RESUMEN
BACKGROUND: Tumor fibrosis plays an important role in chemotherapy resistance in pancreatic ductal adenocarcinoma (PDAC), however there remains a contradiction in the prognostic value of fibrosis. We aimed to investigate the relationship between tumor fibrosis and survival in patients with PDAC, classify patients into high- and low-fibrosis groups, and develop and validate a CT-based radiomics model to non-invasively predict fibrosis before treatment. MATERIALS AND METHODS: This retrospective, bicentric study included 295 patients with PDAC without any treatments before surgery. Tumor fibrosis was assessed using the collagen fraction (CF). Cox regression analysis was used to evaluate the associations of CF with overall survival (OS) and disease-free survival (DFS). Receiver operating characteristic (ROC) analyses were used to determine the rounded threshold of CF. An integrated model (IM) was developed by incorporating selected radiomic features and clinical-radiological characteristics. The predictive performance was validated in the test cohort (Center 2). RESULTS: The CFs were 38.22±6.89% and 38.44±8.66% in center 1 (131 patients, 83 males) and center 2 (164 patients, 100 males), respectively (P=0.814). Multivariable Cox regression revealed that CF was an independent risk factor in the OS and DFS analyses at both centers. ROCs revealed that 40% was the rounded cut-off value of CF. IM predicted CF with areas under the curves (AUCs) of 0.825 (95% confidence interval [CI], 0.749-0.886) and 0.745 (95% CI, 0.671-0.810) in the training and test cohorts, respectively. Decision curve analyses revealed that IM outperformed radiomics model and clinical-radiological model for CF prediction in both cohorts. CONCLUSIONS: Tumor fibrosis was an independent risk factor for survival of patients with PDAC, and a rounded cut-off value of 40% provided a good differentiation of patient prognosis. The model combining CT-based radiomics and clinical-radiological features can satisfactorily predict survival-grade fibrosis in patients with PDAC.
RESUMEN
Background: Most primary bone tumors are often found in the bone around the knee joint. However, the detection of primary bone tumors on radiographs can be challenging for the inexperienced or junior radiologist. This study aimed to develop a deep learning (DL) model for the detection of primary bone tumors around the knee joint on radiographs. Methods: From four tertiary referral centers, we recruited 687 patients diagnosed with bone tumors (including osteosarcoma, chondrosarcoma, giant cell tumor of bone, bone cyst, enchondroma, fibrous dysplasia, etc.; 417 males, 270 females; mean age 22.8±13.2 years) by postoperative pathology or clinical imaging/follow-up, and 1,988 participants with normal bone radiographs (1,152 males, 836 females; mean age 27.9±12.2 years). The dataset was split into a training set for model development, an internal independent and an external test set for model validation. The trained model located bone tumor lesions and then detected tumor patients. Receiver operating characteristic curves and Cohen's kappa coefficient were used for evaluating detection performance. We compared the model's detection performance with that of two junior radiologists in the internal test set using permutation tests. Results: The DL model correctly localized 94.5% and 92.9% bone tumors on radiographs in the internal and external test set, respectively. An accuracy of 0.964/0.920, and an area under the receiver operating characteristic curve (AUC) of 0.981/0.990 in DL detection of bone tumor patients were for the internal and external test set, respectively. Cohen's kappa coefficient of the model in the internal test set was significantly higher than that of the two junior radiologists with 4 and 3 years of experience in musculoskeletal radiology (Model vs. Reader A, 0.927 vs. 0.777, P<0.001; Model vs. Reader B, 0.927 vs. 0.841, P=0.033). Conclusions: The DL model achieved good performance in detecting primary bone tumors around the knee joint. This model had better performance than those of junior radiologists, indicating the potential for the detection of bone tumors on radiographs.
