Cell Mol Life Sci. 2025 Feb 22;82(1):84. doi: 10.1007/s00018-025-05576-1.

ABSTRACT

Coenzyme A (CoA) is a crucial metabolite involved in various biological processes, encompassing lipid metabolism, regulation of mitochondrial function, and membrane modeling. CoA deficiency is associated with severe human diseases, such as Pantothenate Kinase-Associated Neurodegeneration (PKAN) and CoASY protein-associated neurodegeneration (CoPAN), which are linked to genetic mutations in Pantothenate Kinase 2 (PANK2) and CoA Synthase (CoASY). Although the association between CoA deficiency and mitochondrial dysfunction has been established, the underlying molecular alterations and mechanisms remain largely elusive. In this study, we investigated the detailed changes resulting from the functional decline of CoASY using the Drosophila model. Our findings revealed that a reduction of CoASY in muscle and brain led to degenerative phenotypes and apoptosis, accompanied by impaired mitochondrial integrity. The release of mitochondrial DNA was notably augmented, while the assembly and activity of mitochondrial electron transport chain (ETC) complexes, particularly complex I and III, were diminished. Consequently, this resulted in decreased ATP generation, rendering the fly more susceptible to energy insufficiency. Our findings suggest that compromised mitochondrial integrity and energy supply play a crucial role in the pathogenesis associated with CoA deficiency, thereby implying that enhancing mitochondrial integrity can be considered a potential therapeutic strategy in future interventions.

PMID:39985665 | DOI:10.1007/s00018-025-05576-1

J Agric Food Chem. 2025 Feb 22. doi: 10.1021/acs.jafc.4c12616. Online ahead of print.

ABSTRACT

Vibrio natriegens, a fast-growing bacterium, is an emerging chassis of next-generation industrial biotechnology capable of thriving under open and continuous culture conditions. Cadaverine, a valuable industrial C5 platform chemical, has various chemical and biological activities. This study found that V. natriegens exhibited superior tolerance to lysine, the substrate of cadaverine production. For the first time, a cadaverine synthesis pathway was introduced into V. natriegens for whole-cell catalysis of cadaverine from lysine. A high-efficiency cadaverine-producing strain harboring a toxin-antitoxin system, V. natriegens (pSEVA341-pTac-ldcC-pHbpBC-hbpBC) with lysE (PN96_RS17440) inactivation, was constructed. In 7 L bioreactors, the cadaverine titer increased from 115 g/L in the original strain to 158 g/L within 11 h of biotransformation, exhibiting a 37% increase in production. Its productivity reached 14.4 g/L/h with a conversion rate as high as 90%. These results confirm V. natriegens as an exceptional chassis for effective cadaverine bioproduction.

PMID:39985470 | DOI:10.1021/acs.jafc.4c12616

Exp Oncol. 2025 Feb 20;46(4):408-409. doi: 10.15407/exp-oncology.2024.04.408.

ABSTRACT

The Conference was organized on the initiative of the R.E. Kavetsky Institute of Experimental Pathology, Oncology and Radiobiology of the National Academy of Sciences of Ukraine, the State Institution "SP Grigoriev Institute of Medical Radiology and Oncology of the National Academy of Medical Sciences of Ukraine", and public organizations "National Association of Oncologists of Ukraine" and "Ukrainian Society for Cancer Research". The cancer patient's health and the quality of life (QoL) was put in the focus of this conference. Various edges of cancer research were discussed by researchers together with medical doctors, clinical scientists, specialists in demography, economics, law, and the general public.

PMID:39985343 | DOI:10.15407/exp-oncology.2024.04.408

Naunyn Schmiedebergs Arch Pharmacol. 2025 Feb 22. doi: 10.1007/s00210-025-03899-1. Online ahead of print.

