Skin Appendage Disord. 2025 Feb;11(1):63-69. doi: 10.1159/000540104. Epub 2024 Jul 29.

ABSTRACT

INTRODUCTION: Drug-induced hair loss is one of several causes of hair loss commonly seen in clinical practice, and it is often a daunting task to determine a potential culprit drug when a patient is taking numerous medications. Our objective was to identify drugs responsible for hair loss, using the Food and Drug Administration's Adverse Events Reporting System (FAERS) database, a compilation of drug-related adverse events (AEs).

METHODS: Using the FAERS database, we queried all domestic reports with the reaction term "alopecia" listed as an AE in patients ≥18 years old from April 1, 1968, to September 29, 2023. Using descriptive statistics, individual agents were grouped by drug class.

RESULTS: We analyzed a total of 39,346 hair loss AE reports related to a single agent. Immunomodulatory agents and monoclonal antibodies represented the highest proportion of AE reports for alopecia, followed by hair loss drugs, contraceptives, and antitumor necrosis factor (anti-TNF) biologics.

CONCLUSION: In sum, we showed that immunomodulatory agents and monoclonal antibodies, hair loss drugs, including minoxidil and finasteride, contraceptives, kinase inhibitors, and anti-TNF drugs are most frequently associated with hair loss AEs in the FAERS database. Because many of these drugs are not prescribed primarily for dermatologic indications, our study provides guidance for dermatologists in identifying common medications associated with alopecia.

PMID:39911975 | PMC:PMC11793883 | DOI:10.1159/000540104

Eur Rev Med Pharmacol Sci. 2025 Jan;29(1):30-38. doi: 10.26355/eurrev_202501_37057.

ABSTRACT

OBJECTIVE: Antithrombin (AT) has anti-inflammatory and anti-coagulant properties, but its role in COVID-19 and the rate of deficiency is unknown. We hypothesize that AT3 deficiency is common in COVID-19, and supplementing AT3 will impact COVID-19 coagulopathy.

PATIENTS AND METHODS: This is a prospective randomized control trial. Patients with plasma AT3<100% were randomized to either standard of care (SOC) or SOC+AT3 q48hr weight-based for a goal of 120% for up to 5 doses. An additional reference group with AT3>100% received SOC.

RESULTS: 531 subjects were assessed for eligibility; 324 did not meet inclusion criteria, 151 did not consent, 6 withdrew consent, and 50 subjects completed the study. Enrollment AT3 (M±SD) was 91±13%. AT3 levels were <100% in 38 (76%) and <80% in 11 (22%) patients. SOC+AT3, SOC only, and AT3>100% had a disseminated intravascular coagulation (DIC) score change (M±SD) of 0.4±1.5, -0.13±1.85 and 0±1.54, respectively, (p=0.63). Hospital length of stay was 11.7 [6-14], 6 [4.5-10], 8.5 [6-21] respectively, (p=0.176). Mortality occurred in 2 (11%), 3 (15%), and 3 (25%) patients, respectively (p=0.56). There was one bleeding event in a subject with AT3>100%, and no bleeding events were observed with exogenous AT3. There were no observed drug-related adverse events. Subjects received a median dose of 1,825.5 IU (IQR 794).

CONCLUSIONS: COVID-19 is associated with relative AT3 deficiency (22% of this cohort). No bleeding complications or drug-related adverse events with exogenous AT3 were observed. There were no significant differences in length of stay or mortality. Further studies should evaluate higher doses of exogenous AT3 and focus on higher-risk groups.

CLINICALTRIALS: gov: NCT04899232.

PMID:39911044 | DOI:10.26355/eurrev_202501_37057

Stroke. 2025 Mar;56(3):716-724. doi: 10.1161/STROKEAHA.124.047893. Epub 2025 Feb 5.

ABSTRACT

BACKGROUND: Communicative ability after stroke influences patient outcomes. Limited research has explored the impact of aphasia when it intersects with cultural or linguistic differences on receiving stroke care and patient outcomes. We investigated associations between requiring an interpreter and the provision of evidence-based stroke care and outcomes for people with aphasia in the inpatient rehabilitation setting.

