GraphCL-DTA: A Graph Contrastive Learning With Molecular Semantics for Drug-Target Binding Affinity Prediction.

Drug-target binding affinity prediction plays an important role in the early stages of drug discovery, which can infer the strength of interactions between new drugs and new targets. However, the performance of previous computational models is limited by the following drawbacks. The learning of drug representation relies only on supervised data without considering the information in the molecular graph itself. Moreover, most previous studies tended to design complicated representation learning modules, while uniformity used to measure representation quality is ignored. In this study, we propose GraphCL-DTA, a graph contrastive learning with molecular semantics for drug-target binding affinity prediction. This graph contrastive learning framework replaces the dropout-based data augmentation strategy by performing data augmentation in the embedding space, thereby better preserving the semantic information of the molecular graph. A more essential and effective drug representation can be learned through this graph contrastive framework without additional supervised data. Next, we design a new loss function that can be directly used to adjust the uniformity of drug and target representations. By directly optimizing the uniformity of representations, the representation quality of drugs and targets can be improved. The effectiveness of the above innovative elements is verified on two real datasets, KIBA and Davis. Compared with the GraphDTA model, the relative improvement of the GraphCL-DTA model on the two datasets is 2.7% and 4.5%. The graph contrastive learning framework and uniformity function in the GraphCL-DTA model can be embedded into other computational models as independent modules to improve their generalization capability.

Implicit Posteriori Parameter Distribution Optimization in Reinforcement Learning.

Efficient and intelligent exploration remains a major challenge in the field of deep reinforcement learning (DRL). Bayesian inference with a distributional representation is usually an effective way to improve the exploration ability of the RL agent. However, when optimizing Bayesian neural networks (BNNs), most algorithms need to specify an explicit parameter distribution such as a multivariate Gaussian distribution. This may reduce the flexibility of model representation and affect the algorithm performance. Therefore, to improve sample efficiency and exploration based on Bayesian methods, we propose a novel implicit posteriori parameter distribution optimization (IPPDO) algorithm. First, we adopt a distributional perspective on the parameter and model it with an implicit distribution, which is approximated by generative models. Each model corresponds to a learned latent space, providing structured stochasticity for each layer in the network. Next, to make it possible to optimize an implicit posteriori parameter distribution, we build an energy-based model (EBM) with value function to represent the implicit distribution which is not constrained by any analytic density function. Then, we design a training algorithm based on amortized Stein variational gradient descent (SVGD) to improve the model learning efficiency. We compare IPPDO with other prevailing DRL algorithms on the OpenAI Gym, MuJoCo, and Box2D platforms. Experiments on various tasks demonstrate that the proposed algorithm can represent the parameter uncertainty implicitly for a learned policy and can consistently outperform competing approaches.

Pyramid-based self-supervised learning for histopathological image classification.

Large-scale labeled datasets are crucial for the success of supervised learning in medical imaging. However, annotating histopathological images is a time-consuming and labor-intensive task that requires highly trained professionals. To address this challenge, self-supervised learning (SSL) can be utilized to pre-train models on large amounts of unsupervised data and transfer the learned representations to various downstream tasks. In this study, we propose a self-supervised Pyramid-based Local Wavelet Transformer (PLWT) model for effectively extracting rich image representations. The PLWT model extracts both local and global features to pre-train a large number of unlabeled histopathology images in a self-supervised manner. Wavelet is used to replace average pooling in the downsampling of the multi-head attention, achieving a significant reduction in information loss during the transmission of image features. Additionally, we introduce a Local Squeeze-and-Excitation (Local SE) module in the feedforward network in combination with the inverse residual to capture local image information. We evaluate PLWT's performance on three histopathological images and demonstrate the impact of pre-training. Our experiment results indicate that PLWT with self-supervised learning performs highly competitive when compared with other SSL methods, and the transferability of visual representations generated by SSL on domain-relevant histopathological images exceeds that of the supervised baseline trained on ImageNet.

Hierarchical Belief Propagation on Image Segmentation Pyramid.

