Optimized Particle Swarm Optimization (OPSO) and its application to artificial neural network training

Hybrid Smart Strategies to Predict Amine Thermal Degradation in Industrial CO2 Capture Processes

CO2 emission reduction is an essential step to achieve the climate change targets. Solvent-based post-combustion CO2 capture (PCC) processes are efficient to be retrofitted to the existing industrial operations/installations. Solvent degradation (and/or loss) is one of the main concerns in the PCC processes. In this study, the thermal degradation of monoethanolamine (MEA) is investigated through the utilization of hybrid connectionist strategies, including an artificial neural network-particle swarm optimization (ANN-PSO), a coupled simulated annealing-least squares support vector machine (CSA-LSSVM), and an adaptive neuro-fuzzy inference system (ANFIS). Moreover, gene expression programming (GEP) is employed to generate a correlation that relates the solvent concentration to the operating variables involved in the adverse phenomenon of solvent thermal degradation. The input variables are the MEA initial concentration, CO2 loading, temperature, and time, and the output variable is the remaining/final MEA concentration after the degradation phenomenon. According to the training and testing phases, the most accurate model is ANFIS, and the reliability/performance of its optimal network is assessed by the coefficient of determination (R2), mean squared error, and average absolute relative error percentage, which are 0.992, 0.066, and 2.745, respectively. This study reveals that the solvent initial concentration has the most significant impact, and temperature plays the second most influential effect on solvent degradation. The developed models can be used to predict the thermal degradation of any solvent in a solvent-based PCC process regardless of the complicated reactions involved in the degradation phenomenon. The models introduced in this study can be employed for the development of more accurate hybrid models to optimize the proposed systems in terms of cost, energy, and environmental prospects.

Improved laccase production from Pleurotus floridanus using deoiled microalgal biomass: statistical and hybrid swarm-based neural networks modeling approach

Fungal laccases are versatile biocatalyst and occupy a prominent place in various industrial applications due to its broad substrate specificity. The simplest method to enhance the laccase production is by usage of cheap substrates in the fermentation processes incorporating modeling approaches for optimization. Integrated biorefinery concept is receiving wide popularity by making use of various products from microalgal biomass. The research aimed to identify the potential of deoiled microalgal biomass (DMB), a waste product from algal biorefinery as a nutrient supplement to enhance laccase production in Pleurotus floridanus by submerged fermentation. The maximum production was obtained in the presence of DMB as an additional nutrient supplement and copper sulfate as an inducer. The predictive capabilities of the two methodologies Response Surface Methodology (RSM) and hybrid Particle swarm optimization (PSO)-based Artificial Neural Network (ANN) were compared and validated. The results showed that ANN coupled with PSO predicted with more accuracy with an R 2 value of 0.99 than the RSM model with an R 2 value of 0.97. The optimized condition as predicted by superior model hybrid PSO-based ANN was glucose (3.51%), DMB (0.545%), pH (4.9), temperature (24.68 ℃) and CuSO4 (1.35 mM). The experimental laccase activity was 80.45 ± 0.132 U/mL which was 1.3 fold higher than unoptimized condition. This study promotes the usage of DMB as a novel supplement for the improved production of Pleurotus floridanus laccase.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13205-022-03404-y.

Application of Meta-Heuristic Algorithms for Training Neural Networks and Deep Learning Architectures: A Comprehensive Review

The learning process and hyper-parameter optimization of artificial neural networks (ANNs) and deep learning (DL) architectures is considered one of the most challenging machine learning problems. Several past studies have used gradient-based back propagation methods to train DL architectures. However, gradient-based methods have major drawbacks such as stucking at local minimums in multi-objective cost functions, expensive execution time due to calculating gradient information with thousands of iterations and needing the cost functions to be continuous. Since training the ANNs and DLs is an NP-hard optimization problem, their structure and parameters optimization using the meta-heuristic (MH) algorithms has been considerably raised. MH algorithms can accurately formulate the optimal estimation of DL components (such as hyper-parameter, weights, number of layers, number of neurons, learning rate, etc.). This paper provides a comprehensive review of the optimization of ANNs and DLs using MH algorithms. In this paper, we have reviewed the latest developments in the use of MH algorithms in the DL and ANN methods, presented their disadvantages and advantages, and pointed out some research directions to fill the gaps between MHs and DL methods. Moreover, it has been explained that the evolutionary hybrid architecture still has limited applicability in the literature. Also, this paper classifies the latest MH algorithms in the literature to demonstrate their effectiveness in DL and ANN training for various applications. Most researchers tend to extend novel hybrid algorithms by combining MHs to optimize the hyper-parameters of DLs and ANNs. The development of hybrid MHs helps improving algorithms performance and capable of solving complex optimization problems. In general, the optimal performance of the MHs should be able to achieve a suitable trade-off between exploration and exploitation features. Hence, this paper tries to summarize various MH algorithms in terms of the convergence trend, exploration, exploitation, and the ability to avoid local minima. The integration of MH with DLs is expected to accelerate the training process in the coming few years. However, relevant publications in this way are still rare.