METHODS: Retrospective patient-level data from people with aphasia were aggregated from the Australian Stroke Foundation National Stroke Audit-Rehabilitation Services (2016-2020). Multivariable regression models compared adherence to processes of care (eg, home assessment complete, type of aphasia management) and in-hospital outcomes (eg, length of stay, discharge destination) by the requirement of an interpreter. Outcome models were adjusted for sex, stroke type, hospital size, year, and stroke severity factors.

RESULTS: Among 3160 people with aphasia (median age, 76 years; 56% male), 208 (7%) required an interpreter (median age, 77 years; 52% male). The interpreter group had a more severe disability on admission, reflected by reduced cognitive (6% versus 12%, P=0.009) and motor Functional Independence Measure scores (6% versus 12%, P=0.010). The interpreter group were less likely to have phonological and semantic interventions for their aphasia (odds ratio, 0.57 [95% CI, 0.40-0.80]) compared with people not requiring an interpreter. They more often had a carer (68% versus 48%, P<0.001) and were more likely to be discharged home with supports (odds ratio, 1.48 [95% CI, 1.08-2.04]). The interpreter group had longer lengths of stay (median 31 versus 26 days, P=0.005).

CONCLUSIONS: Some processes of care and outcomes differed in inpatient rehabilitation for people with poststroke aphasia who required an interpreter compared with those who did not. Equitable access to therapy is imperative and greater support for cultural/linguistic minorities during rehabilitation is indicated.

PMID:39907026 | DOI:10.1161/STROKEAHA.124.047893

BMC Med Inform Decis Mak. 2025 Feb 5;25(Suppl 1):59. doi: 10.1186/s12911-025-02910-2.

ABSTRACT

BACKGROUND: Virtual Gene Panels (VGP) comprising disease-associated causal genes are utilized in the diagnosis of rare genetic diseases to evaluate candidate genes identified by whole-genome and whole-exome sequencing. VGPs generated by the PanelApp software were utilized in a UK 100,000 Genome Project pilot study to filter candidate genes, thus enhancing diagnostic efficiency for rare diseases. However, PanelApp also filtered out disease-causing genes in nearly 50% of the cases.

METHODS: Here, we propose various methods for optimized approach to design VGPs that significantly improve the diagnostic efficiency by leveraging the hierarchical structure of the Mondo disease ontology, without excluding disease-causing genes. We also performed computational experiments on an evaluation dataset comprising 74 patients to determine the optimal VGP design method.

RESULTS: Our results demonstrate that the proposed method can significantly enhance rare disease diagnosis efficiency by automatically identifying candidate genes. The proposed method successfully designed VGPs that improve diagnosis efficiency without excluding disease-causing genes.

CONCLUSION: We have developed novel methods for VGP design that leverage the hierarchical structure of the Mondo disease ontology to improve rare genetic disease diagnosis efficiency. This approach identifies candidate genes without excluding disease-causing genes, and thereby improves diagnostic efficiency.

PMID:39910609 | DOI:10.1186/s12911-025-02910-2

J Exp Clin Cancer Res. 2025 Feb 5;44(1):40. doi: 10.1186/s13046-025-03306-w.

ABSTRACT

BACKGROUND: Despite the high response rate to PD-1 blockade therapy in metastatic melanoma (MM) patients, a significant proportion of patients do not respond. Identifying biomarkers to predict patient response is crucial, ideally through non-invasive methods such as liquid biopsy.

METHODS: Soluble forms of PD1, PD-L1, LAG-3, CTLA-4, CD4, CD73, and CD74 were quantified using ELISA assay in plasma of a cohort of 110 MM patients, at baseline, to investigate possible correlations with clinical outcomes. A clinical risk prediction model was applied and validated in pilot studies.

RESULTS: No biomarker showed statistically significant differences between responders and non-responders. However, high number of significant correlations were observed among certain biomarkers in non-responders. Through univariate and multivariate Cox analyses, we identified sPD-L1, sCTLA-4, sCD73, and sCD74 as independent biomarkers predicting progression-free survival and overall survival. According to ROC analysis we discovered that, except for sCD73, values of sPD-L1, sCTLA-4, and sCD74 lower than the cut-off predicted lower disease progression and reduced mortality. A comprehensive risk score for predicting progression-free survival was developed by incorporating the values ​​of the two identified independent factors, sCTLA-4 and sCD74, which significantly improved the accuracy of outcome prediction. Pilot validations highlighted the potential use of the risk score in treatment-naive individuals and long responders.

