Zhongguo Zhong Yao Za Zhi. 2024 Dec;49(23):6399-6406. doi: 10.19540/j.cnki.cjcmm.20240904.402.

ABSTRACT

To investigate the therapeutic effect of Fuzheng Tongluo Granules on idiopathic pulmonary fibrosis(IPF) and its mechanism. Seventy-two SD rats were randomly divided into the control group, model group, pirfenidone group(162 mg·kg~(-1)), and low-, medium-and high-dose of Fuzheng Tongluo Granules groups(2.63, 5.25, 10.5 g·kg~(-1)). Rat model of IPF was induced by a single non-invasive tracheal intubation drip of bleomycin(BLM). The corresponding drugs were given daily by gavage after the 2nd day of modeling, and body mass was recorded. On the 28th day, the samples were collected and weighed, and the lung coefficients were calculated. The pathological changes in the lung tissue were observed by HE and Masson staining, and the hydroxyproline(HYP) content of the lung tissue was detected by alkaline hydrolysis. The contents of tumor necrosis factor-α(TNF-α), interleukin-1β(IL-1β), and interleukin-18(IL-18) of the lung tissue were determined by ELISA. The expression of collagen type Ⅰ(collagen Ⅰ) and α-smooth muscle actin(α-SMA) was observed by immunohistochemistry. The expression levels of NOD-, LRR-and pyrin domain-containing 3(NLRP3), cysteine-requiring aspartate protease type 1(caspase-1), gasdermin D-N(GSDMD-N), and apoptosis-associated speck-like protein containing a CARD(ASC) in the lung tissue were detected by Western blot. Immunofluorescence co-localization was used to observe the expression of GSDMD and CD68. The results show that compared with the control group, the model group showed increased lung coefficient, Ashcroft score, Szapiel score, HYP, TNF-α, IL-1β, and IL-18 content in the lung tissue and elevated protein expression levels of NLRP3, caspase-1, GSDMD-N, and ASC. The expression levels of GSDMD and CD68 were increased, and there was a high degree of co-localization between GSDMD and CD68. Compared with those in the model group, the lung coefficient, Ashcroft score, and Szapiel score decreased in all drug administration groups, and the content of HYP, TNF-α, IL-1β, and IL-18 decreased. The protein expression levels of NLRP3, caspase-1, GSDMD-N, and ASC decreased, and the expression levels of GSDMD and CD68 were reduced. There was a high degree of co-localization between GSDMD and CD68. In summary, Fuzheng Tongluo Granules can effectively reduce pulmonary fibrosis and inflammation levels in rats with IPF, and the mechanism may be related to the down-regulation of the NLRP3/caspase-1/GSDMD pathway to inhibit macrophage pyroptosis.

PMID:39805786 | DOI:10.19540/j.cnki.cjcmm.20240904.402

Zhongguo Zhong Yao Za Zhi. 2024 Dec;49(24):6803-6812. doi: 10.19540/j.cnki.cjcmm.20240821.501.

ABSTRACT

This study systematically retrieved the clinical studies in the treatment of idiopathic pulmonary fibrosis(IPF) with traditional Chinese medicine(TCM) and employed evidence mapping to summarize the overall research status and deficiencies of TCM in treating IPF. CNKI, VIP, SinoMed, Wanfang, PubMed, Web of Science, Cochrane Library, and EMbase were searched for the relevant studies published from inception to February 20, 2024. The distribution characteristics of the evidence were analyzed and presented through charts combined with words. A total of 323 studies were included, including 295 randomized controlled trials(RCTs) and 28 Meta-analysis. The number of publications in this field rose with fluctuations, yet the proportion of core papers was low, and the research lacked the attention of foreign researchers. There were scant cross-regional collaboration between researchers and insufficient attention from relevant departments. The included RCT generally had low quality, with small sample sizes, short treatment courses, and insufficient attention to acute exacerbation and complications of IPF. In addition, few studies employed TCM alone, and the TCM syndromes remained to be standardized. A considerable number of outcome indicators were involved in the publications, while the majority of them failed to emphasize the disparity between primary and secondary outcome indicators. There were diverse reference standards for the comprehensive indicators among the outcome indicators, and insufficient attention was paid to long-term prognosis and health economic indicators. The included Meta-analysis concluded that TCM had potential clinical efficacy in treating IPF. However, the methodological credibility grading and the GRADE grading results of outcome indicators were low. The results suggested that TCM demonstrated certain advantages in the treatment of IPF, while the quality of the included studies was not high. In the future, clinical research protocols should be standardized and registered. Multicenter, large-sample, and follow-up clinical studies should be conducted. The research reports should refer to relevant reporting standards to improve the quality and generate high-level evidence, thus providing a reference for the clinical application of TCM in the treatment of IPF.

