Genome-enabled prediction of genetic values using radial basis function neural networks

The availability of high density panels of molecular markers has prompted the adoption of genomic selection (GS) methods in animal and plant breeding. In GS, parametric, semi-parametric and non-parametric regressions models are used for predicting quantitative traits. This article shows how to use neural networks with radial basis functions (RBFs) for prediction with dense molecular markers. We illustrate the use of the linear Bayesian LASSO regression model and of two non-linear regression models, reproducing kernel Hilbert spaces (RKHS) regression and radial basis function neural networks (RBFNN) on simulated data and real maize lines genotyped with 55,000 markers and evaluated for several trait-environment combinations. The empirical results of this study indicated that the three models showed similar overall prediction accuracy, with a slight and consistent superiority of RKHS and RBFNN over the additive Bayesian LASSO model. Results from the simulated data indicate that RKHS and RBFNN models captured epistatic effects; however, adding non-signal (redundant) predictors (interaction between markers) can adversely affect the predictive accuracy of the non-linear regression models.     

Toxic gas dispersion prediction for point source emission using deep learning method

Abstract

Accurate and rapid toxic gas concentration prediction model plays an important role in emergency aid of sudden gas leak. However, it is difficult for existing dispersion model to achieve accuracy and efficiency requirements at the same time. Although some researchers have considered developing new forecasting models with traditional machine learning, such as back propagation (BP) neural network, support vector machine (SVM), the prediction results obtained from such models need to be improved still in terms of accuracy. Then new prediction models based on deep learning are proposed in this paper. Deep learning has obvious advantages over traditional machine learning in prediction and classification. Deep belief networks (DBNs) as well as convolution neural networks (CNNs) are used to build new dispersion models here. Both models are compared with Gaussian plume model, computation fluid dynamics (CFD) model and models based on traditional machine learning in terms of accuracy, prediction time, and computation time. The experimental results turn out that CNNs model performs better considering all evaluation indexes.     

深度学习在药物活性预测研究中的应用

药物从研发到临床应用需要耗费较长的时间，研发期间的投入成本可高达十几亿元。而随着医药研发与人工智能的结合以及生物信息学的飞速发展，药物活性相关数据急剧增加，传统的实验手段进行药物活性预测已经难以满足药物研发的需求。借助算法来辅助药物研发，解决药物研发中的各种问题能够大大推动药物研发进程。传统机器学习方法尤其是随机森林、支持向量机和人工神经网络在药物活性方面能够达到较高的预测精度。深度学习由于具有多层神经网络，模型可以接收高维的输入变量且不需要人工限定数据输入特征，可以拟合较为复杂的函数模型，应用于药物研发可以进一步提高各个环节的效率。在药物活性预测中应用较为广泛的深度学习模型主要是深度神经网络（deep neural networks，DNN）、循环神经网络（recurrent neural networks，RNN）和自编码器（auto encoder，AE），而生成对抗网络（generative adversarial networks，GAN）由于其生成数据的能力常常被用来和其他模型结合进行数据增强。近年来深度学习在药物分子活性预测方面的研究和应用综述表明，深度学习模型的准确度和效率均高于传统实验方法和传统机器学习方法。因此，深度学习模型有望成为药物研发领域未来十年最重要的辅助计算模型。     

Analysis of an optimal hidden Markov model for secondary structure prediction

Background  

Secondary structure prediction is a useful first step toward 3D structure prediction. A number of successful secondary structure prediction methods use neural networks, but unfortunately, neural networks are not intuitively interpretable. On the contrary, hidden Markov models are graphical interpretable models. Moreover, they have been successfully used in many bioinformatic applications. Because they offer a strong statistical background and allow model interpretation, we propose a method based on hidden Markov models.     