CONCLUSION: In summary, risk score based on circulating sCTLA-4 and sCD74 reflects the response to immune checkpoint inhibitor (ICI) therapy in MM patients. If confirmed, through further validation, these findings could assist in recommending therapy to patients likely to experience a long-lasting response.

PMID:39910579 | DOI:10.1186/s13046-025-03306-w

Br J Pharmacol. 2025 Feb 5. doi: 10.1111/bph.17449. Online ahead of print.

ABSTRACT

BACKGROUND AND PURPOSE: Non-adherence to atorvastatin treatment is relatively common and partly due to statin-related myotoxicities (SRMs). The risk of developing SRM is dose- and concentration-dependent, highlighting the importance of atorvastatin pharmacokinetics. This study explored the inter-individual variabilities in expression of the atorvastatin transporter gene contributing to modulation of atorvastatin within the muscle cell.

EXPERIMENTAL APPROACH: mRNA levels of efflux and influx transporters were measured and modulated with siRNAs to evaluate effects on intracellular accumulation of atorvastatin in primary cultures of differentiated myotubes from 12 human volunteers.

KEY RESULTS: All genes assessed were expressed with a high inter-individual variability. In differentiated myotubes, efflux transporters were expressed at higher levels than the influx carriers. When considering efflux and influx transporters separately, ABCC1 and SLCO2B1 are the most highly expressed efflux and influx transporters. Suppression of ABCC1, ABCC4 and/or ABCG2 mRNA levels with siRNA significantly increased intracellular accumulation of atorvastatin in differentiated myotubes. Interestingly, the siRNA targeting ABCG2 had a moderate effect on intracellular accumulation of atorvastatin in a volunteer expressing the ABCG2 variant rs2231142 (c.421C>A, p.Gln141Lys). This hypothesis was further validated in a HEK recombinant model overexpressing ABCG2 either wild-type (421C) or variant (421A). Reduction of SLCO1B1 and SLCO2B1 mRNA levels significantly modified intracellular accumulation of atorvastatin in only some volunteers, depending on the expression levels of transporters.

CONCLUSION AND IMPLICATIONS: Silencing ABCC1, ABCC4 or ABCG2 expression alters accumulation of atorvastatin in myotubes, whereas the effect of silencing influx transporters depends on the expression of these transporters.

PMID:39909477 | DOI:10.1111/bph.17449

Pharmacol Ther. 2025 Feb 4;267:108805. doi: 10.1016/j.pharmthera.2025.108805. Online ahead of print.

ABSTRACT

The interactions of drugs with the host's immune cells determine the drug's efficacy and adverse effects in patients. Nonsteroidal Anti-Inflammatory Drugs (NSAID), such as corticosteroids, NSAIDs, and immunosuppressants, affect the immune cells and alter the immune response. Molecularly, drugs can interact with immune cells via cell surface receptors, changing the antigen presentation by modifying the co-stimulatory molecules and interacting with the signaling pathways of T cells, B cells, Natural killer (NK) cells, mast cells, basophils, and macrophages. Immunotoxicity, resulting from drug-induced changes in redox status, generation of Reactive Oxygen Species (ROS)/Reactive Nitrogen Species (RNS), and alterations in antioxidant enzymes within immune cells, leads to immunodeficiency. This, in turn, causes allergic reactions, autoimmune diseases, and cytokine release syndrome (CRS). The treatment options should include the evaluation of immune status and utilization of the concept of pharmacogenomics to minimize the chances of immunotoxicity. Many strategies in redox, like targeting the redox pathway or using redox-active agents, are available for the modulation of the immune system and developing drugs. Case studies highlight significant drug-immune cell interactions and patient outcomes, underscoring the importance of understanding these complexities. The future direction focuses on the drugs to deliver antiviral therapy, new approaches to immunomodulation, and modern technologies for increasing antidote effects with reduced toxicity. In conclusion, in-depth knowledge of the interaction between drugs and immune cells is critical to protect the patient from the adverse effects of the drug and improve therapeutic outcomes of the treatment process. This review focuses on the multifaceted interactions of drugs and their consequences at the cellular levels of immune cells.

PMID:39908660 | DOI:10.1016/j.pharmthera.2025.108805

Curr Microbiol. 2025 Feb 5;82(3):118. doi: 10.1007/s00284-025-04091-7.