PMID:39805768 | DOI:10.19540/j.cnki.cjcmm.20240821.501

Chest. 2025 Jan 11:S0012-3692(25)00005-4. doi: 10.1016/j.chest.2025.01.001. Online ahead of print.

ABSTRACT

BACKGROUND: Pulmonary rehabilitation (PR) is a beneficial intervention for people with interstitial lung disease (ILD), however the effect of PR on survival is unclear. This study compared the survival outcomes in people with ILD who were allocated to PR versus those who were allocated to control in two published randomised controlled trials (RCTs).

RESEARCH QUESTION: Does participation in PR impact survival among people with ILD?

STUDY DESIGN AND METHODS: The combined data from the two previous RCTs of PR in ILD were included. Time from start of PR until date of death, lung transplantation or censoring was calculated. Kaplan-Meir and Cox proportional hazard regression analysis were used to assess the impact of PR on survival. Baseline variables of age at time of PR, gender, FVC, 6-minute walk distance (6MWD), exertional nadir SpO2 and diagnosis of idiopathic pulmonary fibrosis (IPF) were included as covariates.

RESULTS: Of the 182 participants with ILD (87 IPF, 109 males, mean (SD) age 69(10), FVC%pred 76(19), TLCO%pred 48(16)), death occurred in 62%, 6% were transplanted, 20% were alive and 12% were lost to follow-up. Median survival for those who completed PR was 6.1 years (95% CI 4.4 to 7.9) compared to 4.7 years (95%CI 3.4 to 6.0) for those in the control group, however this was not significantly different (log rank p=0.7). After adjusting for baseline variables, at 5 years, completion of PR was associated a 44% lower risk of mortality (HR 0.56 (0.36-0.88), p=0.01). At 10 years, no difference in survival was observed between the PR and control group.

INTERPRETATION: Participation in PR among people with ILD may impact survival at 5 years. Along with clinical improvements following PR, the potential for a survival benefit further strengthens the importance of PR in the standard care of people with ILD.

PMID:39805518 | DOI:10.1016/j.chest.2025.01.001

Lancet Respir Med. 2025 Jan 10:S2213-2600(24)00364-3. doi: 10.1016/S2213-2600(24)00364-3. Online ahead of print.

ABSTRACT

BACKGROUND: Bronchiectasis is a disease with a global impact, but most published data come from high-income countries. We aimed to describe the clinical characteristics of patients with bronchiectasis in China.

METHODS: The Chinese Bronchiectasis Registry (BE-China) is a prospective, observational cohort enrolling patients from 111 hospitals in China. Data on demographics, comorbidities, and aetiological testing results were collected from adult patients with bronchiectasis at baseline and annual follow-up. Patients who met the inclusion criteria (age ≥18 years; received chest high-resolution CT in the past year showing bronchiectasis affecting one or more lung lobes; and clinical history consistent with bronchiectasis, including chronic cough, daily sputum production, and history of exacerbations) were included. Patients with known cystic fibrosis were excluded. To investigate variations according to different economic regions, two groups were compared based on whether per capita disposable income of residents was greater than US$5553. Clinical characteristics were compared with the European (EMBARC) registry and other national registries.

