Learning dynamical information from static protein and sequencing data.
Ontology highlight
ABSTRACT:
SUBMITTER: Pearce P
PROVIDER: S-EPMC6879630 | biostudies-literature | 2019 Nov
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundBedside monitors in the ICU routinely measure and collect patients' physiologic data in real time to continuously assess the health status of patients who are critically ill. With the advent of increased computational power and the ability to store and rapidly process big data sets in recent years, these physiologic data show promise in identifying specific outcomes and/or events during patients' ICU hospitalization.MethodsWe introduced a methodology designed to automatically extract information from continuous-in-time vital sign data collected from bedside monitors to predict if a patient will experience a prolonged stay (length of stay) on mechanical ventilation, defined as >4 d, in a pediatric ICU.ResultsContinuous-in-time vital signs information and clinical history data were retrospectively collected for 284 ICU subjects from their first 24 h on mechanical ventilation from a medical-surgical pediatric ICU at Boston Children's Hospital. Multiple machine learning models were trained on multiple subsets of these subjects to predict the likelihood that each of these subjects would experience a long stay. We evaluated the predictive power of our models strictly on unseen hold-out validation sets of subjects. Our methodology achieved model performance of >83% (area under the curve) by using only vital sign information as input, and performances of 90% (area under the curve) by combining vital sign information with subjects' static clinical data readily available in electronic health records. We implemented this approach on 300 independently trained experiments with different choices of training and hold-out validation sets to ensure the consistency and robustness of our results in our study sample. The predictive power of our approach outperformed recent efforts that used deep learning to predict a similar task.ConclusionsOur proposed workflow may prove useful in the design of scalable approaches for real-time predictive systems in ICU environments, exploiting real-time vital sign information from bedside monitors. (ClinicalTrials.gov registration NCT02184208.).
| S-EPMC7906608 | biostudies-literature
Project description:The lowest-energy geometrical and electronic structures of Cu38 cluster are investigated by density-functional calculations combined with a genetic algorithm based on a many body semi-empirical interatomic potential, the traditional FCC-truncated Octahedron (OH) and an incomplete-Mackay icosahedron (IMI) are recognized as the two lowest energy structures (energetically degenerate isomers) but with different electronic structures: a semiconductor-type with the energy-gap of 0.356 eV for the IMI and a metallic-type with negligible gap for the OH, which is in good agreement with the experimental results. The electron affinity and ionization potential of Cu38 are also discussed and compared with the observations of the ultraviolet photoelectron spectroscopy experiments. The dynamical isomerization of the OH-like and IMI-like structures of Cu38 is revealed to dominate the pre-melting stage through the investigation by the molecular dynamics annealing simulations.
| S-EPMC6527573 | biostudies-other
Project description:This work proposes a stochastic variational deep kernel learning method for the data-driven discovery of low-dimensional dynamical models from high-dimensional noisy data. The framework is composed of an encoder that compresses high-dimensional measurements into low-dimensional state variables, and a latent dynamical model for the state variables that predicts the system evolution over time. The training of the proposed model is carried out in an unsupervised manner, i.e., not relying on labeled data. Our learning method is evaluated on the motion of a pendulum-a well studied baseline for nonlinear model identification and control with continuous states and control inputs-measured via high-dimensional noisy RGB images. Results show that the method can effectively denoise measurements, learn compact state representations and latent dynamical models, as well as identify and quantify modeling uncertainties.
| S-EPMC9747975 | biostudies-literature
Project description:Many dynamical systems, both natural and artificial, are stimulated by time dependent external signals, somehow processing the information contained therein. We demonstrate how to quantify the different modes in which information can be processed by such systems and combine them to define the computational capacity of a dynamical system. This is bounded by the number of linearly independent state variables of the dynamical system, equaling it if the system obeys the fading memory condition. It can be interpreted as the total number of linearly independent functions of its stimuli the system can compute. Our theory combines concepts from machine learning (reservoir computing), system modeling, stochastic processes, and functional analysis. We illustrate our theory by numerical simulations for the logistic map, a recurrent neural network, and a two-dimensional reaction diffusion system, uncovering universal trade-offs between the non-linearity of the computation and the system's short-term memory.
