reflux events from MII data are crucial for GERD diagnosis. Despite the initial introduction of clinical literature toward software advancements several years ago, the reliable extraction of reflux events from MII data continues to pose a significant challenge. Achieving success necessitates the seamless collaboration of two key components: a reflux definition criteria protocol established by gastrointestinal experts and a comprehensive analysis of MII data for reflux detection.

METHOD: In an endeavor to address this challenge, our team assembled a dataset comprising 201 MII episodes. We meticulously crafted precise reflux episode definition criteria, establishing the gold standard and labels for MII data.

RESULT: A variety of signal-analyzing methods should be explored. The first Isfahan Artificial Intelligence Competition in 2023 featured formal assessments of alternative methodologies across six distinct domains, including MII data evaluations.

DISCUSSION: This article outlines the datasets provided to participants and offers an overview of the competition results.

PMID:40191685 | PMC:PMC11970833 | DOI:10.4103/jmss.jmss_46_24

J Med Signals Sens. 2025 Feb 28;15:5. doi: 10.4103/jmss.jmss_55_24. eCollection 2025.

ABSTRACT

BACKGROUND: Multiple sclerosis (MS) is one of the most common reasons of neurological disabilities in young adults. The disease occurs when the immune system attacks the central nervous system and destroys the myelin of nervous cells. This results in appearing several lesions in the magnetic resonance (MR) images of patients. Accurate determination of the amount and the place of lesions can help physicians to determine the severity and progress of the disease.

METHOD: Due to the importance of this issue, this challenge has been dedicated to the segmentation and localization of lesions in MR images of patients with MS. The goal was to segment and localize the lesions in the flair MR images of patients as close as possible to the ground truth masks.

RESULTS: Several teams sent us their results for the segmentation and localization of lesions in MR images. Most of the teams preferred to use deep learning methods. The methods varied from a simple U-net structure to more complicated networks.

CONCLUSION: The results show that deep learning methods can be useful for segmentation and localization of lesions in MR images. In this study, we briefly described the dataset and the methods of teams attending the competition.

PMID:40191684 | PMC:PMC11970832 | DOI:10.4103/jmss.jmss_55_24

Front Genet. 2025 Mar 21;16:1532651. doi: 10.3389/fgene.2025.1532651. eCollection 2025.

ABSTRACT

MOTIVATION: Predicting the response of cell lines to characteristic drugs based on multi-omics gene information has become the core problem of precision oncology. At present, drug response prediction using multi-omics gene data faces the following three main challenges: first, how to design a gene probe feature extraction model with biological interpretation and high performance; second, how to develop multi-omics weighting modules for reasonably fusing genetic data of different lengths and noise conditions; third, how to construct deep learning models that can handle small sample sizes while minimizing the risk of possible overfitting.

RESULTS: We propose an innovative drug response prediction model (NMDP). First, the NMDP model introduces an interpretable semi-supervised weighted SPCA module to solve the feature extraction problem in multi-omics gene data. Next, we construct a multi-omics data fusion framework based on sample similarity networks, bimodal tests, and variance information, which solves the data fusion problem and enables the NMDP model to focus on more relevant genomic data. Finally, we combine a one-dimensional convolution method and Kolmogorov-Arnold networks (KANs) to predict the drug response. We conduct five sets of real data experiments and compare NMDP against seven advanced drug response prediction methods. The results show that NMDP achieves the best performance, with sensitivity and specificity reaching 0.92 and 0.93, respectively-an improvement of 11%-57% compared to other models. Bio-enrichment experiments strongly support the biological interpretation of the NMDP model and its ability to identify potential targets for drug activity prediction.

PMID:40191608 | PMC:PMC11968432 | DOI:10.3389/fgene.2025.1532651

APL Bioeng. 2025 Apr 3;9(2):026104. doi: 10.1063/5.0242570. eCollection 2025 Jun.

ABSTRACT

Current risk assessment models for predicting ischemic stroke (IS) in patients with atrial fibrillation (AF) often fail to account for the effects of medications and the complex interactions between drugs, proteins, and diseases. We developed an interpretable deep learning model, the AF-Biological-IS-Path (ABioSPath), to predict one-year IS risk in AF patients by integrating drug-protein-disease pathways with real-world clinical data. Using a heterogeneous multilayer network, ABioSPath identifies mechanisms of drug actions and the propagation of comorbid diseases. By combining mechanistic pathways with patient-specific characteristics, the model provides individualized IS risk assessments and identifies potential molecular pathways involved. We utilized the electronic health record data from 7859 AF patients, collected between January 2008 and December 2009 across 43 hospitals in Hong Kong. ABioSPath outperformed baseline models in all evaluation metrics, achieving an AUROC of 0.7815 (95% CI: 0.7346-0.8283), a positive predictive value of 0.430, a negative predictive value of 0.870, a sensitivity of 0.500, a specificity of 0.885, an average precision of 0.409, and a Brier score of 0.195. Cohort-level analysis identified key proteins, such as CRP, REN, and PTGS2, within the most common pathways. Individual-level analysis further highlighted the importance of PIK3/Akt and cytokine and chemokine signaling pathways and identified IS risks associated with less-studied drugs like prochlorperazine maleate. ABioSPath offers a robust, data-driven approach for IS risk prediction, requiring only routinely collected clinical data without the need for costly biomarkers. Beyond IS, the model has potential applications in screening risks for other diseases, enhancing patient care, and providing insights for drug development.

