High-quality AFM image acquisition of living cells by modified residual encoder-decoder network.

Atomic force microscope enables ultra-precision imaging of living cells. However, atomic force microscope imaging is a complex and time-consuming process. The obtained images of living cells usually have low resolution and are easily influenced by noise leading to unsatisfactory imaging quality, obstructing the research and analysis based on cell images. Herein, an adaptive attention image reconstruction network based on residual encoder-decoder was proposed, through the combination of deep learning technology and atomic force microscope imaging supporting high-quality cell image acquisition. Compared with other learning-based methods, the proposed network showed higher peak signal-to-noise ratio, higher structural similarity and better image reconstruction performances. In addition, the cell images reconstructed by each method were used for cell recognition, and the cell images reconstructed by the proposed network had the highest cell recognition rate. The proposed network has brought insights into the atomic force microscope-based imaging of living cells and cell image reconstruction, which is of great significance in biological and medical research.

Cell recognition based on features extracted by AFM and parameter optimization classifiers.

Intelligent technology can assist in the diagnosis and treatment of disease, which would pave the way towards precision medicine in the coming decade. As a key focus of medical research, the diagnosis and prognosis of cancer play an important role in the future survival of patients. In this work, a diagnostic method based on nano-resolution imaging was proposed to meet the demand for precise detection methods in medicine and scientific research. The cell images scanned by AFM were recognized by cell feature engineering and machine learning classifiers. A feature ranking method based on the importance of features to responses was used to screen features closely related to categorization and optimization of feature combinations, which helps to understand the feature differences between cell types at the micro level. The results showed that the Bayesian optimized back propagation neural network has accuracy rates of 90.37% and 92.68% on two cell datasets (HL-7702 & SMMC-7721 and GES-1 & SGC-7901), respectively. This provides an automatic analysis method for identifying cancer cells or abnormal cells, which can help to reduce the burden of medical or scientific research, decrease misjudgment and promote precise medical care for the whole society.

Cell recognition based on atomic force microscopy and modified residual neural network.

Cell recognition methods are in high demand in cell biology and medicine, and the method based on atomic force microscopy (AFM) shows a great value in application. The difference in mechanical properties or morphology of cells has been frequently used to detect whether cells are cancerous, but this detection method cannot be a general means for cancer cell detection, and the traditional artificial feature extraction method also has its limitations. In this work, we proposed an analytic method based on the physical properties of cells and deep learning method for recognizing cell types. The residual neural network used for recognition was modified by multi-scale convolutional fusion, attention mechanism and depthwise separable convolution, so as to optimize feature extraction and reduce operation costs. In the method, the collected cells were imaged by AFM, and the processed images were analyzed by the optimized convolutional neural network. The recognition results of two groups of cells (HL-7702 and SMMC-7721, SGC-7901 and GES-1) by this method show that the recognition rate of dataset with the combination of cell surface morphology, adhesion and Young's modulus is higher, and the recognition rate of the dataset with optimal resolution is higher. Our study indicated that the recognition of physical properties of cells using deep learning technology can serve as a universal and effective method for the automated analysis of cell information.

Suspension culture process for H9N2 avian influenza virus (strain Re-2).

H9N2 avian influenza virus has caused huge economic loss for the Chinese poultry industry since it was first identified. Vaccination is frequently used as a control method for the disease. Meanwhile suspension culture has become an important tool for the development of influenza vaccines. To optimize the suspension culture conditions for the avian influenza H9N2 virus (Re-2 strain) in Madin-Darby Canine Kidney (MDCK) cells, we studied the culture conditions for cell growth and proliferation parameters for H9N2 virus replication. MDCK cells were successfully cultured in suspension, from a small scale to industrial levels of production, with passage time and initial cell density being optimized. The influence of pH on the culture process in the reactor has been discussed and the process parameters for industrial production were explored via amplification of the 650L reactor. Subsequently, we cultivated cells at high cell density and harvested high amounts of virus, reaching 10log2 (1:1024). Furthermore an animal experiment was conducted to detect antibody. Compared to the chicken embryo virus vaccine, virus cultured from MDCK suspension cells can produce a higher amount of antibodies. The suspension culture process is simple and cost efficient, thus providing a solid foundation for the realization of large-scale avian influenza vaccine production.

Theoretical study on the kinetics of OH radical reactions with CH3OOH and CH3CH2OOH.

The mechanisms and kinetics studies of the OH radical with alkyl hydroperoxides CH(3)OOH and CH(3)CH(2)OOH reactions have been carried out theoretically. The geometries and frequencies of all the stationary points are calculated at the UBHandHLYP/6-311G(d,p) level, and the energy profiles are further refined by interpolated single-point energies method at the MC-QCISD level of theory. For two reactions, five H-abstraction channels are found and five products (CH(3)OO, CH(2)OOH, CH(3)CH(2)OO, CH(2)CH(2)OOH, and CH(3)CHOOH) are produced during the above processes. The rate constants for the CH(3)OOH/CH(3)CH(2)OOH + OH reactions are corrected by canonical variational transition state theory within 250-1500 K, and the small-curvature tunneling is included. The total rate constants are evaluated from the sum of the individual rate constants and the branching ratios are in good agreement with the experimental data. The Arrhenius expressions for the reactions are obtained.

Theoretical studies on the mechanisms and dynamics of OH radicals with CH(2)FCF(2)OCHF(2) and CH(2)FOCH(2)F.

The mechanisms and dynamics studies of the multichannel reactions of CH(2)FCF(2)OCHF(2) + OH (R1) and CH(2)FOCH(2)F + OH (R2) have been carried out theoretically. Three hydrogen abstraction channels and two displacement processes are found for reaction R1, whereas there are two hydrogen abstraction channels and one displacement process for reaction R2. The minimum energy paths are optimized at the B3LYP/6-311G(d,p) level, and the energy profiles are further refined by interpolated single-point energies (ISPE) method at the BMC-QCISD level of theory. By means of canonical variational transition state theory with small-curvature tunneling correction, the rate constants of reactions R1 and R2 are obtained over the temperature range of 220-2000 K. The rate constants are in good agreement with the experimental data for reaction R1 and estimated data for reaction R2. The Arrhenius expression k(1) = 1.62 x 10(-20) T(2.75) exp(-1011/T) for reaction R1 and k(2) = 3.40 x 10(-21) T(3.04) exp(-384/T) for reaction R2 over 220-2000 K are obtained. Furthermore, to further reveal the thermodynamics properties, the enthalpies of formation of reactants CH(2)FCF(2)OCHF(2), CH(2)FOCH(2)F, and the product radicals CHFCF(2)OCHF(2), CH(2)FCF(2)OCF(2), and CHFOCH(2)F are calculated by using isodesmic reactions.