The Markov random field (MRF) for stereo matching can be solved using belief propagation (BP). However, the solution space grows significantly with the introduction of high-resolution stereo images and 3D plane labels, making the traditional BP algorithms impractical in inference time and convergence. We present an accurate and efficient hierarchical BP framework using the representation of the image segmentation pyramid (ISP). The pixel-level MRF can be solved by a top-down inference on the ISP. We design a hierarchy of MRF networks using the graph of superpixels at each ISP level. From the highest/image to the lowest/pixel level, the MRF models can be efficiently inferred with constant global guidance using the optimal labels of the previous level. The large texture-less regions can be handled effectively by the MRF model on a high level. The advanced 3D continuous labels and a novel support-points regularization are integrated into our framework for stereo matching. We provide a data-level parallelism implementation which is orders of magnitude faster than the best graph cuts (GC) algorithm. The proposed framework, HBP-ISP, outperforms the best GC algorithm on the Middlebury stereo matching benchmark.

Self-Supervised Learning for Label Sparsity in Computational Drug Repositioning.

The computational drug repositioning aims to discover new uses for marketed drugs, which can accelerate the drug development process and play an important role in the existing drug discovery system. However, the number of validated drug-disease associations is scarce compared to the number of drugs and diseases in the real world. Too few labeled samples will make the classification model unable to learn effective latent factors of drugs, resulting in poor generalization performance. In this work, we propose a multi-task self-supervised learning framework for computational drug repositioning. The framework tackles label sparsity by learning a better drug representation. Specifically, we take the drug-disease association prediction problem as the main task, and the auxiliary task is to use data augmentation strategies and contrast learning to mine the internal relationships of the original drug features, so as to automatically learn a better drug representation without supervised labels. And through joint training, it is ensured that the auxiliary task can improve the prediction accuracy of the main task. More precisely, the auxiliary task improves drug representation and serving as additional regularization to improve generalization. Furthermore, we design a multi-input decoding network to improve the reconstruction ability of the autoencoder model. We evaluate our model using three real-world datasets. The experimental results demonstrate the effectiveness of the multi-task self-supervised learning framework, and its predictive ability is superior to the state-of-the-art model.

The Neural Metric Factorization for Computational Drug Repositioning.

Computational drug repositioning aims to discover new therapeutic diseases for marketed drugs and has the advantages of low cost, short development cycle, and high controllability compared to traditional drug development. The matrix factorization model has become the cornerstone technique for computational drug repositioning due to its ease of implementation and excellent scalability. However, the matrix factorization model uses the inner product operation to represent the association between drugs and diseases, which is lacking in expressive ability. Moreover, the degree of similarity of drugs or diseases could not be implied on their respective latent factor vectors, which is not satisfy the common sense of drug discovery. Therefore, a neural metric factorization model for computational drug repositioning (NMFDR) is proposed in this work. We novelly consider the latent factor vector of drugs and diseases as a point in the high-dimensional coordinate system and propose a generalized euclidean distance to represent the association between drugs and diseases to compensate for the shortcomings of the inner product operation. Furthermore, by embedding multiple drug (disease) metrics information into the encoding space of the latent factor vector, the information about the similarity between drugs (diseases) can be reflected in the distance between latent factor vectors. Finally, we conduct wide analysis experiments on three real datasets to demonstrate the effectiveness of the above improvement points and the superiority of the NMFDR model.

The Computational Drug Repositioning Without Negative Sampling.

Computational drug repositioning technology is an effective tool to accelerate drug development. Although this technique has been widely used and successful in recent decades, many existing models still suffer from multiple drawbacks such as the massive number of unvalidated drug-disease associations and the inner product. The limitations of these works are mainly due to the following two reasons: firstly, previous works used negative sampling techniques to treat unvalidated drug-disease associations as negative samples, which is invalid in real-world settings; secondly, the inner product cannot fully take into account the feature information contained in the latent factor of drug and disease. In this paper, we propose a novel PUON framework for addressing the above deficiencies, which models the risk estimator of computational drug repositioning only using validated (Positive) and unvalidated (Unlabelled) drug-disease associations without employing negative sampling techniques. The PUON also proposed an Outer Neighborhood-based classifier for modeling the cross-feature information of the latent facotor. For a comprehensive comparison, we considered 6 popular baselines. Extensive experiments in four real-world datasets showed that PUON model achieved the best performance based on 6 evaluation metrics.

