The air quality in urban areas is a major concern in modern cities due to significant impacts of air pollution on public health, global environment, and worldwide economy. Recent studies reveal the importance of micro-level pollution information, including human personal exposure and acute exposure to air pollutants. A real-time system with high spatio-temporal resolution is essential because of the limited data availability and non-scalability of conventional air pollution monitoring systems. Currently, researchers focus on the concept of The Next Generation Air Pollution Monitoring System (TNGAPMS) and have achieved significant breakthroughs by utilizing the advance sensing technologies, MicroElectroMechanical Systems (MEMS) and Wireless Sensor Network (WSN). However, there exist potential problems of these newly proposed systems, namely the lack of 3D data acquisition ability and the flexibility of the sensor network. In this paper, we classify the existing works into three categories as Static Sensor Network (SSN), Community Sensor Network (CSN) and Vehicle Sensor Network (VSN) based on the carriers of the sensors. Comprehensive reviews and comparisons among these three types of sensor networks were also performed. Last but not least, we discuss the limitations of the existing works and conclude the objectives that we want to achieve in future systems.

Understanding the phenotypic drug response on cancer cell lines plays a vital role in anti-cancer drug discovery and re-purposing. The Genomics of Drug Sensitivity in Cancer (GDSC) database provides open data for researchers in phenotypic screening to build and test their models. Previously, most research in these areas starts from the molecular fingerprints or physiochemical features of drugs, instead of their structures. In this paper, a model called twin Convolutional Neural Network for drugs in SMILES format (tCNNS) is introduced for phenotypic screening. tCNNS uses a convolutional network to extract features for drugs from their simplified molecular input line entry specification (SMILES) format and uses another convolutional network to extract features for cancer cell lines from the genetic feature vectors respectively. After that, a fully connected network is used to predict the interaction between the drugs and the cancer cell lines. When the training set and the testing set are divided based on the interaction pairs between drugs and cell lines, tCNNS achieves 0.826, 0.831 for the mean and top quartile of the coefficient of determinant (R2) respectively and 0.909, 0.912 for the mean and top quartile of the Pearson correlation (Rp) respectively, which are significantly better than those of the previous works (Ammad-Ud-Din et al., J Chem Inf Model 54:2347–9, 2014), (Haider et al., PLoS ONE 10:0144490, 2015), (Menden et al., PLoS ONE 8:61318, 2013). However, when the training set and the testing set are divided exclusively based on drugs or cell lines, the performance of tCNNS decreases significantly and Rp and R2 drop to barely above 0. Our approach is able to predict the drug effects on cancer cell lines with high accuracy, and its performance remains stable with less but high-quality data, and with fewer features for the cancer cell lines. tCNNS can also solve the problem of outliers in other feature space. Besides achieving high scores in these statistical metrics, tCNNS also provides some insights into the phenotypic screening. However, the performance of tCNNS drops in the blind test.

Microarray technology is widely used in cancer diagnosis. Successfully identifying gene biomarkers will significantly help to classify different cancer types and improve the prediction accuracy. The regularization approach is one of the effective methods for gene selection in microarray data, which generally contain a large number of genes and have a small number of samples. In recent years, various approaches have been developed for gene selection of microarray data. Generally, they are divided into three categories: filter, wrapper and embedded methods. Regularization methods are an important embedded technique and perform both continuous shrinkage and automatic gene selection simultaneously. Recently, there is growing interest in applying the regularization techniques in gene selection. The popular regularization technique is Lasso (L1), and many L1 type regularization terms have been proposed in the recent years. Theoretically, the Lq type regularization with the lower value of q would lead to better solutions with more sparsity. Moreover, the L1/2 regularization can be taken as a representative of Lq (0 < q < 1) regularizations and has been demonstrated many attractive properties. In this work, we investigate a sparse logistic regression with the L1/2 penalty for gene selection in cancer classification problems, and propose a coordinate descent algorithm with a new univariate half thresholding operator to solve the L1/2 penalized logistic regression. Experimental results on artificial and microarray data demonstrate the effectiveness of our proposed approach compared with other regularization methods. Especially, for 4 publicly available gene expression datasets, the L1/2 regularization method achieved its success using only about 2 to 14 predictors (genes), compared to about 6 to 38 genes for ordinary L1 and elastic net regularization approaches. From our evaluations, it is clear that the sparse logistic regression with the L1/2 penalty achieves higher classification accuracy than those of ordinary L1 and elastic net regularization approaches, while fewer but informative genes are selected. This is an important consideration for screening and diagnostic applications, where the goal is often to develop an accurate test using as few features as possible in order to control cost. Therefore, the sparse logistic regression with the L1/2 penalty is effective technique for gene selection in real classification problems.