Designing Artificial Neural Network Using Particle Swarm Optimization: A Survey

Neural network modeling has become a special interest for many engineers and scientists to be utilized in different types of data as time series, regression, and classification and have been used to solve complicated practical problems in different areas, such as medicine, engineering, manufacturing, military, business. To utilize a prediction model that is based upon artificial neural network (ANN), some challenges should be addressed that optimal designing and training of ANN are major ones. ANN can be defined as an optimization task because it has many hyper parameters and weights that can be optimized. Metaheuristic algorithms such as swarm intelligence-based methods are a category of optimization methods that aim to find an optimal structure of ANN and to train the network by optimizing the weights. One of the commonly used swarm intelligence-based algorithms is particle swarm optimization (PSO) that can be used for optimizing ANN. In this study, we review the conducted research works on optimizing the ANNs using PSO. All studies are reviewed from two different perspectives: optimization of weights and optimization of structure and hyper parameters.

Optimized Elastic Network Models With Direct Characterization of Inter-Residue Cooperativity for Protein Dynamics

The elastic network models (ENMs)are known as representative coarse-grained models to capture essential dynamics of proteins. Due to simple designs of the force constants as a decay with spatial distances of residue pairs in many previous studies, there is still much room for the improvement of ENMs. In this article, we directly computed the force constants with the inverse covariance estimation using a ridge-type operater for the precision matrix estimation (ROPE)on a large-scale set of NMR ensembles. Distance-dependent statistical analyses on the force constants were further comprehensively performed in terms of several paired types of sequence and structural information, including secondary structure, relative solvent accessibility, sequence distance and terminal. Various distinguished distributions of the mean force constants highlight the structural and sequential characteristics coupled with the inter-residue cooperativity beyond the spatial distances. We finally integrated these structural and sequential characteristics to build novel ENM variations using the particle swarm optimization for the parameter estimation. The considerable improvements on the correlation coefficient of the mean-square fluctuation and the mode overlap were achieved by the proposed variations when compared with traditional ENMs. This study opens a novel way to develop more accurate elastic network models for protein dynamics.

Energy Management in the Microgrid and Its Optimal Planning for Supplying Wireless Charging Electric Vehicle

The ongoing research work on electric vehicles (EVs) as well as the growing concern around the world to ensure a pollution-free environment is sure to lead to a significant increase in the number of EVs in the near future. The electrification of automobiles is an inevitable trend of future development. However, the growth of EVs relies on several elements: autonomy, the charging practice and infrastructure, the price, and the high amount of energy needed for supplying EV. This tendency impacts several points in transportation such as the road infrastructure and electrical power network. The aim of this article is the integration of new energy power sources as a part of the microgrid (MG) to supply EV with dynamic wireless charging. The main goal is to establish an energy management strategy reducing the running cost. The purpose is suggested for two kinds of operation mode: relying only on the MG (island mode) or relying on the MG and the large grid (grid-connected). The optimization problem is solved on the basis of the particle swarm optimization (PSO) algorithm. We could note that the stability of the microgrid in the off-grid mode is better, when the load is close to the output power of the distributed power supply. Through the coordination and cooperation of the battery output and the other two distributed power generation units, the microgrid can achieve its autonomy and maximize the economy of the system operation. Thanks to our methodology, a better revenue and an enhanced flexible dispatching of the system were met in the grid-connected mode as well.

Two-Phase Switching Optimization Strategy in Deep Neural Networks

Optimization in a deep neural network is always challenging due to the vanishing gradient problem and intensive fine-tuning of network hyperparameters. Inspired by multistage decision control systems, the stochastic diagonal approximate greatest descent (SDAGD) algorithm is proposed in this article to seek for optimal learning weights using a two-phase switching optimization strategy. The proposed optimizer controls the relative step length derived based on the long-term optimal trajectory and adopts the diagonal approximated Hessian for efficient weight update. In Phase-I, it computes the greatest step length at the boundary of each local spherical search region and, subsequently, descends rapidly toward the direction of an optimal solution. In Phase-II, it switches to an approximate Newton method automatically once it is closer to the optimal solution to achieve fast convergence. The experiments show that SDAGD produces steeper learning curves and achieves lower misclassification rates compared with other optimization techniques. Implementation of the proposed optimizer to deeper networks is also investigated in this article to study the vanishing gradient problem.

