Molecular Activity Prediction Research Articles

MIDF-DMAP: Multimodal information dynamic fusion for drug molecule activity prediction

BackgroundComputer-aided drug development can alleviate limitations in drug research and development processes, such as long cycles, high costs, and limited targeting. Deep learning models can be used to predict the activity of drug compound molecules. However, existing models still need to adequately address semantic redundancy, conflicts, and noise between different data modalities. It results in low accuracy in predicting molecular activity and many false positive results that need further resolution. ObjectiveThis study aims to design a parallel deep learning model for processing multimodal molecular information fusion, dynamically adjusting the weights of different modal features during the fusion process. This approach ensures that high-quality modal information is more significant in molecular activity prediction, improving the model’s predictive accuracy. MethodsFirst, three modal features of drug molecules are extracted: one-dimensional fingerprints, two-dimensional topological structures, and three-dimensional geometric structures. Then, a dynamic weighting mechanism is proposed to fuse these three modal features organically. Finally, the fused features are input into the model classifier to obtain molecular activity prediction results. ResultsExperimental results show that the proposed model improved the Receiver Operating Characteristic-Area Under the Curve (ROC-AUC) value by 29.96% compared to the Weave model and 26.38% compared to the GC model on the BBBP dataset. Compared to the GraphMVP model and the multi-channel substructure graph model MSGG, the ROC-AUC value increased by 20.44% and 15.80%, respectively. This method also achieved good results on imbalanced samples and small molecule datasets. ConclusionThis study provides an effective multimodal dynamic fusion method for virtual drug screening, enriching computer-aided drug development theory and improving drug research and development efficiency.

Epigenetic target identification strategy based on multi-feature learning

The identification of potential epigenetic targets for a known bioactive compound is essential and promising as more and more epigenetic drugs are used in cancer clinical treatment and the availability of chemogenomic data related to epigenetics increases. In this study, we introduce a novel epigenetic target identification strategy (ETI-Strategy) that integrates a multi-task graph convolutional neural network prior model and a protein-ligand interaction classification discriminating model using large-scale bioactivity data for a panel of 55 epigenetic targets. Our approach utilizes machine learning techniques to achieve an AUC value of 0.934 for the prior model and 0.830 for the discriminating model, outperforming inverse docking in predicting protein-ligand interactions. When comparing with other open-source target identification tools, it was found that only our tool was able to accurately predict all the targets corresponding to each compound. This further demonstrates the ability of our strategy to take full advantage of molecular-level information as well as protein-level information in molecular activity prediction. Our work highlights the contribution of machine learning in the identification of potential epigenetic targets and offers a novel approach for epigenetic drug discovery and development. Communicated by Ramaswamy H. Sarma

FP-MAP: an extensive library of fingerprint-based molecular activity prediction tools.

Discovering new drugs for disease treatment is challenging, requiring a multidisciplinary effort as well as time, and resources. With a view to improving hit discovery and lead compound identification, machine learning (ML) approaches are being increasingly used in the decision-making process. Although a number of ML-based studies have been published, most studies only report fragments of the wider range of bioactivities wherein each model typically focuses on a particular disease. This study introduces FP-MAP, an extensive atlas of fingerprint-based prediction models that covers a diverse range of activities including neglected tropical diseases (caused by viral, bacterial and parasitic pathogens) as well as other targets implicated in diseases such as Alzheimer's. To arrive at the best predictive models, performance of ≈4,000 classification/regression models were evaluated on different bioactivity data sets using 12 different molecular fingerprints. The best performing models that achieved test set AUC values of 0.62-0.99 have been integrated into an easy-to-use graphical user interface that can be downloaded from https://gitlab.com/vishsoft/fpmap.

VAERHNN: Voting-averaged ensemble regression and hybrid neural network to investigate potent leads against colorectal cancer

In recent years, artificial intelligence (AI) has flourished in drug discovery and sped up the process of drug research and development. Recently, it has been demonstrated that the inhibition of phosphoglycerate kinase 1 (PGK1) can effectively inhibit colorectal cancer (CRC). In this paper, we propose an AI-based drug repurposing protocol, VAERHNN, to investigate potent leads against CRC. VAERHNN can comprehensively integrate the information of the target and its inhibitors or agonists for drug repurposing. During the protocol, we built a voting-averaged ensemble regression (VAER) model based on ensemble learning algorithm for molecular activity prediction. The VAER model outperforms other single ensemble learning regression models. Moreover, we also assemble a hybrid neural network (HNN) consisting of multiple neural networks to predict the drug-target affinity. In HNN, we picked a combination of several top-performing neural networks for weighted average computation. Hereafter, through the evaluation of voting-averaged scores from molecular docking and AI models, we singled out flavin adenosine dinucleotide (FAD) as a potential lead. Ultimately, molecular dynamics simulations and in vitro scratch and transwell assays confirmed the stability of FAD binding to PGK1 and that FAD can significantly inhibit the migration and invasion of CRC cells in vitro. In conclusion, through VAERHNN, we identified FAD as a potential lead compound against CRC, providing a new idea for CRC treatment. The source codes and data of this study are available at https://github.com/gxCaesar/VAERHNN.