FINDINGS: Between Jan 10, 2020, and March 31, 2024, 10 324 patients from 97 centres were included in the study. Among 9501 participants with available data, the most common cause of bronchiectasis was post-infective disease (4101 [43·2%] patients), followed by idiopathic (2809 [29·6%] patients). 6676 (70·0%) of 9541 patients with available data had at least one exacerbation in the year before enrolment and 5427 (57·2%) of 9489 patients with available data were hospitalised at least once due to exacerbations. Treatments commonly used in high-income countries, such as inhaled antibiotics and macrolides, were infrequently used in China. Implementation of airway clearance in China was scarce, with only 1177 (12·2%) of 9647 patients having used at least one method of airway clearance. Compared with upper-middle-income regions, patients from lower-middle-income regions were younger (61·0 years [SD 14·0] vs 63·9 years [14·2]) with a higher proportion of pulmonary comorbidities (521 [17·8%] of 2922 patients vs 639 [8·6%] of 7402 with chronic obstructive pulmonary disease and 194 [6·6%] of 2922 patients vs 364 [4·9%] of 7402 patients with asthma), a higher tuberculosis burden (442 [16·0%] of 2768 patients vs 715 [10·6%] of 6733 patients), more severe radiological involvement (1160 [42·4%] of 2736 patients vs 2415 [35·4%] of 6816 patients with cystic bronchiectasis), more exacerbations (median 1·4 [IQR 0-2] in both groups; mean 1·4 [SD 1·6] vs 1·2 [1·4] in the previous year) and hospitalisations (1662 [60·6%] of 2743 patients vs 3765 [55·8%] of 6746 patients hospitalised at least once in the previous year), and poorer quality of life (median 57·4 [IQR 53·5-63·1] vs 58·7 [54·8-64·8] assessed by the Bronchiectasis Health Questionnaire).

INTERPRETATION: The clinical characteristics of patients with bronchiectasis in China show differences compared with cohorts in Europe and India. Bronchiectasis is more severe with a higher burden of exacerbations in lower-income regions. The management of patients with bronchiectasis in China urgently needs standardisation and improvement.

FUNDING: National Natural Science Foundation of China, Innovation Program of the Shanghai Municipal Education Commission, Program of the Shanghai Municipal Science and Technology Commission, and Program of the Shanghai Shenkang Development Center.

TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.

PMID:39805296 | DOI:10.1016/S2213-2600(24)00364-3

Mol Med. 2025 Jan 14;31(1):12. doi: 10.1186/s10020-025-01069-w.

ABSTRACT

The Systemic Evolutionary Theory of the Origin of Cancer (SETOC) is a recently proposed theory founded on two primary principles: the cooperative and endosymbiotic process of cell evolution as described by Lynn Margulis, and the integration of complex systems operating in eukaryotic cells, which is a core concept in systems biology. The SETOC proposes that malignant transformation occurs when cells undergo a continuous adaptation process in response to long-term injuries, leading to tissue remodeling, chronic inflammation, fibrosis, and ultimately cancer. This process involves a maladaptive response, wherein the 'endosymbiotic contract' between the nuclear-cytoplasmic system (derived from the primordial archaeal cell) and the mitochondrial system (derived from the primordial α-proteobacterium) gradually breaks down. This ultimately leads to uncoordinated behaviors and functions in transformed cells. The decoupling of the two cellular subsystems causes transformed cells to acquire phenotypic characteristics analogous to those of unicellular organisms, as well as certain biological features of embryonic development that are normally suppressed. These adaptive changes enable cancer cells to survive in the harsh tumor microenvironment characterized by low oxygen concentrations, inadequate nutrients, increased catabolic waste, and increased acidity. De-endosymbiosis reprograms the sequential metabolic functions of glycolysis, the TCA cycle, and oxidative phosphorylation (OxPhos). This leads to increased lactate fermentation (Warburg effect), respiratory chain dysfunction, and TCA cycle reversal. Here, we present an updated version of the SETOC that incorporates the fundamental principles outlined by this theory and integrates the epistemological approach used to develop it.

PMID:39806272 | DOI:10.1186/s10020-025-01069-w

Nat Aging. 2025 Jan 13. doi: 10.1038/s43587-024-00794-x. Online ahead of print.

ABSTRACT

DNA methylation marks have recently been used to build models known as epigenetic clocks, which predict calendar age. As methylation of cytosine promotes C-to-T mutations, we hypothesized that the methylation changes observed with age should reflect the accrual of somatic mutations, and the two should yield analogous aging estimates. In an analysis of multimodal data from 9,331 human individuals, we found that CpG mutations indeed coincide with changes in methylation, not only at the mutated site but with pervasive remodeling of the methylome out to ±10 kilobases. This one-to-many mapping allows mutation-based predictions of age that agree with epigenetic clocks, including which individuals are aging more rapidly or slowly than expected. Moreover, genomic loci where mutations accumulate with age also tend to have methylation patterns that are especially predictive of age. These results suggest a close coupling between the accumulation of sporadic somatic mutations and the widespread changes in methylation observed over the course of life.

