Academic literature on the topic 'Deep MCCA'

Abstract Motivation The discovery of cancer subtyping can help explore cancer pathogenesis, determine clinical actionability in treatment, and improve patients' survival rates. However, due to the diversity and complexity of multi-omics data, it is still challenging to develop integrated clustering algorithms for tumor molecular subtyping. Results We propose Subtype-GAN, a deep adversarial learning approach based on the multiple-input multiple-output neural network to model the complex omics data accurately. With the latent variables extracted from the neural network, Subtype-GAN uses consensus clustering and the Gaussian Mixture model to identify tumor samples' molecular subtypes. Compared with other state-of-the-art subtyping approaches, Subtype-GAN achieved outstanding performance on the benchmark datasets consisting of ∼4000 TCGA tumors from 10 types of cancer. We found that on the comparison dataset, the clustering scheme of Subtype-GAN is not always similar to that of the deep learning method AE but is identical to that of NEMO, MCCA, VAE and other excellent approaches. Finally, we applied Subtype-GAN to the BRCA dataset and automatically obtained the number of subtypes and the subtype labels of 1031 BRCA tumors. Through the detailed analysis, we found that the identified subtypes are clinically meaningful and show distinct patterns in the feature space, demonstrating the practicality of Subtype-GAN. Availabilityand implementation The source codes, the clustering results of Subtype-GAN across the benchmark datasets are available at https://github.com/haiyang1986/Subtype-GAN. Supplementary information Supplementary data are available at Bioinformatics online.

Root-knot nematode diseases cause severe yield and economic losses each year in global agricultural production. Virgibacillus dokdonensis MCCC 1A00493, a deep-sea bacterium, shows a significant nematicidal activity against Meloidogyne incognita in vitro. However, information about the active substances of V. dokdonensis MCCC 1A00493 is limited. In this study, volatile organic compounds (VOCs) from V. dokdonensis MCCC 1A00493 were isolated and analyzed through solid-phase microextraction and gas chromatography–mass spectrometry. Four VOCs, namely, acetaldehyde, dimethyl disulfide, ethylbenzene, and 2-butanone, were identified, and their nematicidal activities were evaluated. The four VOCs had a variety of active modes on M. incognita juveniles. Acetaldehyde had direct contact killing, fumigation, and attraction activities; dimethyl disulfide had direct contact killing and attraction activities; ethylbenzene had an attraction activity; and 2-butanone had a repellent activity. Only acetaldehyde had a fumigant activity to inhibit egg hatching. Combining this fumigant activity against eggs and juveniles could be an effective strategy to control the different developmental stages of M. incognita. The combination of direct contact and attraction activities could also establish trapping and killing strategies against root-knot nematodes. Considering all nematicidal modes or strategies, we could use V. dokdonensis MCCC 1A00493 to set up an integrated strategy to control root-knot nematodes.

Precipitation nowcasting has been gaining importance in the operational weather forecast, being essential for economic and social development. Conventional methods of precipitation nowcasting are mainly focused on the task of radar echo extrapolation. In recent years, deep learning methods have been used in this task. Nevertheless, raising the accuracy and extending the lead time of prediction remains as a challenging problem. To address the problem, we proposed a Multi-Scale Criss-Cross Attention Context Sensing Long Short-Term Memory (MCCS-LSTM). In this model, Context Sensing framework (CS framework) focuses on contextual correlations, and Multi-Scale Spatiotemporal block (MS block) with criss-cross attention is designed to extract multi-scale spatiotemporal feature and full-image dependency. To validate the effectiveness of our model, we conduct experiments on CIKM AnalytiCup 2017 data sets and Guangdong Province of China radar data sets. By comparing with existing deep learning models, the results demonstrate that the MCCS-LSTM has the best prediction performance, especially for predicting accuracy with longer lead times.

A Gram-reaction-positive bacterial strain of the genus Serinicoccus, designated MCCC 1A05965T, was isolated from a deep-sea (5368 m) sediment of the Indian Ocean. Comparison of 16S rRNA gene sequences revealed that the isolate shared 97.6 % sequence similarity with Serinicoccus marinus JC1078T, the type strain of the only described species of the genus Serinicoccus. The DNA–DNA relatedness between these two strains was 46.2 % (standard deviation 1.86 %). The cell wall contained alanine, glycine, serine, l-ornithine and glutamic acid, which corresponds to the description of the genus Serinicoccus. The acyl type of the glycan chain of the peptidoglycan was glycolyl. Other characteristics of strain MCCC 1A05965T were consistent with those of the genus Serinicoccus. Cells were coccoid, moderately halophilic, oxidase-negative, catalase-positive and non-spore-forming. The major menaquinone was MK-8(H4). The predominant cellular fatty acids were iso-C15 : 0 (34.7 %) and iso-C16 : 0 (17.0 %). The polar lipids were phosphatidylglycerol, diphosphatidylglycerol, phosphatidylcholine, phosphatidylinositol and an unknown glycolipid. The DNA G+C content was 72 mol%. Strain MCCC 1A05965T (=0714S6-1T =DSM 21363T =CGMCC 4.5582T) is assigned as the type strain of a novel species, for which the name Serinicoccus profundi sp. nov. is proposed.

