Eur J Med Res. 2025 Feb 27;30(1):143. doi: 10.1186/s40001-025-02406-9.

ABSTRACT

BACKGROUND: Overactive bladder (OAB) syndrome has a significant impact on quality of life, and vibegron has emerged as a therapeutic option. This study aims to evaluate the safety profile of vibegron in a disproportionality analysis by analyzing adverse event (AE) reports from the Food and Drug Administration Adverse Event Reporting System (FAERS) database.

METHODS: We conducted a retrospective analysis of the FAERS database from January 2021 to September 2023. After duplicate removal and thorough screening, 1137 vibegron-related AE reports were identified. We analyzed these reports for demographic and clinical characteristics, signal detection at the system organ class (SOC) level, and specific AEs.

RESULTS: Females comprised a higher percentage (67.72%) of AE reports compared to males. The elderly population (age > 64 years) accounted for 15.84% of the cases. The majority (95.69%) of the reports originated from the USA. Signal detection revealed significant findings across 19 organ systems with notable SOCs, including renal and urinary disorders (ROR = 7.72, 95%CI 6.83-8.72), gastrointestinal disorders (ROR = 1.38, 95%CI 1.21-1.58), and respiratory, thoracic, and mediastinal disorders (ROR = 1.21, 95%CI 1.01-1.45). In addition, several unexpected AEs were identified, such as dry mouth, hot flush, constipation, and increased blood pressure.

CONCLUSIONS: This study provides comprehensive insights into vibegron's safety profile, revealing both known and unexpected AEs. The findings highlight the need for careful patient selection and monitoring, especially among females and the elderly. The results advocate for ongoing pharmacovigilance and further research to ensure vibegron's safe and effective use in OAB treatment.

PMID:40016845 | DOI:10.1186/s40001-025-02406-9

Sci Rep. 2025 Feb 27;15(1):7035. doi: 10.1038/s41598-024-83555-5.

ABSTRACT

The relationship between ischemic stroke (IS) and pyroptosis centers on the inflammatory response elicited by cerebral tissue damage during an ischemic stroke event. However, an in-depth mechanistic understanding of their connection remains limited. This study aims to comprehensively analyze the gene expression patterns of pyroptosis-related differentially expressed genes (PRDEGs) by employing integrated IS datasets and machine learning techniques. The primary objective was to develop classification models to identify crucial PRDEGs integral to the ischemic stroke process. Leveraging three distinct machine learning algorithms (LASSO, Random Forest, and Support Vector Machine), models were developed to differentiate between the Control and the IS patient samples. Through this approach, a core set of 10 PRDEGs consistently emerged as significant across all three machine learning models. Subsequent analysis of these genes yielded significant insights into their functional relevance and potential therapeutic approaches. In conclusion, this investigation underscores the pivotal role of pyroptosis pathways in ischemic stroke and identifies pertinent targets for therapeutic development and drug repurposing.

PMID:40016488 | DOI:10.1038/s41598-024-83555-5

Sci Rep. 2025 Feb 28;15(1):7109. doi: 10.1038/s41598-025-91096-8.

ABSTRACT

Computational approaches complement traditional in-vitro or in-vivo assays, significantly accelerating the drug discovery process by increasing the probability of identifying promising lead compounds. In this study, the apoptotic compounds were assessed for antimycobacterial activity and immunomodulatory potential in infected THP-1 macrophage cells. The antimycobacterial activity of the apoptotic compounds was evaluated using the minimum inhibitory concentration (MIC) assay. The immunomodulatory potential of the apoptotic compounds was determined on mycobacterial-infected THP-1 and non-infected THP-1 macrophage cells. The potential binding dynamics of the compounds against InhA were predicted using molecular docking, molecular dynamics, and MM-GBSA binding free energies. The in-vitro MIC assay showed that cepharanthine (CEP) had the highest antimycobacterial activity against Mycobacterium smegmatis mc2155 and Mycobacterium tuberculosis H37Rv, with MICs of 3.1 and 1.5 µg/mL, respectively, followed by CP-31398 dihydrochloride hydrate (DIH) (MICs = 6.2 and 3.1 µg/mL, respectively), marinopyrrole A (MAR) (MICs = 25 and 12.5 µg/mL, respectively), and nutlin-3a (NUT) (MICs = 50 and 25 µg/mL, respectively). MICs for the rest of the drugs were > 200 µg/mL against both M. smegmatis mc2155 and M. tuberculosis H37Rv. Furthermore, the growth of M. smegmatis mc2155 in infected THP-1 macrophage cells treated with DIH, CEP, carboxyatractyloside potassium salt (CAR), and NUT was inhibited by the mentioned drugs. Cytokine profiling showed that DIH optimally regulated the secretion of IL-1β and TNF-α which potentially enhanced the clearance of the intracellular pathogen. Molecular dynamics simulations showed that NUT, MAR, 17-(allylamino)-17-demethoxygeldanamycin (17-AAG), and BV02 strongly bind to InhA. However, 17-AAG and BV02 did not show significant activity in-vitro. This study highlights the importance of probing already existing chemical scaffolds as a starting point for discovery of therapeutic agents against M. tuberculosis H37Rv using both pathogen and host directed approaches. The integration of molecular dynamics simulations provides valuable insights into potential scaffold modifications to enhance the affinity.

