RESUMO
The continuous progress of society and the vigorous development of science and technology have brought people the dawn of maintaining health and preventing and controlling diseases. At the same time, with the update and iteration of bioinformatics technology, the current biological gene research has also undergone revolutionary changes. However, a long-standing problem in genetic research has always plagued researchers, that is, how to find the most needed sample genes from a large number of sample genes, so as to reduce unnecessary research and reduce research costs. By studying the extraction path of biological genes, it can help researchers to extract the most valuable research genes and avoid wasting time and energy. In order to solve the above problems, this paper used the Bhattacharyya distance index and the Gini index to screen the sample genes when extracting the characteristic genes of breast cancer. In the selected 49 public genes, 6 principal components were extracted by principal component analysis (PCA), and finally the experimental results were tested. It was found that when the optimal number of characteristic genes was selected as 5, the recognition rate of genes reached the highest 90.31%, which met the experimental requirements. In addition, the experiment also proved that the characteristic gene extraction method designed in this paper had a removal rate of 99.75% of redundant genes, which can greatly reduce the time and money cost of research.
RESUMO
SBS-modified bitumen (SMB) is susceptible to aging, which seriously influences its service performance and life. In order to strengthen the anti-aging ability of SMB, triethoxyvinylsilane was designed to organically modify layered double hydroxides (LDHs) and was applied to modify SMB. The dispersibility and storage stability of LDHs in SMB were markedly enhanced after triethoxyvinylsilane organic modification, and the compatibility and storage stability of SBS in bitumen were simultaneously enhanced. Compared with SMB, the introduction of LDHs and organic LDHs (OLDHs) could ameliorate the high-temperature properties of SMB, and the thermostability of SBS in bitumen at a high temperature was also distinctly improved, especially OLDHs. After aging, due to the oxidation of molecular bitumen and the degradation of molecular SBS, SMB became hardened and brittle, and the rheological properties were significantly deteriorated, which had serious impacts on the performance of SMB. LDHs can mitigate the detriment of aging to bitumen and SBS, and the deterioration of the rheological properties of SMB is obviously alleviated. As a result of the better dispersibility and storage stability, OLDHs exerted superior reinforcement of the anti-aging ability of SMB.
RESUMO
To improve the anti-aging ability of SBS modified bitumen (SMB), layered double hydroxide (LDH) organically modified by hexadecyltrimethoxysilane was prepared and utilized for the modification of SMB. According to X-ray photoelectron spectroscopy, hexadecyltrimethoxysilane has been grafted into LDH through chemical bonding. Compared with LDH, the hydrophilicity of organic LDH (OLDH) was obviously reduced, and OLDH possessed better dispersibility and stability in SMB, because of the decrease of hydroxyl and the introduced organo-functional groups on the surface of LDH. The addition of OLDH and LDH can ameliorate the high temperature behavior of SMB, especially OLDH. After aging, bitumen was oxidized and SBS was degraded, which resulted in the physical and rheological property deterioration of SMB. LDH can alleviate the destruction of aging on the performance and chemical structure of SMB. Furthermore, the improvement of LDH on the anti-aging ability of SMB has been further enhanced after hexadecyltrimethoxysilane organic modification.
RESUMO
BACKGROUND: In recent years, deep learning methods have been applied to many natural language processing tasks to achieve state-of-the-art performance. However, in the biomedical domain, they have not out-performed supervised word sense disambiguation (WSD) methods based on support vector machines or random forests, possibly due to inherent similarities of medical word senses. RESULTS: In this paper, we propose two deep-learning-based models for supervised WSD: a model based on bi-directional long short-term memory (BiLSTM) network, and an attention model based on self-attention architecture. Our result shows that the BiLSTM neural network model with a suitable upper layer structure performs even better than the existing state-of-the-art models on the MSH WSD dataset, while our attention model was 3 or 4 times faster than our BiLSTM model with good accuracy. In addition, we trained "universal" models in order to disambiguate all ambiguous words together. That is, we concatenate the embedding of the target ambiguous word to the max-pooled vector in the universal models, acting as a "hint". The result shows that our universal BiLSTM neural network model yielded about 90 percent accuracy. CONCLUSION: Deep contextual models based on sequential information processing methods are able to capture the relative contextual information from pre-trained input word embeddings, in order to provide state-of-the-art results for supervised biomedical WSD tasks.
Assuntos
Algoritmos , Redes Neurais de Computação , Vocabulário , Humanos , Processamento de Linguagem Natural , Máquina de Vetores de SuporteRESUMO
γ-(2,3-Epoxypropoxy)propyltrimethoxy silane surface modified layered double hydroxides (KH560-LDHs) were prepared and used to improve the ultraviolet ageing resistance of asphalt. The results of X-ray photoelectron spectrometry (XPS) indicated that KH560 has been successfully grafted onto the surface of LDHs. The agglomeration of LDHs particles notably reduced after KH560 surface modification according to scanning electron microscopy (SEM), which implied that the KH560 surface modification was helpful to promote the dispersibility of LDHs in asphalt. Then, the influence of KH560-LDHs and LDHs on the physical and rheological properties of asphalt before and after UV ageing was thoroughly investigated. The storage stability test showed that the difference in softening point (ΔS) of LDHs modified asphalt decreased from 0.6 °C to 0.2 °C at an LDHs content of 1% after KH560 surface modification, and the tendency became more pronounced with the increase of LDH content, indicating that KH560 surface modification could improve the stability of LDHs in asphalt. After UV ageing, the viscous modulus (G'') of asphalt significantly reduced, and correspondingly, the elastic modulus (G') and rutting factor (G*/sin δ) rapidly increased. Moreover, the asphaltene increased and the amount of "bee-like" structures of the asphalt decreased. Compared with LDHs, KH560-LDHs obviously restrained performance deterioration of the asphalt, and helped to relieve the variation of the chemical compositions and morphology of asphalt, which suggested that the improvement of KH560-LDHs on UV ageing resistance of asphalt was superior to LDHs.
RESUMO
Tri-block copolymer styrene-butadiene (SBS) is extensively applied in bituminous highway construction due to its high elasticity and excellent weather resistance. With the extension of time, tri-block structural SBS automatically degrades into bi-block structural SB- with some terminal oxygen-containing groups under the comprehensive effects of light, heat, oxygen, etc. In this paper, the effects of aging temperature, aging time and oxygen concentration on the molecular structure of thermo-oxidative aged SBS were mainly investigated using Fourier transform infrared spectroscopy (FTIR) and X-ray photoelectron spectroscopy (XPS), and the correlation between oxygen-containing groups and thermal properties (TG-DTG) was further discussed. The FTIR and XPS results show that rapid decomposition of SBS will occur with increments of aging temperature, aging time and oxygen concentration, and a large number of oxygen-containing groups such as -OH, C=O, -COOH, etc. will be formed during thermo-oxidative aging. In short-term aging, changes in aging temperature and oxygen concentration have a significant impact on the structural damage of SBS. However, in long-term aging, it has no further effect on the molecular structure of SBS or on increasing oxygen concentration. The TG and DTG results indicate that the concentration of substances with low molecular weight gradually increases with the improvement of the degree of aging of the SBS, while the initial decomposition rate increases at the beginning of thermal weightlessness and the decomposition rate slows down in comparison with neat SBS. From the relation between the XPS and TG results, it can be seen that the initial thermal stability of SBS rapidly reduces as the relative concentration of the oxygen-containing groups accumulates around 3%, while the maximum decomposition temperature slowly decreases when the relative concentration of the oxygen-containing groups is more than 3%, due to the difficult damage to strong bonds on the molecular structure of aged SBS.