Binary classification of aqueous solubility using support vector machines with reduction and recombination feature selection

Aqueous solubility is recognized as a critical parameter in both the early- and late-stage drug discovery. Therefore, in silico modeling of solubility has attracted extensive interests in recent years. Most previous studies have been limited in using relatively small data sets with limited diversity, which in turn limits the predictability of derived models. In this work, we present a support vector machines model for the binary classification of solubility by taking advantage of the largest known public data set that contains over 46?000 compounds with experimental solubility. Our model was optimized in combination with a reduction and recombination feature selection strategy. The best model demonstrated robust performance in both cross-validation and prediction of two independent test sets, indicating it could be a practical tool to select soluble compounds for screening, purchasing, and synthesizing. Moreover, our work may be used for comparative evaluation of solubility classification studies ascribe to the use of completely public resources.     

Identifying microRNAs involved in cancer pathway using support vector machines

Since Ambros’ discovery of small non-protein coding RNAs in the early 1990s, the past two decades have seen an upsurge in the number of reports of predicted microRNAs (miR), which have been implicated in various functions. The correlation of miRs with cancer has spurred the usage of this class of non-coding RNAs in various cancer therapies, although most of them are at trial stages. However, the experimental identification of a miR to be associated with cancer is still an elaborate, time-consuming process. To aid this process of miR association, we undertook an in-silico study involving the identification of global signatures in experimentally validated microRNAs associated with cancer. Subsequently, a support vector machine based two-step binary classifier system has been trained and modeled from the features extracted from the above study. A total of 60 distinguishing features were selected and ranked to form the feature set for classification – 26 of these extracted from the miR sequence itself, and the remainder from the thermodynamics of folding and the hybridized miRNA–mRNA structure. The two step classifier model – miRSEQ and miRINT had reasonably good performance measures with fairly high values of Matthew’s correlation coefficient (MCC) values ranging from 0.72 to 0.82 (availability: https://sites.google.com/site/sumitslab/tools).     

Enzyme classification using multiclass support vector machine and feature subset selection

Proteins are the macromolecules responsible for almost all biological processes in a cell. With the availability of large number of protein sequences from different sequencing projects, the challenge with the scientist is to characterize their functions. As the wet lab methods are time consuming and expensive, many computational methods such as FASTA, PSI-BLAST, DNA microarray clustering, and Nearest Neighborhood classification on protein–protein interaction network have been proposed. Support vector machine is one such method that has been used successfully for several problems such as protein fold recognition, protein structure prediction etc. Cai et al. in 2003 have used SVM for classifying proteins into different functional classes and to predict their function. They used the physico-chemical properties of proteins to represent the protein sequences. In this paper a model comprising of feature subset selection followed by multiclass Support Vector Machine is proposed to determine the functional class of a newly generated protein sequence. To train and test the model for its performance, 32 physico-chemical properties of enzymes from 6 enzyme classes are considered. To determine the features that contribute significantly for functional classification, Sequential Forward Floating Selection (SFFS), Orthogonal Forward Selection (OFS), and SVM Recursive Feature Elimination (SVM-RFE) algorithms are used and it is observed that out of 32 properties considered initially, only 20 features are sufficient to classify the proteins into its functional classes with an accuracy ranging from 91% to 94%. On comparison it is seen that, OFS followed by SVM performs better than other methods. Our model generalizes the existing model to include multiclass classification and to identify most significant features affecting the protein function.     

The pharmacophore kernel for virtual screening with support vector machines

We introduce a family of positive definite kernels specifically optimized for the manipulation of 3D structures of molecules with kernel methods. The kernels are based on the comparison of the three-point pharmacophores present in the 3D structures of molecules, a set of molecular features known to be particularly relevant for virtual screening applications. We present a computationally demanding exact implementation of these kernels, as well as fast approximations related to the classical fingerprint-based approaches. Experimental results suggest that this new approach is competitive with state-of-the-art algorithms based on the 2D structure of molecules for the detection of inhibitors of several drug targets.     

Identifying the interacting positions of a protein using Boolean learning and support vector machines

It is known that in the three-dimensional structure of a protein, certain amino acids can interact with each other in order to provide structural integrity or aid in its catalytic function. If these positions are mutated the loss of this interaction usually leads to a non-functional protein. Directed evolution experiments, which probe the sequence space of a protein through mutations in search for an improved variant, frequently result in such inactive sequences. In this work, we address the use of machine learning algorithms, Boolean learning and support vector machines (SVMs), to find such pairs of amino acid positions. The recombination method of imparting mutations was simulated to create in silico sequences that were used as training data for the algorithms. The two algorithms were combined together to develop an approach that weighs the structural risk as well as the empirical risk to solve the problem. This strategy was adapted to a multi-round framework of experiments where the data generated in the present round is used to design experiments for the next round to improve the generated library, as well as the estimation of the interacting positions. It is observed that this strategy can greatly improve the number of functional variants that are generated as well as the average number of mutations that can be made in the library.     

Triarylcarbinol functionalized gold nanoparticles for the colorimetric detection of nerve agent simulants

Gold nanoparticles functionalized with a triarylcarbinol derivative have been used as colorimetric molecular probes for the naked-eye detection of the nerve agent simulants DCNP and DFP. The detection process is based on the compensation of charges at the surface of the nanoparticles which triggers their aggregation in solution with the resulting change in their plasmon band.     