PMID:39806003 | DOI:10.1038/s43587-024-00794-x

Nat Microbiol. 2025 Jan 13. doi: 10.1038/s41564-024-01891-8. Online ahead of print.

ABSTRACT

Despite ongoing antibiotic development, evolution of resistance may render candidate antibiotics ineffective. Here we studied in vitro emergence of resistance to 13 antibiotics introduced after 2017 or currently in development, compared with in-use antibiotics. Laboratory evolution showed that clinically relevant resistance arises within 60 days of antibiotic exposure in Escherichia coli, Klebsiella pneumoniae, Acinetobacter baumannii and Pseudomonas aeruginosa, priority Gram-negative ESKAPE pathogens. Resistance mutations are already present in natural populations of pathogens, indicating that resistance in nature can emerge through selection of pre-existing bacterial variants. Functional metagenomics showed that mobile resistance genes to antibiotic candidates are prevalent in clinical bacterial isolates, soil and human gut microbiomes. Overall, antibiotic candidates show similar susceptibility to resistance development as antibiotics currently in use, and the corresponding resistance mechanisms overlap. However, certain combinations of antibiotics and bacterial strains were less prone to developing resistance, revealing potential narrow-spectrum antibacterial therapies that could remain effective. Finally, we develop criteria to guide efforts in developing effective antibiotic candidates.

PMID:39805953 | DOI:10.1038/s41564-024-01891-8

Pharmacoepidemiol Drug Saf. 2025 Jan;34(1):e70088. doi: 10.1002/pds.70088.

ABSTRACT

Drug-drug interactions (DDIs) represent a significant concern for clinical care and public health, but the health consequences of many DDIs remain largely underexplored. This knowledge gap underscores the critical need for pharmacoepidemiologic research to evaluate real-world health outcomes of DDIs. In this review, we summarize the definitions commonly used in pharmacoepidemiologic DDI studies, discuss common sources of bias, and illustrate through examples how these biases can be mitigated.

PMID:39805810 | DOI:10.1002/pds.70088

Pharmacoepidemiol Drug Saf. 2025 Jan;34(1):e70097. doi: 10.1002/pds.70097.

ABSTRACT

PURPOSE: This study aimed to obtain a better understanding of the characteristics of the risk management plans (RMP) and the background regulatory policies governing them, in the European Union (EU) and Japan. This was done by descriptively comparing the safety concerns (SCs) listed in the RMP and examining their relationships with product labeling.

METHODS: Information regarding SCs was collected from the published RMP of both the EU and Japan for the targeted products-all of which were commonly approved in both regions. The concordance rate of the SCs for each product between the EU- and Japan-RMP was calculated. The warning information for each product was collected from the product labeling, summary of product characteristics for the EU, and package insert for Japan, and compared with the SCs listed in the corresponding RMP.

RESULTS: A total of 259 products that were approved for sale in both the EU and Japan (1998-2023), for which RMP were available in both regions, were analyzed. While 51.0% of the SCs labeled as important identified risks (IIRs) in the EU-RMP were concordant with those in the Japan-RMP, 20.4% of the SCs listed as IIRs in the Japan-RMP were concordant with those in the EU-RMP. The concordance rate between the SCs identified as IIRs and the warning information was 18.6% for the EU-RMP and 88.4% for the Japan-RMP.

CONCLUSIONS: The low SC concordance rate between the EU- and Japan-RMP indicates a different approach to selecting RMP SCs by the two regulatory authorities.

PMID:39805803 | DOI:10.1002/pds.70097

Pigment Cell Melanoma Res. 2025 Jan;38(1):e13225. doi: 10.1111/pcmr.13225.

ABSTRACT

Beta-blockers have generated an exciting discourse for their potential as a cheap, safe, and effective adjunctive therapy for cutaneous melanoma patients, but the field remains murky. This systematic review investigates the association between beta-blocker use and survival outcomes in cutaneous melanoma patients. We reviewed 12 studies with 21,582 patients in a network meta-analysis and found a benefit between beta-blocker use and disease-free survival but no other significant association for melanoma-specific or overall survival. However, some evidence suggests that pan-selective beta-blockers, rather than cardio-selective ones, may have a protective effect. We conclude that the current evidence is insufficient to recommend beta-blockers for melanoma treatment but suggest further research focusing on pan-selective beta-blockers to clarify their potential benefits.