PMID:40016256 | DOI:10.1038/s41598-025-91096-8

NPJ Genom Med. 2025 Feb 27;10(1):13. doi: 10.1038/s41525-025-00474-8.

ABSTRACT

Advances in genomic technologies have revolutionized the diagnosis of rare genetic diseases, leading to the emergence of precision therapies. However, there remains significant effort ahead to ensure the promise of precision medicine translates to improved outcomes. Here, we discuss the challenges in advancing precision child health and highlight how international collaborations such as the International Precision Child Health Partnership, which embed research into clinical care, can maximize benefits for children globally.

PMID:40016282 | DOI:10.1038/s41525-025-00474-8

Neuromolecular Med. 2025 Feb 27;27(1):18. doi: 10.1007/s12017-025-08840-6.

ABSTRACT

Cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL) is the most common genetic form of stroke. It is caused by a cysteine-altering variant in one of the 34 epidermal growth factor-like repeat (EGFr) domains of Notch3. NOTCH3 pathogenic variants in EGFr 1-6 are associated with high disease severity, whereas those in EGFr 7-34 are associated with late stroke onset and increased survival. However, whether and how the position of the NOTCH3 variant directly affects the disease severity remains unclear. In this study, we aimed to generate human-induced pluripotent stem cells (hiPSCs) from patients with CADASIL with EGFr 1-6 and 7-34 pathogenic variants to evaluate whether the NOTCH3 position affects the cell phenotype and protein profile of the generated hiPSCs lines. Six hiPSCs lines were generated: two from patients with CADASIL with EGFr 1-6 pathogenic variants, two from patients with EGFr 7-34 variants, and two from controls. Notch3 aggregation and protein profiles were tested in the established six hiPSCs lines. Cell analysis revealed that the NOTCH3 variants did not limit the cell reprogramming efficiency. However, EGFr 1-6 variant position was associated with increased accumulation of Notch3 protein in pluripotent stem cells and proteomic changes related with cytoplasmic reorganization mechanisms. In conclusion, our analysis of hiPSCs derived from patients with CADASIL support the clinical association between the NOTCH3 variant position and severity of CADASIL.

PMID:40016442 | DOI:10.1007/s12017-025-08840-6

Chem Biol Interact. 2025 Feb 25:111448. doi: 10.1016/j.cbi.2025.111448. Online ahead of print.

ABSTRACT

A comprehensive understanding of isoniazid (INH)-mediated hepatotoxic effects is essential for developing strategies to predict and prevent severe liver toxicity in tuberculosis treatment. In this study, we used multi-omics profiling in vitro to investigate the toxic effects of INH, revealing significant involvement of endoplasmic reticulum (ER) stress, mitochondrial impairment, redox imbalance, and altered metabolism. Additional analysis using transcriptomics data from repeated time-course INH treatments on human-specific hepatic microtissues revealed that cellular responses to ER stress and oxidative stress happened prior to disturbances in mitochondrial complexes. Mechanistic validation studies using time-lapse measurements of cytosolic and mitochondrial reactive oxygen species (ROS) revealed that INH initially triggered cytosolic ROS increasement and Nrf2 signaling pathway activation before mitochondrial ROS accumulation. Molecular imaging showed that INH subsequently disrupted mitochondrial function by impairing respiratory complexes I-IV and caused mitochondrial membrane proton leakage without affecting mitochondrial complex V, leading to mitochondrial depolarization and reduced ATP production. These disturbances enhanced mitochondrial fission and mitophagy. Our findings highlight the potential of inhibiting ER stress during early INH exposure to mitigate cytosolic and mitochondrial oxidative stress. We also revealed the critical role of Nrf2 signaling in protecting hepatocytes under INH-induced oxidative stress by maintaining redox homeostasis and enabling metabolic reprogramming through regulating antioxidant gene expression and cellular lipid abundance. Alternative antioxidant pathways, including selenocompound metabolism, HIF-1 signaling, and the pentose phosphate pathway-also responded to INH-induced oxidative stress. Collectively, our study emphasizes the importance of ER stress, redox imbalance, metabolic changes, and mitochondrial dysfunction that underlie INH-induced hepatotoxicity.