Noise incorporated subwindow permutation analysis for informative gene selection using support vector machines

Selecting a small subset of informative genes plays an important role in accurate prediction of clinical tumor samples. Based on model population analysis, a novel variable selection method, called noise incorporated subwindow permutation analysis (NISPA), is proposed in this study to work with support vector machines (SVMs). The essence of NISPA lies in the point that one noise variable is added into each sampled sub-dataset and then the distribution of variable importance of the added noise could be computed and serves as the common reference to evaluate the experimental variables. Further, by using the non-parametric Mann-Whitney U test, a P value can be assigned to each variable which describes to what extent the distributions of the gene variable and the noise variable are different. According to the computed P values, all the variables could be ranked and then a small subset of informative variables could be determined to build the model. Moreover, by NISPA, we are the first to distinguish the variables into a more detailed classification as informative, uninformative (noise) and interfering variables in comparison with other methods. In this study, two microarray datasets are employed to evaluate the performance of NISPA. The results show that the prediction errors of SVM classifiers could be significantly reduced by variable selection using NISPA. It is concluded that NISPA is a good alternative of variable selection algorithm.     

B‐factor profile prediction for RNA flexibility using support vector machines

Determining the flexibility of structured biomolecules is important for understanding their biological functions. One quantitative measurement of flexibility is the atomic Debye‐Waller factor or temperature B‐factor. Most existing studies are limited to temperature B‐factors of proteins and their prediction. Only one method attempted to predict temperature B‐factors of ribosomal RNA. Here, we developed and compared machine‐learning techniques in prediction of temperature B‐factors of RNAs. The best model based on Support Vector Machines yields Pearson's correction coefficient at 0.51 for fivefold cross validation and 0.50 for the independent test. Analysis of the performance indicates that the model has the best performance on rRNAs, tRNAs, and protein‐bound RNAs, for long chains in particular. The server is available at http://sparks-lab.org/server/RNAflex . © 2017 Wiley Periodicals, Inc.     

Active learning with support vector machines in the drug discovery process

We investigate the following data mining problem from computer-aided drug design: From a large collection of compounds, find those that bind to a target molecule in as few iterations of biochemical testing as possible. In each iteration a comparatively small batch of compounds is screened for binding activity toward this target. We employed the so-called "active learning paradigm" from Machine Learning for selecting the successive batches. Our main selection strategy is based on the maximum margin hyperplane-generated by "Support Vector Machines". This hyperplane separates the current set of active from the inactive compounds and has the largest possible distance from any labeled compound. We perform a thorough comparative study of various other selection strategies on data sets provided by DuPont Pharmaceuticals and show that the strategies based on the maximum margin hyperplane clearly outperform the simpler ones.     

Statistical discrimination of steroid profiles in doping control with support vector machines

Due to their performance enhancing properties, use of anabolic steroids (e.g. testosterone, nandrolone, etc.) is banned in elite sports. Therefore, doping control laboratories accredited by the World Anti-Doping Agency (WADA) screen among others for these prohibited substances in urine. It is particularly challenging to detect misuse with naturally occurring anabolic steroids such as testosterone (T), which is a popular ergogenic agent in sports and society.     

Near-infrared (NIR) spectroscopy for motor oil classification: From discriminant analysis to support vector machines

Near-infrared (NIR) spectroscopy is a non-destructive measurement technique for many chemical compounds that has proved its efficiency for laboratory and industrial applications (including petroleum industry). Motor oil classification is an important task for quality control and identification of oil adulteration. Type of motor oil base stock is a key factor in product price formation. In this paper we have tried to evaluate the efficiency of different methods for motor oils classification by base stock (synthetic, semi-synthetic and mineral) and kinematic viscosity at low and high temperature. We have compared the abilities of seven (7) different classification methods: regularized discriminant analysis (RDA), soft independent modelling of class analogy (SIMCA), partial least squares classification (PLS), K-nearest neighbour (KNN), artificial neural network - multilayer perceptron (ANN-MLP), support vector machine (SVM), and probabilistic neural network (PNN) - for classification of motor oils. Three (3) sets of near-infrared spectra (1125, 1010, and 1050 items) were used for classification of motor oils into three or four classes. In all cases NIR spectroscopy was found to be effective for motor oil classification when combined with an effective multivariate data analysis (MDA) technique. SVM and PNN chemometric techniques were found to be the most effective ones for classification of motor oil based on its NIR spectrum.     

Predictive activity profiling of drugs by topological-fragment-spectra-based support vector machines

Aiming at the prediction of pleiotropic effects of drugs, we have investigated the multilabel classification of drugs that have one or more of 100 different kinds of activity labels. Structural feature representation of each drug molecule was based on the topological fragment spectra method, which was proposed in our previous work. Support vector machine (SVM) was used for the classification and the prediction of their activity classes. Multilabel classification was carried out by a set of the SVM classifiers. The collective SVM classifiers were trained with a training set of 59,180 compounds and validated by another set (validation set) of 29,590 compounds. For a test set that consists of 9,864 compounds, the classifiers correctly classified 80.8% of the drugs into their own active classes. The SVM classifiers also successfully performed predictions of the activity spectra for multilabel compounds.