PMID:40191603 | PMC:PMC11970939 | DOI:10.1063/5.0242570

R Soc Open Sci. 2024 Oct 23;11(10):240720. doi: 10.1098/rsos.240720. eCollection 2024 Oct.

ABSTRACT

Contemporary drug discovery paradigms rely heavily on binding assays about the bio-physicochemical processes. However, this dominant approach suffers from overlooked higher-order interactions arising from the intricacies of molecular mechanisms, such as those involving cis-regulatory elements. It introduces potential impairments and restrains the potential development of computational methods. To address this limitation, I developed a deep learning model that leverages an end-to-end approach, relying exclusively on therapeutic information about drugs. By transforming textual representations of drug and virus genetic information into high-dimensional latent representations, this method evades the challenges arising from insufficient information about binding specificities. Its strengths lie in its ability to implicitly consider complexities such as epistasis and chemical-genetic interactions, and to handle the pervasive challenge of data scarcity. Through various modeling skills and data augmentation techniques, the proposed model demonstrates outstanding performance in out-of-sample validations, even in scenarios with unknown complex interactions. Furthermore, the study highlights the importance of chemical diversity for model training. While the method showcases the feasibility of deep learning in data-scarce scenarios, it reveals a promising alternative for drug discovery in situations where knowledge of underlying mechanisms is limited.

PMID:40191531 | PMC:PMC11972434 | DOI:10.1098/rsos.240720

Imaging Sci Dent. 2025 Mar;55(1):1-10. doi: 10.5624/isd.20240139. Epub 2025 Jan 15.

ABSTRACT

PURPOSE: This study was performed to assess the performance and accuracy of artificial intelligence (AI) in the detection and diagnosis of maxillary sinus pathologies using computed tomography (CT)/cone-beam computed tomography (CBCT) imaging.

MATERIALS AND METHODS: A comprehensive literature search was conducted across 4 databases: Google Scholar, BioMed Central (BMC), ProQuest, and PubMed. Combinations of keywords such as "DCNN," "deep learning," "convolutional neural network," "machine learning," "predictive modeling," and "data mining" were used to identify relevant articles. The study included articles that were published within the last 5 years, written in English, available in full text, and focused on diagnostic accuracy.

RESULTS: Of an initial 530 records, 12 studies with a total of 3,349 patients (7,358 images) were included. All articles employed deep learning methods. The most commonly tested pathologies were maxillary rhinosinusitis and maxillary sinusitis, while the most frequently used AI models were convolutional neural network architectures, including ResNet and DenseNet, YOLO, and U-Net. DenseNet and ResNet architectures have demonstrated superior precision in detecting maxillary sinus pathologies due to their capacity to handle deeper networks without overfitting. The performance in detecting maxillary sinus pathology varied, with an accuracy ranging from 85% to 97%, a sensitivity of 87% to 100%, a specificity of 87.2% to 99.7%, and an area under the curve of 0.80 to 0.91.

CONCLUSION: AI with various architectures has been used to detect maxillary sinus abnormalities on CT/CBCT images, achieving near-perfect results. However, further improvements are needed to increase accuracy and consistency.

PMID:40191392 | PMC:PMC11966023 | DOI:10.5624/isd.20240139

J Respir Biol Transl Med. 2025 Mar;2(1):10001. doi: 10.70322/jrbtm.2025.10001. Epub 2025 Mar 7.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF) is a progressive, irreversible, and fatal disease with an increasing incidence and limited therapeutic options. It is characterized by the formation and deposition of excess extracellular matrix proteins resulting in the gradual replacement of normal lung architecture by fibrous tissue. The cellular and molecular mechanism of IPF has not been fully understood. A hallmark in IPF is pulmonary fibroblast to myofibroblast transformation (FMT). During excessive lung repair upon exposure to harmful stimuli, lung fibroblasts transform into myofibroblasts under stimulation of cytokines, chemokines, and vesicles from various cells. These mediators interact with lung fibroblasts, initiating multiple signaling cascades, such as TGFβ1, MAPK, Wnt/β-catenin, NF-κB, AMPK, endoplasmic reticulum stress, and autophagy, contributing to lung FMT. Furthermore, single-cell transcriptomic analysis has revealed significant heterogeneity among lung myofibroblasts, which arise from various cell types and are adapted to the altered microenvironment during pathological lung repair. This review provides an overview of recent research on the origins of lung myofibroblasts and the molecular pathways driving their formation, with a focus on the interactions between lung fibroblasts and epithelial cells, endothelial cells, and macrophages in the context of lung fibrosis. Based on these molecular insights, targeting the lung FMT could offer promising avenues for the treatment of IPF.

PMID:40190620 | PMC:PMC11970920 | DOI:10.70322/jrbtm.2025.10001