ABSTRACT

Cyclic dimeric guanosine monophosphate (c-di-GMP) plays a vital role within the nucleotide signaling network of bacteria, participating in various biological processes such as biofilm formation and toxin production, among others. Substantial evidence demonstrates its critical involvement in the progression of chronic infections. Treating chronic infections seems critical, and there is a worldwide quest for drugs that target pathogens' unique and complex virulence-associated signaling networks. c-di-GMP is a promising therapeutic target by serving as a distinct virulence factor, solving problems associated with drug resistance, biofilm dispersion, and its related septicemia complications. c-di-GMP levels act as checkpoints for several biofilm-associated molecular pathways, viz., Gac/Rsm, BrlR, and SagS signaling systems. C-di-GMP is also engaged in the Wsp chemosensory pathway responsible for rugose small colony variants observed in cystic fibrosis-related lung infections. Considering all factors, c-di-GMP serves as a pivotal hub in the intricate cascade of biofilm regulation. By overseeing QS systems, exopolysaccharide synthesis, and antibiotic resistance pathways in chronic infections, it emerges as a linchpin for effective drug development strategies against biofilm-related ailments. This underscores the significance of understanding the multifaceted signaling networks. c-di-GMP's role is highlighted in this review as a concealed virulence component in various bacterial pathogens, suggesting that medications targeting it could hold promise in treating chronic disorders associated with biofilms.

PMID:39909925 | DOI:10.1007/s00284-025-04091-7

J Cyst Fibros. 2025 Feb 5:S1569-1993(25)00051-7. doi: 10.1016/j.jcf.2025.02.002. Online ahead of print.

ABSTRACT

OBJECTIVE: Access to highly effective modulator therapies (HEMT) in resource-limited countries is limited by prohibitive cost and restrictive patents. We report the clinical outcomes of a cost-reduction strategy in South Africa (SA), where generic elexacaftor/tezacaftor/ivacaftor (gETI) was pharmacokinetically enhanced with clarithromycin (gETI/c) for people with CF (pwCF) eligible for HEMT.

METHODS: A multi-center observational study from December 2021 to May 2024. Analysis of variance (ANOVA) and linear mixed effects analyses were conducted to describe and compare change in sweat chloride (SC), FEV1pp, BMI (m/kg2) and adverse events (AE) over 18-months follow-up for different gETI dose categories: a) standard, full or b) modulator sparing dose (gETI/c at 25-50 % recommended dose, twice/thrice weekly).

RESULTS: 70/413 (17 %) eligible pwCF [median age 27 years (range 6-52); 68 (97 %) with ≥ one copy F508del] received gETI with standard (n = 38) or modulator-sparing doses (n = 32); 29 changed dosing regimens across the study period. The overall mean (SD) reduction in SC after 1-month of treatment was -52.9 (16.9) mmol/L (p < 0.001), with no evidence of difference between dose groups (p = 0.2). Overall mean (SD) FEV1pp and BMI increased at 1-month by 14.9 (95 % CI 11.49-18.40) and 0.84 (95 % CI 0.16-1.49), respectively. Improvements in FEV1pp and BMI were sustained throughout follow-up, with no evidence of difference between dosing groups. No serious AEs were reported.

CONCLUSION: Our experience with gETI is similar to real-world reports using the originator product. Boosting ETI with CYP3A-inhibitors is a safe and effective strategy to increase access to ETI in settings where access to HEMT is restricted.

PMID:39909761 | DOI:10.1016/j.jcf.2025.02.002

J Cheminform. 2025 Feb 5;17(1):17. doi: 10.1186/s13321-025-00959-9.