A comparative study on kernel-based probabilistic neural networks for speaker verification

This paper compares kernel-based probabilistic neural networks for speaker verification based on 138 speakers of the YOHO corpus. Experimental evaluations using probabilistic decision-based neural networks (PDBNNs), Gaussian mixture models (GMMs) and elliptical basis function networks (EBFNs) as speaker models were conducted. The original training algorithm of PDBNNs was also modified to make PDBNNs appropriate for speaker verification. Results show that the equal error rate obtained by PDBNNs and GMMs is less than that of EBFNs (0.33% vs. 0.48%), suggesting that GMM- and PDBNN-based speaker models outperform the EBFN ones. This work also finds that the globally supervised learning of PDBNNs is able to find decision thresholds that not only maintain the false acceptance rates to a low level but also reduce their variation, whereas the ad-hoc threshold-determination approach used by the EBFNs and GMMs causes a large variation in the error rates. This property makes the performance of PDBNN-based systems more predictable.     

Neural network models for earthquake magnitude prediction using multiple seismicity indicators

Neural networks are investigated for predicting the magnitude of the largest seismic event in the following month based on the analysis of eight mathematically computed parameters known as seismicity indicators. The indicators are selected based on the Gutenberg-Richter and characteristic earthquake magnitude distribution and also on the conclusions drawn by recent earthquake prediction studies. Since there is no known established mathematical or even empirical relationship between these indicators and the location and magnitude of a succeeding earthquake in a particular time window, the problem is modeled using three different neural networks: a feed-forward Levenberg-Marquardt backpropagation (LMBP) neural network, a recurrent neural network, and a radial basis function (RBF) neural network. Prediction accuracies of the models are evaluated using four different statistical measures: the probability of detection, the false alarm ratio, the frequency bias, and the true skill score or R score. The models are trained and tested using data for two seismically different regions: Southern California and the San Francisco bay region. Overall the recurrent neural network model yields the best prediction accuracies compared with LMBP and RBF networks. While at the present earthquake prediction cannot be made with a high degree of certainty this research provides a scientific approach for evaluating the short-term seismic hazard potential of a region.     

Fish distribution predictions from different points of view: comparing associative neural networks,geostatistics and regression models

Accurate prediction of species distributions based on sampling and environmental data is essential for further scientific analysis, such as stock assessment, detection of abundance fluctuation due to climate change or overexploitation, and to underpin management and legislation processes. The evolution of computer science and statistics has allowed the development of sophisticated and well-established modelling techniques as well as a variety of promising innovative approaches for modelling species distribution. The appropriate selection of modelling approach is crucial to the quality of predictions about species distribution. In this study, modelling techniques based on different approaches are compared and evaluated in relation to their predictive performance, utilizing fish density acoustic data. Generalized additive models and mixed models amongst the regression models, associative neural networks (ANNs) and artificial neural networks ensemble amongst the artificial neural networks and ordinary kriging amongst the geostatistical techniques are applied and evaluated. A verification dataset is used for estimating the predictive performance of these models. A combination of outputs from the different models is applied for prediction optimization to exploit the ability of each model to explain certain aspects of variation in species acoustic density. Neural networks and especially ANNs appear to provide more accurate results in fitting the training dataset while generalized additive models appear more flexible in predicting the verification dataset. The efficiency of each technique in relation to certain sampling and output strategies is also discussed.     

Graph neural network approaches for drug-target interactions

Developing new drugs remains prohibitively expensive, time-consuming, and often involves safety issues. Accurate prediction of drug-target interactions (DTIs) can guide the drug discovery process and thus facilitate drug development. Non-Euclidian data such as drug-like molecule structures, key pocket residue structures, and protein interaction networks can be represented effectively using graphs. Therefore, the emerging graph neural network has been rapidly applied to predict DTIs, and proved effective in finding repositioning drugs and accelerating drug discovery. In this review, we provide a brief overview of deep neural networks used in DTI models. Then, we summarize the database required for DTI prediction, followed by a comprehensive introduction of applications of graph neural networks for DTI prediction. We also highlight current challenges and future directions to guide the further development of this field.     