| S-EPMC3400147 | biostudies-literature
Project description:BackgroundDetermining protein-protein interactions and their binding affinity are important in understanding cellular biological processes, discovery and design of novel therapeutics, protein engineering, and mutagenesis studies. Due to the time and effort required in wet lab experiments, computational prediction of binding affinity from sequence or structure is an important area of research. Structure-based methods, though more accurate than sequence-based techniques, are limited in their applicability due to limited availability of protein structure data.ResultsIn this study, we propose a novel machine learning method for predicting binding affinity that uses protein 3D structure as privileged information at training time while expecting only protein sequence information during testing. Using the method, which is based on the framework of learning using privileged information (LUPI), we have achieved improved performance over corresponding sequence-based binding affinity prediction methods that do not have access to privileged information during training. Our experiments show that with the proposed framework which uses structure only during training, it is possible to achieve classification performance comparable to that which is obtained using structure-based features. Evaluation on an independent test set shows improved performance over the PPA-Pred2 method as well.ConclusionsThe proposed method outperforms several baseline learners and a state-of-the-art binding affinity predictor not only in cross-validation, but also on an additional validation dataset, demonstrating the utility of the LUPI framework for problems that would benefit from classification using structure-based features. The implementation of LUPI developed for this work is expected to be useful in other areas of bioinformatics as well.
| S-EPMC6238365 | biostudies-literature
Project description:CONSPECTUS: The image is not the thing. Just as a pipe rendered in an oil painting cannot be smoked, quantum mechanical coupling pathways rendered on LCDs do not convey electrons. The aim of this Account is to examine some of our recent discoveries regarding biological electron transfer (ET) and transport mechanisms that emerge when one moves beyond treacherous static views to dynamical frameworks. Studies over the last two decades introduced both atomistic detail and macromolecule dynamics to the description of biological ET. The first model to move beyond the structureless square-barrier tunneling description is the Pathway model, which predicts how protein secondary motifs and folding-induced through-bond and through-space tunneling gaps influence kinetics. Explicit electronic structure theory is applied routinely now to elucidate ET mechanisms, to capture pathway interferences, and to treat redox cofactor electronic structure effects. Importantly, structural sampling of proteins provides an understanding of how dynamics may change the mechanisms of biological ET, as ET rates are exponentially sensitive to structure. Does protein motion average out tunneling pathways? Do conformational fluctuations gate biological ET? Are transient multistate resonances produced by energy gap fluctuations? These questions are becoming accessible as the static view of biological ET recedes and dynamical viewpoints take center stage. This Account introduces ET reactions at the core of bioenergetics, summarizes our team's progress toward arriving at an atomistic-level description, examines how thermal fluctuations influence ET, presents metrics that characterize dynamical effects on ET, and discusses applications in very long (micrometer scale) bacterial nanowires. The persistence of structural effects on the ET rates in the face of thermal fluctuations is considered. Finally, the flickering resonance (FR) view of charge transfer is presented to examine how fluctuations control low-barrier transport among multiple groups in van der Waals contact. FR produces exponential distance dependence in the absence of tunneling; the exponential character emerges from the probability of matching multiple vibronically broadened electronic energies within a tolerance defined by the rms coupling among interacting groups. FR thus produces band like coherent transport on the nanometer length scale, enabled by conformational fluctuations. Taken as a whole, the emerging context for ET in dynamical biomolecules provides a robust framework to design and interpret the inner workings of bioenergetics from the molecular to the cellular scale and beyond, with applications in biomedicine, biocatalysis, and energy science.
| S-EPMC4333612 | biostudies-other
Project description:Behavior involves the ongoing interaction between an organism and its environment. One of the prevailing theories of adaptive behavior is that organisms are constantly making predictions about their future environmental stimuli. However, how they acquire that predictive information is still poorly understood. Two complementary mechanisms have been proposed: predictions are generated from an agent's internal model of the world or predictions are extracted directly from the environmental stimulus. In this work, we demonstrate that predictive information, measured using bivariate mutual information, cannot distinguish between these two kinds of systems. Furthermore, we show that predictive information cannot distinguish between organisms that are adapted to their environments and random dynamical systems exposed to the same environment. To understand the role of predictive information in adaptive behavior, we need to be able to identify where it is generated. To do this, we decompose information transfer across the different components of the organism-environment system and track the flow of information in the system over time. To validate the proposed framework, we examined it on a set of computational models of idealized agent-environment systems. Analysis of the systems revealed three key insights. First, predictive information, when sourced from the environment, can be reflected in any agent irrespective of its ability to perform a task. Second, predictive information, when sourced from the nervous system, requires special dynamics acquired during the process of adapting to the environment. Third, the magnitude of predictive information in a system can be different for the same task if the environmental structure changes.
