ASPEN, a methodology for reconstructing protein evolution with improved accuracy using ensemble models.
Ontology highlight
ABSTRACT:
SUBMITTER: Sloutsky R
PROVIDER: S-EPMC6797483 | biostudies-literature | 2019 Oct
REPOSITORIES: biostudies-literature
Publications
ASPEN, a methodology for reconstructing protein evolution with improved accuracy using ensemble models.
Sloutsky Roman R Naegle Kristen M KM
eLife 20191017
Evolutionary reconstruction algorithms produce models of the evolutionary history of proteins or species. Such algorithms are highly sensitive to their inputs: the sequences used and their alignments. Here, we asked whether the variance introduced by selecting different input sequences could be used to better identify accurate evolutionary models. We subsampled from available ortholog sequences and measured the distribution of observed relationships between paralogs produced across hundreds of m ...[more]
Similar Datasets
Project description:BackgroundThree-dimensional (3D) scanning is an established method of breast volume estimation. However, this method can never be entirely precise, since the thoracic wall cannot be imaged by the surface scanner. Current methods rely on interpolation of the posterior breast border from the surrounding thoracic wall. Here, we present a novel method to calculate the posterior border and increase the accuracy of the measurement.MethodsUsing principal component analysis, computed tomography images were used to build a statistical shape model (SSM) of the thoracic wall. The model was fitted to 3D images and the missing thoracic wall curvature interpolated (indirect volumetry). The calculations were evaluated by ordinary least squares regression between the preoperative and postoperative volume differences and the resection weights in breast reduction surgery (N = 36). Also, an SSM of the breast was developed, allowing direct volumetry. Magnetic-resonance images (MRI) and 3D scans were acquired from 5 patients in order to validate the direct 3D volumetry.ResultsVolumetry based on a SSM exhibited a higher determination coefficient (R2 = 0,737) than the interpolation method (R2 = 0,404). The methods were not equivalent (p = 0.75), suggesting that the methods significantly differ. There was no influence of BMI on the correlation in either method. The MRI volumetry had a strong correlation with the 3D volumetry (R2 = 0,978).ConclusionThe SSM-based method of posterior breast border calculation is reliable and superior to the currently used method of interpolation. It should serve as a basis of software applications aiming at calculation of breast volume from 3D surface scanning data.
| S-EPMC7685503 | biostudies-literature
Project description:MotivationComparing protein tertiary structures is a fundamental procedure in structural biology and protein bioinformatics. Structure comparison is important particularly for evaluating computational protein structure models. Most of the model structure evaluation methods perform rigid body superimposition of a structure model to its crystal structure and measure the difference of the corresponding residue or atom positions between them. However, these methods neglect intrinsic flexibility of proteins by treating the native structure as a rigid molecule. Because different parts of proteins have different levels of flexibility, for example, exposed loop regions are usually more flexible than the core region of a protein structure, disagreement of a model to the native needs to be evaluated differently depending on the flexibility of residues in a protein.ResultsWe propose a score named FlexScore for comparing protein structures that consider flexibility of each residue in the native state of proteins. Flexibility information may be extracted from experiments such as NMR or molecular dynamics simulation. FlexScore considers an ensemble of conformations of a protein described as a multivariate Gaussian distribution of atomic displacements and compares a query computational model with the ensemble. We compare FlexScore with other commonly used structure similarity scores over various examples. FlexScore agrees with experts' intuitive assessment of computational models and provides information of practical usefulness of models.Availability and implementationhttps://bitbucket.org/mjamroz/flexscoreContactdkihara@purdue.eduSupplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC4908346 | biostudies-literature
Project description:Major histocompatibility complex Class I (MHC-I) molecules bind to peptides derived from intracellular antigens and present them on the surface of cells, allowing the immune system (T cells) to detect them. Elucidating the process of this presentation is essential for regulation and potential manipulation of the cellular immune system. Predicting whether a given peptide binds to an MHC molecule is an important step in the above process and has motivated the introduction of many computational approaches to address this problem. NetMHCPan, a pan-specific model for predicting binding of peptides to any MHC molecule, is one of the most widely used methods which focuses on solving this binary classification problem using shallow neural networks. The recent successful results of Deep Learning (DL) methods, especially Natural Language Processing (NLP-based) pretrained models in various applications, including protein structure determination, motivated us to explore their use in this problem. Specifically, we consider the application of deep learning models pretrained on large datasets of protein sequences to predict MHC Class I-peptide binding. Using the standard performance metrics in this area, and the same training and test sets, we show that our models outperform NetMHCpan4.1, currently considered as the-state-of-the-art.
