Residue-Residue Interaction Prediction via Stacked Meta-Learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Chen KH
PROVIDER: S-EPMC8232778 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Residue-residue close contact (R2R-C) data procured from three-dimensional protein-protein interaction (PPI) experiments is currently used for predicting residue-residue interaction (R2R-I) in PPI. However, due to complex physiochemical environments, R2R-I incidences, facilitated by multiple factors, are usually entangled in the source environment and masked in the acquired data. Here we present a novel method, P2K (Pattern to Knowledge), to disentangle R2R-I patterns and render much succinct discriminative information expressed in different specific R2R-I statistical/functional spaces. Since such knowledge is not visible in the data acquired, we refer to it as deep knowledge. Leveraging the deep knowledge discovered to construct machine learning models for sequence-based R2R-I prediction, without trial-and-error combination of the features over external knowledge of sequences, our R2R-I predictor was validated for its effectiveness under stringent leave-one-complex-out-alone cross-validation in a benchmark dataset, and was surprisingly demonstrated to perform better than an existing sequence-based R2R-I predictor by 28% (p: 1.9E-08). P2K is accessible via our web server on https://p2k.uwaterloo.ca .
| S-EPMC6172270 | biostudies-literature
Project description:Structure-based virtual screenings (SBVSs) play an important role in drug discovery projects. However, it is still a challenge to accurately predict the binding affinity of an arbitrary molecule binds to a drug target and prioritize top ligands from an SBVS. In this study, we developed a novel method, using ligand-residue interaction profiles (IPs) to construct machine learning (ML)-based prediction models, to significantly improve the screening performance in SBVSs. Such a kind of the prediction model is called an IP scoring function (IP-SF). We systematically investigated how to improve the performance of IP-SFs from many perspectives, including the sampling methods before interaction energy calculation and different ML algorithms. Using six drug targets with each having hundreds of known ligands, we conducted a critical evaluation on the developed IP-SFs. The IP-SFs employing a gradient boosting decision tree (GBDT) algorithm in conjunction with the MIN + GB simulation protocol achieved the best overall performance. Its scoring power, ranking power and screening power significantly outperformed the Glide SF. First, compared with Glide, the average values of mean absolute error and root mean square error of GBDT/MIN + GB decreased about 38 and 36%, respectively. Second, the mean values of squared correlation coefficient and predictive index increased about 225 and 73%, respectively. Third, more encouragingly, the average value of the areas under the curve of receiver operating characteristic for six targets by GBDT, 0.87, is significantly better than that by Glide, which is only 0.71. Thus, we expected IP-SFs to have broad and promising applications in SBVSs.
| S-EPMC8425425 | biostudies-literature
Project description:BackgroundWith the prevalence of cerebrovascular disease (CD) and the increasing strain on healthcare resources, forecasting the healthcare demands of cerebrovascular patients has significant implications for optimizing medical resources.MethodsIn this study, a stacking ensemble model comprised of four base learners (ridge regression, random forest, gradient boosting decision tree, and artificial neural network) and a meta learner (elastic net) was proposed for predicting the daily number of hospital admissions (HAs) for CD using the historical HAs data, air quality data, and meteorological data in Chengdu, China from 2015 to 2018. To solve the label imbalance problem, a re-weighting method based on label distribution smoothing was integrated into the meta learner. We trained the model using the data from 2015 to 2017 and evaluated its predictive ability using the data in 2018 based on four metrics, including mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination (R2). In addition, the SHapley Additive exPlanations (SHAP) framework was applied to provide explanation for the prediction of our stacking model.ResultsOur proposed model outperformed all the base learners and long short-term memory (LSTM) on two datasets. Particularly, compared with the optimal results obtained by individual models, the MAE, RMSE, and MAPE of the stacking model decreased by 13.9%, 12.7%, and 5.8%, respectively, and the R2 improved by 6.8% on CD dataset. The model explanation demonstrated that environmental features played a role in further improving the model performance and identified that high temperature and high concentrations of gaseous air pollutants might strongly associate with an increased risk of CD.ConclusionsOur stacking model considering environmental exposure is efficient in predicting daily HAs for CD and has practical value in early warning and healthcare resource allocation.