ABSTRACT

Studies on the assessment of anticancer efficacy of plant-derived phytochemicals by targeting signaling pathways have drawn a lot of attention recently for human health. Multiple investigations have proposed an involvement of Notch pathway in the processes of cancer angiogenesis and metastasis, and drug resistance. Moreover, overexpression of Notch signaling is associated with increased prostate cancer (PrCa) cell growth and development. A number of chemotherapeutic agents are reported to become resistant over a period of time and have severe side effects. To increase efficacy and lessen drug-induced toxicity, a variety of bioactive compounds have been utilized alone or as adjuncts to traditional chemotherapy. Therefore, in the present study, the potential of AKBA in inhibiting the proliferation of PrCa cells by modulating Notch signaling components and its efficacy in combination with cisplatin was investigated. The results exhibited a substantial reduction in cell survival (IC50 = 25.28 µM at 24 h and 16.50 µM at 48 h) and cellular alterations in AKBA-treated PrCa cells. Additionally, AKBA caused nuclear condensation, increased reactive oxygen species (ROS) generation, mitochondrial membrane depolarization, and caspase activation, ultimately leading to apoptosis in PrCa cells. Moreover, AKBA-elicited apoptosis was evidenced by an augmentation in the Bax to Bcl2 ratio. AKBA was also found to induce G0/G1 arrest which was substantiated by reduced cyclin D1 and CDK4 expression levels concomitantly with increased expression of p21 and p27 genes. Intriguingly, AKBA demonstrated significant downregulation of Notch signaling mediators. Furthermore, the isobolograms of the combination treatment indicated that AKBA has the potential to synergistically enhance the cytotoxic efficacy of cisplatin in DU145 cells, as evidenced by CI < 1 across all tested combinations. Overall, the results of this study suggest strong antiproliferative, apoptotic, and chemo-sensitizing potential of AKBA. Thus, AKBA holds a promising drug candidature warranting further investigation as a probable therapeutic option for both the prevention and treatment of PrCa and other solid tumors.

PMID:39985578 | DOI:10.1007/s00210-025-03899-1

Curr Med Res Opin. 2025 Feb;41(2):369-373. doi: 10.1080/03007995.2025.2470735. Epub 2025 Mar 4.

ABSTRACT

Patients with ultra rare cancers have a high unmet medical need for the development of safe and effective treatments. To advance cancer drug development is often considered economically unattractive, and usually infeasible with the use of traditional paradigms. Compounding the challenges, evolving scientific understanding of the molecular biology of cancers has resulted in further subdivision of rare cancers into small molecularly defined subsets that may be eligible for targeted therapies. Indeed, research in oncology has undergone an evolution due to advances in biomarker discovery and drug target innovation moving towards a more personalized medicine and effective approach to cancer treatment. These therapies have shown remarkable efficacy with better disease management and brought a higher quality of life for cancer patients. Given the rarity of the diseases, standard randomized controlled trials may not be feasible, and innovative study designs and statistical methods should be applied to evaluate new treatments. To this aim, regulatory agencies have developed guidelines to introduce flexibility in planning of clinical trials, including new adaptive designs, use of real-world data, and surrogate endpoints. This commentary aims at reporting challenges on the evaluation of new treatments for ultra rare cancers with a focus on innovative trial designs, statistical methods, and managing of patients as these cancers are often poorly understood, have limited clinical data, and may require specialized treatment approaches.

PMID:39980369 | DOI:10.1080/03007995.2025.2470735

Z Rheumatol. 2025 Mar;84(2):128-137. doi: 10.1007/s00393-025-01616-0. Epub 2025 Feb 21.