Non-fragile sliding mode control for one-sided Lipschitz chaotic systems.

This paper deals with the sliding mode stabilization for chaotic systems. In the system under consideration, the nonlinear function is one-sided Lipschitz with quadratic inner-boundedness. Specifically, a non-fragile sliding mode surface is constructed, and the sufficient condition for the convergence is derived. Then, a new feedback law is proposed to enable the state trajectories of the closed-loop system to reach the sliding mode surface in finite time. Finally, an example in the background of the unified chaos system is simulated to show the validation of the designed controller.

[Convolutional neural network human gesture recognition algorithm based on phase portrait of surface electromyography energy kernel].

Surface electromyography (sEMG) is a weak signal which is non-stationary and non-periodic. The sEMG classification methods based on time domain and frequency domain features have low recognition rate and poor stability. Based on the modeling and analysis of sEMG energy kernel, this paper proposes a new method to recognize human gestures utilizing convolutional neural network (CNN) and phase portrait of sEMG energy kernel. Firstly, the matrix counting method is used to process the sEMG energy kernel phase portrait into a grayscale image. Secondly, the grayscale image is preprocessed by moving average method. Finally, CNN is used to recognize sEMG of gestures. Experiments on gesture sEMG signal data set show that the effectiveness of the recognition framework and the recognition method of CNN combined with the energy kernel phase portrait have obvious advantages in recognition accuracy and computational efficiency over the area extraction methods. The algorithm in this paper provides a new feasible method for sEMG signal modeling analysis and real-time identification.

An Improved Normalized Mutual Information Variable Selection Algorithm for Neural Network-Based Soft Sensors.

In this paper, normalized mutual information feature selection (NMIFS) and tabu search (TS) are integrated to develop a new variable selection algorithm for soft sensors. NMIFS is applied to select influential variables contributing to the output variable and avoids selecting redundant variables by calculating mutual information (MI). A TS based strategy is designed to prevent NMIFS from falling into a local optimal solution. The proposed algorithm performs the variable selection by combining the entropy information and MI and validating error information of artificial neural networks (ANNs); therefore, it has advantages over previous MI-based variable selection algorithms. Several simulation datasets with different scales, correlations and noise parameters are implemented to demonstrate the performance of the proposed algorithm. A set of actual production data from a power plant is also used to check the performance of these algorithms. The experiments showed that the developed variable selection algorithm presents better model accuracy with fewer selected variables, compared with other state-of-the-art methods. The application of this algorithm to soft sensors can achieve reliable results.

A low dimensional approach on network characterization.

In many applications, one may need to characterize a given network among a large set of base networks, and these networks are large in size and diverse in structure over the search space. In addition, the characterization algorithms are required to have low volatility and with a small circle of uncertainty. For large datasets, these algorithms are computationally intensive and inefficient. However, under the context of network mining, a major concern of some applications is speed. Hence, we are motivated to develop a fast characterization algorithm, which can be used to quickly construct a graph space for analysis purpose. Our approach is to transform a network characterization measure, commonly formulated based on similarity matrices, into simple vector form signatures. We shall show that the [Formula: see text] similarity matrix can be represented by a dyadic product of two N-dimensional signature vectors; thus the network alignment process, which is usually solved as an assignment problem, can be reduced into a simple alignment problem based on separate signature vectors.

An approximation solution to refinery crude oil scheduling problem with demand uncertainty using joint constrained programming.

This paper is devoted to develop an approximation method for scheduling refinery crude oil operations by taking into consideration the demand uncertainty. In the stochastic model the demand uncertainty is modeled as random variables which follow a joint multivariate distribution with a specific correlation structure. Compared to deterministic models in existing works, the stochastic model can be more practical for optimizing crude oil operations. Using joint chance constraints, the demand uncertainty is treated by specifying proximity level on the satisfaction of product demands. However, the joint chance constraints usually hold strong nonlinearity and consequently, it is still hard to handle it directly. In this paper, an approximation method combines a relax-and-tight technique to approximately transform the joint chance constraints to a serial of parameterized linear constraints so that the complicated problem can be attacked iteratively. The basic idea behind this approach is to approximate, as much as possible, nonlinear constraints by a lot of easily handled linear constraints which will lead to a well balance between the problem complexity and tractability. Case studies are conducted to demonstrate the proposed methods. Results show that the operation cost can be reduced effectively compared with the case without considering the demand correlation.