Graph-Based Feature Selection Approach for Molecular Activity Prediction.

In the construction of QSAR models for the prediction of molecular activity, feature selection is a common task aimed at improving the results and understanding of the problem. The selection of features allows elimination of irrelevant and redundant features, reduces the effect of dimensionality problems, and improves the generalization and interpretability of the models. In many feature selection applications, such as those based on ensembles of feature selectors, it is necessary to combine different selection processes. In this work, we evaluate the application of a new feature selection approach to the prediction of molecular activity, based on the construction of an undirected graph to combine base feature selectors. The experimental results demonstrate the efficiency of the graph-based method in terms of the classification performance, reduction, and redundancy compared to the standard voting method. The graph-based method can be extended to different feature selection algorithms and applied to other cheminformatics problems.

Graph label prediction based on local structure characteristics representation

A recent study has shown that the real-time anti-noise challenges faced by molecular activity prediction algorithms can be solved by using the part structure features of the molecular graph. However, the sub-structures selected by this method are distributed in a scattered manner such that although they include as many block features as possible, they do not fully consider the connections between these blocks. Therefore, this study was conducted to fully consider the physical interpretation of the betweenness centrality node in the graph, and a sub-structure was obtained by depth-first search (DFS) from this node. This sub-structure not only contains the characteristics of each region but also retains the connections between each region. Then, a cascading multi-layer perception (MLP) model was designed to learn the characteristic representation of the graph from its local structure features. Experiments demonstrated that the performance of our algorithm is superior to that of other algorithms when evaluated on different datasets.

Experimental and density functional theory study of complexing agents on cobalt dissolution in alkaline solutions

Glycine (GLY), potassium tartrate (PT), and hydroxyethylidene diphosphonic acid (HEDP) have been used as effective complexing agents for chemical mechanical polishing (CMP) of a cobalt (Co) barrier layer, but the most suitable of these three complexing agents is still unclear. In this paper, the density functional theory (DFT) method is employed to predict the complexing capability of the three complexing agents to Co ions. The prediction results show that the complexing capability of the three complexing agents is in the order of: HEDP > GLY > PT. Then, electrochemical experiments, static corrosion tests, UV-Vis spectra, and XPS analysis successfully prove the effectiveness of the DFT method for molecular activity prediction. The experimental results show that regardless of the presence or absence of H2O2, PT has the weakest complexing capability, which results in sufficient Co removal rate without causing unnecessary Co dissolution. In addition, the complexation capability of HEDP is stronger than that of GLY when the oxidation of the Co surface is not a limiting factor.

2-D chemical structure image-based in silico model to predict agonist activity for androgen receptor

BackgroundAbnormal activation of human nuclear hormone receptors disrupts endocrine systems and thereby affects human health. There have been machine learning-based models to predict androgen receptor agonist activity. However, the models were constructed based on limited numerical features such as molecular descriptors and fingerprints.ResultIn this study, instead of the numerical features, 2-D chemical structure images of compounds were used to build an androgen receptor toxicity prediction model. The images may provide unknown features that were not represented by conventional numerical features. As a result, the new strategy resulted in a construction of highly accurate prediction model: Mathews correlation coefficient (MCC) of 0.688, positive predictive value (PPV) of 0.933, sensitivity of 0.519, specificity of 0.998, and overall accuracy of 0.981 in 10-fold cross-validation. Validation on a test dataset showed MCC of 0.370, sensitivity of 0.211, specificity of 0.991, PPV of 0.882, and overall accuracy of 0.801. Our chemical image-based prediction model outperforms conventional models based on numerical features.ConclusionOur constructed prediction model successfully classified molecular images into androgen receptor agonists or inactive compounds. The result indicates that 2-D molecular mimetic diagram would be used as another feature to construct molecular activity prediction models.