ABSTRACT

Metabolic bone diseases cause bone and joint pain and are manifested as rheumatism. Typical for the rare genetic disease hypophosphatasia is a reduced activity of alkaline phosphatase (AP), where the variable residual activity causes the heterogeneous symptoms (e.g., arthralgia, myalgia and fractures). It is indicated by repeatedly low AP measurements. The diagnosis requires a meticulous medical history and laboratory-based clarification in order to rule out other differential diagnoses. Although supportive measures form the basis of treatment, costly enzyme replacement therapy is a possible treatment option for severe forms. Multidisciplinary care under the direction of a rheumatologist experienced in osteology or an osteologist is crucial in order to provide adequate care to affected patients. Phosphate loss syndromes due to overactivity of fibroblast growth factor 23 (FGF-23) lead to deformities of the lower extremities and short stature (in congenital disorders), bone and muscle pain, muscular weakness and pathological fractures, depending on the time of occurrence during life. In genetic forms of the disease (especially X‑linked hypophosphatemia), supplementation with calcitriol and phosphates and, if necessary, complex corrective surgery in adolescence are traditional treatment methods, which are increasingly being replaced by treatment with antibodies against FGF-23. The acquired variant is a paraneoplastic phenomenon from small mostly benign mesenchymal tumors, which clinically shows a relatively acute course with severe bone pain, pathological fractures and muscle weakness in previously healthy patients and can ideally be cured by resection of the tumor. The disease can be suspected by significantly reduced serum phosphate levels and narrowed down with further laboratory diagnostics. In our opinion, the measurement of calcium, phosphate and alkaline phosphatase should be part of the primary laboratory diagnostics performed by rheumatologists and the follow-up of pathological findings is indicated.

PMID:39982479 | DOI:10.1007/s00393-025-01616-0

Sci Rep. 2025 Feb 21;15(1):6360. doi: 10.1038/s41598-025-85582-2.

ABSTRACT

As a high-risk production unit, natural gas supply enterprises are increasingly recognizing the need to enhance production safety management. Traditional process warning methods, which rely on fixed alarm values, often fail to adequately account for dynamic changes in the production process. To address this issue, this study utilizes deep learning techniques to enhance the accuracy and reliability of natural gas load forecasting. By considering the benefits and feasibility of integrating multiple models, a VMD-CNN-LSTM-Self-Attention interval prediction method was innovatively proposed and developed. Empirical research was conducted using data from natural gas field station outgoing loads. The primary model constructed is a deep learning model for interval prediction of natural gas loads, which implements a graded alarm mechanism based on 85%, 90%, and 95% confidence intervals of real-time observations. This approach represents a novel strategy for enhancing enterprise safety production management. Experimental results demonstrate that the proposed method outperforms traditional warning models, reducing MAE, MAPE, MESE, and REMS by 1.13096 m3/h, 1.3504%, 7.6363 m3/h, 1.6743 m3/h, respectively, while improving R2 by 0.04698. These findings are expected to offer valuable insights for enhancing safe production management in the natural gas industry and provide new perspectives for the industry's digital and intelligent transformation.

PMID:39984509 | DOI:10.1038/s41598-025-85582-2

Nat Commun. 2025 Feb 21;16(1):1838. doi: 10.1038/s41467-025-57072-6.

ABSTRACT

Inferring cell spatial profiles from histology images is critical for cancer diagnosis and treatment in clinical settings. In this study, we report a weakly-supervised deep-learning method, HistoCell, to directly infer super-resolution cell spatial profiles consisting of cell types, cell states and their spatial network from histology images at the single-nucleus-level. Benchmark analysis demonstrates that HistoCell robustly achieves state-of-the-art performance in terms of cell type/states prediction solely from histology images across multiple cancer tissues. HistoCell can significantly enhance the deconvolution accuracy for the spatial transcriptomics data and enable accurate annotation of subtle cancer tissue architectures. Moreover, HistoCell is applied to de novo discovery of clinically relevant spatial organization indicators, including prognosis and drug response biomarkers, across diverse cancer types. HistoCell also enable image-based screening of cell populations that drives phenotype of interest, and is applied to discover the cell population and corresponding spatial organization indicators associated with gastric malignant transformation risk. Overall, HistoCell emerges as a powerful and versatile tool for cancer studies in histology image-only cohorts.

PMID:39984438 | DOI:10.1038/s41467-025-57072-6

Comput Biol Med. 2025 Feb 20;188:109757. doi: 10.1016/j.compbiomed.2025.109757. Online ahead of print.