Category: Trauma; Ankle Introduction/Purpose: The modified Charlson Comorbidity Index (mCCI), Elixhauser comorbidity measure (ECM), and 5- factor modified Frailty Index (mFI-5) have been validated for the purpose of outcome prediction in foot and ankle orthopedic care. However, from the perspective of clinical utility, no study has sought to compare the predictive performance of these measures specifically following traumatic ankle fracture. The present study compares the discriminative ability of the mCCI, ECM, and mFI-5, as well as various demographic characteristics, such as age, gender, and race, to predict in-hospital mortality and complications after the surgical management of traumatic ankle fracture. Methods: We performed a retrospective cohort study of adult patients registered in the National Trauma Data Bank (NTDB) 2011-2016 experiencing ankle trauma as malleolar fracture and undergoing surgical management. Patients missing baseline or comorbidity information, dead on arrival, or with a pilon fracture or stress fracture were excluded. Enhanced ICD-9 algorithms were used to calculate mCCI, ECM, and mFI-5 as has been done in prior orthopedic literature. The discriminative ability of the indices for adverse outcomes was assessed using area under the curve analysis from receiver operating characteristic curves. Outcomes included death, severe adverse events (death, deep surgical site infection (SSI), myocardial infarction (MI), cardiac arrest, deep vein thrombosis (DVT), pulmonary embolism (PE), sepsis, stroke, compartment syndrome), minor adverse events (acute kidney injury (AKI), pneumonia, superficial SSI, urinary tract infection (UTI)), infectious events (deep SSI, organ/space SSI, superficial SSI, pneumonia, UTI, catheter-related bloodstream infection, osteomyelitis, sepsis), and any adverse event. Results: In total, 171,097 patients met inclusion criteria. The median age was 50 years and 49% of patients were male. Compared to ECM and mFI-5, mCCI had the largest discriminative ability for the outcome of in-hospital mortality (P=0.02 versus ECM, P<0.001 versus mFI-5, Table I). ECM, however, had a larger discriminative ability for major adverse event, minor adverse event, infectious event, and any complication during the hospitalization (P<0.001, all comparisons). In an analysis of demographic factors, age demonstrated higher discriminative ability for in-hospital mortality compared to gender (P<0.001) and race (P<0.001). Race had sole or shared inferior discriminative ability for all outcomes. The most discriminative comorbidity index (ECM) outperformed the most discriminative demographic factor (age, gender) for any complication, minor adverse event, and infectious events. A combination analysis of the most predictive comorbidity index and the most predictive demographic factor resulted in discriminative improvements in all five outcome variables. Conclusion: Among comorbidity indices, the mCCI demonstrated significantly greater discriminative ability for mortality and the ECM demonstrated significantly greater discriminative ability for multiple adverse events during hospitalization. The use of these indices in conjunction with easily accessible demographic factors, such as age, resulted in further improvements in discrimination ability. These findings suggest that increased use of the mCCI and ECM may assist in the identification and management of patients at risk of death and postoperative complications, respectively, and thereby help optimize risk stratification, inform patient expectations, and guide outcomes-based reimbursements in the management of traumatic ankle fracture.

Plant-parasitic nematodes cause severe losses to crop production and economies all over the world. Bacillus aryabhattai MCCC 1K02966, a deep-sea bacterium, was obtained from the Southwest Indian Ocean and showed nematicidal and fumigant activities against Meloidogyne incognita in vitro. The nematicidal volatile organic compounds (VOCs) from the fermentation broth of B. aryabhattai MCCC 1K02966 were investigated further using solid-phase microextraction gas chromatography-mass spectrometry. Four VOCs, namely, pentane, 1-butanol, methyl thioacetate, and dimethyl disulfide, were identified in the fermentation broth. Among these VOCs, methyl thioacetate exhibited multiple nematicidal activities, including contact nematicidal, fumigant, and repellent activities against M. incognita. Methyl thioacetate showed a significant contact nematicidal activity with 87.90% mortality at 0.01 mg/mL by 72 h, fumigant activity in mortality 91.10% at 1 mg/mL by 48 h, and repellent activity at 0.01–10 mg/mL. In addition, methyl thioacetate exhibited 80–100% egg-hatching inhibition on the 7th day over the range of 0.5 mg/mL to 5 mg/mL. These results showed that methyl thioacetate from MCCC 1K02966 control M. incognita with multiple nematicidal modes and can be used as a potential biological control agent.

A systematic chemical investigation of the deep-sea-derived fungus Penicillium solitum MCCC 3A00215 resulted in the isolation of one novel polyketide (1), two new alkaloids (2 and 3), and 22 known (4–25) compounds. The structures of the new compounds were established mainly on the basis of exhaustive analysis of 1D and 2D NMR data. Viridicatol (13) displayed moderate anti-tumor activities against PANC-1, Hela, and A549 cells with IC50 values of around 20 μM. Moreover, 13 displayed potent in vitro anti-food allergic activity with an IC50 value of 13 μM, compared to that of 92 μM for the positive control, loratadine, while indole-3-acetic acid methyl ester (9) and penicopeptide A (10) showed moderate effects (IC50 = 50 and 58 μM, respectively).