RESUMEN
Developing anode-free batteries is the ultimate goal in pursuit of high energy density and safety. It is more urgent for sodium (Na)-based batteries due to its inherently low energy density and safety hazards induced by highly reactive Na metal anodes. However, there is no electrolyte that can meet the demanding Na plating-stripping Coulomb efficiency (CE) while resisting oxidative decomposition at high voltages for building stable anode-free Na batteries. Here, a "liquid-in-solid" electrolyte design strategy is proposed to integrate target performances of liquid and solid-state electrolytes. Breaking through the Na+ transport channel of Na-containing zeolite molecular sieve by ion-exchange and confining aggregated liquid ether electrolytes in the nanopore and void of zeolites, it achieves excellent high-voltage stability enabled by solid-state zeolite electrolytes, while inheriting the ultra-high CE (99.84%) from liquid ether electrolytes. When applied in a 4.25 V-class anode-free Na battery, an ultra-high energy density of 412 W h kg-1 (based on the active material of both cathodes and anodes) can be reached, which is comparable to the state-of-the-art graphite||LiNi0.8Co0.1Mn0.1O2 lithium-ion batteries. Furthermore, the assembled anode-free pouch cell exhibits excellent cycling stability, and a high capacity retention of 89.2% can be preserved after 370 cycles.
RESUMEN
BACKGROUND: Early identification of high-risk groups of children with sepsis is beneficial to reduce sepsis mortality. This article used artificial intelligence (AI) technology to predict the risk of death effectively and quickly in children with sepsis in the pediatric intensive care unit (PICU). STUDY DESIGN: This retrospective observational study was conducted in the PICUs of the First Affiliated Hospital of Sun Yat-sen University from December 2016 to June 2019 and Shenzhen Children's Hospital from January 2019 to July 2020. The children were divided into a death group and a survival group. Different machine language (ML) models were used to predict the risk of death in children with sepsis. RESULTS: A total of 671 children with sepsis were enrolled. The accuracy (ACC) of the artificial neural network model was better than that of support vector machine, logical regression analysis, Bayesian, K nearest neighbor method and decision tree models, with a training set ACC of 0.99 and a test set ACC of 0.96. CONCLUSIONS: The AI model can be used to predict the risk of death due to sepsis in children in the PICU, and the artificial neural network model is better than other AI models in predicting mortality risk.
Asunto(s)
Inteligencia Artificial , Unidades de Cuidado Intensivo Pediátrico , Sepsis , Humanos , Sepsis/mortalidad , Estudios Retrospectivos , Masculino , Preescolar , Femenino , Lactante , Niño , Unidades de Cuidado Intensivo Pediátrico/estadística & datos numéricos , Redes Neurales de la Computación , Máquina de Vectores de Soporte , Recién Nacido , AdolescenteRESUMEN
Introduction: MicroRNAs (miRNAs) are a class of non-coding RNA molecules that play a crucial role in the regulation of diverse biological processes across various organisms. Despite not encoding proteins, miRNAs have been found to have significant implications in the onset and progression of complex human diseases. Methods: Conventional methods for miRNA functional enrichment analysis have certain limitations, and we proposed a novel method called MiRNA Set Enrichment Analysis based on Multi-source Heterogeneous Information Fusion (MHIF-MSEA). Three miRNA similarity networks (miRSN-DA, miRSN-GOA, and miRSN-PPI) were constructed in MHIF-MSEA. These networks were built based on miRNA-disease association, gene ontology (GO) annotation of target genes, and protein-protein interaction of target genes, respectively. These miRNA similarity networks were fused into a single similarity network with the averaging method. This fused network served as the input for the random walk with restart algorithm, which expanded the original miRNA list. Finally, MHIF-MSEA performed enrichment analysis on the expanded list. Results and Discussion: To determine the optimal network fusion approach, three case studies were introduced: colon cancer, breast cancer, and hepatocellular carcinoma. The experimental results revealed that the miRNA-miRNA association network constructed using miRSN-DA and miRSN-GOA exhibited superior performance as the input network. Furthermore, the MHIF-MSEA model performed enrichment analysis on differentially expressed miRNAs in breast cancer and hepatocellular carcinoma. The achieved p-values were 2.17e(-75) and 1.50e(-77), and the hit rates improved by 39.01% and 44.68% compared to traditional enrichment analysis methods, respectively. These results confirm that the MHIF-MSEA method enhances the identification of enriched miRNA sets by leveraging multiple sources of heterogeneous information, leading to improved insights into the functional implications of miRNAs in complex diseases.
