Search

The escalating apprehension surrounding the carcinogenic potential of chemicals emphasizes the imperative need for efficient methods of assessing carcinogenicity. Conventional experimental approaches such as in vitro and in vivo assays, albeit effective, suffer from being costly and time-consuming. In response to this challenge, new alternative methodologies, notably machine learning and deep learning techniques, have attracted attention for their potential in developing carcinogenicity prediction models. This article reviews the progress in predicting carcinogenicity using various machine learning and deep learning algorithms. A comparative analysis on these developed models reveals that support vector machine, random forest, and ensemble learning are commonly preferred for their robustness and effectiveness in predicting chemical carcinogenicity. Conversely, models based on deep learning algorithms, such as feedforward neural network, convolutional neural network, graph convolutional neural network, capsule neural network, and hybrid neural networks, exhibit promising capabilities but are limited by the size of available carcinogenicity datasets. This review provides a comprehensive analysis of current machine learning and deep learning models for carcinogenicity prediction, underscoring the importance of high-quality and large datasets. These observations are anticipated to catalyze future advancements in developing effective and generalizable machine learning and deep learning models for predicting chemical carcinogenicity.

Background: Cardiotoxicity is a major cause of drug withdrawal. The hERG channel, regulating ion flow, is pivotal for heart and nervous system function. Its blockade is a concern in drug development. Predicting hERG blockade is essential for identifying cardiac safety issues. Various QSAR models exist, but their performance varies. Ongoing improvements show promise, necessitating continued efforts to enhance accuracy using emerging deep learning algorithms in predicting potential hERG blockade., Study Design and Method: Using a large training dataset, six individual QSAR models were developed. Additionally, three ensemble models were constructed. All models were evaluated using 10-fold cross-validations and two external datasets., Results: The 10-fold cross-validations resulted in Mathews correlation coefficient (MCC) values from 0.682 to 0.730, surpassing the best-reported model on the same dataset (0.689). External validations yielded MCC values from 0.520 to 0.715 for the first dataset, exceeding those of previously reported models (0-0.599). For the second dataset, MCC values fell between 0.025 and 0.215, aligning with those of reported models (0.112-0.220)., Conclusions: The developed models can assist the pharmaceutical industry and regulatory agencies in predicting hERG blockage activity, thereby enhancing safety assessments and reducing the risk of adverse cardiac events associated with new drug candidates.

The wide application of nanomaterials in consumer and medical products has raised concerns about their potential adverse effects on human health. Thus, more and more biological assessments regarding the toxicity of nanomaterials have been performed. However, the different ways the evaluations were performed, such as the utilized assays, cell lines, and the differences of the produced nanoparticles, make it difficult for scientists to analyze and effectively compare toxicities of nanomaterials. Fortunately, machine learning has emerged as a powerful tool for the prediction of nanotoxicity based on the available data. Among different types of toxicity assessments, nanomaterial cytotoxicity was the focus here because of the high sensitivity of cytotoxicity assessment to different treatments without the need for complicated and time-consuming procedures. In this review, we summarized recent studies that focused on the development of machine learning models for prediction of cytotoxicity of nanomaterials. The goal was to provide insight into predicting potential nanomaterial toxicity and promoting the development of safe nanomaterials.

Motivation Drug combination therapy has exhibited remarkable therapeutic efficacy and has gradually become a promising clinical treatment strategy of complex diseases such as cancers. As the related databases keep expanding, computational methods based on deep learning model have become powerful tools to predict synergistic drug combinations. However, predicting effective synergistic drug combinations is still a challenge due to the high complexity of drug combinations, the lack of biological interpretability, and the large discrepancy in the response of drug combinations in vivo and in vitro biological systems. Results Here, we propose DGSSynADR, a new d eep learning method based on g lobal s tructured features of drugs and targets for predicting syn ergistic a nticancer dr ug combinations. DGSSynADR constructs a heterogeneous graph by integrating the drug–drug, drug–target, protein–protein interactions and multi-omics data, utilizes a low-rank global attention (LRGA) model to perform global weighted aggregation of graph nodes and learn the global structured features of drugs and targets, and then feeds the embedded features into a bilinear predictor to predict the synergy scores of drug combinations in different cancer cell lines. Specifically, LRGA network brings better model generalization ability, and effectively reduces the complexity of graph computation. The bilinear predictor facilitates the dimension transformation of the features and fuses the feature representation of the two drugs to improve the prediction performance. The loss function Smooth L1 effectively avoids gradient explosion, contributing to better model convergence. To validate the performance of DGSSynADR, we compare it with seven competitive methods. The comparison results demonstrate that DGSSynADR achieves better performance. Meanwhile, the prediction of DGSSynADR is validated by previous findings in case studies. Furthermore, detailed ablation studies indicate that the one-hot coding drug feature, LRGA model and bilinear predictor play a key role in improving the prediction performance. Availability and implementation DGSSynADR is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DHUDBlab/DGSSynADR. [ABSTRACT FROM AUTHOR]