Dynamic particle swarm optimization of biomolecular simulation parameters with flexible objective functions

Molecular simulations are a powerful tool to complement and interpret ambiguous experimental data on biomolecules to obtain structural models. Such data-assisted simulations often rely on parameters, the choice of which is highly non-trivial and crucial to performance. The key challenge is weighting experimental information with respect to the underlying physical model. We introduce FLAPS, a self-adapting variant of dynamic particle swarm optimization, to overcome this parameter selection problem. FLAPS is suited for the optimization of composite objective functions that depend on both the optimization parameters and additional, a priori unknown weighting parameters, which substantially influence the search-space topology. These weighting parameters are learned at runtime, yielding a dynamically evolving and iteratively refined search-space topology. As a practical example, we show how FLAPS can be used to find functional parameters for small-angle X-ray scattering-guided protein simulations.

Recent Advances in the Prediction of Protein Structural Classes: Feature Descriptors and Machine Learning Algorithms

In the postgenomic age, rapid growth in the number of sequence-known proteins has been accompanied by much slower growth in the number of structure-known proteins (as a result of experimental limitations), and a widening gap between the two is evident. Because protein function is linked to protein structure, successful prediction of protein structure is of significant importance in protein function identification. Foreknowledge of protein structural class can help improve protein structure prediction with significant medical and pharmaceutical implications. Thus, a fast, suitable, reliable, and reasonable computational method for protein structural class prediction has become pivotal in bioinformatics. Here, we review recent efforts in protein structural class prediction from protein sequence, with particular attention paid to new feature descriptors, which extract information from protein sequence, and the use of machine learning algorithms in both feature selection and the construction of new classification models. These new feature descriptors include amino acid composition, sequence order, physicochemical properties, multiprofile Bayes, and secondary structure-based features. Machine learning methods, such as artificial neural networks (ANNs), support vector machine (SVM), K-nearest neighbor (KNN), random forest, deep learning, and examples of their application are discussed in detail. We also present our view on possible future directions, challenges, and opportunities for the applications of machine learning algorithms for prediction of protein structural classes.

2D QSAR studies on a series of (4S,5R)-5-[3,5-bis(trifluoromethyl)phenyl]-4-methyl-1,3-oxazolidin-2-one as CETP inhibitors

Cardiovascular disease (CVD) is one of the major causes of human death. Preliminary evidence indicates that the inhibition treatment of Cholesteryl Ester Transfer Protein (CETP) causes the most pronounced increase in HDL cholesterol reported so far. Merck has disclosed certain (4S,5R)-5-[3,5-bis(trifluoromethyl)phenyl]-4-methyl-1,3-oxazolidin-2-one derivatives, which show potent CETP inhibitory activity. Therefore, it would be desirable to develop computational models to facilitate the screening of these inhibitors. In the present work, quantitative structure-activity relationship (QSAR) models have been developed to predict the therapeutic potency of 108 derivatives of (4S,5R)-5-[3,5-bis(trifluoromethyl)phenyl]-4-methyl-1,3-oxazolidin-2-one: Multiple Linear Regression (MLR), Support Vector Regression (SVR) and Feedforward Neural Network using Particle Swarm Optimization (FNN-PSO). Six descriptors were selected using genetic algorithms, whereas, internal and external validation of the models was performed according to all available validation strategies. It was shown that CETP inhibitory activity is mainly governed by electronegativity, the structure of the molecule, and the electronic properties. The best results were obtained with the SVR model. The results obtained may assist in the design of new CETP inhibitors.