PMID:39804765 | DOI:10.1111/pcmr.13225

Adv Sci (Weinh). 2025 Jan 13:e2410981. doi: 10.1002/advs.202410981. Online ahead of print.

ABSTRACT

Protein phosphorylation plays a crucial role in regulating a wide range of biological processes, and its dysregulation is strongly linked to various diseases. While many phosphorylation sites have been identified so far, their functionality and regulatory effects are largely unknown. Here, a deep learning model MMFuncPhos, based on a multi-modal deep learning framework, is developed to predict functional phosphorylation sites. MMFuncPhos outperforms existing functional phosphorylation site prediction approaches. EFuncType is further developed based on transfer learning to predict whether phosphorylation of a residue upregulates or downregulates enzyme activity for the first time. The functional phosphorylation sites predicted by MMFuncPhos and the regulatory types predicted by EFuncType align with experimental findings from several newly reported protein phosphorylation studies. The study contributes to the understanding of the functional regulatory mechanism of phosphorylation and provides valuable tools for precision medicine, enzyme engineering, and drug discovery. For user convenience, these two prediction models are integrated into a web server which can be accessed at http://pkumdl.cn:8000/mmfuncphos.

PMID:39804866 | DOI:10.1002/advs.202410981

FEBS J. 2025 Jan 13. doi: 10.1111/febs.17398. Online ahead of print.

ABSTRACT

Vesicle trafficking is pivotal in heparan sulfate (HS) biosynthesis, influencing its spatial and temporal regulation within distinct Golgi compartments. This regulation modulates the sulfation pattern of HS, which is crucial for governing various biological processes. Here, we investigate the effects of silencing Rab1A and Rab2A expression on the localisation of 3-O-sulfotransferase-5 (3OST5) within Golgi compartments and subsequent alterations in HS structure and levels. Interestingly, silencing Rab1A led to a shift in 3OST5 localization towards the trans-Golgi, resulting in increased HS levels within 24 and 48 h, while silencing Rab2A caused 3OST5 accumulation in the cis-Golgi, with a delayed rise in HS content observed after 48 h. Furthermore, a compensatory mechanism was evident in Rab2A-silenced cells, where increased Rab1A protein expression was detected. This suggests a dynamic interplay between Rab1A and Rab2A in maintaining the fine balance of vesicle trafficking processes involved in HS biosynthesis. Additionally, we demonstrate that the trafficking of 3OST5 in COPI vesicles is facilitated by GOLPH3 protein. These findings identify novel vesicular transport mechanisms regulating HS biosynthesis and reveal a compensatory relationship between Rab1A and Rab2A in maintaining baseline HS production.

PMID:39804811 | DOI:10.1111/febs.17398

Turk Arch Pediatr. 2025 Jan 2;60(1):22-28. doi: 10.5152/TurkArchPediatr.2025.24003.

ABSTRACT

Objective: Nebulizer contamination has potential harmful effects on the respiratory system. The aim was to investigate the contamination profile of the nebulizers in cystic fibrosis patients and evaluate the relationship between hygiene practices and microbial contamination. Materials and Methods: Microbiological swab samples were taken from 3 different locations of the nebulizers of 102 patients. A questionnaire regarding nebulizer hygiene practices was applied to participants. Results: Contamination rate was 40.2%, while chambers were the most contaminated area. The bacterial contamination rate was 37.3%, with gram-negative bacterial growth being predominant. The organisms identified were mostly environmental or floral. Only 3 of the patients were performing the whole steps correctly. This number was not sufficient to assess the relationship between nebulizer cleaning and disinfection practices and microbial growth from nebulizers. When the relationship between nebulizer cleaning/disinfection frequencies, methods, and storage locations was evaluated separately with microbial growth from nebulizers, no statistically significant relationship was found for all (P > .05 for all). Conclusion: The nebulizer contamination rate with pathogenic microorganisms is low in the present study. Regular educational interventions regarding nebulizer hygiene practices should be implemented in all Cystic Fibrosis Centers.

