Using Multi-Scale Convolutional Neural Network Based on Multi-Instance Learning to Predict the Efficacy of Neoadjuvant Chemoradiotherapy for Rectal Cancer.

BACKGROUND: At present, radical total mesorectal excision after neoadjuvant chemoradiotherapy is crucial for locally advanced rectal cancer. Therefore, the use of histopathological images analysis technology to predict the efficacy of neoadjuvant chemoradiotherapy for rectal cancer is of great significance for the subsequent treatment of patients. METHODS: In this study, we propose a new pathological images analysis method based on multi-instance learning to predict the efficacy of neoadjuvant chemoradiotherapy for rectal cancer. Specifically, we proposed a gated attention normalization mechanism based on the multilayer perceptron, which accelerates the convergence of stochastic gradient descent optimization and can speed up the training process. We also proposed a bilinear attention multi-scale feature fusion mechanism, which organically fuses the global features of the larger receptive fields and the detailed features of the smaller receptive fields and alleviates the problem of pathological images context information loss caused by block sampling. At the same time, we also designed a weighted loss function to alleviate the problem of imbalance between cancerous instances and normal instances. RESULTS: We evaluated our method on a locally advanced rectal cancer dataset containing 150 whole slide images. In addition, to verify our method's generalization performance, we also tested on two publicly available datasets, Camelyon16 and MSKCC. The results show that the AUC values of our method on the Camelyon16 and MSKCC datasets reach 0.9337 and 0.9091, respectively. CONCLUSION: Our method has outstanding performance and advantages in predicting the efficacy of neoadjuvant chemoradiotherapy for rectal cancer. Clinical and Translational Impact Statement -This study aims to predict the efficacy of neoadjuvant chemoradiotherapy for rectal cancer to assist clinicians quickly diagnose and formulate personalized treatment plans for patients.

Binding screen for cystic fibrosis transmembrane conductance regulator correctors finds new chemical matter and yields insights into cystic fibrosis therapeutic strategy.

The most common mutation in cystic fibrosis (CF) patients is deletion of F508 (ΔF508) in the first nucleotide binding domain (NBD1) of the CF transmembrane conductance regulator (CFTR). ΔF508 causes a decrease in the trafficking of CFTR to the cell surface and reduces the thermal stability of isolated NBD1; it is well established that both of these effects can be rescued by additional revertant mutations in NBD1. The current paradigm in CF small molecule drug discovery is that, like revertant mutations, a path may exist to ΔF508 CFTR correction through a small molecule chaperone binding to NBD1. We, therefore, set out to find small molecule binders of NBD1 and test whether it is possible to develop these molecules into potent binders that increase CFTR trafficking in CF-patient-derived human bronchial epithelial cells. Several fragments were identified that bind NBD1 at either the CFFT-001 site or the BIA site. However, repeated attempts to improve the affinity of these fragments resulted in only modest gains. Although these results cannot prove that there is no possibility of finding a high-affinity small molecule binder of NBD1, they are discouraging and lead us to hypothesize that the nature of these two binding sites, and isolated NBD1 itself, may not contain the features needed to build high-affinity interactions. Future work in this area may, therefore, require constructs including other domains of CFTR in addition to NBD1, if high-affinity small molecule binding is to be achieved.

Separation of fluorescently labeled phosphoinositides and sphingolipids by capillary electrophoresis.

Phosphoinositides (PIs) and sphingolipids regulate many aspects of cell behavior and are often involved in disease processes such as oncogenesis. Capillary electrophoresis with laser induced fluorescence detection (CE-LIF) is emerging as an important tool for enzymatic assays of the metabolism of these lipids, particularly in cell-based formats. Previous separations of phosphoinositide lipids by CE required a complex buffer with polymer additives which had the disadvantages of high cost and/or short shelf life. Further a simultaneous separation of these classes of lipids has not been demonstrated in a robust buffer system. In the current work, a simple separation buffer based on NaH(2)PO(4) and 1-propanol was optimized to separate two sphingolipids and multiple phosphoinositides by CE. The NaH(2)PO(4) concentration, pH, 1-propanol fraction, and a surfactant additive to the buffer were individually optimized to achieve simultaneous separation of the sphingolipids and phosphoinositides. Fluorescein-labeled sphingosine (SFL) and sphingosine 1-phosphate (S1PFL), fluorescein-labeled phosphatidyl-inositol 4,5-bisphosphate (PIP2) and phosphatidyl-inositol 3,4,5-trisphosphate (PIP3), and bodipy-fluorescein (BFL)-labeled PIP2 and PIP3 were separated pairwise and in combination to demonstrate the generalizability of the method. Theoretical plate numbers achieved were as high as 2×10(5) in separating fluorophore-labeled PIP2 and PIP3. Detection limits for the 6 analytes were in the range of 10(-18)-10(-20)mol. The method also showed high reproducibility, as the relative standard deviation of the normalized migration time for each analyte in the simultaneous separation of all 6 compounds was less than 1%. The separation of a mixture composed of diacylglycerol (DAG) and multiple phosphoinositides was also demonstrated. As a final test, fluorescent lipid metabolites formed within cells loaded with BFLPIP2 were separated from a cell lysate as well as a single cell. This simple and robust separation method for SFL and S1PFL and various metabolites of phosphoinositide-related signal transduction is expected to enable improved enzymatic assays for biological and clinical applications.