ABSTRACT

Cancer treatment is often confounded by development of resistance to chemotherapy. This research explores the complex relationship between p62 (also known as SQSTM1), a multifunctional protein central in cancer signaling pathways - especially the NF-κB pathway - and chemoresistance. Our data indicate that disruption of the interaction between p62 and the serine/threonine protein kinase RIP1 is a viable strategy to counteract NF-κB activation and overcome chemoresistance. Employing a comprehensive drug repositioning approach, we utilized bioinformatics tools to perform docking, virtual screening, absorption, distribution, metabolism, and excretion analyses, toxicity analysis, and molecular dynamics simulations to identify FDA-approved drugs that prevent the binding of p62 to RIP1. Notable candidates, particularly montelukast and asunaprevir, blocked the p62-RIP1 interaction, establishing a basis for potential therapeutic interventions against chemoresistant cancers. This study highlights the critical role of the ZZ domain of p62 protein in chemotherapy resistance and sheds light on the possibility of repurposing existing drugs for novel applications in cancer treatment. Our findings provide a solid groundwork for preclinical studies.

PMID:39983356 | DOI:10.1016/j.compbiomed.2025.109757

Sci Rep. 2025 Feb 21;15(1):6295. doi: 10.1038/s41598-025-87251-w.

ABSTRACT

Parenting a child with rare paediatric neurological diseases (RPNDs) severely affects parents' quality of life and the caregiver burden. Since mothers tend to be the primary caregivers more often, this study focuses on previously unexplored experiences of mothers of four RPNDs: 22q11.2 deletion syndrome (22q11.2DS), Angelman syndrome (AS), Dravet syndrome (DS) and Williams syndrome (WS). A cross-sectional survey of 302 mothers revealed that, while caring for RPND children seriously impacts well-being and stress in all mothers, there also exist some significant differences in diagnostic experiences, quality of life and the caregiver burden across conditions. DS and AS mothers reported difficulties in the access to and reimbursement for modern genetic testing and psychological support. DS and WS mothers were concerned over the impact of the delayed diagnosis on unnecessary hospitalisations and medication in their children. 22q11.2DS mothers felt more supported than others. While DS and AS mothers reported a greater burden in caregiving and reduced quality of life, WS mothers reported significantly lower burdens and higher scores across all quality-of-life domains. Mothers' financial well-being, employment status and early diagnosis significantly influenced their experiences. These findings underscore the need for tailored support for RPND mothers, with a focus on early diagnosis and financial and psychological help.

PMID:39984547 | DOI:10.1038/s41598-025-87251-w

Biochem Pharmacol. 2025 Feb 19:116809. doi: 10.1016/j.bcp.2025.116809. Online ahead of print.

ABSTRACT

The importance of the intestinal microbita in a multitude of physiological processes is well-evidenced. These include metabolism of nutrients and xenobiotics, biosynthesis of vitamin K and vitamin B12, immunomodulation, maintenance of the gut mucosal barrier integrity and protection against some pathogens. Interindividual differences in the intestinal microbiota composition have impacts on health. The bioavailability and activity of some pharmaceuticals are heavily influenced by interindividual variability in metabolism, which has a genetic basis. This variability, primarily occurring in the liver but also in the intestine, has been studied extensively. Despite the advancement of this field - pharmacogenetics - its integration into clinical practice remains limited for reasons discussed herein. This highlights the even greater challenge of applying emerging knowledge on variability in the gut microbiota to drug therapy. However, ignoring these opportunities would be a mistake. While clinical applications of microbiota-guided drug therapy are currently absent and the ideas in this article are largely theoretical, research is uncovering that in cases where a substantial portion of a drug or its metabolites reaches the colon, or where drugs are formulated for colonic delivery, the gut microbiota can significantly affect drug metabolism and activity. Greater focus should be placed on research into how interindividual variability in the intestinal microbiome can modify pharmaceutical bioavailability and activity. This article is deliberately speculative and exploratory but proposes that, though there are still no clinical examples of microbiome-guided drug therapy, these interactions could afford opportunities for improvements in personalised medicine and also for drug design.

PMID:39983848 | DOI:10.1016/j.bcp.2025.116809

BMC Pulm Med. 2025 Feb 21;25(1):85. doi: 10.1186/s12890-025-03553-9.