Silva L, Gonçales RA, Neves BJ, Soares CM, Pereira M. Setting New Routes for Antifungal Drug Discovery Against Pathogenic Fungi

:

Fungal diseases are life-threatening to human health and responsible for millions of deaths around the world. Fungal pathogens lead to a high number of morbidity and mortality. Current antifungal treatment comprises drugs, such as azoles, echinocandins, and polyenes and the cure is not guaranteed. In addition, such drugs are related to severe side effects and the treatment lasts for an extended period. Thus, setting new routes for the discovery of effective and safe antifungal drugs should be a priority within the health care system. The discovery of alternative and efficient antifungal drugs showing fewer side effects is time-consuming and remains a challenge. Natural products can be a source of antifungals and used in combinatorial therapy. The most important natural products are antifungal peptides, antifungal lectins, antifungal plants, and fungi secondary metabolites. Several proteins, enzymes, and metabolic pathways could be targets for the discovery of efficient inhibitor compounds and recently, heat shock proteins, calcineurin, salinomycin, the trehalose biosynthetic pathway, and the glyoxylate cycle have been investigated in several fungal species. HSP protein inhibitors and echinocandins have been shown to have a fungicidal effect against azole-resistant fungi strains. Transcriptomic and proteomic approaches have advanced antifungal drug discovery and pointed to new important specific-pathogen targets. Certain enzymes, such as those from the glyoxylate cycle, have been a target of antifungal compounds in several fungi species. Natural and synthetic compounds inhibited the activity of such enzymes and reduced the ability of fungal cells to transit from mycelium to yeast, proving to be promisor antifungal agents. Finally, computational biology has developed effective approaches, setting new routes for early antifungal drug discovery since normal approaches take several years from discovery to clinical use. Thus, the development of new antifungal strategies might reduce the therapeutic time and increase the quality of life of patients.

Deep Random Subspace Learning: A Spatial-Temporal Modeling Approach for Air Quality Prediction

Decrease in air quality is one of the most crucial threats to human health. There is an imperative and necessary need for more accurate air quality prediction. To meet this need, we propose a novel long short-term memory-based deep random subspace learning (LSTM-DRSL) framework for air quality forecasting. Specifically, we incorporate real-time pollutant emission data into the model input. We also design a spatial-temporal analysis approach to make good use of these data. The prediction model is developed by combining random subspace learning with a deep learning algorithm in order to improve the prediction accuracy. Empirical analyses based on multiple datasets over China from January 2015 to September 2017 are performed to demonstrate the efficacy of the proposed framework for hourly pollutant concentration prediction at an urban-agglomeration scale. The empirical results indicate that our framework is a viable method for air quality prediction. With consideration of the regional scale, the LSTM-DRSL framework performs better at a relatively large regional scale (around 200–300 km). In addition, the quality of predictions is higher in industrial areas. From a temporal point of view, the LSTM-DRSL framework is more suitable for hourly predictions.

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

Study on Selecting the Optimal Algorithm and the Effective Methodology to ANN-Based Short-Term Load Forecasting Model for the Southern Power Company in Vietnam

Recently, power companies apply optimal algorithms for short-term load forecasting, especially the daily load. However, in Vietnam, the load forecasting of the power system has not focused on this solution. Optimal algorithms and can help experts improve forecasting results including accuracy and the time required for forecasting. To achieve both goals, the combinations of different algorithms are still being studied. This article describes research using a new combination of two optimal algorithms: Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). This combination limits the weakness of the convergence speed of GA as well as the weakness of PSO that it easily falls into local optima (thereby reducing accuracy). This new hybrid algorithm was applied to the Southern Power Corporation’s (SPC—a large Power company in Vietnam) daily load forecasting. The results show the algorithm’s potential to provide a solution. The most accurate result was for the forecasting of a normal working day with an average error of 1.15% while the largest error was 3.74% and the smallest was 0.02%. For holidays and weekends, the average error always approximated the allowable limit of 3%. On the other hand, some poor results also provide an opportunity to re-check the real data provided by SPC.

What Can We Learn from Multi-Objective Meta-Optimization of Evolutionary Algorithms in Continuous Domains?

Properly configuring Evolutionary Algorithms (EAs) is a challenging task made difficult by many different details that affect EAs’ performance, such as the properties of the fitness function, time and computational constraints, and many others. EAs’ meta-optimization methods, in which a metaheuristic is used to tune the parameters of another (lower-level) metaheuristic which optimizes a given target function, most often rely on the optimization of a single property of the lower-level method. In this paper, we show that by using a multi-objective genetic algorithm to tune an EA, it is possible not only to find good parameter sets considering more objectives at the same time but also to derive generalizable results which can provide guidelines for designing EA-based applications. In particular, we present a general framework for multi-objective meta-optimization, to show that “going multi-objective” allows one to generate configurations that, besides optimally fitting an EA to a given problem, also perform well on previously unseen ones.