PMID:40015660 | DOI:10.1016/j.cbi.2025.111448

Intensive Care Med Exp. 2025 Feb 27;13(1):27. doi: 10.1186/s40635-025-00731-1.

ABSTRACT

BACKGROUND: Streptococcus pneumoniae, a primary cause of community-acquired pneumonia (CAP), is typically treated with β-lactams and macrolides or quinolones. Corticosteroids are now recommended as adjunctive therapy in severe CAP to improve outcomes. In this prospective randomized animal study, we evaluated the bactericidal efficacy of various antibiotic regimens combined with corticosteroids using a porcine pneumococcal pneumonia model.

RESULTS: In 30 White-Landrace female pigs, pneumonia was induced by intrabronchial inoculation of macrolide-resistant S. pneumoniae 19A isolate. Animals were randomized to receive saline, ceftriaxone (CRO) with levofloxacin (LVX), CRO with azithromycin (AZM), or combinations of these with methylprednisolone (MP). The primary outcome, S. pneumoniae concentrations in lung tissue after 48 h of treatment, showed that the CRO + LVX, CRO + AZM, CRO + LVX + MP, and CRO + AZM + MP groups were equally effective in reducing bacterial load. However, complete bacterial eradication from lung tissue was achieved only in the CRO + AZM + MP group. Secondary outcomes, including bacterial burden in tracheal aspirates and bronchoalveolar lavage (BAL) samples, showed similar bactericidal activity across all treatment groups. The CRO + AZM + MP group demonstrated the most controlled inflammatory response, achieving baseline levels of inflammation, while other groups exhibited elevated inflammatory markers.

CONCLUSIONS: Despite using a macrolide-resistant S. pneumoniae isolate, the combination of CRO, AZM, and MP achieves similar or even superior results compared to other antibiotic combinations. This regimen provides both bactericidal and immunomodulatory benefits, suggesting its effectiveness in treating macrolide-resistant S. pneumoniae pneumonia.

PMID:40016489 | DOI:10.1186/s40635-025-00731-1

Methods Mol Biol. 2025;2903:97-111. doi: 10.1007/978-1-0716-4410-2_9.

ABSTRACT

Rhinovirus primarily infects airway epithelial cells lining the conductive airways. Mucociliary-differentiated airway epithelial cell cultures, established from airway basal cells, are relevant in vitro model systems to examine the rhinovirus-stimulated innate immune responses and changes in barrier function. The airway epithelium in patients with chronic respiratory diseases such as asthma, cystic fibrosis, and chronic obstructive pulmonary disease often shows remodeling, such as goblet cell metaplasia, squamous metaplasia, and basal cell hyperplasia. Such changes profoundly affect the airway epithelial responses to rhinovirus infection. Previously, we have demonstrated that mucociliary-differentiated cell cultures, established from airway basal cells isolated from COPD patients, show goblet cell and basal cell hyperplasia similar to that observed in patients. These cultures also show a pro-inflammatory phenotype and abnormal innate immune responses to rhinovirus infection. We describe a culturing method that maintains these in vivo features.

PMID:40016461 | DOI:10.1007/978-1-0716-4410-2_9

Transplant Proc. 2025 Feb 26:S0041-1345(25)00084-3. doi: 10.1016/j.transproceed.2025.01.007. Online ahead of print.