ABSTRACT

BACKGROUND: Nontuberculous mycobacterial pulmonary disease (NTM-PD) poses substantial diagnostic and management challenges, particularly among individuals with pre-existing lung conditions and/ or immunodeficiencies. NTM-PD can severely impair lung function and quality of life, potentially leading to both increased healthcare costs and mortality. There is a lack of comprehensive understanding of the disease burden and healthcare gaps from the patients' perspective. The European NTM-PD Patient Disease Experience (ENPADE) survey aimed to collect insights into these aspects.

METHODS: The survey aim was addressed by several methods. First, an online questionnaire was carried out from July 2021 to February 2022 across eight European countries for quantitative data collection. Additionally, semi-structured qualitative patient interviews were conducted with a subset of patients, eliciting their insights on the aspects surveyed. Descriptive statistics were used for quantitative analysis and interview outcomes were categorised along the online questionnaire for qualitative analysis.

RESULTS: A total of 543 patients participated in the survey and 23 patients were interviewed. Satisfaction with care received before and after diagnosis was scored, on average, moderate with 32% "highly satisfied" patients and 25% "highly dissatisfied" patients across the aspects surveyed. Dissatisfaction was expressed particularly regarding referral and access to expert care, and information received on their disease and its management. Patients reported high restrictions in daily life (49%), work (31%), and social activities (43%), often leading to substantial emotional distress, such as experiencing an increase in feeling depressed or anxious (82%). Interviews with patients highlighted a need for improved disease information, faster diagnosis, and enhanced physician-patient relationships.

CONCLUSIONS: The ENPADE survey outcomes revealed dissatisfaction among patients with care and restrictions in daily life, work, and social activities, often leading to emotional distress. These findings underscore the need for improved disease information, standardised care, and enhanced physician-patient relationships with appropriate support measures.

PMID:39984983 | DOI:10.1186/s12890-025-03553-9

Dig Dis Sci. 2025 Feb 21. doi: 10.1007/s10620-025-08932-0. Online ahead of print.

NO ABSTRACT

PMID:39984786 | DOI:10.1007/s10620-025-08932-0

J Cyst Fibros. 2025 Feb 20:S1569-1993(25)00053-0. doi: 10.1016/j.jcf.2025.02.004. Online ahead of print.

ABSTRACT

BACKGROUND: As the lifespan of people with cystic fibrosis (pwCF) improves, more individuals are pursuing pregnancy. Historically, pregnancy was not recommended in this population; however, more recent evidence has revealed inconsistent survival and lung function outcomes. Our aim was to assess the differences in survival and lung function between pregnant and never-pregnant pwCF and to provide updated recommendations for contemporary clinical practice.

METHODS: In this retrospective matched parallel cohort study, data was collected from the American Cystic Fibrosis Foundation Patient Registry (CFFPR) from 1999 to 2019. 1743 adult pwCF with a reported pregnancy were matched with 1743 never-pregnant patients. Regression models were developed to estimate associations between patient characteristics, pregnancy, and outcomes. The primary endpoint was the probability of survival comparing pregnant and never-pregnant pwCF, while the secondary endpoint was lung function over time.

RESULTS: The study cohort (n = 3486) had a mean age of 24.96 years. There was no significant difference in survival probabilities between pregnant and never-pregnant pwCF (56.2 %, CI95 %: 51.3 %-61.5 % vs. 55.8 %, CI95 %: 52.1 %-59.7 %, p = 0.5). The multivariable time-dependent Cox regression analysis resulted in a significantly lower mortality hazard rate for pregnant cohorts (HR:0.78, p < 0.01). There was no significant association between pregnancy and lung function over time (0.99, p = 0.21).

CONCLUSION: Pregnancy was associated with a reduced hazard of death compared to never-pregnant pwCF and did not demonstrate a significant impact on lung function. Therefore, pregnancy should not be generally discouraged in pwCF and clinicians should evaluate pregnancy risks and benefits on an individualized basis.

PMID:39984374 | DOI:10.1016/j.jcf.2025.02.004

Epilepsy Behav. 2025 Feb 20;165:110292. doi: 10.1016/j.yebeh.2025.110292. Online ahead of print.