A deep dense inception network for protein beta-turn prediction

Beta-turn prediction is useful in protein function studies and experimental design. Although recent approaches using machine-learning techniques such as support vector machine (SVM), neural networks, and K nearest neighbor have achieved good results for beta-turn prediction, there is still significant room for improvement. As previous predictors utilized features in a sliding window of 4-20 residues to capture interactions among sequentially neighboring residues, such feature engineering may result in incomplete or biased features and neglect interactions among long-range residues. Deep neural networks provide a new opportunity to address these issues. Here, we proposed a deep dense inception network (DeepDIN) for beta-turn prediction, which takes advantage of the state-of-the-art deep neural network design of dense networks and inception networks. A test on a recent BT6376 benchmark data set shows that DeepDIN outperformed the previous best tool BetaTPred3 significantly in both the overall prediction accuracy and the nine-type beta-turn classification accuracy. A tool, called MUFold-BetaTurn, was developed, which is the first beta-turn prediction tool utilizing deep neural networks. The tool can be downloaded at http://dslsrv8.cs.missouri.edu/~cf797/MUFoldBetaTurn/download.html .     

Computational methods for prediction of T-cell epitopes--a framework for modelling, testing, and applications

Computational models complement laboratory experimentation for efficient identification of MHC-binding peptides and T-cell epitopes. Methods for prediction of MHC-binding peptides include binding motifs, quantitative matrices, artificial neural networks, hidden Markov models, and molecular modelling. Models derived by these methods have been successfully used for prediction of T-cell epitopes in cancer, autoimmunity, infectious disease, and allergy. For maximum benefit, the use of computer models must be treated as experiments analogous to standard laboratory procedures and performed according to strict standards. This requires careful selection of data for model building, and adequate testing and validation. A range of web-based databases and MHC-binding prediction programs are available. Although some available prediction programs for particular MHC alleles have reasonable accuracy, there is no guarantee that all models produce good quality predictions. In this article, we present and discuss a framework for modelling, testing, and applications of computational methods used in predictions of T-cell epitopes.     

Deep transformation models for functional outcome prediction after acute ischemic stroke

In many medical applications, interpretable models with high prediction performance are sought. Often, those models are required to handle semistructured data like tabular and image data. We show how to apply deep transformation models (DTMs) for distributional regression that fulfill these requirements. DTMs allow the data analyst to specify (deep) neural networks for different input modalities making them applicable to various research questions. Like statistical models, DTMs can provide interpretable effect estimates while achieving the state-of-the-art prediction performance of deep neural networks. In addition, the construction of ensembles of DTMs that retain model structure and interpretability allows quantifying epistemic and aleatoric uncertainty. In this study, we compare several DTMs, including baseline-adjusted models, trained on a semistructured data set of 407 stroke patients with the aim to predict ordinal functional outcome three months after stroke. We follow statistical principles of model-building to achieve an adequate trade-off between interpretability and flexibility while assessing the relative importance of the involved data modalities. We evaluate the models for an ordinal and dichotomized version of the outcome as used in clinical practice. We show that both tabular clinical and brain imaging data are useful for functional outcome prediction, whereas models based on tabular data only outperform those based on imaging data only. There is no substantial evidence for improved prediction when combining both data modalities. Overall, we highlight that DTMs provide a powerful, interpretable approach to analyzing semistructured data and that they have the potential to support clinical decision-making.     

Analysis of heart rate variability for predicting cardiorespiratory events in infants

Cardiorespiratory events (CREs), including bradycardia and apnea, in infants are a major concern for physicians and families. Our hypothesis was that there is a difference in the heart rate variability (HRV) of infants who have CREs when compared to normal control infants. The purpose of this study was to develop CRE prediction models based on HRV measured during a polysomnographic (PSG) recording. ANCOVA analysis accounting for factors such as age and sleep state show a relationship between HRV variables and CRE. Prediction models, including neural networks and support vector machines, were developed to predict CRE within either (a) 1-week or (b) 1-month after the PSG. The support vector machine prediction accuracy, for CRE susceptibility one month after the PSG on an independent testing dataset, was 50.0% sensitivity and 82.6% specificity. Although the developed prediction models were not sufficiently accurate for clinical decision making, these results support the potential role of abnormalities in autonomic control of heart rate among infants at risk for CREs.     