Single-cell RNA sequencing (scRNA-seq) measures transcriptome-wide gene expression at single-cell resolution. Clustering analysis of scRNA-seq data enables researchers to characterize cell types and states, shedding new light on cell-to-cell heterogeneity in complex tissues. Recently, self-supervised contrastive learning has become a prominent technique for underlying feature representation learning. However, for the noisy, high-dimensional and sparse scRNA-seq data, existing methods still encounter difficulties in capturing the intrinsic patterns and structures of cells, and seldom utilize prior knowledge, resulting in clusters that mismatch with the real situation. To this end, we propose scDECL, a novel deep enhanced constraint clustering algorithm for scRNA-seq data analysis based on contrastive learning and pairwise constraints. Specifically, based on interpolated contrastive learning, a pre-training model is trained to learn the feature embedding, and then perform clustering according to the constructed enhanced pairwise constraint. In the pre-training stage, a mixup data augmentation strategy and interpolation loss is introduced to improve the diversity of the dataset and the robustness of the model. In the clustering stage, the prior information is converted into enhanced pairwise constraints to guide the clustering. To validate the performance of scDECL, we compare it with six state-of-the-art algorithms on six real scRNA-seq datasets. The experimental results demonstrate the proposed algorithm outperforms the six competing methods. In addition, the ablation studies on each module of the algorithm indicate that these modules are complementary to each other and effective in improving the performance of the proposed algorithm. Our method scDECL is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DBLABDHU/scDECL. [ABSTRACT FROM AUTHOR]

The formation of crosslinking network between polymer chains has significant influence on polymer properties. In particular, the crosslinked structure of ionic networks like proton exchange membrane affects the conductivity performance. To further develop in this area, a framework for polymer membrane design based on the developed quantitative prediction model of the properties of crosslinked polymer is proposed. First, polymers with different crosslinking degrees are constructed by a crosslinking algorithm. Next, molecular dynamics is used to calculate the properties of crosslinked polymers. Then, the quantitative relationship between crosslinked polymer structures and macroscopical properties is developed. Subsequently, computer‐aided polymer design method is integrated with the developed quantitative predict model. The crosslinked polymer design problem is expressed as an optimization problem to obtain the optimal crosslinking degree. Bayesian optimization strategy is used to solve the established optimization model. Finally, two case studies of perfluoro sulfonic acid and perfluoro imide acid design are given to illustrate the application of the proposed polymer design framework. [ABSTRACT FROM AUTHOR]

Metal–organic frameworks (MOFs), a class of porous nanomaterials, have been widely used in gas adsorption-based applications due to their high porosities and chemical tunability. To facilitate the discovery of high-performance MOFs for different applications, a variety of machine learning models have been developed to predict the gas adsorption capacities of MOFs. Most of the predictive models are developed using traditional machine learning algorithms. However, the continuously increasing sizes of MOF datasets and the complicated relationships between MOFs and their gas adsorption capacities make deep learning a suitable candidate to handle such big data with increased computational power and accuracy. In this study, we developed models for predicting gas adsorption capacities of MOFs using two deep learning algorithms, multilayer perceptron (MLP) and long short-term memory (LSTM) networks, with a hypothetical set of about 130,000 structures of MOFs with methane and carbon dioxide adsorption data at different pressures. The models were evaluated using 10 iterations of 10-fold cross validations and 100 holdout validations. The MLP and LSTM models performed similarly with high prediction accuracy. The models for predicting gas adsorption at a higher pressure outperformed the models for predicting gas adsorption at a lower pressure. The deep learning models are more accurate than the random forest models reported in the literature, especially for predicting gas adsorption capacities at low pressures. Our results demonstrated that deep learning algorithms have a great potential to generate models that can accurately predict the gas adsorption capacities of MOFs. [ABSTRACT FROM AUTHOR]

In Wireless Body Area Networks (WBANs), on the one hand, the energy of nodes is limited. On the other hand, the network topology often changes due to human movement or posture changes. Unstable network topology is easy to cause packet loss, and packet loss will cause inaccurate data collection. Therefore, how to effectively use energy to transmit data reliably becomes a key issue. For this problem, we propose an optimized routing protocol namely Energy Efficient and Reliable Routing based on Reinforcement Learning and Fuzzy Logic (EERR-RLFL). In EERR-RLFL, considering the heterogeneity of nodes in WBANs, we first establish a node rank division mechanism, by which sensor nodes are divided into different ranks from three aspects. Each rank is considered to be one of the factors that affect the link quality. Then, we propose the Fuzzy-Logic-based Link Quality Evaluation (FLLQE) algorithm. It makes use of the fuzzy evaluation method of fuzzy logic and considers the comprehensive influence of multiple factors to evaluate the link quality between two nodes, which will provide reference for routing path selection. In the process of data transmission, based on the FLLQE algorithm, we use a hybrid data transmission mode, in which the time when a forwarding node is needed is first determined, and then the Reinforcement Learning algorithm is used to select the global optimized routing path. Simulation results show that EERR-RLFL outperforms Single Hop Transmission and Optimized Cost Effective and Energy Efficient Routing in terms of network lifetime, packet loss ratio and energy efficiency. [ABSTRACT FROM AUTHOR]