ABSTRACT

OBJECTIVE: To assess documentation of pregnancy-related counseling and care for people with epilepsy of childbearing potential (PWECP) in pediatric and adult neurology who became pregnant.

METHODS: We reviewed health records for primigravida PWECP prescribed an antiseizure medication (ASM) who delivered between June 2014 and May 2024 within one academic medical center. We used chi-squared tests to compare counseling, ASM prescriptions, and recommendations for supplemental folic acid between individuals in pediatric and adult neurology care before pregnancy. We performed logistic regression for these outcomes of pre-pregnancy counseling associated with type of neurology care, race, ethnicity, intellectual disability (ID), teratogenic profile of ASMs prescribed, and ASM polytherapy.

RESULTS: 173 PWECP (84 % White non-Hispanic, 9 % with intellectual disability (ID) were included. Twenty-one (12 %) transferred from pediatric to adult neurology care due to pregnancy ("pediatric group") and 152 (88 %) were previously established with adult neurology ("adult group"). PWECP in the pediatric group compared to the adult group had lower rates of documentation of clinician discussion of ASM teratogenicity (43 % vs 66 %, p = 0.041) and folic acid use (24 % vs 63 %, p = 0.001) before pregnancy. PWECP established with adult neurology prior to pregnancy were significantly more likely to have been taking folic acid before pregnancy (OR 5.21, 95 % CI 1.78-15.3). Individuals with ID were significantly less likely to have documentation of discussion of ASM teratogenicity (OR 0.18, 95 % CI 0.05-0.62).

CONCLUSION: Our findings suggest a need for improvement in providing pre-pregnancy guidance and care for PWECP, especially for PWECP in pediatric neurology care and those with ID.

PMID:39983588 | DOI:10.1016/j.yebeh.2025.110292

BMC Med. 2025 Feb 21;23(1):97. doi: 10.1186/s12916-025-03887-5.

ABSTRACT

BACKGROUND: Early detection of cancer can help patients with more effective treatments and result in better prognosis. Unfortunately, established cancer screening technologies are limited for use, especially for multi-cancer early detection. In this study, we described a serum-based platform integrating surface-enhanced Raman spectroscopy (SERS) technology with resampling strategy, feature dimensionality enhancement, deep learning and interpretability analysis methods for sensitive and accurate pan-cancer screening.

METHODS: Totally, 1655 early-stage patients with breast cancer (BC, n = 569), lung cancer (LC, n = 513), thyroid cancer (TC, n = 220), colorectal cancer (CC, n = 215), gastric cancer (GC, n = 100), esophageal cancer (EC, n = 38), and 1896 healthy controls (HC) were enrolled. The serum SERS spectra were obtained from each participant. Data dimension enhancement was conducted by heatmap transformation and continuous wavelet transform (CWT). The dimensionalization SERS spectral data were subsequently analyzed by residual neural network (ResNet) as convolutional neural network (CNN) algorithm. Class activation mapping (CAM) method was performed to elucidate the potential biological significance of spectral data classification.

RESULTS: All participants were divided into a training set and a test set with a ratio of 7:3. The BorderlineSMOTE method was selected as the most appropriate resampling strategy and the deep neural network (DNN) model achieved desirable performance among all groups (accuracy rate: 93.15%, precision rate: 88:46%, recall rate: 85.68%, and F1-score: 86.98%), with the generated AUC values of 0.991 for HC, 0.995 for BC, 0.979 for LC, 0.996 for TC, 0.994 for CC, 0.982 for GC, and 0.941 for EC, respectively. Furthermore, the combination use of SERS spectra data and ResNet (form of heatmap) were also capable of effectively distinguishing different categories and making accurate predictions (accuracy rate: 94.75%, precision rate: 89.02, recall rate: 86.97, and F1-score: 87.88), with the AUC values of 0.996 for HC, 0.995 for BC, 0.988 for LC, 0.999 for TC, 0.993 for CC, 0.985 for GC, and 0.940 for EC, respectively. Additionally, strong wave number range of the spectral data was observed in the CAM analysis.