ABSTRACT

Genetic mutations are increasingly recognized as significant contributors to post-transplant complications. Common genetic conditions, such as short telomere syndrome (STS), lymphangioleiomyomatosis, cystic fibrosis (CF), and alpha-1 antitrypsin deficiency (AAT), have been documented to influence outcomes in lung transplant recipients. Here, we present a case of hereditary transthyretin (ATTR) cardiac amyloidosis leading to heart failure in a 71-year-old female, six years after undergoing a single-lung transplantation (LTx) for interstitial lung disease. This case report highlights the need for awareness of genetic predispositions, including rare conditions such as hereditary ATTR amyloidosis, among individuals being considered for solid organ transplantation.

PMID:40016044 | DOI:10.1016/j.transproceed.2025.01.007

J Biol Chem. 2025 Feb 25:108355. doi: 10.1016/j.jbc.2025.108355. Online ahead of print.

ABSTRACT

The 2-methylcitrate cycle (2-MCC) and the glyoxylate cycle are central metabolic pathways in Pseudomonas aeruginosa, enabling the organism to utilize organic acids such as propionate and acetate during infection. Here, we show that these cycles are linked through enzymatic redundancy, with isocitrate lyase (AceA) exhibiting secondary 2-methylisocitrate lyase (2-MICL) activity. Furthermore, we use a combination of structural analyses, enzyme kinetics, metabolomics, and targeted mutation of PrpBPa to demonstrate that whereas loss of PrpB function impairs growth on propionate, the promiscuous 2-MICL activity of AceA compensates for this by mitigating the accumulation of toxic 2-MCC intermediates. Our findings suggest that simultaneous inhibition of PrpB and AceA could present a robust antimicrobial strategy to target P. aeruginosa in propionate-rich environments, such as the cystic fibrosis airways. Our results emphasize the importance of understanding pathway interconnections in the development of novel antimicrobial agents.

PMID:40015638 | DOI:10.1016/j.jbc.2025.108355

Lancet Infect Dis. 2025 Feb 24:S1473-3099(24)00804-1. doi: 10.1016/S1473-3099(24)00804-1. Online ahead of print.

ABSTRACT

BACKGROUND: Sipavibart is an anti-spike monoclonal antibody that neutralises SARS-CoV-2 with exceptions, including Phe456Leu-containing variants (eg, KP.2* and KP.3*). This trial assessed sipavibart efficacy and safety for prevention of symptomatic COVID-19 in participants who are immunocompromised.

METHODS: In this ongoing, double-blind, international, phase 3 trial, we enrolled participants who were immunocompromised and aged 12 years or older at 197 hospitals, university health centres, and clinical trial units in 18 countries. Participants were randomly allocated 1:1 to a sipavibart group (intramuscular sipavibart 300 mg on days 1 and 181) or a comparator group (tixagevimab 300 mg-cilgavimab 300 mg on day 1 and placebo on day 181 or placebo on days 1 and 181), stratified by previous COVID-19 vaccination and infection status and use of tixagevimab-cilgavimab. The primary efficacy outcomes were symptomatic COVID-19 caused by any variant or symptomatic COVID-19 caused by non-Phe456Leu-containing variants within 181 days of dosing, assessed in the SARS-CoV-2-negative set, comprising all participants without a positive RT-PCR test for SARS-CoV-2 at baseline and who received at least one trial intervention dose. Safety outcomes for adverse events were assessed 90 days following the first dose and for serious adverse events throughout the study in the safety analysis set (ie, all participants who received at least one injection of sipavibart or comparator). This study is registered with ClinicalTrials.gov, NCT05648110.

FINDINGS: Participants were screened from March 31 to Oct 27, 2023; 3349 participants (56·8% female) were randomly assigned: 1674 to the sipavibart group (five no first dose; 1669 sipavibart) and 1675 to the comparator group (nine no first dose; 1105 tixagevimab-cilgavimab and 561 placebo). Within 181 days of dosing, 122 (7·4%) of 1649 participants in the sipavibart group and 178 (10·9%) of 1631 participants in the comparator group had symptomatic COVID-19 due to any variant (relative risk reduction [RRR] 34·9% [97·5% CI 15·0 to 50·1]; p=0·0006), 54 (3·3%) participants in the sipavibart group and 90 (5·5%) participants in the comparator group had symptomatic COVID-19 due to non-Phe456Leu-containing variants (RRR 42·9% [95% CI 19·9 to 59·3]; p=0·0012), and 47 (2·9%) participants in the sipavibart group and 64 (3·9%) participants in the comparator group had symptomatic COVID-19 due to Phe456Leu-containing variants (30·4% [-1·8 to 52·5]). Adverse events occurred in 833 (49·9%) of 1671 participants in the sipavibart group and 857 (51·5%) of 1663 participants in the comparator group within 3 months of the first dose. One COVID-19-related death occurred in the comparator group. Serious adverse events considered related to trial intervention occurred in two (0·1%) of 1671 participants in the sipavibart group and seven (0·4%) of 1663 participants in the comparator group (none fatal). No serious cardiovascular or thrombotic events were considered to be related to sipavibart.