| S-EPMC10080841 | biostudies-literature
Project description:Toxicity prediction using quantitative structure-activity relationship has achieved significant progress in recent years. However, most existing machine learning methods in toxicity prediction utilize only one type of feature representation and one type of neural network, which essentially restricts their performance. Moreover, methods that use more than one type of feature representation struggle with the aggregation of information captured within the features since they use predetermined aggregation formulas. In this paper, we propose a deep learning framework for quantitative toxicity prediction using five individual base deep learning models and their own base feature representations. We then propose to adopt a meta ensemble approach using another separate deep learning model to perform aggregation of the outputs of the individual base deep learning models. We train our deep learning models in a weighted multitask fashion combining four quantitative toxicity data sets of LD50, IGC50, LC50, and LC50-DM and minimizing the root-mean-square errors. Compared to the current state-of-the-art toxicity prediction method TopTox on LD50, IGC50, and LC50-DM, that is, three out of four data sets, our method, respectively, obtains 5.46, 16.67, and 6.34% better root-mean-square errors, 6.41, 11.80, and 12.16% better mean absolute errors, and 5.21, 7.36, and 2.54% better coefficients of determination. We named our method QuantitativeTox, and our implementation is available from the GitHub repository https://github.com/Abdulk084/QuantitativeTox.
| S-EPMC8154128 | biostudies-literature
Project description:BackgroundNon-coding RNAs (ncRNAs) play crucial roles in many biological processes, such as post-transcription of gene regulation. ncRNAs mainly function through interaction with RNA binding proteins (RBPs). To understand the function of a ncRNA, a fundamental step is to identify which protein is involved into its interaction. Therefore it is promising to computationally predict RBPs, where the major challenge is that the interaction pattern or motif is difficult to be found.ResultsIn this study, we propose a computational method IPMiner (Interaction Pattern Miner) to predict ncRNA-protein interactions from sequences, which makes use of deep learning and further improves its performance using stacked ensembling. One of the IPMiner's typical merits is that it is able to mine the hidden sequential interaction patterns from sequence composition features of protein and RNA sequences using stacked autoencoder, and then the learned hidden features are fed into random forest models. Finally, stacked ensembling is used to integrate different predictors to further improve the prediction performance. The experimental results indicate that IPMiner achieves superior performance on the tested lncRNA-protein interaction dataset with an accuracy of 0.891, sensitivity of 0.939, specificity of 0.831, precision of 0.945 and Matthews correlation coefficient of 0.784, respectively. We further comprehensively investigate IPMiner on other RNA-protein interaction datasets, which yields better performance than the state-of-the-art methods, and the performance has an increase of over 20 % on some tested benchmarked datasets. In addition, we further apply IPMiner for large-scale prediction of ncRNA-protein network, that achieves promising prediction performance.ConclusionBy integrating deep neural network and stacked ensembling, from simple sequence composition features, IPMiner can automatically learn high-level abstraction features, which had strong discriminant ability for RNA-protein detection. IPMiner achieved high performance on our constructed lncRNA-protein benchmark dataset and other RNA-protein datasets. IPMiner tool is available at http://www.csbio.sjtu.edu.cn/bioinf/IPMiner .
| S-EPMC4979166 | biostudies-literature
Project description:Computational identification of heme-binding residues is beneficial for predicting and designing novel heme proteins. Here we proposed a novel method for heme-binding residue prediction by exploiting topological properties of these residues in the residue interaction networks derived from three-dimensional structures. Comprehensive analysis showed that key residues located in heme-binding regions are generally associated with the nodes with higher degree, closeness and betweenness, but lower clustering coefficient in the network. HemeNet, a support vector machine (SVM) based predictor, was developed to identify heme-binding residues by combining topological features with existing sequence and structural features. The results showed that incorporation of network-based features significantly improved the prediction performance. We also compared the residue interaction networks of heme proteins before and after heme binding and found that the topological features can well characterize the heme-binding sites of apo structures as well as those of holo structures, which led to reliable performance improvement as we applied HemeNet to predicting the binding residues of proteins in the heme-free state. HemeNet web server is freely accessible at http://mleg.cse.sc.edu/hemeNet/.
| S-EPMC3184988 | biostudies-literature
Project description:Prediction of drug-target interactions (DTIs) is essential in medicine field, since it benefits the identification of molecular structures potentially interacting with drugs and facilitates the discovery and reposition of drugs. Recently, much attention has been attracted to network representation learning to learn rich information from heterogeneous data. Although network representation learning algorithms have achieved success in predicting DTI, several manually designed meta-graphs limit the capability of extracting complex semantic information. To address the problem, we introduce an adaptive meta-graph-based method, termed AMGDTI, for DTI prediction. In the proposed AMGDTI, the semantic information is automatically aggregated from a heterogeneous network by training an adaptive meta-graph, thereby achieving efficient information integration without requiring domain knowledge. The effectiveness of the proposed AMGDTI is verified on two benchmark datasets. Experimental results demonstrate that the AMGDTI method overall outperforms eight state-of-the-art methods in predicting DTI and achieves the accurate identification of novel DTIs. It is also verified that the adaptive meta-graph exhibits flexibility and effectively captures complex fine-grained semantic information, enabling the learning of intricate heterogeneous network topology and the inference of potential drug-target relationship.