PMID:39803923 | DOI:10.5152/TurkArchPediatr.2025.24003

J Med Internet Res. 2025 Jan 13;27:e63004. doi: 10.2196/63004.

ABSTRACT

BACKGROUND: Digital biomarkers are increasingly used in clinical decision support for various health conditions. Speech features as digital biomarkers can offer insights into underlying physiological processes due to the complexity of speech production. This process involves respiration, phonation, articulation, and resonance, all of which rely on specific motor systems for the preparation and execution of speech. Deficits in any of these systems can cause changes in speech signal patterns. Increasing efforts are being made to develop speech-based clinical decision support systems.

OBJECTIVE: This systematic scoping review investigated the technological revolution and recent digital clinical speech signal analysis trends to understand the key concepts and research processes from clinical and technical perspectives.

METHODS: A systematic scoping review was undertaken in 6 databases guided by a set of research questions. Articles that focused on speech signal analysis for clinical decision-making were identified, and the included studies were analyzed quantitatively. A narrower scope of studies investigating neurological diseases were analyzed using qualitative content analysis.

RESULTS: A total of 389 articles met the initial eligibility criteria, of which 72 (18.5%) that focused on neurological diseases were included in the qualitative analysis. In the included studies, Parkinson disease, Alzheimer disease, and cognitive disorders were the most frequently investigated conditions. The literature explored the potential of speech feature analysis in diagnosis, differentiating between, assessing the severity and monitoring the treatment of neurological conditions. The common speech tasks used were sustained phonations, diadochokinetic tasks, reading tasks, activity-based tasks, picture descriptions, and prompted speech tasks. From these tasks, conventional speech features (such as fundamental frequency, jitter, and shimmer), advanced digital signal processing-based speech features (such as wavelet transformation-based features), and spectrograms in the form of audio images were analyzed. Traditional machine learning and deep learning approaches were used to build predictive models, whereas statistical analysis assessed variable relationships and reliability of speech features. Model evaluations primarily focused on analytical validations. A significant research gap was identified: the need for a structured research process to guide studies toward potential technological intervention in clinical settings. To address this, a research framework was proposed that adapts a design science research methodology to guide research studies systematically.

CONCLUSIONS: The findings highlight how data science techniques can enhance speech signal analysis to support clinical decision-making. By combining knowledge from clinical practice, speech science, and data science within a structured research framework, future research may achieve greater clinical relevance.

PMID:39804693 | DOI:10.2196/63004

Bioinformatics. 2025 Jan 13:btaf016. doi: 10.1093/bioinformatics/btaf016. Online ahead of print.

ABSTRACT

MOTIVATION: Recent computational approaches for predicting phage-host interaction have explored the use of sequence-only protein language models to produce embeddings of phage proteins without manual feature engineering. However, these embeddings do not directly capture protein structure information and structure-informed signals related to host specificity.

RESULTS: We present PHIStruct, a multilayer perceptron that takes in structure-aware embeddings of receptor-binding proteins, generated via the structure-aware protein language model SaProt, and then predicts the host from among the ESKAPEE genera. Compared against recent tools, PHIStruct exhibits the best balance of precision and recall, with the highest and most stable F1 score across a wide range of confidence thresholds and sequence similarity settings. The margin in performance is most pronounced when the sequence similarity between the training and test sets drops below 40%, wherein, at a relatively high-confidence threshold of above 50%, PHIStruct presents a 7% to 9% increase in class-averaged F1 over machine learning tools that do not directly incorporate structure information, as well as a 5% to 6% increase over BLASTp.

AVAILABILITY AND IMPLEMENTATION: The data and source code for our experiments and analyses are available at https://github.com/bioinfodlsu/PHIStruct.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:39804673 | DOI:10.1093/bioinformatics/btaf016

Bioinformatics. 2025 Jan 13:btaf018. doi: 10.1093/bioinformatics/btaf018. Online ahead of print.

ABSTRACT

MOTIVATION: Predicting RNA-binding proteins (RBPs) is central to understanding post-transcriptional regulatory mechanisms. Here, we introduce EnrichRBP, an automated and interpretable computational platform specifically designed for the comprehensive analysis of RBP interactions with RNA.