INTERPRETATION: The primary analysis showed efficacy and safety of sipavibart in preventing symptomatic COVID-19 in participants who are immunocompromised when susceptible (ie, non-Phe456Leu-containing) variants dominated, although no efficacy was shown against resistant (ie, Phe456Leu-containing) variants that dominate as of November, 2024.

FUNDING: AstraZeneca.

PMID:40015292 | DOI:10.1016/S1473-3099(24)00804-1

J Cannabis Res. 2025 Feb 27;7(1):13. doi: 10.1186/s42238-025-00268-w.

ABSTRACT

BACKGROUND: Cannabis sativa L. with a rich history of traditional medicinal use, has garnered significant attention in contemporary research for its potential therapeutic applications in various human diseases, including pain, inflammation, cancer, and osteoarthritis. However, the specific molecular targets and mechanisms underlying the synergistic effects of its diverse phytochemical constituents remain elusive. Understanding these mechanisms is crucial for developing targeted, effective cannabis-based therapies.

METHODS: To investigate the molecular targets and pathways involved in the synergistic effects of cannabis compounds, we utilized DRIFT, a deep learning model that leverages attention-based neural networks to predict compound-target interactions. We considered both whole plant extracts and specific plant-based formulations. Predicted targets were then mapped to the Reactome pathway database to identify the biological processes affected. To facilitate the prediction of molecular targets and associated pathways for any user-specified cannabis formulation, we developed CANDI (Cannabis-derived compound Analysis and Network Discovery Interface), a web-based server. This platform offers a user-friendly interface for researchers and drug developers to explore the therapeutic potential of cannabis compounds.

RESULTS: Our analysis using DRIFT and CANDI successfully identified numerous molecular targets of cannabis compounds, many of which are involved in pathways relevant to pain, inflammation, cancer, and other diseases. The CANDI server enables researchers to predict the molecular targets and affected pathways for any specific cannabis formulation, providing valuable insights for developing targeted therapies.

CONCLUSIONS: By combining computational approaches with knowledge of traditional cannabis use, we have developed the CANDI server, a tool that allows us to harness the therapeutic potential of cannabis compounds for the effective treatment of various disorders. By bridging traditional pharmaceutical development with cannabis-based medicine, we propose a novel approach for botanical-based treatment modalities.

PMID:40016810 | DOI:10.1186/s42238-025-00268-w

Breast Cancer Res. 2025 Feb 27;27(1):30. doi: 10.1186/s13058-025-01971-5.

ABSTRACT

OBJECTIVE: The aim of this study was to develop and validate a deep learning radiomics (DLR) model based on longitudinal ultrasound data and clinical features to predict pathologic complete response (pCR) after neoadjuvant chemotherapy (NAC) in breast cancer patients.

METHODS: Between January 2018 and June 2023, 312 patients with histologically confirmed breast cancer were enrolled and randomly assigned to a training cohort (n = 219) and a test cohort (n = 93) in a 7:3 ratio. Next, pre-NAC and post-treatment 2-cycle ultrasound images were collected, and radiomics and deep learning features were extracted from NAC pre-treatment (Pre), post-treatment 2 cycle (Post), and Delta (pre-NAC-NAC 2 cycle) images. In the training cohort, to filter features, the intraclass correlation coefficient test, the Boruta algorithm, and the least absolute shrinkage and selection operator (LASSO) logistic regression were used. Single-modality models (Pre, Post, and Delta) were constructed based on five machine-learning classifiers. Finally, based on the classifier with the optimal predictive performance, the DLR model was constructed by combining Pre, Post, and Delta ultrasound features and was subsequently combined with clinical features to develop a combined model (Integrated). The discriminative power, predictive performance, and clinical utility of the models were further evaluated in the test cohort. Furthermore, patients were assigned into three subgroups, including the HR+/HER2-, HER2+, and TNBC subgroups, according to molecular typing to validate the predictability of the model across the different subgroups.