| S-EPMC10749791 | biostudies-literature
Project description:A new optimization-based method is presented to predict the hydrophobic residue contacts in alpha-helical proteins. The proposed approach uses a high resolution distance dependent force field to calculate the interaction energy between different residues of a protein. The formulation predicts the hydrophobic contacts by minimizing the sum of these contact energies. These residue contacts are highly useful in narrowing down the conformational space searched by protein structure prediction algorithms. The proposed algorithm also offers the algorithmic advantage of producing a rank ordered list of the best contact sets. This model was tested on four independent alpha-helical protein test sets and was found to perform very well. The average accuracy of the predictions (separated by at least six residues) obtained using the presented method was approximately 66% for single domain proteins. The average true positive and false positive distances were also calculated for each protein test set and they are 8.87 and 14.67 A, respectively.
| S-EPMC2635923 | biostudies-literature
Project description:Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, application of these models in clinically realistic environments can result in poor generalization and decreased accuracy, mainly due to the domain shift across different hospitals, scanner vendors, imaging protocols, and patient populations etc. Common transfer learning and domain adaptation techniques are proposed to address this bottleneck. However, these solutions require data (and annotations) from the target domain to retrain the model, and is therefore restrictive in practice for widespread model deployment. Ideally, we wish to have a trained (locked) model that can work uniformly well across unseen domains without further training. In this paper, we propose a deep stacked transformation approach for domain generalization. Specifically, a series of n stacked transformations are applied to each image during network training. The underlying assumption is that the "expected" domain shift for a specific medical imaging modality could be simulated by applying extensive data augmentation on a single source domain, and consequently, a deep model trained on the augmented "big" data (BigAug) could generalize well on unseen domains. We exploit four surprisingly effective, but previously understudied, image-based characteristics for data augmentation to overcome the domain generalization problem. We train and evaluate the BigAug model (with n=9 transformations) on three different 3D segmentation tasks (prostate gland, left atrial, left ventricle) covering two medical imaging modalities (MRI and ultrasound) involving eight publicly available challenge datasets. The results show that when training on relatively small dataset (n = 10~32 volumes, depending on the size of the available datasets) from a single source domain: (i) BigAug models degrade an average of 11%(Dice score change) from source to unseen domain, substantially better than conventional augmentation (degrading 39%) and CycleGAN-based domain adaptation method (degrading 25%), (ii) BigAug is better than "shallower" stacked transforms (i.e. those with fewer transforms) on unseen domains and demonstrates modest improvement to conventional augmentation on the source domain, (iii) after training with BigAug on one source domain, performance on an unseen domain is similar to training a model from scratch on that domain when using the same number of training samples. When training on large datasets (n = 465 volumes) with BigAug, (iv) application to unseen domains reaches the performance of state-of-the-art fully supervised models that are trained and tested on their source domains. These findings establish a strong benchmark for the study of domain generalization in medical imaging, and can be generalized to the design of highly robust deep segmentation models for clinical deployment.
| S-EPMC7393676 | biostudies-literature
Project description:In the paradigm of materials informatics for accelerated materials discovery, the choice of feature set (i.e. attributes that capture aspects of structure, chemistry and/or bonding) is critical. Ideally, the feature sets should provide a simple physical basis for extracting major structural and chemical trends and furthermore, enable rapid predictions of new material chemistries. Orbital radii calculated from model pseudopotential fits to spectroscopic data are potential candidates to satisfy these conditions. Although these radii (and their linear combinations) have been utilized in the past, their functional forms are largely justified with heuristic arguments. Here we show that machine learning methods naturally uncover the functional forms that mimic most frequently used features in the literature, thereby providing a mathematical basis for feature set construction without a priori assumptions. We apply these principles to study two broad materials classes: (i) wide band gap AB compounds and (ii) rare earth-main group RM intermetallics. The AB compounds serve as a prototypical example to demonstrate our approach, whereas the RM intermetallics show how these concepts can be used to rapidly design new ductile materials. Our predictive models indicate that ScCo, ScIr, and YCd should be ductile, whereas each was previously proposed to be brittle.
| S-EPMC4548442 | biostudies-literature