Five Typical Stenches Detection Using an Electronic Nose.

This paper deals with the classification of stenches, which can stimulate olfactory organs to discomfort people and pollute the environment. In China, the triangle odor bag method, which only depends on the state of the panelist, is widely used in determining odor concentration. In this paper, we propose a stenches detection system composed of an electronic nose and machine learning algorithms to discriminate five typical stenches. These five chemicals producing stenches are 2-phenylethyl alcohol, isovaleric acid, methylcyclopentanone, γ-undecalactone, and 2-methylindole. We will use random forest, support vector machines, backpropagation neural network, principal components analysis (PCA), and linear discriminant analysis (LDA) in this paper. The result shows that LDA (support vector machine (SVM)) has better performance in detecting the stenches considered in this paper.

Incorporating dictionaries into deep neural networks for the Chinese clinical named entity recognition.

Clinical named entity recognition aims to identify and classify clinical terms such as diseases, symptoms, treatments, exams, and body parts in electronic health records, which is a fundamental and crucial task for clinical and translational research. In recent years, deep neural networks have achieved significant success in named entity recognition and many other natural language processing tasks. Most of these algorithms are trained end to end, and can automatically learn features from large scale labeled datasets. However, these data-driven methods typically lack the capability of processing rare or unseen entities. Previous statistical methods and feature engineering practice have demonstrated that human knowledge can provide valuable information for handling rare and unseen cases. In this paper, we propose a new model which combines data-driven deep learning approaches and knowledge-driven dictionary approaches. Specifically, we incorporate dictionaries into deep neural networks. In addition, two different architectures that extend the bi-directional long short-term memory neural network and five different feature representation schemes are also proposed to handle the task. Computational results on the CCKS-2017 Task 2 benchmark dataset show that the proposed method achieves the highly competitive performance compared with the state-of-the-art deep learning methods.

ChemMapper: a versatile web server for exploring pharmacology and chemical structure association based on molecular 3D similarity method.

SUMMARY: ChemMapper is an online platform to predict polypharmacology effect and mode of action for small molecules based on 3D similarity computation. ChemMapper collects >350 000 chemical structures with bioactivities and associated target annotations (as well as >3 000 000 non-annotated compounds for virtual screening). Taking the user-provided chemical structure as the query, the top most similar compounds in terms of 3D similarity are returned with associated pharmacology annotations. ChemMapper is designed to provide versatile services in a variety of chemogenomics, drug repurposing, polypharmacology, novel bioactive compounds identification and scaffold hopping studies. AVAILABILITY: http://lilab.ecust.edu.cn/chemmapper/. CONTACT: xfliu@ecust.edu.cn or hlli@ecust.edu.cn SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PTID: an integrated web resource and computational tool for agrochemical discovery.

SUMMARY: Although in silico drug discovery approaches are crucial for the development of pharmaceuticals, their potential advantages in agrochemical industry have not been realized. The challenge for computer-aided methods in agrochemical arena is a lack of sufficient information for both pesticides and their targets. Therefore, it is important to establish such knowledge repertoire that contains comprehensive pesticides' profiles, which include physicochemical properties, environmental fates, toxicities and mode of actions. Here, we present an integrated platform called Pesticide-Target interaction database (PTID), which comprises a total of 1347 pesticides with rich annotation of ecotoxicological and toxicological data as well as 13 738 interactions of pesticide-target and 4245 protein terms via text mining. Additionally, through the integration of ChemMapper, an in-house computational approach to polypharmacology, PTID can be used as a computational platform to identify pesticides targets and design novel agrochemical products. AVAILABILITY: http://lilab.ecust.edu.cn/ptid/. CONTACT: hlli@ecust.edu.cn; xhqian@ecust.edu.cn SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A primal analysis system of brain neurons data.

It is a very challenging work to classify the 86 billions of neurons in the human brain. The most important step is to get the features of these neurons. In this paper, we present a primal system to analyze and extract features from brain neurons. First, we make analysis on the original data of neurons in which one neuron contains six parameters: room type, X, Y, Z coordinate range, total number of leaf nodes, and fuzzy volume of neurons. Then, we extract three important geometry features including rooms type, number of leaf nodes, and fuzzy volume. As application, we employ the feature database to fit the basic procedure of neuron growth. The result shows that the proposed system is effective.

SimG: an alignment based method for evaluating the similarity of small molecules and binding sites.

In this study, a Gaussian volume overlap and chemical feature based molecular similarity metric was devised, and a downhill simplex searching was carried out to evaluate the corresponding similarity. By representing the shapes of both the candidate small molecules and the binding site with chemical features and comparing the corresponding Gaussian volumes overlaps, the active compounds could be identified. These two aspects compose the proposed method named SimG which supports both structure-based and ligand-based strategies. The validity of the proposed method was examined by analyzing the similarity score variation between actives and decoys as well as correlation among distinct reference methods. A retrospective virtual screening test was carried out on DUD data sets, demonstrating that the performance of structure-based shape matching virtual screening in DUD data sets is substantially dependent on some physical properties, especially the solvent-exposure extent of the binding site: The enrichments of targets with less solvent-exposed binding sites generally exceeds that of the one with more solvent-exposed binding sites and even surpasses the corresponding ligand-based virtual screening.