RESULTS: After feature screening, 16, 13, and 10 features were selected to construct the Pre model, Post model, and Delta model based on the five machine learning classifiers, respectively. The three single-modality models based on the XGBoost classifier displayed optimal predictive performance. Meanwhile, the DLR model (AUC of 0.827) was superior to the single-modality model (Pre, Post, and Delta AUCs of 0.726, 0.776, and 0.710, respectively) in terms of prediction performance. Moreover, multivariate logistic regression analysis identified Her-2 status and histological grade as independent risk factors for NAC response in breast cancer. In both the training and test cohorts, the Integrated model, which included Pre, Post, and Delta ultrasound features and clinical features, exhibited the highest predictive ability, with AUC values of 0.924 and 0.875, respectively. Likewise, the Integrated model displayed the highest predictive performance across the different subgroups.

CONCLUSION: The Integrated model, which incorporated pre-NAC treatment and early treatment ultrasound data and clinical features, accurately predicted pCR after NAC in breast cancer patients and provided valuable insights for personalized treatment strategies, allowing for timely adjustment of chemotherapy regimens.

PMID:40016785 | DOI:10.1186/s13058-025-01971-5

BMC Med. 2025 Feb 27;23(1):127. doi: 10.1186/s12916-025-03962-x.

ABSTRACT

BACKGROUND: Early diagnosis of biliary atresia (BA) is crucial for improving patient outcomes, yet remains a significant global challenge. This challenge may be ameliorated through the application of artificial intelligence (AI). Despite the promise of AI in medical diagnostics, its application to multimodal BA data has not yet achieved substantial breakthroughs. This study aims to leverage diverse data sources and formats to develop an intelligent diagnostic system for BA.

METHODS: We constructed the largest known multimodal BA dataset, comprising ultrasound images, clinical data, and laboratory results. Using this dataset, we developed a novel deep learning model and simplified it using easily obtainable data, eliminating the need for blood samples. The models were externally validated in a prospective study. We compared the performance of our model with human experts of varying expertise levels and evaluated the AI system's potential to enhance its diagnostic accuracy.

RESULTS: The retrospective study included 1579 participants. The multimodal model achieved an AUC of 0.9870 on the internal test set, outperforming human experts. The simplified model yielded an AUC of 0.9799. In the prospective study's external test set of 171 cases, the multimodal model achieved an AUC of 0.9740, comparable to that of a radiologist with over 10 years of experience (AUC = 0.9766). For less experienced radiologists, the AI-assisted diagnostic AUC improved from 0.6667 to 0.9006.

CONCLUSIONS: This AI-based screening application effectively facilitates early diagnosis of BA and serves as a valuable reference for addressing common challenges in rare diseases. The model's high accuracy and its ability to enhance the diagnostic performance of human experts underscore its potential for significant clinical impact.

PMID:40016769 | DOI:10.1186/s12916-025-03962-x

BMC Biol. 2025 Feb 27;23(1):63. doi: 10.1186/s12915-025-02166-2.

ABSTRACT

BACKGROUND: Cyclic peptides, known for their high binding affinity and low toxicity, show potential as innovative drugs for targeting "undruggable" proteins. However, their therapeutic efficacy is often hindered by poor membrane permeability. Over the past decade, the FDA has approved an average of one macrocyclic peptide drug per year, with romidepsin being the only one targeting an intracellular site. Biological experiments to measure permeability are time-consuming and labor-intensive. Rapid assessment of cyclic peptide permeability is crucial for their development.

RESULTS: In this work, we proposed a novel deep learning model, dubbed as MultiCycPermea, for predicting cyclic peptide permeability. MultiCycPermea extracts features from both the image information (2D structural information) and sequence information (1D structural information) of cyclic peptides. Additionally, we proposed a substructure-constrained feature alignment module to align the two types of features. MultiCycPermea has made a leap in predictive accuracy. In the in-distribution setting of the CycPeptMPDB dataset, MultiCycPermea reduced the mean squared error (MSE) by approximately 44.83% compared to the latest model Multi_CycGT (0.29 vs 0.16). By leveraging visual analysis tools, MultiCycPermea can reveal the relationship between peptide modification structures and membrane permeability, providing insights to improve the membrane permeability of cyclic peptides.