A novel algorithm combining finite state method and genetic algorithm for solving crude oil scheduling problem.

A hybrid optimization algorithm combining finite state method (FSM) and genetic algorithm (GA) is proposed to solve the crude oil scheduling problem. The FSM and GA are combined to take the advantage of each method and compensate deficiencies of individual methods. In the proposed algorithm, the finite state method makes up for the weakness of GA which is poor at local searching ability. The heuristic returned by the FSM can guide the GA algorithm towards good solutions. The idea behind this is that we can generate promising substructure or partial solution by using FSM. Furthermore, the FSM can guarantee that the entire solution space is uniformly covered. Therefore, the combination of the two algorithms has better global performance than the existing GA or FSM which is operated individually. Finally, a real-life crude oil scheduling problem from the literature is used for conducting simulation. The experimental results validate that the proposed method outperforms the state-of-art GA method.

A Parameter Estimation Method for Biological Systems modelled by ODE/DDE Models Using Spline Approximation and Differential Evolution Algorithm.

The inverse problem of identifying unknown parameters of known structure dynamical biological systems, which are modelled by ordinary differential equations or delay differential equations, from experimental data is treated in this paper. A two stage approach is adopted: first, combine spline theory and Nonlinear Programming (NLP), the parameter estimation problem is formulated as an optimization problem with only algebraic constraints; then, a new differential evolution (DE) algorithm is proposed to find a feasible solution. The approach is designed to handle problem of realistic size with noisy observation data. Three cases are studied to evaluate the performance of the proposed algorithm: two are based on benchmark models with priori-determined structure and parameters; the other one is a particular biological system with unknown model structure. In the last case, only a set of observation data available and in this case a nominal model is adopted for the identification. All the test systems were successfully identified by using a reasonable amount of experimental data within an acceptable computation time. Experimental evaluation reveals that the proposed method is capable of fast estimation on the unknown parameters with good precision.

A similarity matrix-based hybrid algorithm for the contact map overlaps problem.

This paper proposes a similarity matrix-based hybrid algorithm for the contact map overlap (CMO) problem in protein structure alignment. In this algorithm, Genetic Algorithm (GA) is used as a framework, in which the initial solutions are constructed with similarity matrix heuristic, and Extremal Optimization (EO) is embedded as a mutated operator. In this process, EO quickly approaches near-optimal solutions and GA generates improved global approximations. Five similarity measurements including ratio, inner product, cosine function, Jaccard index and Dice coefficient have been exploited to compute the similarity matrix between two contact maps. The simulations demonstrate that our algorithm is significantly faster and gets better results for most of the test sets.

Genetic programming-based chaotic time series modeling.

This paper proposes a Genetic Programming-Based Modeling (GPM) algorithm on chaotic time series. GP is used here to search for appropriate model structures in function space, and the Particle Swarm Optimization (PSO) algorithm is used for Nonlinear Parameter Estimation (NPE) of dynamic model structures. In addition, GPM integrates the results of Nonlinear Time Series Analysis (NTSA) to adjust the parameters and takes them as the criteria of established models. Experiments showed the effectiveness of such improvements on chaotic time series modeling.

Design PID controllers for desired time-domain or frequency-domain response.

Practical requirements on the design of control systems, especially process control systems, are usually specified in terms of time-domain response, such as overshoot and rise time, or frequency-domain response, such as resonance peak and stability margin. Although numerous methods have been developed for the design of the proportional-integral-derivative (PID) controller, little work has been done in relation to the quantitative time-domain and frequency-domain responses. In this paper, we study the following problem: Given a nominal stable process with time delay, we design a suboptimal PID controller to achieve the required time-domain response or frequency-domain response for the nominal system or the uncertain system. An H(infinity) PID controller is developed based on optimal control theory and the parameters are derived analytically. Its properties are investigated and compared with that of two developed suboptimal controllers: an H2 PID controller and a Maclaurin PID controller. It is shown that all three controllers can provide the quantitative time-domain and frequency-domain responses.