RESUMEN
Hard carbons are emerging as the most viable anodes to support the commercialization of sodium-ion (Na-ion) batteries due to their competitive performance. However, the hard carbon anode suffers from low initial Coulombic efficiency (ICE), and the ambiguous Na-ion (Na+) storage mechanism and interfacial chemistry fail to give a reasonable interpretation. Here, we have identified the time-dependent ion pre-desolvation on the nanopore of hard carbons, which significantly affects the Na+ storage efficiency by altering the solvation structure of electrolytes. Consummating the pre-desolvation by extending the aging time, generates a highly aggregated electrolyte configuration inside the nanopore, resulting in negligible reductive decomposition of electrolytes. When applying the above insights, the hard carbon anodes achieve a high average ICE of 98.21% in the absence of any Na supplementation techniques. Therefore, the negative-to-positive capacity ratio can be reduced to 1.02 for full cells, which enables an improved energy density. The insight into hard carbons and related interphases may be extended to other battery systems and support the continued development of battery technology.
RESUMEN
Near-Infrared-II (NIR-II) spans wavelengths between 1,000 to 1,700 nanometers, featuring deep tissue penetration and reduced tissue scattering and absorption characteristics, providing robust support for cancer treatment and tumor imaging research. This review explores the utilization of activatable NIR-II photodiagnosis and phototherapy based on tumor microenvironments (e. g., reactive oxygen species, pH, glutathione, hypoxia) and external stimulation (e. g., laser, ultrasound, photothermal) for precise tumor treatment and imaging. Special emphasis is placed on the advancements and advantages of activatable NIR-II nanomedicines in novel therapeutic modalities like photodynamic therapy, photothermal therapy, and photoacoustic imaging. This encompasses achieving deep tumor penetration, real-time monitoring of the treatment process, and obtaining high-resolution, high signal-to-noise ratio images even at low material concentrations. Lastly, from a clinical perspective, the challenges faced by activatable NIR-II phototherapy are discussed, alongside potential strategies to overcome these hurdles.
Asunto(s)
Rayos Infrarrojos , Nanoestructuras , Neoplasias , Humanos , Nanoestructuras/química , Nanoestructuras/uso terapéutico , Neoplasias/diagnóstico por imagen , Neoplasias/terapia , Fototerapia/métodos , Animales , Microambiente Tumoral , Fotoquimioterapia , Técnicas Fotoacústicas/métodos , Especies Reactivas de Oxígeno/metabolismo , Fármacos Fotosensibilizantes/química , Fármacos Fotosensibilizantes/uso terapéuticoRESUMEN
OBJECTIVES: To develop a deep learning (DL) model for differentiating between osteolytic osteosarcoma (OS) and giant cell tumor (GCT) on radiographs. METHODS: Patients with osteolytic OS and GCT proven by postoperative pathology were retrospectively recruited from four centers (center A, training and internal testing; centers B, C, and D, external testing). Sixteen radiologists with different experiences in musculoskeletal imaging diagnosis were divided into three groups and participated with or without the DL model's assistance. DL model was generated using EfficientNet-B6 architecture, and the clinical model was trained using clinical variables. The performance of various models was compared using McNemar's test. RESULTS: Three hundred thirty-three patients were included (mean age, 27 years ± 12 [SD]; 186 men). Compared to the clinical model, the DL model achieved a higher area under the curve (AUC) in both the internal (0.97 vs. 0.77, p = 0.008) and external test set (0.97 vs. 0.64, p < 0.001). In the total test set (including the internal and external test sets), the DL model achieved higher accuracy than the junior expert committee (93.1% vs. 72.4%; p < 0.001) and was comparable to the intermediate and senior expert committee (93.1% vs. 88.8%, p = 0.25; 87.1%, p = 0.35). With DL model assistance, the accuracy of the junior expert committee was improved from 72.4% to 91.4% (p = 0.051). CONCLUSION: The DL model accurately distinguished osteolytic OS and GCT with better performance than the junior radiologists, whose own diagnostic performances were significantly improved with the aid of the model, indicating the potential for the differential diagnosis of the two bone tumors on radiographs. CRITICAL RELEVANCE STATEMENT: The deep learning model can accurately distinguish osteolytic osteosarcoma and giant cell tumor on radiographs, which may help radiologists improve the diagnostic accuracy of two types of tumors. KEY POINTS: ⢠The DL model shows robust performance in distinguishing osteolytic osteosarcoma and giant cell tumor. ⢠The diagnosis performance of the DL model is better than junior radiologists'. ⢠The DL model shows potential for differentiating osteolytic osteosarcoma and giant cell tumor.