Aristolochic acid I (AAI) as one of the major aristolochic acids (AAs) can cause progressive aristolochic acid nephropathy (AAN), which has been widely investigated since the early 1990s. Besides renal diseases, it has been recently revealed that AAI can induce liver damage. In this study, we report the molecular mapping of liver tissue sections from AAI-exposed mice using atmospheric pressure matrix-assisted laser desorption/ionization mass spectrometry (AP-MALDI MS) and show the distinct metabolic alterations when compared to the control group. We first used renal tissue sections to evaluate the performance of AP-MALDI MSI in spatial discrimination of different morphological regions. Then, the hepatic tissues from the AAI-induced and the control mice were analyzed, displaying rich metabolic profiles from both groups. Orthogonal partial least squares-discriminant analysis (OPLS-DA) is used to show complete separation of the two groups. A machine learning algorithm--least absolute shrinkage and selection operator (lasso) is used for statistical analysis of a total of 11,726 pixels of imaging data extracted from 3 normal liver and 3 AAI-exposed liver tissue sections, generating a classifier with high accuracy (99.81%). In total, 16 m/z values, including small metabolites and lipid species, are selected to discriminate AAI-exposed liver tissues. Finally, we explore the potentially impacted pathways using metabolomics pathway analysis (MetPA), indicating multiple metabolic pathway alterations including taurine and hypotaurine metabolism, glycerophospholipid metabolism, d -Glutamine and d -glutamate metabolism, and arachidonic acid metabolism, which provides new insights in AAI-induced hepatotoxicity. Atmospheric pressure matrix-assisted laser desorption/ionization mass spectrometry imaging (AP-MALDI MSI) and machine learning are combined for molecular mapping of metabolic alterations and accurate classification of aristolochic acid I (AAI) exposed liver tissues. [Display omitted] • AP-MALDI MSI is used to evaluate the performance of spatially visualizing the molecular distributions in biological tissues. • Machine learning achieves high classification accuracy of differentiating AAI-exposed mice liver from the control group. • Altered taurine and hypotaurine, glycerophospholipid, and arachidonic acid metabolism in AAI-exposed liver is disclosed. [ABSTRACT FROM AUTHOR]

Channels and locks are crucial resources for ships of inland waterways. This paper addresses the ship scheduling problem based on channel-lock coordination, where ships entering the channel are affected by water discharge during flood season. A ship scheduling optimization model is formulated to minimize the total waiting time of ships at the anchorage. The model takes into account the decision-making of the departure time of ships, the change of water discharge in different scenarios, and the coordinated allocation of channels and locks. A dynamic multi-population particle swarm optimization algorithm with recombined learning and hybrid mutation (DMPSO-RH) is proposed to solve the model of ship scheduling. Numerical experiments conducted for the Three Gorges Dam (TGD) demonstrate that the DMPSO-RH can obtain nearly optimal solutions for practical large-sized ship scheduling problems within a reasonable time. By optimizing the departure time and sequence of ships, the scheduling scheme generated by the DMPSO-RH can effectively match the channel operation time and the lockage starting time, which helps to enhance the coordination of channels and locks at the TGD in different scenarios. Due to these improvements, the total waiting time of ships in the two scenarios is reduced by 29.08% and 28.59%, respectively, and the carbon emissions of ships are reduced accordingly. This approach can avoid navigation risks and improve the efficiency of ship scheduling in flood season. Moreover, the result of this study is very useful to reduce the waiting time and improve the environmental pollution of ships at the TGD. [ABSTRACT FROM AUTHOR]

Deep semi-supervised learning is becoming an active research topic because it jointly utilizes labeled and unlabeled samples in training deep neural networks. Recent advances are mainly focused on inductive semi-supervised learning which generally extends supervised algorithms to include unlabeled data. In this paper, we propose CL_PLP, a new transductive deep semi-supervised learning algorithm based on contrastive self-supervised learning and partial label propagation. The proposed method consists of two modules, contrastive self-supervised learning module extracting features from labeled and unlabeled data and partial label propagation module generating confident pseudo-labels through label propagation. For contrastive learning, we propose an improved twins network model by adding multiple projector layers and the contrastive loss term. Meanwhile, we adopt strong and weak data augmentation to increase the diversity of the dataset and the robustness of the model. For the partial label propagation module, we interrupt the label propagation process according to the quality of pseudo-labels and improve the impact of high-quality pseudo-labels. The performance of our algorithm on three standard baseline datasets CIFAR-10, CIFAR-100 and miniImageNet is better than previous state-of-the-art transductive deep semi-supervised learning methods. By transferring our model to the medical COVID19-Xray dataset, it also achieves good performance. Finally, we propose a strategy to integrate our partial label propagation module with inductive semi-supervised learning method, and the results prove that it can further improve their performance and obtain additional high-quality pseudo-labels for the unlabeled data. [ABSTRACT FROM AUTHOR]