| S-EPMC10469926 | biostudies-literature
Project description:Lung abnormalities pose significant health concerns, underscoring the need for swift and accurate diagnoses to facilitate timely medical intervention. This study introduces a novel methodology for the sub-classification of lung abnormalities within chest X-rays captured via smartphones. An accurate and timely diagnosis of lung abnormalities is essential for the successful implementation of appropriate therapy. In this paper, we propose a novel approach using a Convolutional neural network (CNN) with three maximum pooling layers and early fusion for sub-classifying lung abnormalities from chest Xrays. Based on the kind of abnormality, the CheXpert dataset is divided into 13 sub-classes, each of which is trained using a different sub-model. An early fusion procedure is then used to integrate the outputs of the sub-model.•3M-CNN (Method 1): We employed a Convolutional Neural Network (CNN) with three max pooling layers and an early fusion strategy to train dedicated sub-models for each of the 13 distinct sub-classes of lung abnormalities using the CheXpert dataset.•Ensemble Model (Method 2): Our 'Ensemble model' integrated the outputs of the trained sub-models, providing a powerful approach for the sub-classification of lung abnormalities.•Exceptional Accuracy: Our '3M-CNN' and 'fused model' achieved an accuracy of 98.79%, surpassing established methodologies, which is beneficial in resource-constrained environments embracing smartphone-based imaging.
| S-EPMC10957444 | biostudies-literature
Project description:Brachypodium distachyon is a model for the temperate cereals and grasses and has a biology, genomics infrastructure and cytogenetic platform fit for purpose. It is a member of a genus with fewer than 20 species, which have different genome sizes, basic chromosome numbers and ploidy levels. The phylogeny and interspecific relationships of this group have not to date been resolved by sequence comparisons and karyotypical studies. The aims of this study are not only to reconstruct the evolution of Brachypodium karyotypes to resolve the phylogeny, but also to highlight the mechanisms that shape the evolution of grass genomes. This was achieved through the use of comparative chromosome painting (CCP) which hybridises fluorescent, chromosome-specific probes derived from B. distachyon to homoeologous meiotic chromosomes of its close relatives. The study included five diploids (B. distachyon 2n = 10, B. sylvaticum 2n = 18, B. pinnatum 2n = 16; 2n = 18, B. arbuscula 2n = 18 and B. stacei 2n = 20) three allotetraploids (B. pinnatum 2n = 28, B. phoenicoides 2n = 28 and B. hybridum 2n = 30), and two species of unknown ploidy (B. retusum 2n = 38 and B. mexicanum 2n = 40). On the basis of the patterns of hybridisation and incorporating published data, we propose two alternative, but similar, models of karyotype evolution in the genus Brachypodium. According to the first model, the extant genome of B. distachyon derives from B. mexicanum or B. stacei by several rounds of descending dysploidy, and the other diploids evolve from B. distachyon via ascending dysploidy. The allotetraploids arise by interspecific hybridisation and chromosome doubling between B. distachyon and other diploids. The second model differs from the first insofar as it incorporates an intermediate 2n = 18 species between the B. mexicanum or B. stacei progenitors and the dysploidic B. distachyon.
| S-EPMC4262448 | biostudies-literature
Project description:BackgroundThe reconstruction of gene regulatory networks from time series gene expression data is one of the most difficult problems in systems biology. This is due to several reasons, among them the combinatorial explosion of possible network topologies, limited information content of the experimental data with high levels of noise, and the complexity of gene regulation at the transcriptional, translational and post-translational levels. At the same time, quantitative, dynamic models, ideally with probability distributions over model topologies and parameters, are highly desirable.ResultsWe present a novel approach to infer such models from data, based on nonlinear differential equations, which we embed into a stochastic Bayesian framework. We thus address both the stochasticity of experimental data and the need for quantitative dynamic models. Furthermore, the Bayesian framework allows it to easily integrate prior knowledge into the inference process. Using stochastic sampling from the Bayes' posterior distribution, our approach can infer different likely network topologies and model parameters along with their respective probabilities from given data. We evaluate our approach on simulated data and the challenge #3 data from the DREAM 2 initiative. On the simulated data, we study effects of different levels of noise and dataset sizes. Results on real data show that the dynamics and main regulatory interactions are correctly reconstructed.ConclusionsOur approach combines dynamic modeling using differential equations with a stochastic learning framework, thus bridging the gap between biophysical modeling and stochastic inference approaches. Results show that the method can reap the advantages of both worlds, and allows the reconstruction of biophysically accurate dynamic models from noisy data. In addition, the stochastic learning framework used permits the computation of probability distributions over models and model parameters, which holds interesting prospects for experimental design purposes.