Boundary-Eliminated Pseudoinverse Linear Discriminant for Imbalanced Problems.

Existing learning models for classification of imbalanced data sets can be grouped as either boundary-based or nonboundary-based depending on whether a decision hyperplane is used in the learning process. The focus of this paper is a new approach that leverages the advantage of both approaches. Specifically, our new model partitions the input space into three parts by creating two additional boundaries in the training process, and then makes the final decision based on a heuristic measurement between the test sample and a subset of selected training samples. Since the original hyperplane used by the underlying original classifier will be eliminated, the proposed model is named the boundary-eliminated (BE) model. Additionally, the pseudoinverse linear discriminant (PILD) is adopted for the BE model so as to obtain a novel classifier abbreviated as BEPILD. Experiments validate both the effectiveness and the efficiency of BEPILD, compared with 13 state-of-the-art classification methods, based on 31 imbalanced and 7 standard data sets.

Reduced multiple empirical kernel learning machine.

Multiple kernel learning (MKL) is demonstrated to be flexible and effective in depicting heterogeneous data sources since MKL can introduce multiple kernels rather than a single fixed kernel into applications. However, MKL would get a high time and space complexity in contrast to single kernel learning, which is not expected in real-world applications. Meanwhile, it is known that the kernel mapping ways of MKL generally have two forms including implicit kernel mapping and empirical kernel mapping (EKM), where the latter is less attracted. In this paper, we focus on the MKL with the EKM, and propose a reduced multiple empirical kernel learning machine named RMEKLM for short. To the best of our knowledge, it is the first to reduce both time and space complexity of the MKL with EKM. Different from the existing MKL, the proposed RMEKLM adopts the Gauss Elimination technique to extract a set of feature vectors, which is validated that doing so does not lose much information of the original feature space. Then RMEKLM adopts the extracted feature vectors to span a reduced orthonormal subspace of the feature space, which is visualized in terms of the geometry structure. It can be demonstrated that the spanned subspace is isomorphic to the original feature space, which means that the dot product of two vectors in the original feature space is equal to that of the two corresponding vectors in the generated orthonormal subspace. More importantly, the proposed RMEKLM brings a simpler computation and meanwhile needs a less storage space, especially in the processing of testing. Finally, the experimental results show that RMEKLM owns a much efficient and effective performance in terms of both complexity and classification. The contributions of this paper can be given as follows: (1) by mapping the input space into an orthonormal subspace, the geometry of the generated subspace is visualized; (2) this paper first reduces both the time and space complexity of the EKM-based MKL; (3) this paper adopts the Gauss Elimination, one of the on-the-shelf techniques, to generate a basis of the original feature space, which is stable and efficient.

Performance evaluation of multilayer perceptrons for discriminating and quantifying multiple kinds of odors with an electronic nose.

This paper studies several types and arrangements of perceptron modules to discriminate and quantify multiple odors with an electronic nose. We evaluate the following types of multilayer perceptron. (A) A single multi-output (SMO) perceptron both for discrimination and for quantification. (B) An SMO perceptron for discrimination followed by multiple multi-output (MMO) perceptrons for quantification. (C) An SMO perceptron for discrimination followed by multiple single-output (MSO) perceptrons for quantification. (D) MSO perceptrons for discrimination followed by MSO perceptrons for quantification, called the MSO-MSO perceptron model, under the following conditions: (D1) using a simple one-against-all (OAA) decomposition method; (D2) adopting a simple OAA decomposition method and virtual balance step; and (D3) employing a local OAA decomposition method, virtual balance step and local generalization strategy all together. The experimental results for 12 kinds of volatile organic compounds at 85 concentration levels in the training set and 155 concentration levels in the test set show that the MSO-MSO perceptron model with the D3 learning procedure is the most effective of those tested for discrimination and quantification of many kinds of odors.

A novel, customizable and optimizable parameter method using spherical harmonics for molecular shape similarity comparisons.

A novel molecular shape similarity comparison method, namely SHeMS, derived from spherical harmonic (SH) expansion, is presented in this study. Through weight optimization using genetic algorithms for a customized reference set, the optimal combination of weights for the translationally and rotationally invariant (TRI) SH shape descriptor, which can specifically and effectively distinguish overall and detailed shape features according to the molecular surface, is obtained for each molecule. This method features two key aspects: firstly, the SH expansion coefficients from different bands are weighted to calculate similarity, leading to a distinct contribution of overall and detailed features to the final score, and thus can be better tailored for each specific system under consideration. Secondly, the reference set for optimization can be totally configured by the user, which produces great flexibility, allowing system-specific and customized comparisons. The directory of useful decoys (DUD) database was adopted to validate and test our method, and principal component analysis (PCA) reveals that SH descriptors for shape comparison preserve sufficient information to separate actives from decoys. The results of virtual screening indicate that the proposed method based on optimal SH descriptor weight combinations represents a great improvement in performance over original SH (OSH) and ultra-fast shape recognition (USR) methods, and is comparable to many other popular methods. Through combining efficient shape similarity comparison with SH expansion method, and other aspects such as chemical and pharmacophore features, SHeMS can play a significant role in this field and can be applied practically to virtual screening by means of similarity comparison with 3D shapes of known active compounds or the binding pockets of target proteins.