| S-EPMC7547683 | biostudies-literature
Project description:Allele-specific expression (ASE) is the imbalance in transcription between maternal and paternal alleles at a locus and can be probed in single individuals using massively parallel DNA sequencing technology. Assessing ASE within a single sample provides a static picture of the ASE, but the magnitude of ASE for a given transcript may vary between different biological conditions in an individual. Such condition-dependent ASE could indicate a genetic variation with a functional role in the phenotypic difference. We investigated ASE through RNA-sequencing of primary white blood cells from eight human individuals before and after the controlled induction of an inflammatory response, and detected condition-dependent and static ASE at 211 and 13021 variants, respectively. We developed a method, GeneiASE, to detect genes exhibiting static or condition-dependent ASE in single individuals. GeneiASE performed consistently over a range of read depths and ASE effect sizes, and did not require phasing of variants to estimate haplotypes. We observed condition-dependent ASE related to the inflammatory response in 19 genes, and static ASE in 1389 genes. Allele-specific expression was confirmed by validation of variants through real-time quantitative RT-PCR, with RNA-seq and RT-PCR ASE effect-size correlations r = 0.67 and r = 0.94 for static and condition-dependent ASE, respectively.
| S-EPMC4758070 | biostudies-literature
Project description:In recent years, next generation sequencing (NGS) has gradually replaced microarray as the major platform in measuring gene expressions. Compared to microarray, NGS has many advantages, such as less noise and higher throughput. However, the discreteness of NGS data also challenges the existing statistical methodology. In particular, there still lacks an appropriate statistical method for reconstructing gene regulatory networks using NGS data in the literature. The existing local Poisson graphical model method is not consistent and can only infer certain local structures of the network. In this article, we propose a random effect model-based transformation to continuize NGS data and then we transform the continuized data to Gaussian via a semiparametric transformation and apply an equivalent partial correlation selection method to reconstruct gene regulatory networks. The proposed method is consistent. The numerical results indicate that the proposed method can lead to much more accurate inference of gene regulatory networks than the local Poisson graphical model and other existing methods. The proposed data-continuized transformation fills the theoretical gap for how to transform discrete data to continuous data and facilitates NGS data analysis. The proposed data-continuized transformation also makes it feasible to integrate different types of data, such as microarray and RNA-seq data, in reconstruction of gene regulatory networks.
| S-EPMC6258556 | biostudies-literature
Project description:MotivationThe automatic discovery of sparse biomarkers that are associated with an outcome of interest is a central goal of bioinformatics. In the context of high-throughput sequencing (HTS) data, and compositional data (CoDa) more generally, an important class of biomarkers are the log-ratios between the input variables. However, identifying predictive log-ratio biomarkers from HTS data is a combinatorial optimization problem, which is computationally challenging. Existing methods are slow to run and scale poorly with the dimension of the input, which has limited their application to low- and moderate-dimensional metagenomic datasets.ResultsBuilding on recent advances from the field of deep learning, we present CoDaCoRe, a novel learning algorithm that identifies sparse, interpretable and predictive log-ratio biomarkers. Our algorithm exploits a continuous relaxation to approximate the underlying combinatorial optimization problem. This relaxation can then be optimized efficiently using the modern ML toolbox, in particular, gradient descent. As a result, CoDaCoRe runs several orders of magnitude faster than competing methods, all while achieving state-of-the-art performance in terms of predictive accuracy and sparsity. We verify the outperformance of CoDaCoRe across a wide range of microbiome, metabolite and microRNA benchmark datasets, as well as a particularly high-dimensional dataset that is outright computationally intractable for existing sparse log-ratio selection methods.Availability and implementationThe CoDaCoRe package is available at https://github.com/egr95/R-codacore. Code and instructions for reproducing our results are available at https://github.com/cunningham-lab/codacore.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC8696089 | biostudies-literature