RESULTS: EnrichRBP is a web service that enables researchers to develop original deep learning and machine learning architectures to explore the complex dynamics of RNA-binding proteins. The platform supports 70 deep learning algorithms, covering feature representation, selection, model training, comparison, optimization, and evaluation, all integrated within an automated pipeline. EnrichRBP is adept at providing comprehensive visualizations, enhancing model interpretability, and facilitating the discovery of functionally significant sequence regions crucial for RBP interactions. In addition, EnrichRBP supports base-level functional annotation tasks, offering explanations and graphical visualizations that confirm the reliability of the predicted RNA binding sites. Leveraging high-performance computing, EnrichRBP provides ultra-fast predictions ranging from seconds to hours, applicable to both pre-trained and custom model scenarios, thus proving its utility in real-world applications. Case studies highlight that EnrichRBP provides robust and interpretable predictions, demonstrating the power of deep learning in the functional analysis of RBP interactions. Finally, EnrichRBP aims to enhance the reproducibility of computational method analyses for RNA-binding protein sequences, as well as reduce the programming and hardware requirements for biologists, thereby offering meaningful functional insights.

AVAILABILITY AND IMPLEMENTATION: EnrichRBP is available at https://airbp.aibio-lab.com/. The source code is available at https://github.com/wangyb97/EnrichRBP, and detailed online documentation can be found at https://enrichrbp.readthedocs.io/en/latest/.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:39804669 | DOI:10.1093/bioinformatics/btaf018

Insights Imaging. 2025 Jan 13;16(1):14. doi: 10.1186/s13244-024-01874-7.

ABSTRACT

OBJECTIVE: To develop an automatic segmentation model to delineate the adnexal masses and construct a machine learning model to differentiate between low malignant risk and intermediate-high malignant risk of adnexal masses based on ovarian-adnexal reporting and data system (O-RADS).

METHODS: A total of 663 ultrasound images of adnexal mass were collected and divided into two sets according to experienced radiologists: a low malignant risk set (n = 446) and an intermediate-high malignant risk set (n = 217). Deep learning segmentation models were trained and selected to automatically segment adnexal masses. Radiomics features were extracted utilizing a feature analysis system in Pyradiomics. Feature selection was conducted using the Spearman correlation analysis, Mann-Whitney U-test, and least absolute shrinkage and selection operator (LASSO) regression. A nomogram integrating radiomic and clinical features using a machine learning model was established and evaluated. The SHapley Additive exPlanations were used for model interpretability and visualization.

RESULTS: The FCN ResNet101 demonstrated the highest segmentation performance for adnexal masses (Dice similarity coefficient: 89.1%). Support vector machine achieved the best AUC (0.961, 95% CI: 0.925-0.996). The nomogram using the LightGBM algorithm reached the best AUC (0.966, 95% CI: 0.927-1.000). The diagnostic performance of the nomogram was comparable to that of experienced radiologists (p > 0.05) and outperformed that of less-experienced radiologists (p < 0.05). The model significantly improved the diagnostic accuracy of less-experienced radiologists.

CONCLUSIONS: The segmentation model serves as a valuable tool for the automated delineation of adnexal lesions. The machine learning model exhibited commendable classification capability and outperformed the diagnostic performance of less-experienced radiologists.

CRITICAL RELEVANCE STATEMENT: The ultrasound radiomics-based machine learning model holds the potential to elevate the professional ability of less-experienced radiologists and can be used to assist in the clinical screening of ovarian cancer.

KEY POINTS: We developed an image segmentation model to automatically delineate adnexal masses. We developed a model to classify adnexal masses based on O-RADS. The machine learning model has achieved commendable classification performance. The machine learning model possesses the capability to enhance the proficiency of less-experienced radiologists. We used SHapley Additive exPlanations to interpret and visualize the model.

PMID:39804536 | DOI:10.1186/s13244-024-01874-7

Int J Cardiovasc Imaging. 2025 Jan 13. doi: 10.1007/s10554-025-03327-8. Online ahead of print.