rsRNASP: A residue-separation-based statistical potential for RNA 3D structure evaluation

Knowledge-based statistical potentials have been shown to be rather effective in protein 3-dimensional (3D) structure evaluation and prediction. Recently, several statistical potentials have been developed for RNA 3D structure evaluation, while their performances are either still at a low level for the test datasets from structure prediction models or dependent on the “black-box” process through neural networks. In this work, we have developed an all-atom distance-dependent statistical potential based on residue separation for RNA 3D structure evaluation, namely rsRNASP, which is composed of short- and long-ranged potentials distinguished by residue separation. The extensive examinations against available RNA test datasets show that rsRNASP has apparently higher performance than the existing statistical potentials for the realistic test datasets with large RNAs from structure prediction models, including the newly released RNA-Puzzles dataset, and is comparable to the existing top statistical potentials for the test datasets with small RNAs or near-native decoys. In addition, rsRNASP is superior to RNA3DCNN, a recently developed scoring function through 3D convolutional neural networks. rsRNASP and the relevant databases are available to the public.     

Genome-enabled methods for predicting litter size in pigs: a comparison

Predictive ability of models for litter size in swine on the basis of different sources of genetic information was investigated. Data represented average litter size on 2598, 1604 and 1897 60K genotyped sows from two purebred and one crossbred line, respectively. The average correlation (r) between observed and predicted phenotypes in a 10-fold cross-validation was used to assess predictive ability. Models were: pedigree-based mixed-effects model (PED), Bayesian ridge regression (BRR), Bayesian LASSO (BL), genomic BLUP (GBLUP), reproducing kernel Hilbert spaces regression (RKHS), Bayesian regularized neural networks (BRNN) and radial basis function neural networks (RBFNN). BRR and BL used the marker matrix or its principal component scores matrix (UD) as covariates; RKHS employed a Gaussian kernel with additive codes for markers whereas neural networks employed the additive genomic relationship matrix (G) or UD as inputs. The non-parametric models (RKHS, BRNN, RNFNN) gave similar predictions to the parametric counterparts (average r ranged from 0.15 to 0.23); most of the genome-based models outperformed PED (r = 0.16). Predictive abilities of linear models and RKHS were similar over lines, but BRNN varied markedly, giving the best prediction (r = 0.31) when G was used in crossbreds, but the worst (r = 0.02) when the G matrix was used in one of the purebred lines. The r values for RBFNN ranged from 0.16 to 0.23. Predictive ability was better in crossbreds (0.26) than in purebreds (0.15 to 0.22). This may be related to family structure in the purebred lines.     

Predicting Growth Traits with Genomic Selection Methods in Zhikong Scallop (<Emphasis Type="Italic">Chlamys farreri</Emphasis>)

Selective breeding is a common and effective approach for genetic improvement of aquaculture stocks with parental selection as the key factor. Genomic selection (GS) has been proposed as a promising tool to facilitate selective breeding. Here, we evaluated the predictability of four GS methods in Zhikong scallop (Chlamys farreri) through real dataset analyses of four economical traits (e.g., shell length, shell height, shell width, and whole weight). Our analysis revealed that different GS models exhibited variable performance in prediction accuracy depending on genetic and statistical factors, but non-parametric method, including reproducing kernel Hilbert spaces regression (RKHS) and sparse neural networks (SNN), generally outperformed parametric linear method, such as genomic best linear unbiased prediction (GBLUP) and BayesB. Furthermore, we demonstrated that the predictability relied mainly on the heritability regardless of GS methods. The size of training population and marker density also had considerable effects on the predictive performance. In practice, increasing the training population size could better improve the genomic prediction than raising the marker density. This study is the first to apply non-linear model and neural networks for GS in scallop and should be valuable to help develop strategies for aquaculture breeding programs.