Kinetic analysis of PI3K reactions with fluorescent PIP2 derivatives.

Phosphatidylinositol 3-kinase (PI3K) signaling plays important roles in cell differentiation, proliferation, and migration. Increased mutations and expression levels of PI3K are hallmarks for the development of certain cancers. Pharmacological targeting of PI3K activity has also been actively pursued as a novel cancer therapeutic. Consequently, measurement of PI3K activity in different cell types or patient samples holds the promise as being a novel diagnostic tool. However, the direct measurement of cellular PI3K activity has been a challenging task. We report here the characterization of two fluorescent PIP(2) derivatives as reporters for PI3K enzymatic activity. The reporters are efficiently separated from their corresponding PI3K enzymatic products through either thin layer chromatography (TLC) or capillary electrophoresis (CE), and can be detected with high sensitivity by fluorescence. The biophysical and kinetic properties of the two probes are measured, and their suitability to characterize PI3K inhibitors is explored. Both probes show similar capacity as PI3K substrates for inhibitor characterization, yet also possess distinct properties that may suggest their different applications. These characterizations have laid the groundwork to systematically measure cellular PI3K activity, and have the potential to generate molecular fingerprints for diagnostic and therapeutic applications.

The effects of flow type on aptamer capture in differential mobility cytometry cell separations.

In this work, differential mobility cytometry (DMC) was used to monitor cell separation based on aptamer recognition for target cells. In this device, open-tubular capillaries coated with Sgc8 aptamers were used as affinity chromatography columns for separation. After cells were injected into the columns, oscillating flow was generated to allow for long-term cell adhesion studies. This process was monitored by optical microscopy, and differential imaging was used to analyze the cells as they adhered to the affinity surface. We investigated the capture time, capture efficiency, purity of target and control cells, as well as the reusability of the affinity columns. Capture time for both CCRF-CEM cells and Jurkat T cells was 0.4+/-0.2 s, which demonstrated the high separation affinity between aptamers and target cells. The capture efficiency for CCRF-CEM cells was 95% and purity was 99% in a cell mixture. With the advantage of both high cell capture efficiency and purity, DMC combined with aptamer-based separation emerges as a powerful tool for rare cell enrichment. In addition, aptamer-based DMC channels were found to be more robust than antibody based channels with respect to reuse of the separation device.

Simultaneous cell capture and induction of apoptosis using an anti-CD95 affinity microdevice.

A microfluidic device is designed and demonstrated for the simultaneous capture and induction of apoptosis in Jurkat cells. In this unique case, the cell capture event initiates a biological process. The device features a single channel made from poly(dimethylsiloxane) sealed to a glass substrate. The channel is coated with a series of reagents used in affinity chromatography separations of cells. In this case, the antibody used to capture the cells is functional anti-CD95 which captures the cells by binding to the Fas receptor on the cell membrane and, at the same time, inducing apoptosis via the caspase 8 pathway. Cells retained on the surface of the channel are known to be induced to undergo apoptosis. Medium is flowed slowly through the channel to maintain cell viability while the cells undergo apoptosis. After 3 h, staining with Annexin V-PE and 7-AAD revealed that 43.5% of the cells bound to the anti-CD95 coated channel are apoptotic, whereas 7.9% of cultured Jurkat cells induced with anti-CD95 for 3 h and stained in the same way were determined to be apoptotic by flow cytometry. The device provides a method of determining when apoptosis is induced, maintaining cell viability for long-term analysis and observing cells in real time as they are exposed to reagents that affect apoptosis. In the future, the device will be an invaluable tool for the study of the temporal dynamics of apoptosis.

Local sequence information-based support vector machine to classify voltage-gated potassium channels.

In our previous work, we developed a computational tool, PreK-ClassK-ClassKv, to predict and classify potassium (K+) channels. For K+ channel prediction (PreK) and classification at family level (ClassK), this method performs well. However, it does not perform so well in classifying voltage-gated potassium (Kv) channels (ClassKv). In this paper, a new method based on the local sequence information of Kv channels is introduced to classify Kv channels. Six transmembrane domains of a Kv channel protein are used to define a protein, and the dipeptide composition technique is used to transform an amino acid sequence to a numerical sequence. A Kv channel protein is represented by a vector with 2000 elements, and a support vector machine algorithm is applied to classify Kv channels. This method shows good performance with averages of total accuracy (Acc), sensitivity (SE), specificity (SP), reliability (R) and Matthews correlation coefficient (MCC) of 98.0%, 89.9%, 100%, 0.95 and 0.94 respectively. The results indicate that the local sequence information-based method is better than the global sequence information-based method to classify Kv channels.