RESUMEN
Objective: To explore the efficacy of Danshen injection combined with calcitriol and calcium/Vitamin-D in the treatment of osteoporotic fractures. Methods: This was a case-control study. We retrospectively reviewed clinical data of 91 patients with osteoporotic fractures who received treatment in Rui'an People's Hospital from February 2021 to July 2022. The data were divided into a control group with 44 records of patients who received treatment with calcitriol and calcium/Vitamin-D, and a study group with 47 patients who received Danshen injection combined with calcitriol and calcium/Vitamin-D. The control group individuals were coordinated with the patients in terms of their age and gender. Treatment effects, inflammatory response levels, and bone metabolic status levels were comparable between the two groups before and after the treatment. Results: The total efficacy of the treatment in the study group was better than that in the control group (P<0.05). After the treatment, levels of serum inflammatory factors in both groups decreased compared to those before the treatment, and the study group displayed lower levels than the control group (P<0.05). After the treatment, the bone metabolism status of both groups improved, and the improvement effect of the study group was better (P<0.05). The incidences of adverse reactions were similar in both groups (P>0.05). Conclusions: Danshen injection combined with calcitriol and calcium/Vitamin-D for the treatment of osteoporotic fractures can effectively reduce inflammation, regulate bone metabolism, and improve fracture treatment efficacy with a favorable safety profile.
RESUMEN
The deposition/stripping behavior of lithium metal is intriguing, and the associated formation of inactive lithium at various temperatures remains elusive, which hinders the practical application of lithium metal batteries. Here, utilizing the variable-temperature operando solid-state nuclear magnetic resonance (SS NMR) technique, we reveal the temperature effects on the lithium microstructure evolution in a carbonate-based electrolyte system. In addition, the mass spectrometry titration (MST) method is used to quantify the evolution of inactive lithium components, including dead lithium, solid electrolyte interface (SEI), and lithium hydride (LiH). Combined SS NMR and MST results show that the morphology of lithium metal is reasonably correlated to the amount of inactive Li formed. At low/ambient temperature, the lithium microstructure has a similar evolution pattern, and its poor morphology leads to a large amount of dead lithium, which dominates capacity loss; however, at high temperature large and dense lithium deposits form with less dead Li detected, and the intensified electrolyte consumption in SEI formation is the major cause for capacity loss. Our phase-field simulation results reveal that the compact lithium deposition formed at higher temperature is due to the more uniformly distributed electric field and Li+ concentration. Lastly, two strategies in forming a dense Li deposit are proposed and tested that show performance-enhancing results.
RESUMEN
Superoxide dismutase (SOD) is a crucial metal-containing enzyme that plays a vital role in catalyzing the dismutation of superoxide anions, converting them into molecular oxygen and hydrogen peroxide, essential for enhancing plant stress tolerance. We identified 8 SOD genes (4 CSODs, 2 FSODs, and 2 MSODs) in cassava. Bioinformatics analyses provided insights into chromosomal location, phylogenetic relationships, gene structure, conserved motifs, and gene ontology annotations. MeSOD genes were classified into two groups through phylogenetic analysis, revealing evolutionary connections. Promoters of these genes harbored stress-related cis-elements. Duplication analysis indicated the functional significance of MeCSOD2/MeCSOD4 and MeMSOD1/MeMSOD2. Through qRT-PCR, MeCSOD2 responded to salt stress, MeMSOD2 to drought, and cassava bacterial blight. Silencing MeMSOD2 increased XpmCHN11 virulence, indicating MeMSOD2 is essential for cassava's defense against XpmCHN11 infection. These findings enhance our understanding of the SOD gene family's role in cassava and contribute to strategies for stress tolerance improvement.