CONCLUSIONS: MultiCycPermea provides an effective tool that accurately predicts the permeability of cyclic peptides, offering valuable insights for improving the membrane permeability of cyclic peptides. This work paves a new path for the application of artificial intelligence in assisting the design of membrane-permeable cyclic peptides.

PMID:40016695 | DOI:10.1186/s12915-025-02166-2

BMC Bioinformatics. 2025 Feb 27;26(1):68. doi: 10.1186/s12859-025-06081-9.

ABSTRACT

BACKGROUND: Protein large language models (LLM) have been used to extract representations of enzyme sequences to predict their function, which is encoded by enzyme commission (EC) numbers. However, a comprehensive comparison of different LLMs for this task is still lacking, leaving questions about their relative performance. Moreover, protein sequence alignments (e.g. BLASTp or DIAMOND) are often combined with machine learning models to assign EC numbers from homologous enzymes, thus compensating for the shortcomings of these models' predictions. In this context, LLMs and sequence alignment methods have not been extensively compared as individual predictors, raising unaddressed questions about LLMs' performance and limitations relative to the alignment methods. In this study, we set out to assess the performance of ESM2, ESM1b, and ProtBERT language models in their ability to predict EC numbers, comparing them with BLASTp, against each other and against models that rely on one-hot encodings of amino acid sequences.

RESULTS: Our findings reveal that combining these LLMs with fully connected neural networks surpasses the performance of deep learning models that rely on one-hot encodings. Moreover, although BLASTp provided marginally better results overall, DL models provide results that complement BLASTp's, revealing that LLMs better predict certain EC numbers while BLASTp excels in predicting others. The ESM2 stood out as the best model among the LLMs tested, providing more accurate predictions on difficult annotation tasks and for enzymes without homologs.

CONCLUSIONS: Crucially, this study demonstrates that LLMs still have to be improved to become the gold standard tool over BLASTp in mainstream enzyme annotation routines. On the other hand, LLMs can provide good predictions for more difficult-to-annotate enzymes, particularly when the identity between the query sequence and the reference database falls below 25%. Our results reinforce the claim that BLASTp and LLM models complement each other and can be more effective when used together.

PMID:40016653 | DOI:10.1186/s12859-025-06081-9

BMC Cancer. 2025 Feb 27;25(1):367. doi: 10.1186/s12885-025-13740-w.

ABSTRACT

As reported by the International Agency for Research on Cancer (IARC), the global incidence of cancer reached nearly 20 million new cases in recent years, with cancer-related fatalities amounting to around 9.7 million. This underscores the profound impact cancer has on public health worldwide. Deep learning has become a mainstream approach in cancer recognition. Despite its significant progress, deep learning is known for its requirement of large quantities of labeled data. Few-shot learning addresses this limitation by reducing the need for extensive labeled samples. In the field of cancer recognition, data collection is particularly challenging due to the scarcity of categories compared to other fields, and current few-shot learning methods have not yielded satisfactory results. To tackle this, we propose an auxiliary meta-learning strategy for cancer recognition. During the auxiliary training phase, the feature mapping model is trained in conjunction with external data. This process neutralizes the prediction probability of misclassification, allowing the model to more readily learn distinguishing features and avoid performance degradation caused by discrepancies in external data. Additionally, the redundancy of some input principal components in the feature mapping model is reduced, while the implicit information within these components is extracted. The training process is further accelerated by utilizing depthwise over-parameterized convolutional layers. Moreover, the implementation of a three-branch structure contributes to faster training and enhanced performance. In the meta-training stage, the feature mapping model is optimized within the embedding space, utilizing category prototypes and cosine distance. During the meta-testing phase, a small number of labeled samples are employed to classify unknown data. We have conducted extensive experiments on the BreakHis, Pap smear, and ISIC 2018 datasets. The results demonstrate that our method achieves superior accuracy in cancer recognition. Furthermore, experiments on few-shot benchmark datasets indicate that our approach exhibits excellent generalization capabilities.