CONCLUSIONS: Our study has offered a highly effective serum SERS-based approach for multi-cancer early detection, which might shed new light on cancer screening in clinical practice.

PMID:39984977 | DOI:10.1186/s12916-025-03887-5

BMC Ophthalmol. 2025 Feb 21;25(1):86. doi: 10.1186/s12886-025-03908-0.

ABSTRACT

BACKGROUND: Morphological changes in the retina are crucial and serve as valuable references in the clinical diagnosis of ophthalmic and cardiovascular diseases. However, the retinal vascular structure is complex, making manual segmentation time-consuming and labor-intensive.

METHODS: This paper proposes a retinal segmentation network that integrates feature channel attention and the Convolutional Block Attention Module (CBAM) attention within the U2Net model. First, a feature channel attention module is introduced into the RSU (Residual Spatial Unit) block of U2Net, forming an Attention-RSU block, which focuses more on significant areas during feature extraction and suppresses the influence of noise; Second, a Spatial Attention Module (SAM) is introduced into the high-resolution module of Attention-RSU to enrich feature extraction from both spatial and channel dimensions, and a Channel Attention Module (CAM) is integrated into the lowresolution module of Attention-RSU, which uses dual channel attention to reduce detail loss.Finally, dilated convolution is applied during the upscaling and downscaling processes to expand the receptive field in low-resolution states, allowing the model to better integrate contextual information.

RESULTS: The evaluation across multiple clinical datasets demonstrated excellent performance on various metrics, with an accuracy (ACC) of 98.71%.

CONCLUSION: The proposed Network is general enough and we believe it can be easily extended to other medical image segmentation tasks where large scale variation and complicated features are the main challenges.

PMID:39984892 | DOI:10.1186/s12886-025-03908-0

BMC Biol. 2025 Feb 21;23(1):47. doi: 10.1186/s12915-025-02148-4.

ABSTRACT

BACKGROUND: Long non-coding RNA (LncRNA) play pivotal roles in various cellular processes, and elucidating their subcellular localization can offer crucial insights into their functional significance. Accurate prediction of lncRNA subcellular localization is of paramount importance. Despite numerous computational methods developed for this purpose, existing approaches still encounter challenges stemming from the complexity of data representation and the difficulty in capturing nucleotide distribution information within sequences.

RESULTS: In this study, we propose a novel deep learning-based model, termed MGBLncLoc, which incorporates a unique multi-class encoding technique known as generalized encoding based on the Distribution Density of Multi-Class Nucleotide Groups (MCD-ND). This encoding approach enables more precise reflection of nucleotide distributions, distinguishing between constant and discriminative regions within sequences, thereby enhancing prediction performance. Additionally, our deep learning model integrates advanced neural network modules, including Multi-Dconv Head Transposed Attention, Gated-Dconv Feed-forward Network, Convolutional Neural Network, and Bidirectional Gated Recurrent Unit, to comprehensively exploit sequence features of lncRNA.

CONCLUSIONS: Comparative analysis against commonly used sequence feature encoding methods and existing prediction models validates the effectiveness of MGBLncLoc, demonstrating superior performance. This research offers novel insights and effective solutions for predicting lncRNA subcellular localization, thereby providing valuable support for related biological investigations.

PMID:39984880 | DOI:10.1186/s12915-025-02148-4

BMC Med Imaging. 2025 Feb 21;25(1):56. doi: 10.1186/s12880-024-01517-9.

ABSTRACT

PURPOSE: To develop MRI-based deep learning (DL) models for distinguishing sinonasal squamous cell carcinoma (SCC), adenoid cystic carcinoma (ACC) and olfactory neuroblastoma (ONB) and to evaluate whether the DL models could improve the diagnostic performance of Senior radiologist (SR) and Junior radiologist (JR).