ABSTRACT

Coronary artery calcification (CAC) is a key marker of coronary artery disease (CAD) but is often underreported in cancer patients undergoing non-gated CT or PET/CT scans. Traditional CAC assessment requires gated CT scans, leading to increased radiation exposure and the need for specialized personnel. This study aims to develop an artificial intelligence (AI) method to automatically detect CAC from non-gated, freely-breathing, low-dose CT images obtained from positron emission tomography/computed tomography scans. A retrospective analysis of 677 PET/CT scans from a medical center was conducted. The dataset was divided into training (88%) and testing (12%) sets. The DLA-3D model was employed for high-resolution representation learning of cardiac CT images. Data preprocessing techniques were applied to normalize and augment the images. Performance was assessed using the area under the curve (AUC), accuracy, sensitivity, specificity and p-values. The AI model achieved an average AUC of 0.85 on the training set and 0.80 on the testing set. The model demonstrated expert-level performance with a specificity of 0.79, a sensitivity of 0.67, and an overall accuracy of 0.73 for the test group. In real-world scenarios, the model yielded a specificity of 0.8, sensitivity of 0.6, and an accuracy of 0.76. Comparison with human experts showed comparable performance. This study developed an AI method utilizing DLA-3D for automated CAC detection in non-gated PET/CT images. Findings indicate reliable CAC detection in routine PET/CT scans, potentially enhancing both cancer diagnosis and cardiovascular risk assessment. The DLA-3D model shows promise in aiding non-specialist physicians and may contribute to improved cardiovascular risk assessment in oncological imaging, encouraging additional CAC interpretation.

PMID:39804436 | DOI:10.1007/s10554-025-03327-8

Clin Oral Investig. 2025 Jan 13;29(1):59. doi: 10.1007/s00784-024-06136-w.

ABSTRACT

OBJECTIVES: To investigate the performance of a deep learning (DL) model for segmenting cone-beam computed tomography (CBCT) scans taken before and after mandibular horizontal guided bone regeneration (GBR) to evaluate hard tissue changes.

MATERIALS AND METHODS: The proposed SegResNet-based DL model was trained on 70 CBCT scans. It was tested on 10 pairs of pre- and post-operative CBCT scans of patients who underwent mandibular horizontal GBR. DL segmentations were compared to semi-automated (SA) segmentations of the same scans. Augmented hard tissue segmentation performance was evaluated by spatially aligning pre- and post-operative CBCT scans and subtracting preoperative segmentations obtained by DL and SA segmentations from the respective postoperative segmentations. The performance of DL compared to SA segmentation was evaluated based on the Dice similarity coefficient (DSC), intersection over the union (IoU), Hausdorff distance (HD95), and volume comparison.

RESULTS: The mean DSC and IoU between DL and SA segmentations were 0.96 ± 0.01 and 0.92 ± 0.02 in both pre- and post-operative CBCT scans. While HD95 values between DL and SA segmentations were 0.62 mm ± 0.16 mm and 0.77 mm ± 0.31 mm for pre- and post-operative CBCTs respectively. The DSC, IoU and HD95 averaged 0.85 ± 0.08; 0.78 ± 0.07 and 0.91 ± 0.92 mm for augmented hard tissue models respectively. Volumes mandible- and augmented hard tissue segmentations did not differ significantly between the DL and SA methods.

CONCLUSIONS: The SegResNet-based DL model accurately segmented CBCT scans acquired before and after mandibular horizontal GBR. However, the training database must be further increased to increase the model's robustness.

CLINICAL RELEVANCE: Automated DL segmentation could aid treatment planning for GBR and subsequent implant placement procedures and in evaluating hard tissue changes.

PMID:39804427 | DOI:10.1007/s00784-024-06136-w

J Gen Virol. 2025 Jan;106(1). doi: 10.1099/jgv.0.002067.

ABSTRACT

The complexity and speed of evolution in viruses with RNA genomes makes predictive identification of variants with epidemic or pandemic potential challenging. In recent years, machine learning has become an increasingly capable technology for addressing this challenge, as advances in methods and computational power have dramatically improved the performance of models and led to their widespread adoption across industries and disciplines. Nascent applications of machine learning technology to virus research have now expanded, providing new tools for handling large-scale datasets and leading to a reshaping of existing workflows for phenotype prediction, phylogenetic analysis, drug discovery and more. This review explores how machine learning has been applied to and has impacted the study of viruses, before addressing the strengths and limitations of its techniques and finally highlighting the next steps that are needed for the technology to reach its full potential in this challenging and ever-relevant research area.

PMID:39804261 | DOI:10.1099/jgv.0.002067