| S-EPMC2811124 | biostudies-literature
Project description:UnlabelledBackgroundPubChem is a free and publicly available resource containing substance descriptions and their associated biological activity information. PubChem3D is an extension to PubChem containing computationally-derived three-dimensional (3-D) structures of small molecules. All the tools and services that are a part of PubChem3D rely upon the quality of the 3-D conformer models. Construction of the conformer models currently available in PubChem3D involves a clustering stage to sample the conformational space spanned by the molecule. While this stage allows one to downsize the conformer models to more manageable size, it may result in a loss of the ability to reproduce experimentally determined "bioactive" conformations, for example, found for PDB ligands. This study examines the extent of this accuracy loss and considers its effect on the 3-D similarity analysis of molecules.ResultsThe conformer models consisting of up to 100,000 conformers per compound were generated for 47,123 small molecules whose structures were experimentally determined, and the conformers in each conformer model were clustered to reduce the size of the conformer model to a maximum of 500 conformers per molecule. The accuracy of the conformer models before and after clustering was evaluated using five different measures: root-mean-square distance (RMSD), shape-optimized shape-Tanimoto (STST-opt) and combo-Tanimoto (ComboTST-opt), and color-optimized color-Tanimoto (CTCT-opt) and combo-Tanimoto (ComboTCT-opt). On average, the effect of clustering decreased the conformer model accuracy, increasing the conformer ensemble's RMSD to the bioactive conformer (by 0.18 ± 0.12 Å), and decreasing the STST-opt, ComboTST-opt, CTCT-opt, and ComboTCT-opt scores (by 0.04 ± 0.03, 0.16 ± 0.09, 0.09 ± 0.05, and 0.15 ± 0.09, respectively).ConclusionThis study shows the RMSD accuracy performance of the PubChem3D conformer models is operating as designed. In addition, the effect of PubChem3D sampling on 3-D similarity measures shows that there is a linear degradation of average accuracy with respect to molecular size and flexibility. Generally speaking, one can likely expect the worst-case minimum accuracy of 90% or more of the PubChem3D ensembles to be 0.75, 1.09, 0.43, and 1.13, in terms of STST-opt, ComboTST-opt, CTCT-opt, and ComboTCT-opt, respectively. This expected accuracy improves linearly as the molecule becomes smaller or less flexible.
| S-EPMC3547714 | biostudies-literature
Project description:B-cell epitope prediction tools are of great medical and commercial interest due to their practical applications in vaccine development and disease diagnostics. The introduction of protein language models (LMs), trained on unprecedented large datasets of protein sequences and structures, tap into a powerful numeric representation that can be exploited to accurately predict local and global protein structural features from amino acid sequences only. In this paper, we present BepiPred-3.0, a sequence-based epitope prediction tool that, by exploiting LM embeddings, greatly improves the prediction accuracy for both linear and conformational epitope prediction on several independent test sets. Furthermore, by carefully selecting additional input variables and epitope residue annotation strategy, performance was further improved, thus achieving unprecedented predictive power. Our tool can predict epitopes across hundreds of sequences in minutes. It is freely available as a web server and a standalone package at https://services.healthtech.dtu.dk/service.php?BepiPred-3.0 with a user-friendly interface to navigate the results.
| S-EPMC9679979 | biostudies-literature
Project description:We present a new approach to semi-supervised anomaly detection. Given a set of training examples believed to come from the same distribution or class, the task is to learn a model that will be able to distinguish examples in the future that do not belong to the same class. Traditional approaches typically compare the position of a new data point to the set of "normal" training data points in a chosen representation of the feature space. For some data sets, the normal data may not have discernible positions in feature space, but do have consistent relationships among some features that fail to appear in the anomalous examples. Our approach learns to predict the values of training set features from the values of other features. After we have formed an ensemble of predictors, we apply this ensemble to new data points. To combine the contribution of each predictor in our ensemble, we have developed a novel, information-theoretic anomaly measure that our experimental results show selects against noisy and irrelevant features. Our results on 47 data sets show that for most data sets, this approach significantly improves performance over current state-of-the-art feature space distance and density-based approaches.
| S-EPMC3197694 | biostudies-literature
Project description:BackgroundProtein-protein interactions are central to cellular organization, and must have appeared at an early stage of evolution. To understand better their role, we consider a simple model of protein evolution and determine the effect of an explicit selection for Protein-protein interactions.ResultsIn the model, viable sequences all have the same fitness, following the neutral evolution theory. A very simple, two-dimensional lattice representation of the protein structures is used, and the model only considers two kinds of amino acids: hydrophobic and polar. With these approximations, exact calculations are performed. The results do not depend too strongly on these assumptions, since a model using a 3D, off-lattice representation of the proteins gives results in qualitative agreement with the 2D one. With both models, the evolutionary dynamics lead to a steady state population that is enriched in sequences that dimerize with a high affinity, well beyond the minimal level needed to survive. Correspondingly, sequences close to the viability threshold are less abundant in the steady state, being subject to a larger proportion of lethal mutations. The set of viable sequences has a "funnel" shape, consistent with earlier studies: sequences that are highly populated in the steady state are "close" to each other (with proximity being measured by the number of amino acids that differ).ConclusionThis bias in the the steady state sequences should lead to an increased resistance of the population to environmental change and an increased ability to evolve.
| S-EPMC2248192 | biostudies-literature