NetNCSP: Nonoverlapping closed sequential pattern mining.

Sequential pattern mining (SPM) has been applied in many fields. However, traditional SPM neglects the pattern repetition in sequence. To solve this problem, gap constraint SPM was proposed and can avoid finding too many useless patterns. Nonoverlapping SPM, as a branch of gap constraint SPM, means that any two occurrences cannot use the same sequence letter in the same position as the occurrences. Nonoverlapping SPM can make a balance between efficiency and completeness. The frequent patterns discovered by existing methods normally contain redundant patterns. To reduce redundant patterns and improve the mining performance, this paper adopts the closed pattern mining strategy and proposes a complete algorithm, named Nettree for Nonoverlapping Closed Sequential Pattern (NetNCSP) based on the Nettree structure. NetNCSP is equipped with two key steps, support calculation and closeness determination. A backtracking strategy is employed to calculate the nonoverlapping support of a pattern on the corresponding Nettree, which reduces the time complexity. This paper also proposes three kinds of pruning strategies, inheriting, predicting, and determining. These pruning strategies are able to find the redundant patterns effectively since the strategies can predict the frequency and closeness of the patterns before the generation of the candidate patterns. Experimental results show that NetNCSP is not only more efficient but can also discover more closed patterns with good compressibility. Furtherly, in biological experiments NetNCSP mines the closed patterns in SARS-CoV-2 and SARS viruses. The results show that the two viruses are of similar pattern composition with different combinations.

Functional activities of three Rehmannia glutinosa enzymes: Elucidation of the Rehmannia glutinosa salidroside biosynthesis pathway in Saccharomyces cerevisiae.

Rehmannia glutinosa produces many phenylethanoid glycoside (PhG) compounds, including salidroside, which not only possesses various biological activities but also is a core precursor of some medicinal PhGs, so it is very important to elucidate the species' salidroside biosynthesis pathway to enhance the production of salidroside and its derivations. Although some plant copper-containing amine oxidases (CuAOs), phenylacetaldehyde reductases (PARs) and UDP-glucose glucosyltransferases (UGTs) are thought to be vital catalytic enzymes involved in the downstream salidroside biosynthesis pathways, to date, none of these proteins or the associated genes in R. glutinosa have been characterized. To verify a postulated R. glutinosa salidroside biosynthetic pathway starting from tyrosine, this study identified and characterized a set of R. glutinosa genes encoding RgCuAO, RgPAR and RgUGT enzymes for salidroside biosynthesis. The functional activities of these proteins were tested in vitro by heterologous expression of these genes in Escherichia coli, confirming these catalytic abilities in these corresponding reaction steps of the biosynthetic pathway. Importantly, four enzyme-encoding genes (including the previously reported RgTyDC2 encoding tyrosine decarboxylase and the RgCuAO1, RgPAR1 and RgUGT2 genes) were cointegrated into Saccharomyces cerevisiae to reconstitute the R. glutinosa salidroside biosynthetic pathway, achieving an engineered strain that produced salidroside and validating these enzymes' catalytic functions. This study elucidates the complete R. glutinosa salidroside biosynthesis pathway from tyrosine metabolism in S. cerevisiae, establishing a basic platform for the efficient production of salidroside and its derivatives.

Segmentation and classification of thyroid follicular neoplasm using cascaded convolutional neural network.

In this paper, we present a segmentation and classification method for thyroid follicular neoplasms based on a combination of the prior-based level set method and deep convolutional neural network. The proposed method aims to discriminate thyroid follicular adenoma (TFA) and follicular thyroid carcinoma (FTC) in ultrasound images. In their appearance, these two kinds of tumours have similar shapes, sizes and contrasts. Therefore, it is difficult for even ultrasound specialists to distinguish them. Because of the complex background in thyroid ultrasound images, before distinguishing TFA and FTC, we need to segment the lesions from the whole image for each patient. The main challenge of segmentation is that the images often have weak edges and heterogeneous regions. The main issue of classification is that the accuracy depends on the features extracted from the segmentation results. To solve these problems, we conduct the two tasks, i.e. segmentation and classification, by a cascaded learning architecture. For segmentation, to obtain more accurate results, we exploit the Res-U-net framework and the prior-based level set method to enhance their respective abilities. Then, the classification network is trained by sharing shallow layers of the segmentation network. Testing the proposed method on real patient data shows that it is able to segment the lesion areas in thyroid ultrasound images with a Dice score of 92.65% and to distinguish TFA and FTC with a classification accuracy of 96.00%.