ABSTRACT

Recently, advancements in cheminformatics such as representation learning for chemical structures, deep learning (DL) for property prediction, data-driven discovery, and optimization of chemical data handling, have led to increased demands for handling chemical simplified molecular input line entry system (SMILES) data, particularly in text analysis tasks. These advancements have driven the need to optimize components like positional encoding and positional embeddings (PEs) in transformer model to better capture the sequential and contextual information embedded in molecular representations. SMILES data represent complex relationships among atoms or elements, rendering them critical for various learning tasks within the field of cheminformatics. This study addresses the critical challenge of encoding complex relationships among atoms in SMILES strings to explore various PEs within the transformer-based framework to increase the accuracy and generalization of molecular property predictions. The success of transformer-based models, such as the bidirectional encoder representations from transformer (BERT) models, in natural language processing tasks has sparked growing interest from the domain of cheminformatics. However, the performance of these models during pretraining and fine-tuning is significantly influenced by positional information such as PEs, which help in understanding the intricate relationships within sequences. Integrating position information within transformer architectures has emerged as a promising approach. This encoding mechanism provides essential supervision for modeling dependencies among elements situated at different positions within a given sequence. In this study, we first conduct pretraining experiments using various PEs to explore diverse methodologies for incorporating positional information into the BERT model for chemical text analysis using SMILES strings. Next, for each PE, we fine-tune the best-performing BERT (masked language modeling) model on downstream tasks for molecular-property prediction. Here, we use two molecular representations, SMILES and DeepSMILES, to comprehensively assess the potential and limitations of the PEs in zero-shot learning analysis, demonstrating the model's proficiency in predicting properties of unseen molecular representations in the context of newly proposed and existing datasets.Scientific contributionThis study explores the unexplored potential of PEs using BERT model for molecular property prediction. The study involved pretraining and fine-tuning the BERT model on various datasets related to COVID-19, bioassay data, and other molecular and biological properties using SMILES and DeepSMILES representations. The study details the pretraining architecture, fine-tuning datasets, and the performance of the BERT model with different PEs. It also explores zero-shot learning analysis and the model's performance on various classification and regression tasks. In this study, newly proposed datasets from different domains were introduced during fine-tuning in addition to the existing and commonly used datasets. The study highlights the robustness of the BERT model in predicting chemical properties and its potential applications in cheminformatics and bioinformatics.

PMID:39910649 | DOI:10.1186/s13321-025-00959-9

Plant Methods. 2025 Feb 5;21(1):12. doi: 10.1186/s13007-024-01321-0.

ABSTRACT

Genomic Selection (GS) predicts traits using genome-wide markers, speeding up genetic progress and enhancing breeding efficiency. Recent emphasis has been placed on deep learning models to enhance prediction accuracy. However, current deep learning models focus on learning specific phenotypes for the given task, overlooking the inter-correlations among different phenotypes. In response, we introduce MtCro, a multi-task learning approach that simultaneously captures diverse plant phenotypes within a shared parameter space. Extensive experiments reveal that MtCro outperforms mainstream models, including DNNGP and SoyDNGP, with performance gains of 1-9% on the Wheat2000 dataset, 1-8% on Wheat599, and 1-3% on Maize8652. Furthermore, comparative analysis shows a consistent 2-3% improvement in multi-phenotype predictions, emphasizing the impact of inter-phenotype correlations on accuracy. By leveraging multi-task learning, MtCro efficiently captures diverse plant phenotypes, enhancing both model training efficiency and prediction accuracy, ultimately accelerating the progress of plant genetic breeding. Our code is available on https://github.com/chaodian12/mtcro .

PMID:39910577 | DOI:10.1186/s13007-024-01321-0

BMC Oral Health. 2025 Feb 5;25(1):187. doi: 10.1186/s12903-025-05482-9.

ABSTRACT

BACKGROUND: Artificial intelligence (AI) methods, including machine learning and deep learning, are increasingly applied in orthodontics for tasks like assessing skeletal maturity. Accurate timing of treatment is crucial, but traditional methods such as cervical vertebral maturation (CVM) staging have limitations due to observer variability and complexity. AI has the potential to automate CVM assessment, enhancing reliability and user-friendliness. This systematic review and meta-analysis aimed to evaluate the overall performance of artificial intelligence (AI) models in assessing cervical vertebrae maturation (CVM) in radiographs, when compared to clinicians.

METHODS: Electronic databases of Medline (via PubMed), Google Scholar, Scopus, Embase, IEEE ArXiv and MedRxiv were searched for publications after 2010, without any limitation on language. In the present review, we included studies that reported AI models' performance on CVM assessment. Quality assessment was done using Quality assessment and diagnostic accuracy Tool-2 (QUADAS-2). Quantitative analysis was conducted using hierarchical logistic regression for meta-analysis on diagnostic accuracy. Subgroup analysis was conducted on different AI subsets (Deep learning, and Machine learning).