RESUMEN
Collagen fibers play an important role in the progression of liver diseases. The formation and progression of liver fibrosis is a dynamic pathological process accompanied by morphological changes in collagen fibers. In this study, we used multiphoton microscopy for label-free imaging of liver tissues, allowing direct detection of various components including collagen fibers, tumors, blood vessels, and lymphocytes. Then, we developed a deep learning classification model to automatically identify tumor regions, and the accuracy reaches 0.998. We introduced an automated image processing method to extract eight collagen morphological features from various stages of liver diseases. Statistical analysis showed significant differences between them, indicating the potential use of these quantitative features for monitoring fibrotic changes during the progression of liver diseases. Therefore, multiphoton imaging combined with automatic image processing method would hold a promising future in rapid and label-free diagnosis of liver diseases.
RESUMEN
In order to develop new electrode and electrolyte materials for advanced sodium-ion batteries (SIBs), it is crucial to understand a number of fundamental issues. These include the compositions of the bulk and interface, the structures of the materials used, and the electrochemical reactions in the batteries. Solid-state NMR (SS-NMR) has unique advantages in characterizing the local or microstructure of solid electrode/electrolyte materials and their interfaces-one such advantage is that these are determined in a noninvasive and nondestructive manner at the atomic level. In this review, we provide a survey of the recent advances in the understanding of the fundamental issues of SIBs using advanced NMR techniques. First, we summarize the applications of SS-NMR in characterizing electrode material structures and solid electrolyte interfaces (SEI). In particular, we elucidate the key role of in-situ NMR/MRI in revealing the complex reactions and degradation mechanisms of SIBs. Next, the characteristics and shortcomings of SS-NMR and MRI techniques in SIBs are also discussed in comparison to similar Li-ion batteries. Finally, an overview of SS-NMR and MRI techniques for sodium batteries are briefly discussed and presented.
RESUMEN
Long non-coding RNAs (lncRNAs) play an important regulatory role in gene transcription and post-transcriptional modification, and lncRNA regulatory dysfunction leads to a variety of complex human diseases. Hence, it might be beneficial to detect the underlying biological pathways and functional categories of genes that encode lncRNA. This can be carried out by using gene set enrichment analysis, which is a pervasive bioinformatic technique that has been widely used. However, accurately performing gene set enrichment analysis of lncRNAs remains a challenge. Most conventional enrichment analysis methods have not exhaustively included the rich association information among genes, which usually affects the regulatory functions of genes. Here, we developed a novel tool for lncRNA set enrichment analysis (TLSEA) to improve the accuracy of the gene functional enrichment analysis, which extracted the low-dimensional vectors of lncRNAs in two functional annotation networks with the graph representation learning method. A novel lncRNA-lncRNA association network was constructed by merging lncRNA-related heterogeneous information obtained from multiple sources with the different lncRNA-related similarity networks. In addition, the random walk with restart method was adopted to effectively expand the lncRNAs submitted by users according to the lncRNA-lncRNA association network of TLSEA. In addition, a case study of breast cancer was performed, which demonstrated that TLSEA could detect breast cancer more accurately than conventional tools. The TLSEA can be accessed freely at http://www.lirmed.com:5003/tlsea.
RESUMEN
Photodynamic therapy (PDT), with its advantages of high targeting, minimally invasive, and low toxicity side effects, has been widely used in the clinical therapy of various tumors, especially superficial tumors. However, the tumor microenvironment (TME) presents hypoxia due to the low oxygen (O2 ) supply caused by abnormal vascularization in neoplastic tissues and high O2 consumption induced by the rapid proliferation of tumor cells. The efficacy of oxygen-consumping PDT can be hampered by a hypoxic TME. To address this problem, researchers have been developing advanced nanoplatforms and strategies to enhance the therapeutic effect of PDT in tumor treatment. This review summarizes recent advanced PDT therapeutic strategies to against the hypoxic TME, thus enhancing PDT efficacy, including increasing O2 content in TME through delivering O2 to the tumors and in situ generations of O2 ; decreasing the O2 consumption during PDT by design of type I photosensitizers. Moreover, recent synergistically combined therapy of PDT and other therapeutic methods such as chemotherapy, photothermal therapy, immunotherapy, and gas therapy is accounted for by addressing the challenging problems of mono PDT in hypoxic environments, including tumor resistance, proliferation, and metastasis. Finally, perspectives of the opportunities and challenges of PDT in future clinical research and translations are provided.