Inductive transfer learning for molecular activity prediction: Next-Gen QSAR Models with MolPMoFiT

Deep neural networks can directly learn from chemical structures without extensive, user-driven selection of descriptors in order to predict molecular properties/activities with high reliability. But these approaches typically require large training sets to learn the endpoint-specific structural features and ensure reasonable prediction accuracy. Even though large datasets are becoming the new normal in drug discovery, especially when it comes to high-throughput screening or metabolomics datasets, one should also consider smaller datasets with challenging endpoints to model and forecast. Thus, it would be highly relevant to better utilize the tremendous compendium of unlabeled compounds from publicly-available datasets for improving the model performances for the user’s particular series of compounds. In this study, we propose the Molecular Prediction Model Fine-Tuning (MolPMoFiT) approach, an effective transfer learning method based on self-supervised pre-training + task-specific fine-tuning for QSPR/QSAR modeling. A large-scale molecular structure prediction model is pre-trained using one million unlabeled molecules from ChEMBL in a self-supervised learning manner, and can then be fine-tuned on various QSPR/QSAR tasks for smaller chemical datasets with specific endpoints. Herein, the method is evaluated on four benchmark datasets (lipophilicity, FreeSolv, HIV, and blood–brain barrier penetration). The results showed the method can achieve strong performances for all four datasets compared to other state-of-the-art machine learning modeling techniques reported in the literature so far.

Influence of feature rankers in the construction of molecular activity prediction models.

In the construction of activity prediction models, the use of feature ranking methods is a useful mechanism for extracting information for ranking features in terms of their significance to develop predictive models. This paper studies the influence of feature rankers in the construction of molecular activity prediction models; for this purpose, a comparative study of fourteen rankings methods for feature selection was conducted. The activity prediction models were constructed using four well-known classifiers and a wide collection of datasets. The ranking algorithms were compared considering the performance of these classifiers using different metrics and the consistency of the ranked features.

Molecular activity prediction by means of supervised subspace projection based ensembles of classifiers

This paper proposes a method for molecular activity prediction in QSAR studies using ensembles of classifiers constructed by means of two supervised subspace projection methods, namely nonparametric discriminant analysis (NDA) and hybrid discriminant analysis (HDA). We studied the performance of the proposed ensembles compared to classical ensemble methods using four molecular datasets and eight different models for the representation of the molecular structure. Using several measures and statistical tests for classifier comparison, we observe that our proposal improves the classification results with respect to classical ensemble methods. Therefore, we show that ensembles constructed using supervised subspace projections offer an effective way of creating classifiers in cheminformatics.

An ensemble approach for in silico prediction of Ames mutagenicity

In this paper, we evaluate three learning algorithms based on supervised projections for molecular activity prediction. Using an approach based on supervised projections of the input space to construct ensembles of classifiers, three algorithms were tested. We constructed the projections by considering only instances that were misclassified by a previous classifier using the hidden layer of an Artificial Neural Network. We applied a supervised linear projection of the input space using a Nonparametric Discriminant Analysis method. Finally, we projected onto a subspace that minimizes the weighted error for each step. Using these three methods to construct ensembles of classifiers for the in silico prediction of Ames mutagenicity, we demonstrated the improved behavior of our proposal compared to classical methods.

Robust support vector machines for multiple instance learning

This paper presents the multiple instance classification problem that can be used for drug and molecular activity prediction, text categorization, image annotation, and object recognition. In order to model a more robust representation of outliers, hard margin loss formulations that minimize the number of misclassified instances are proposed. Although the problem is $\mathcal{NP}$ -hard, computational studies show that medium sized problems can be solved to optimality in reasonable time using integer programming and constraint programming formulations. A three-phase heuristic algorithm is proposed for larger problems. Furthermore, different loss functions such as hinge loss, ramp loss, and hard margin loss are empirically compared in the context of multiple instance classification. The proposed heuristic and robust support vector machines with hard margin loss demonstrate superior generalization performance compared to other approaches for multiple instance learning.

Multiple instance learning via margin maximization

In this paper, we consider the classification problem within the multiple instance learning (MIL) context. Training data is composed of labeled bags of instances. Despite the large number of margin maximization based classification methods, there are only a few methods that consider the margin for MIL problems in the literature. We first formulate a combinatorial margin maximization problem for multiple instance classification and prove that it is NP -hard. We present a way to apply the kernel trick in this formulation for classifying nonlinear multiple instance data. We also propose a branch and bound algorithm and present computational results on publicly available benchmark data sets. Our approach outperforms a leading commercial solver in terms of the best integer solution and optimality gap in the majority of image annotation and molecular activity prediction test cases.