RESULTS: A total of 1606 studies were screened of which 25 studies were included. The performance of the models was acceptable. However, it varied based on the methods employed. Eight studies had a low risk of bias in all domains. Twelve studies were included in the meta-analysis and their pooled values for sensitivity, specificity, positive and negative likelihood ratios, and diagnostic odds ratio (DOR) were calculated for each cervical stage (CS). The most accurate CVM evaluation was observed for CS1, boasting a sensitivity of 0.87, a specificity of 0.97, and a DOR of 213. Conversely, CS3 exhibited the lowest performance with a sensitivity of 0.64, and a specificity of 0.96, yet maintaining a DOR of 32.

CONCLUSION: AI has demonstrated encouraging outcomes in CVM assessment, achieving notable accuracy.

PMID:39910512 | DOI:10.1186/s12903-025-05482-9

BMC Med Imaging. 2025 Feb 5;25(1):40. doi: 10.1186/s12880-025-01579-3.

ABSTRACT

BACKGROUND: Long-term severe cholangitis can lead to dense adhesions and increased fragility of the bile duct, complicating surgical procedures and elevating operative risk in children with pancreaticobiliary maljunction (PBM). Consequently, preoperative diagnosis of moderate-to-severe chronic cholangitis is essential for guiding treatment strategies and surgical planning. This study aimed to develop and validate a deep learning radiomics nomogram (DLRN) based on contrast-enhanced CT images and clinical characteristics to preoperatively identify moderate-to-severe chronic cholangitis in children with PBM.

METHODS: A total of 323 pediatric patients with PBM who underwent surgery were retrospectively enrolled from three centers, and divided into a training cohort (n = 153), an internal validation cohort (IVC, n = 67), and two external test cohorts (ETC1, n = 58; ETC2, n = 45). Chronic cholangitis severity was determined by postoperative pathology. Handcrafted radiomics features and deep learning (DL) radiomics features, extracted using transfer learning with the ResNet50 architecture, were obtained from portal venous-phase CT images. Multivariable logistic regression was used to establish the DLRN, integrating significant clinical factors with handcrafted and DL radiomics signatures. The diagnostic performances were evaluated in terms of discrimination, calibration, and clinical usefulness.

RESULTS: Biliary stones and peribiliary fluid collection were selected as important clinical factors. 5 handcrafted and 5 DL features were retained to build the two radiomics signatures, respectively. The integrated DLRN achieved satisfactory performance, achieving area under the curve (AUC) values of 0.913 (95% CI, 0.834-0.993), 0.916 (95% CI, 0.845-0.987), and 0.895 (95% CI, 0.801-0.989) in the IVC, and two ETCs, respectively. In comparison, the clinical model, handcrafted signature, and DL signature had AUC ranges of 0.654-0.705, 0.823-0.857, and 0.840-0.872 across the same cohorts. The DLRN outperformed single-modality clinical, handcrafted radiomics, and DL radiomics models, with all integrated discrimination improvement values > 0 and P < 0.05. The Hosmer-Lemeshow test and calibration curves showed good consistency of the DLRN (P > 0.05), and the decision curve analysis and clinical impact curve further confirmed its clinical utility.

CONCLUSIONS: The integrated DLRN can be a useful and non-invasive tool for preoperatively identifying moderate-to-severe chronic cholangitis in children with PBM, potentially enhancing clinical decision-making and personalized management strategies.

PMID:39910477 | DOI:10.1186/s12880-025-01579-3

J Cheminform. 2025 Feb 5;17(1):18. doi: 10.1186/s13321-025-00952-2.

ABSTRACT

Accurate prediction of drug-target interactions is critical for advancing drug discovery. By reducing time and cost, machine learning and deep learning can accelerate this laborious discovery process. In a novel approach, BarlowDTI, we utilise the powerful Barlow Twins architecture for feature-extraction while considering the structure of the target protein. Our method achieves state-of-the-art predictive performance against multiple established benchmarks using only one-dimensional input. The use of our hybrid approach of deep learning and gradient boosting machine as the underlying predictor ensures fast and efficient predictions without the need for substantial computational resources. We also propose the use of an influence method to investigate how the model reaches its decision based on individual training samples. By comparing co-crystal structures, we find that BarlowDTI effectively exploits catalytically active and stabilising residues, highlighting the model's ability to generalise from one-dimensional input data. In addition, we further benchmark new baselines against existing methods. Together, these innovations improve the efficiency and effectiveness of drug-target interactions predictions, providing robust tools for accelerating drug development and deepening the understanding of molecular interactions. Therefore, we provide an easy-to-use web interface that can be freely accessed at https://www.bio.nat.tum.de/oc2/barlowdti . SCIENTIFIC CONTRIBUTION: Our computationally efficient and effective hybrid approach, combining the deep learning model Barlow Twins and gradient boosting machines, outperforms state-of-the-art methods across multiple splits and benchmarks using only one-dimensional input. Furthermore, we advance the field by proposing an influence method that elucidates model decision-making, thereby providing deeper insights into molecular interactions and improving the interpretability of drug-target interactions predictions.