Dendritic Neuron Model With Effective Learning Algorithms for Classification, Approximation, and Prediction

An artificial neural network (ANN) that mimics the information processing mechanisms and procedures of neurons in human brains has achieved a great success in many fields, e.g., classification, prediction, and control. However, traditional ANNs suffer from many problems, such as the hard understanding problem, the slow and difficult training problems, and the difficulty to scale them up. These problems motivate us to develop a new dendritic neuron model (DNM) by considering the nonlinearity of synapses, not only for a better understanding of a biological neuronal system, but also for providing a more useful method for solving practical problems. To achieve its better performance for solving problems, six learning algorithms including biogeography-based optimization, particle swarm optimization, genetic algorithm, ant colony optimization, evolutionary strategy, and population-based incremental learning are for the first time used to train it. The best combination of its user-defined parameters has been systemically investigated by using the Taguchi's experimental design method. The experiments on 14 different problems involving classification, approximation, and prediction are conducted by using a multilayer perceptron and the proposed DNM. The results suggest that the proposed learning algorithms are effective and promising for training DNM and thus make DNM more powerful in solving classification, approximation, and prediction problems.

Comparison of multi-linear regression, particle swarm optimization artificial neural networks and genetic programming in the development of mini-tablets

In the present study, the preparation of pharmaceutical mini-tablets was attempted in the framework of Quality by Design (QbD) context, by comparing traditionally used multi-linear regression (MLR), with artificially-intelligence based regression techniques (such as standard artificial neural networks (ANNs), particle swarm optimization (PSO) ANNs and genetic programming (GP)) during Design of Experiment (DoE) implementation. Specifically, the effect of diluent type and particle size fraction for three commonly used direct compression diluents (lactose, pregelatinized starch and dibasic calcium phosphate dihydrate, DCPD) blended with either hydrophilic or hydrophobic flowing aids was evaluated in terms of: a) powder blend properties (such as bulk (Y1) and tapped (Y₂) density, Carr's compressibility index (Y₃, CCI), Kawakita's compaction fitting parameters a (Y₄) and 1/b (Y₅)), and b) mini-tablet's properties (such as relative density (Y₆), average weight (Y₇) and weight variation (Y₈)). Results showed better flowing properties for pregelatinized starch and improved packing properties for lactose and DPCD. MLR analysis showed high goodness of fit for the Y₁, Y₂, Y₄, Y₆ and Y₈ with RMSE values of Y₁ = 0.028, Y₂ = 0.032, Y₄ = 0.019, Y₆ = 0.015 and Y₈ = 0.130; while for rest responses, high correlation was observed from both standard ANNs and GP. PSO-ANNs fitting was the only regression technique that was able to adequately fit all responses simultaneously (RMSE values of Y₁ = 0.026, Y₂ = 0.022, Y₃ = 0.025, Y₄ = 0.010, Y₅ = 0.063, Y₆ = 0.013, Y₇ = 0.064 and Y₈ = 0.104).

Double-Group Particle Swarm Optimization and Its Application in Remote Sensing Image Segmentation

Particle Swarm Optimization (PSO) is a well-known meta-heuristic. It has been widely used in both research and engineering fields. However, the original PSO generally suffers from premature convergence, especially in multimodal problems. In this paper, we propose a double-group PSO (DG-PSO) algorithm to improve the performance. DG-PSO uses a double-group based evolution framework. The individuals are divided into two groups: an advantaged group and a disadvantaged group. The advantaged group works according to the original PSO, while two new strategies are developed for the disadvantaged group. The proposed algorithm is firstly evaluated by comparing it with the other five popular PSO variants and two state-of-the-art meta-heuristics on various benchmark functions. The results demonstrate that DG-PSO shows a remarkable performance in terms of accuracy and stability. Then, we apply DG-PSO to multilevel thresholding for remote sensing image segmentation. The results show that the proposed algorithm outperforms five other popular algorithms in meta-heuristic-based multilevel thresholding, which verifies the effectiveness of the proposed algorithm.

Descriptor Selection via Log-Sum Regularization for the Biological Activities of Chemical Structure

The quantitative structure-activity relationship (QSAR) model searches for a reliable relationship between the chemical structure and biological activities in the field of drug design and discovery. (1) Background: In the study of QSAR, the chemical structures of compounds are encoded by a substantial number of descriptors. Some redundant, noisy and irrelevant descriptors result in a side-effect for the QSAR model. Meanwhile, too many descriptors can result in overfitting or low correlation between chemical structure and biological bioactivity. (2) Methods: We use novel log-sum regularization to select quite a few descriptors that are relevant to biological activities. In addition, a coordinate descent algorithm, which uses novel univariate log-sum thresholding for updating the estimated coefficients, has been developed for the QSAR model. (3) Results: Experimental results on artificial and four QSAR datasets demonstrate that our proposed log-sum method has good performance among state-of-the-art methods. (4) Conclusions: Our proposed multiple linear regression with log-sum penalty is an effective technique for both descriptor selection and prediction of biological activity.