PMID:40016648 | DOI:10.1186/s12885-025-13740-w

Sci Rep. 2025 Feb 27;15(1):7009. doi: 10.1038/s41598-025-90646-4.

ABSTRACT

Detecting cassava leaf disease is challenging because it is hard to identify diseases accurately through visual inspection. Even trained agricultural experts may struggle to diagnose the disease correctly which leads to potential misjudgements. Traditional methods to diagnose these diseases are time-consuming, prone to error, and require expert knowledge, making automated solutions highly preferred. This paper explores the application of advanced deep learning techniques to detect as well as classify cassava leaf diseases which includes EfficientNet models, DenseNet169, Xception, MobileNetV2, ResNet models, Vgg19, InceptionV3, and InceptionResNetV2. A dataset consisting of around 36,000 labelled images of cassava leaves, afflicted by diseases such as Cassava Brown Streak Disease, Cassava Mosaic Disease, Cassava Green Mottle, Cassava Bacterial Blight, and healthy leaves, was used to train these models. Further the images were pre-processed by converting them into grayscale, reducing noise using Gaussian filter, obtaining the region of interest using Otsu binarization, Distance transformation, as well as Watershed technique followed by employing contour-based feature selection to enhance model performance. Models, after fine-tuned with ADAM optimizer computed that among the tested models, the hybrid model (DenseNet169 + EfficientNetB0) had superior performance with classification accuracy of 89.94% while as EfficientNetB0 had the highest values of precision, recall, and F1score with 0.78 each. The novelty of the hybrid model lies in its ability to combine DenseNet169's feature reuse capability with EfficientNetB0's computational efficiency, resulting in improved accuracy and scalability. These results highlight the potential of deep learning for accurate and scalable cassava leaf disease diagnosis, laying the foundation for automated plant disease monitoring systems.

PMID:40016508 | DOI:10.1038/s41598-025-90646-4

NPJ Digit Med. 2025 Feb 27;8(1):126. doi: 10.1038/s41746-025-01455-y.

ABSTRACT

Recognizing the limitations of computer-assisted tools for thyroid nodule diagnosis using static ultrasound images, this study developed a diagnostic tool utilizing dynamic ultrasound video, namely Thyroid Nodules Visualization (TNVis), by leveraging a two-stage deep learning framework that involved three-dimensional (3D) visualization. In this multicenter study, 4569 cases were included for framework development, and data from seven hospitals were employed for diagnostic validation. TNVis achieved a Dice similarity coefficient of 0.90 after internal testing. For the external validation, TNVis significantly improved radiologists' performance, reaching an AUC of 0.79, compared to their diagnostic performance without the use of TNVis (AUC: 0.66; p < 0.001) and those with partial assistance (AUC: 0.72; p < 0.001). In conclusion, the TNVis-assisted diagnostic strategy not only significantly improves the diagnostic ability of radiologists but also closely imitates their clinical diagnostic procedures and provides them with an objective 3D representation of the nodules for precise and personalized diagnosis and treatment planning.

PMID:40016505 | DOI:10.1038/s41746-025-01455-y

NPJ Digit Med. 2025 Feb 27;8(1):130. doi: 10.1038/s41746-025-01473-w.

ABSTRACT

Glaucoma, a leading cause of blindness, requires accurate early detection. We present an AI-based Glaucoma Screening (AI-GS) network comprising six lightweight deep learning models (total size: 110 MB) that analyze fundus images to identify early structural signs such as optic disc cupping, hemorrhages, and nerve fiber layer defects. The segmentation of the optic cup and disc closely matches that of expert ophthalmologists. AI-GS achieved a sensitivity of 0.9352 (95% CI 0.9277-0.9435) at 95% specificity. In real-world testing, sensitivity dropped to 0.5652 (95% CI 0.5218-0.6058) at ~0.9376 specificity (95% CI 0.9174-0.9562) for the standalone binary glaucoma classification model, whereas the full AI-GS network maintained higher sensitivity (0.8053, 95% CI 0.7704-0.8382) with good specificity (0.9112, 95% CI 0.8887-0.9356). The sub-models in AI-GS, with enhanced capabilities in detecting early glaucoma-related structural changes, drive these improvements. With low computational demands and tunable detection parameters, AI-GS promises widespread glaucoma screening, portable device integration, and improved understanding of disease progression.

PMID:40016437 | DOI:10.1038/s41746-025-01473-w