Asunto(s)
Neoplasias , Fotoquimioterapia , Humanos , Fármacos Fotosensibilizantes/uso terapéutico , Fármacos Fotosensibilizantes/farmacología , Neoplasias/tratamiento farmacológico , Hipoxia/tratamiento farmacológico , Oxígeno , Línea Celular Tumoral , Microambiente TumoralRESUMEN
Introduction: Drug-target interaction (DTI) prediction is a key step in drug function discovery and repositioning. The emergence of large-scale heterogeneous biological networks provides an opportunity to identify drug-related target genes, which led to the development of several computational methods for DTI prediction. Methods: Considering the limitations of conventional computational methods, a novel tool named LM-DTI based on integrated information related to lncRNAs and miRNAs was proposed, which adopted the graph embedding (node2vec) and the network path score methods. First, LM-DTI innovatively constructed a heterogeneous information network containing eight networks composed of four types of nodes (drug, target, lncRNA, and miRNA). Next, the node2vec method was used to obtain feature vectors of drug as well as target nodes, and the path score vector of each drug-target pair was calculated using the DASPfind method. Finally, the feature vectors and path score vectors were merged and input into the XGBoost classifier to predict potential drug-target interactions. Results and Discussion: The 10-fold cross validations evaluate the classification accuracies of the LM-DTI. The prediction performance of LM-DTI in AUPR reached 0.96, which showed a significant improvement compared with those of conventional tools. The validity of LM-DTI has also been verified by manually searching literature and various databases. LM-DTI is scalable and computing efficient; thus representing a powerful drug relocation tool that can be accessed for free at http://www.lirmed.com:5038/lm_dti.
RESUMEN
Introduction: Plants and arbuscular mycorrhizal fungi (AMF) mutualistic interactions are essential for sustainable agriculture production. Although it is shown that AMF inoculation improves cassava physiological performances and yield traits, the molecular mechanisms involved in AM symbiosis remain largely unknown. Herein, we integrated metabolomics and transcriptomics analyses of symbiotic (Ri) and asymbiotic (CK) cassava roots and explored AM-induced biochemical and transcriptional changes. Results: Three weeks (3w) after AMF inoculations, proliferating fungal hyphae were observable, and plant height and root length were significantly increased. In total, we identified 1,016 metabolites, of which 25 were differentially accumulated (DAMs) at 3w. The most highly induced metabolites were 5-aminolevulinic acid, L-glutamic acid, and lysoPC 18:2. Transcriptome analysis identified 693 and 6,481 differentially expressed genes (DEGs) in the comparison between CK (3w) against Ri at 3w and 6w, respectively. Functional enrichment analyses of DAMs and DEGs unveiled transport, amino acids and sugar metabolisms, biosynthesis of secondary metabolites, plant hormone signal transduction, phenylpropanoid biosynthesis, and plant-pathogen interactions as the most differentially regulated pathways. Potential candidate genes, including nitrogen and phosphate transporters, transcription factors, phytohormone, sugar metabolism-related, and SYM (symbiosis) signaling pathway-related, were identified for future functional studies. Discussion: Our results provide molecular insights into AM symbiosis and valuable resources for improving cassava production.
RESUMEN
OBJECTIVES: To compare the diagnostic performance of a novel deep learning (DL) method based on T2-weighted imaging with the vesical imaging-reporting and data system (VI-RADS) in predicting muscle invasion in bladder cancer (MIBC). METHODS: A total of 215 tumours (129 for training and 31 for internal validation, centre 1; 55 for external validation, centre 2) were included. MIBC was confirmed by pathological examination. VI-RADS scores were provided by two groups of radiologists (readers 1 and readers 2) independently. A deep convolutional neural network was constructed in the training set, and validation was conducted on the internal and external validation sets. ROC analysis was performed to evaluate the performance for MIBC diagnosis. RESULTS: The AUCs of the DL model, readers 1, and readers 2 were as follows: in the internal validation set, 0.963, 0.843, and 0.852, respectively; in the external validation set, 0.861, 0.808, and 0.876, respectively. The accuracy of the DL model in the tumours scored VI-RADS 2 or 3 was higher than that of radiologists in the external validation set: for readers 1, 0.886 vs. 0.600, p = 0.006; for readers 2, 0.879 vs. 0.636, p = 0.021. The average processing time (38 s and 43 s in two validation sets) of the DL method was much shorter than the readers, with a reduction of over 100 s in both validation sets. CONCLUSIONS: Compared to radiologists using VI-RADS, the DL method had a better diagnostic performance, shorter processing time, and robust generalisability, indicating good potential for diagnosing MIBC. KEY POINTS: ⢠The DL model shows robust performance for MIBC diagnosis in both internal and external validation. ⢠The diagnostic performance of the DL model in the tumours scored VI-RADS 2 or 3 is better than that obtained by radiologists using VI-RADS. ⢠The DL method shows potential in the preoperative assessment of MIBC.
