Virtual screening (VS) can be accomplished in either ligand- or structure-based methods. In recent times, an increasing number of 2D fingerprint and 3D shape similarity methods have been used ligand-based VS. To evaluate the performance these methods, retrospective VS was performed on a tailored directory useful decoys (DUD). The performances 14 fingerprints four were compared. results revealed that ECFP_2 FCFP_4 yielded better than Phase Shape These also compared with such as Glide docking...

Abstract Predicting students' performance is one of the most important issues in educational data mining (EDM), which has received more and attention. By predicting performance, we can identify risk academic failure help instructors to take some actions such as guidance or interventions learners early possible, carry out continual evaluation optimize learning path personalized resources recommendation. In this survey, reviewed 80 studies on using EDM methods 2016–2021, synthesized procedure...

Cytochrome P450 inhibitory promiscuity of a drug has potential effects on the occurrence clinical drug–drug interactions. Understanding how molecular property is related to could help avoid such adverse effects. In this study, an entropy-based index was defined quantify compound based comprehensive data set, containing more than 11,500 drug-like compounds with inhibition against five major isoforms, 1A2, 2C9, 2C19, 2D6, and 3A4. The results indicated that would have moderate correlation...

To address three issues identified in previous research this study proposes a clustering-based MOOC dropout identification method and an early prediction model based on deep learning. The learning behavior of self-paced students was analyzed, two well-known datasets were used for analysis validation. findings are as follows: Firstly, the rate among MOOCs exceeds 90%, with over 50% participating online activities only one day. Furthermore, starting dates same course differ significantly....

Abstract Finding frequent itemsets in a continuous streaming data is an important mining task which widely used network monitoring, Internet of Things analysis and so on. In the era big data, it necessary to develop distributed itemset algorithm meet needs massive processing. Apache Spark unified analytic engine for processing has been successfully many fields. this paper, we propose over named SWEclat. The uses sliding window process vertical structure store dataset window. This implemented...

Abstract Background Immune cells play a pivotal role in the tumor microenvironment, exerting significant influence on progression and patient outcomes, but current biomarkers are insufficient to fully capture complex diverse immune microenvironment impact of immunotherapy. Methods The advent single‐cell sequencing allows us explore at an unprecedented resolution, enabling identification characterization distinct subsets cells, thereby paving way for development prognostic models using cells....

Allosteric modulators are important regulation elements that bind the allosteric site beyond active site, leading to changes in dynamic and/or thermodynamic properties of protein. have been a considerable interest as potential drugs with high selectivity and safety. However, current experimental methods limitations identify sites. Therefore, molecular dynamics simulation based on empirical force field becomes an complement methods. Moreover, precision efficiency fields need improvement. Deep...

How to analyze effective factors of online learning performance is a research issue that has received great attention. The commonly used multiple regression and structural equation models for analyzing are linear, while nonlinear based on machine short interpretation. In this study, framework proposed by interpreting models. Four benchmark datasets analyzed according framework. differences in the impact different performance, interaction between factors, representative learners analyzed....

Clustering is one of the most important unsupervised machine learning tasks, which widely used in information retrieval, social network analysis, image processing, and other fields. With explosive growth data, classical clustering algorithms cannot meet requirements for big data. Spark popular parallel processing platforms many researchers have proposed based on Spark. In this paper, existing are classified summarized, design framework each kind discussed, after comparing different kinds...

Predicting students’ performance is one of the most important issues in educational data mining. In this study, a method for representing partial sequence learning activities proposed, and an early prediction model designed based on deep neural network. This uses pre-trained autoencoder to extract latent features from order make predictions. The experimental results show that: (1) compared with demographic assessment scores, 20% wholly online activity sequences can achieve classifier...

Bladder cancer is a malignant tumor of the urinary and reproductive tract that seriously threatens human health. It urgent to develop new drugs for bladder cancer. This study aims explore whether curcumin could inhibit potential mechanism.

The genus Trachypithecus is the most diverse langur taxon, distributed in southwestern China, south and southeastern Asia. In this study, we include 16 recognized species to reconstruct phylogeny with particular concern taxonomy of three subspecies T. phayrei using multiple genes. Our results support a sister-relationship between p. shanicus. However, mitochondrial CYT B gene supported crepuscula as distinct species, but nuclear PRM1 suggested closer relationship phayrei. incongruence genes...

Predicting students’ performance is one of the most concerned issues in education data mining (EDM), which has received more and attentions. Feature selection key step to build prediction model performance, can improve accuracy help identify factors that have significant impact on performance. In this paper, a hybrid feature method named rank heuristic (RnkHEU) was proposed. This novel generates set candidate features by scoring ranking firstly then uses generate final results. The...

Chinese skink (Eumeces chinensis) is a ground-dwelling oviparous sincid lizard, which widely distributed in the southern Provinces of China, including Taiwan and Hainan. Here, complete mitochondrial genome E. chinensis (17 175 bp length) has been analyzed for building database. It contains 37 genes (13 protein-coding genes, 2 rRNA 22 tRNA genes) non-coding region (D-loop). Overall base composition DNA A (32.1%), G (14.3%), C (28.8%), T (24.8%), so percentage (56.9%) slightly higher than...

Abstract Predicting students' performance is one of the most important issue in educational data mining. In order to investigate state‐of‐the‐art research development predicting by using artificial neural networks (ANN), we conducted a survey on 39 studies this from 2016 2021. The results show that: (1) objectives prediction model learners program and course; (2) datasets used for training are collected logs learning management system; (3) commonly ANN feedforward network; (4) researchers...

Abstract Introduction: An increasing number of studies have proven that the kinase suppressor Ras (KSR1) functions as a scaffolding protein coordinates assembly multiprotein complex containing mitogen‐activated and its upstream regulators. However, few reported KSR1 can activate c‐Raf‐1. Therefore, whether possesses activity has been an unresolved issue until now. Materials Methods: pCMV‐Tag2b‐KSR plasmids were transfected into 293T cells. In vitro autophosphorylation was assayed by...

Online self-directed professional learning plays a crucial role in sustainable career development. This study leverages high-quality log dataset to thoroughly analyze the features of online learners, focusing on their engagement, performance, and satisfaction. The reveals that engagement levels among learners are predominantly low, with 56% categorized as 33% medium, 11% high. performance is generally strong, 47% achieving excellent results, although 4% fall into poor category. satisfaction...

Clustering is one of the most important unsupervised machine learning tasks. It widely used to solve problems intrusion detection, text analysis, image segmentation etc. Subspace clustering method for high-dimensional data clustering. In order problem parallel subspace big data, this paper proposes a algorithm based on spark named PSubCLUS which inspired by SubCLU, classical algorithm. While Spark popular processing platform currently, uses Resilient Distributed Datasets (RDD) provided store...