Application of the Intuitionistic Fuzzy InterCriteria Analysis Method with Triples to a Neural Network Preprocessing Procedure

The approach of InterCriteria Analysis (ICA) was applied for the aim of reducing the set of variables on the input of a neural network, taking into account the fact that their large number increases the number of neurons in the network, thus making them unusable for hardware implementation. Here, for the first time, with the help of the ICA method, correlations between triples of the input parameters for training of the neural networks were obtained. In this case, we use the approach of ICA for data preprocessing, which may yield reduction of the total time for training the neural networks, hence, the time for the network's processing of data and images.

Gaussian network model can be enhanced by combining solvent accessibility in proteins

Gaussian network model (GNM), regarded as the simplest and most representative coarse-grained model, has been widely adopted to analyze and reveal protein dynamics and functions. Designing a variation of the classical GNM, by defining a new Kirchhoff matrix, is the way to improve the residue flexibility modeling. We combined information arising from local relative solvent accessibility (RSA) between two residues into the Kirchhoff matrix of the parameter-free GNM. The undetermined parameters in the new Kirchhoff matrix were estimated by using particle swarm optimization. The usage of RSA was motivated by the fact that our previous work using RSA based linear regression model resulted out higher prediction quality of the residue flexibility when compared with the classical GNM and the parameter free GNM. Computational experiments, conducted based on one training dataset, two independent datasets and one additional small set derived by molecular dynamics simulations, demonstrated that the average correlation coefficients of the proposed RSA based parameter-free GNM, called RpfGNM, were significantly increased when compared with the parameter-free GNM. Our empirical results indicated that a variation of the classical GNMs by combining other protein structural properties is an attractive way to improve the quality of flexibility modeling.

Deep Learning in Drug Discovery

Artificial neural networks had their first heyday in molecular informatics and drug discovery approximately two decades ago. Currently, we are witnessing renewed interest in adapting advanced neural network architectures for pharmaceutical research by borrowing from the field of "deep learning". Compared with some of the other life sciences, their application in drug discovery is still limited. Here, we provide an overview of this emerging field of molecular informatics, present the basic concepts of prominent deep learning methods and offer motivation to explore these techniques for their usefulness in computer-assisted drug discovery and design. We specifically emphasize deep neural networks, restricted Boltzmann machine networks and convolutional networks.

Perspective: crystal structure prediction at high pressures

Crystal structure prediction at high pressures unbiased by any prior known structure information has recently become a topic of considerable interest. We here present a short overview of recently developed structure prediction methods and propose current challenges for crystal structure prediction. We focus on first-principles crystal structure prediction at high pressures, paying particular attention to novel high pressure structures uncovered by efficient structure prediction methods. Finally, a brief perspective on the outstanding issues that remain to be solved and some directions for future structure prediction researches at high pressure are presented and discussed.

Modeling cell-cell interactions in regulating multiple myeloma initiating cell fate

Cancer initiating cells have been documented in multiple myeloma and believed to be a key factor that initiates and drives tumor growth, differentiation,metastasis, and recurrence of the diseases. Although myeloma initiating cells (MICs) are likely to share many properties of normal stem cells, the underlying mechanisms regulating the fate of MICs are largely unknown. Studies designed to explore such communication are urgently needed to enhance our ability to predict the fate decisions of ICs (self-renewal, differentiation, and proliferation). In this study, we developed a novel system to understand the intercellular communication between MICs and their niche by seamlessly integrating experimental data and mathematical model. We first designed dynamic cell culture experiments and collected three types of cells (side population cells, progenitor cells, and mature myeloma cells) under various cultural conditions with flow cytometry. Then we developed a lineage model with ordinary differential equations by considering secreted factors, self-renewal, differentiation, and other biological functions of those cells, to model the cell–cell interactions among the three cell types. Particle swarm optimization was employed to estimate the model parameters by fitting the experimental data to the lineage model. The theoretical results show that the correlation coefficient analysis can reflect the feedback loops among the three cell types, the intercellular feedback signaling can regulate cell population dynamics, and the culture strategies can decide cell growth. This study provides a basic framework of studying cell–cell interactions in regulating MICs fate.