PMID:39910404 | DOI:10.1186/s13321-025-00952-2

Sci Rep. 2025 Feb 5;15(1):4415. doi: 10.1038/s41598-025-88582-4.

ABSTRACT

Cavitation is a technical challenge for high-speed underwater vehicles, such as nuclear submarines and underwater robots, et al. The cavitation phenomena of hydrofoils are typically studied through water tunnel experiments or numerical simulations, which yield extensive cavitation images. To conveniently extract cavitation features from the massive images, a feature extraction method for hydrofoil cavitation was proposed in this work based on deep learning image semantic segmentation techniques. This method is employed to investigate the mechanism of the transition process from sheet cavitation to cloud cavitation on hydrofoils. The accuracy and generalization ability of the proposed method have been validated. The results indicate that, in addition to accurately obtaining the cavitation length automatically, the method can also derive more sensitive indicators such as area and position changes of the cavitation regions. This heightened sensitivity is invaluable for precisely pinpointing the transition from sheet-like cavitation to cloud cavitation, thereby aiding in a more effective analysis of the development mechanism of attached cavitation. In summary, our proposed method not only streamlines the extraction of cavitation features from massive images but also enhances the understanding of development mechanisms of attached cavitation by providing additional data and more sensitive indicators for analysis.

PMID:39910333 | DOI:10.1038/s41598-025-88582-4

Sci Rep. 2025 Feb 5;15(1):4416. doi: 10.1038/s41598-025-88982-6.

ABSTRACT

This study aims to refine a radiomics-based diagnostic approach for detecting neonatal respiratory distress syndrome (NRDS) and examines the influence of rib suppression on the diagnostic precision of radiomics models using neonatal chest X-ray (CXR) images. A total of 138 CXR images were collected in this study. The data was partitioned into training and validation subsets based on chronological order. We applied rib suppression to the CXR images and extracted and analyzed radiomic features from lung regions both before and after rib suppression. This approach was designed to identify NRDS, develop radiomics models, and assess the impact of rib suppression on model performance. To establish these radiomics models, six machine learning models were utilized in the study. The performance was evaluated using the area under the receiver operating characteristic curve (AUC). On the validation set, the models demonstrated significant improvements after rib suppression. Specifically, the Gradient Boosting Machine (GBM) achieved an AUC of 0.781 post-suppression compared to 0.556 pre-suppression. Notably, Linear Discriminant Analysis (LDA) and Logistic Regression (LR) performed particularly well when combining features from both scenarios, achieving AUCs of 0.762 and 0.756. The results indicate the feasibility of developing radiomics models for diagnosing NRDS and highlight the enhancement in model performance due to rib suppression. This study provides a promising new method for the imaging diagnosis and prognosis evaluation of neonatal respiratory distress syndrome, showcasing the potential of radiomics in pediatric imaging.

PMID:39910276 | DOI:10.1038/s41598-025-88982-6

Sci Rep. 2025 Feb 5;15(1):4337. doi: 10.1038/s41598-025-88450-1.