Docking scoring functions can be used to predict the strength of protein-ligand binding. It is widely believed that training a scoring function with low-quality data is detrimental for its predictive performance. Nevertheless, there is a surprising lack of systematic validation experiments in support of this hypothesis. In this study, we investigated to which extent training a scoring function with data containing low-quality structural and binding data is detrimental for predictive performance. We actually found that low-quality data is not only non-detrimental, but beneficial for the predictive performance of machine-learning scoring functions, though the improvement is less important than that coming from high-quality data. Furthermore, we observed that classical scoring functions are not able to effectively exploit data beyond an early threshold, regardless of its quality. This demonstrates that exploiting a larger data volume is more important for the performance of machine-learning scoring functions than restricting to a smaller set of higher data quality.

State-of-the-art protein-ligand docking methods are generally limited by the traditionally low accuracy of their scoring functions, which are used to predict binding affinity and thus vital for discriminating between active and inactive compounds. Despite intensive research over the years, classical scoring functions have reached a plateau in their predictive performance. These assume a predetermined additive functional form for some sophisticated numerical features, and use standard multivariate linear regression (MLR) on experimental data to derive the coefficients. In this study we show that such a simple functional form is detrimental for the prediction performance of a scoring function, and replacing linear regression by machine learning techniques like random forest (RF) can improve prediction performance. We investigate the conditions of applying RF under various contexts and find that given sufficient training samples RF manages to comprehensively capture the non-linearity between structural features and measured binding affinities. Incorporating more structural features and training with more samples can both boost RF performance. In addition, we analyze the importance of structural features to binding affinity prediction using the RF variable importance tool. Lastly, we use Cyscore, a top performing empirical scoring function, as a baseline for comparison study. Machine-learning scoring functions are fundamentally different from classical scoring functions because the former circumvents the fixed functional form relating structural features with binding affinities. RF, but not MLR, can effectively exploit more structural features and more training samples, leading to higher prediction performance. The future availability of more X-ray crystal structures will further widen the performance gap between RF-based and MLR-based scoring functions. This further stresses the importance of substituting RF for MLR in scoring function development.

Hepatocellular carcinoma (HCC) is one of the leading causes of cancer-related deaths worldwide. Surgical resection and conventional chemotherapy and radiotherapy ultimately fail due to tumor recurrence and HCC’s resistance. The development of novel therapies against HCC is thus urgently required. The cyclin-dependent kinase (CDK) pathways are important and well-established targets for cancer treatment. In particular, CDK2 is a key factor regulating the cell cycle G1 to S transition and a hallmark for cancers. In this study, we utilized our free and open-source protein-ligand docking software, idock, prospectively to identify potential CDK2 inhibitors from 4,311 FDA-approved small molecule drugs using a repurposing strategy and an ensemble docking methodology. Sorted by average idock score, nine compounds were purchased and tested in vitro. Among them, the anti-psychotic drug fluspirilene exhibited the highest anti-proliferative effect in human hepatocellular carcinoma HepG2 and Huh7 cells. We demonstrated for the first time that fluspirilene treatment significantly increased the percentage of cells in G1 phase, and decreased the expressions of CDK2, cyclin E and Rb, as well as the phosphorylations of CDK2 on Thr160 and Rb on Ser795. We also examined the anti-cancer effect of fluspirilene in vivo in BALB/C nude mice subcutaneously xenografted with human hepatocellular carcinoma Huh7 cells. Our results showed that oral fluspirilene treatment significantly inhibited tumor growth. Fluspirilene (15 mg/kg) exhibited strong anti-tumor activity, comparable to that of the leading cancer drug 5-fluorouracil (10 mg/kg). Moreover, the cocktail treatment with fluspirilene and 5-fluorouracil exhibited the highest therapeutic effect. These results suggested for the first time that fluspirilene is a potential CDK2 inhibitor and a candidate anti-cancer drug for the treatment of human hepatocellular carcinoma. In view of the fact that fluspirilene has a long history of safe human use, our discovery of fluspirilene as a potential anti-HCC drug may present an immediately applicable clinical therapy.