METHODS: This retrospective analysis consisted of 465 patients (229 sinonasal SCCs, 128 ACCs and 108 ONBs). The training and validation cohorts included 325 and 47 patients and the independent external testing cohort consisted of 93 patients. MRI images included T2-weighted image (T2WI), contrast-enhanced T1-weighted image (CE-T1WI) and apparent diffusion coefficient (ADC). We analyzed the conventional MRI features to choose the independent predictors and built the conventional MRI model. Then we compared the macro- and micro- area under the curves (AUCs) of different sequences and different DL networks to formulate the best DL model [artificial intelligence (AI) model scheme]. With AI assistance, we observed the diagnostic performances between SR and JR. The diagnostic efficacies of SR and JR were assessed by accuracy, Recall, precision, F1-Score and confusion matrices.

RESULTS: The independent predictors of conventional MRI included intensity on T2WI and intracranial invasion of sinonasal malignancies. With ExtraTrees (ET) classier, the conventional MRI model owned AUC of 78.8%. For DL models, ResNet101 network showed better performance than ResNet50 and DensNet121, especially for the mean fusion sequence (macro-AUC = 0.892, micro-AUC = 0.875, Accuracy = 0.810), and also good for the ADC sequence (macro-AUC = 0.872, micro-AUC = 0.874, Accuracy = 0.814). Grad-CAM showed that DL models focused on solid component of lesions. With the best AI scheme (ResNet101-mean sequence-based DL model) assistance, the diagnosis performances of SR (accuracy = 0.957, average Recall = 0.962, precision = 0.955, F1-Score = 0.957) and JR (accuracy = 0.925, average Recall = 0.917, precision = 0.931, F1-Score = 0.923) were significantly improved.

CONCLUSION: The ResNet101 network with mean sequence based DL model could effectively differential between sinonasal SCC, ACC and ONB and improved the diagnostic performances of both senior and junior radiologists.

PMID:39984860 | DOI:10.1186/s12880-024-01517-9

BMC Med Res Methodol. 2025 Feb 21;25(1):45. doi: 10.1186/s12874-025-02463-y.

ABSTRACT

BACKGROUND: This scoping review systematically maps externally validated machine learning (ML)-based models in cancer patient care, quantifying their performance, and clinical utility, and examining relationships between models, cancer types, and clinical decisions. By synthesizing evidence, this study identifies, strengths, limitations, and areas requiring further research.

METHODS: The review followed the Joanna Briggs Institute's methodology, Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines, and the Population, Concept, and Context mnemonic. Searches were conducted across Embase, IEEE Xplore, PubMed, Scopus, and Web of Science (January 2014-September 2022), targeting English-language quantitative studies in Q1 journals (SciMago Journal and Country Ranking > 1) that used ML to evaluate clinical outcomes for human cancer patients with commonly available data. Eligible models required external validation, clinical utility assessment, and performance metric reporting. Studies involving genetics, synthetic patients, plants, or animals were excluded. Results were presented in tabular, graphical, and descriptive form.

RESULTS: From 4023 deduplicated abstracts and 636 full-text reviews, 56 studies (2018-2022) met the inclusion criteria, covering diverse cancer types and applications. Convolutional neural networks were most prevalent, demonstrating high performance, followed by gradient- and decision tree-based algorithms. Other algorithms, though underrepresented, showed promise. Lung and digestive system cancers were most frequently studied, focusing on diagnosis and outcome predictions. Most studies were retrospective and multi-institutional, primarily using image-based data, followed by text-based and hybrid approaches. Clinical utility assessments involved 499 clinicians and 12 tools, indicating improved clinician performance with AI assistance and superior performance to standard clinical systems.

DISCUSSION: Interest in ML-based clinical decision-making has grown in recent years alongside increased multi-institutional collaboration. However, small sample sizes likely impacted data quality and generalizability. Persistent challenges include limited international validation across ethnicities, inconsistent data sharing, disparities in validation metrics, and insufficient calibration reporting, hindering model comparison reliability.

CONCLUSION: Successful integration of ML in oncology decision-making requires standardized data and methodologies, larger sample sizes, greater transparency, and robust validation and clinical utility assessments.

OTHER: Financed by FCT-Fundação para a Ciência e a Tecnologia (Portugal, project LA/P/0063/2020, grant 2021.09040.BD) as part of CSS's Ph.D. This work was not registered.

PMID:39984835 | DOI:10.1186/s12874-025-02463-y