ABSTRACT

Disabled persons demanding healthcare is a developing global occurrence. The support in longer-term care includes nursing, intricate medical, recovery, and social help services. The price is large, but advanced technologies can aid in decreasing expenditure by certifying effective health services and enhancing the superiority of life. The transformative latent of the Internet of Things (IoT) prolongs the existence of nearly one billion persons worldwide with disabilities. By incorporating smart devices and technologies, the IoT provides advanced solutions to tackle numerous tasks challenged by individuals with disabilities and promote equality. Human activity detection methods are the technical area which studies the classification of actions or movements an individual achieves over the recognition of signals directed by smartphones or wearable sensors or over images or video frames. They are efficient in certifying functions of detection of actions, observing crucial functions, and tracking. Conventional machine learning and deep learning approaches effectively detect human activity. This study develops and designs a metaheuristic optimization-driven ensemble model for smart monitoring of indoor activities for disabled persons (MOEM-SMIADP) model. The proposed MOEM-SMIADP model concentrates on detecting and classifying indoor activities using IoT applications for physically challenged people. First, data preprocessing is performed using min-max normalization to convert input data into useful format. Furthermore, the marine predator algorithm is employed in feature selection. For the detection of indoor activities, the proposed MOEM-SMIADP model utilizes an ensemble of three classifiers, namely the graph convolutional network model, long short-term memory sequence-to-sequence (LSTM-seq2seq) method, and convolutional autoencoder. Eventually, the hyperparameter tuning is accomplished by an improved coati optimization algorithm to enhance the classification outcomes of ensemble models. A wide range of experiments was accompanied to endorse the performance of the MOEM-SMIADP technique. The performance validation of the MOEM-SMIADP technique portrayed a superior accracy value of 99.07% over existing methods.

PMID:39910242 | DOI:10.1038/s41598-025-88450-1

Sci Rep. 2025 Feb 5;15(1):4406. doi: 10.1038/s41598-025-88907-3.

ABSTRACT

Employing two standard mammography views is crucial for radiologists, providing comprehensive insights for reliable clinical evaluations. This study introduces paired mammogram view based-network(PMVnet), a novel algorithm designed to enhance breast lesion detection by integrating relational information from paired whole mammograms, addressing the limitations of current methods. Utilizing 1,636 private mammograms, PMVnet combines cosine similarity and the squeeze-and-excitation method within a U-shaped architecture to leverage correlated information. Performance comparisons with single view-based models with VGGnet16, Resnet50, and EfficientnetB5 as encoders revealed PMVnet's superior capability. Using VGGnet16, PMVnet achieved a Dice Similarity Coefficient (DSC) of 0.709 in segmentation and a recall of 0.950 at 0.156 false positives per image (FPPI) in detection tasks, outperforming the single-view model, which had a DSC of 0.579 and a recall of 0.813 at 0.188 FPPI. These findings demonstrate PMVnet's effectiveness in reducing false positives and avoiding missed true positives, suggesting its potential as a practical tool in computer-aided diagnosis systems. PMVnet can significantly enhance breast lesion detection, aiding radiologists in making more precise evaluations and improving patient outcomes. Future applications of PMVnet may offer substantial benefits in clinical settings, improving patient care through enhanced diagnostic accuracy.

PMID:39910228 | DOI:10.1038/s41598-025-88907-3

Commun Biol. 2025 Feb 5;8(1):181. doi: 10.1038/s42003-025-07570-6.

ABSTRACT

Oligodendrocytes are the myelinating cells within the central nervous system, but the mechanisms by which transcription factors (TFs) cooperate for gene regulation in oligodendrocytes remain unclear. We introduce coTF-reg, an analytical framework that integrates scRNA-seq and scATAC-seq data to identify cooperative TFs co-regulating the target gene (TG). First, we identify co-binding TF pairs in the same oligodendrocyte-specific regulatory regions. Next, we train a deep learning model to predict each TG expression using the co-binding TFs' expressions. Shapley interaction scores reveal high interactions between co-binding TF pairs, such as SOX10-TCF12. Validation using oligodendrocyte eQTLs and their eGenes that are regulated by these cooperative TFs show potential regulatory roles for genetic variants. Experimental validation using ChIP-seq data confirms some cooperative TF pairs, such as SOX10-OLIG2. Prediction performance of our models is evaluated through holdout data and additional datasets, and an ablation study is also conducted. The results demonstrate stable and consistent performance.

PMID:39910206 | DOI:10.1038/s42003-025-07570-6

J Med Chem. 2025 Feb 5. doi: 10.1021/acs.jmedchem.5c00263. Online ahead of print.

ABSTRACT

Despite significant advancements in the treatment options for idiopathic pulmonary fibrosis (IPF), the disease remains aggressive and incurable. This viewpoint summarizes the discovery of a neutral, potent, and selective lysophosphatidic acid receptor 1 antagonist for the treatment of IPF. The lead optimization without the cocrystal structure guidance is worth it to highlight.

PMID:39909836 | DOI:10.1021/acs.jmedchem.5c00263