Asunto(s)
Aprendizaje Profundo , Neoplasias de la Vejiga Urinaria , Humanos , Imagen por Resonancia Magnética/métodos , Neoplasias de la Vejiga Urinaria/diagnóstico por imagen , Neoplasias de la Vejiga Urinaria/patología , Vejiga Urinaria/patología , Músculos/patología , Estudios RetrospectivosRESUMEN
Working memory capacity may be a critical factor that influences the effectiveness of collaborative learning; however, no studies have directly explored this effect. Using worked examples as learning tasks, Experiment 1 used a 2 (working memory capacity) × 2 (learning format) factorial design to examine the effects of collaborative learning versus individual learning of 4th-grade Chinese elementary school students with different working memory capacities. High-capacity learners displayed less working memory resource depletion and better transfer performance during collaborative learning than individual learning. In contrast, no differences were found among the low-capacity learners. Collaborative learning benefited high-capacity learners but not low-capacity learners, per our observations. To further optimize collaborative learning for low-capacity learners and expand the findings to heterogeneous collaborative learning, Experiment 2 adopted a 2 (member capacity) × 2 (group capacity) factorial design to explore the effects of member and group working memory capacity on collaborative learning in heterogeneous groups. High-capacity members displayed less working memory resource depletion and better far transfer performance in high-capacity groups compared to low-capacity groups. Simultaneously, all members had better near transfer performance in high-capacity groups compared to low-capacity groups. Both member and group working memory capacities influenced the effect of heterogeneous collaborative learning. However, low-capacity members only partially benefited from collaborative learning in high-capacity heterogeneous groups.
RESUMEN
MicroRNAs (miRNAs) are closely associated with the occurrences and developments of many complex human diseases. Increasing studies have shown that miRNAs emerge as new therapeutic targets of small molecule (SM) drugs. Since traditional experiment methods are expensive and time consuming, it is particularly crucial to find efficient computational approaches to predict potential small molecule-miRNA (SM-miRNA) associations. Considering that integrating multi-source heterogeneous information related with SM-miRNA association prediction would provide a comprehensive insight into the features of both SMs and miRNAs, we proposed a novel model of Small Molecule-MiRNA Association prediction based on Heterogeneous Network Representation Learning (SMMA-HNRL) for more precisely predicting the potential SM-miRNA associations. In SMMA-HNRL, a novel heterogeneous information network was constructed with SM nodes, miRNA nodes and disease nodes. To access and utilize of the topological information of the heterogeneous information network, feature vectors of SM and miRNA nodes were obtained by two different heterogeneous network representation learning algorithms (HeGAN and HIN2Vec) respectively and merged with connect operation. Finally, LightGBM was chosen as the classifier of SMMA-HNRL for predicting potential SM-miRNA associations. The 10-fold cross validations were conducted to evaluate the prediction performance of SMMA-HNRL, it achieved an area under of ROC curve of 0.9875, which was superior to other three state-of-the-art models. With two independent validation datasets, the test experiment results revealed the robustness of our model. Moreover, three case studies were performed. As a result, 35, 37, and 22 miRNAs among the top 50 predicting miRNAs associated with 5-FU, cisplatin, and imatinib were validated by experimental literature works respectively, which confirmed the effectiveness of SMMA-HNRL. The source code and experimental data of SMMA-HNRL are available at https://github.com/SMMA-HNRL/SMMA-HNRL.