Performance of an open machine learning model to classify sleep/wake from actigraphy across ∼24-hour intervals without knowledge of rest timing.

GOAL AND AIMS: Commonly used actigraphy algorithms are designed to operate within a known in-bed interval. However, in free-living scenarios this interval is often unknown. We trained and evaluated a sleep/wake classifier that operates on actigraphy over ∼24-hour intervals, without knowledge of in-bed timing. FOCUS TECHNOLOGY: Actigraphy counts from ActiWatch Spectrum devices. REFERENCE TECHNOLOGY: Sleep staging derived from polysomnography, supplemented by observation of wakefulness outside of the staged interval. Classifications from the Oakley actigraphy algorithm were additionally used as performance reference. SAMPLE: Adults, sleeping in either a home or laboratory environment. DESIGN: Machine learning was used to train and evaluate a sleep/wake classifier in a supervised learning paradigm. The classifier is a temporal convolutional network, a form of deep neural network. CORE ANALYTICS: Performance was evaluated across ∼24 hours, and additionally restricted to only in-bed intervals, both in terms of epoch-by-epoch performance, and the discrepancy of summary statistics within the intervals. ADDITIONAL ANALYTICS AND EXPLORATORY ANALYSES: Performance of the trained model applied to the Multi-Ethnic Study of Atherosclerosis dataset. CORE OUTCOMES: Over ∼24 hours, the temporal convolutional network classifier produced the same or better performance as the Oakley classifier on all measures tested. When restricting analysis to the in-bed interval, the temporal convolutional network remained favorable on several metrics. IMPORTANT SUPPLEMENTAL OUTCOMES: Performance decreased on the Multi-Ethnic Study of Atherosclerosis dataset, especially when restricting analysis to the in-bed interval. CORE CONCLUSION: A classifier using data labeled over ∼24-hour intervals allows for the continuous classification of sleep/wake without knowledge of in-bed intervals. Further development should focus on improving generalization performance.

MetaScore: A Novel Machine-Learning-Based Approach to Improve Traditional Scoring Functions for Scoring Protein-Protein Docking Conformations.

Protein-protein interactions play a ubiquitous role in biological function. Knowledge of the three-dimensional (3D) structures of the complexes they form is essential for understanding the structural basis of those interactions and how they orchestrate key cellular processes. Computational docking has become an indispensable alternative to the expensive and time-consuming experimental approaches for determining the 3D structures of protein complexes. Despite recent progress, identifying near-native models from a large set of conformations sampled by docking-the so-called scoring problem-still has considerable room for improvement. We present MetaScore, a new machine-learning-based approach to improve the scoring of docked conformations. MetaScore utilizes a random forest (RF) classifier trained to distinguish near-native from non-native conformations using their protein-protein interfacial features. The features include physicochemical properties, energy terms, interaction-propensity-based features, geometric properties, interface topology features, evolutionary conservation, and also scores produced by traditional scoring functions (SFs). MetaScore scores docked conformations by simply averaging the score produced by the RF classifier with that produced by any traditional SF. We demonstrate that (i) MetaScore consistently outperforms each of the nine traditional SFs included in this work in terms of success rate and hit rate evaluated over conformations ranked among the top 10; (ii) an ensemble method, MetaScore-Ensemble, that combines 10 variants of MetaScore obtained by combining the RF score with each of the traditional SFs outperforms each of the MetaScore variants. We conclude that the performance of traditional SFs can be improved upon by using machine learning to judiciously leverage protein-protein interfacial features and by using ensemble methods to combine multiple scoring functions.

Connected in health: Place-to-place commuting networks and COVID-19 spillovers.

Biweekly county COVID-19 data were linked with Longitudinal Employer-Household Dynamics data to analyze population risk exposures enabled by pre-pandemic, country-wide commuter networks. Results from fixed-effects, spatial, and computational statistical approaches showed that commuting network exposure to COVID-19 predicted an area's COVID-19 cases and deaths, indicating spillovers. Commuting spillovers between counties were independent from geographic contiguity, pandemic-time mobility, or social media ties. Results suggest that commuting connections form enduring social linkages with effects on health that can withstand mobility disruptions. Findings contribute to a growing relational view of health and place, with implications for neighborhood effects research and place-based policies.

Personalized Sleep Parameters Estimation from Actigraphy: A Machine Learning Approach.

BACKGROUND: The current gold standard for measuring sleep is polysomnography (PSG), but it can be obtrusive and costly. Actigraphy is a relatively low-cost and unobtrusive alternative to PSG. Of particular interest in measuring sleep from actigraphy is prediction of sleep-wake states. Current literature on prediction of sleep-wake states from actigraphy consists of methods that use population data, which we call generalized models. However, accounting for variability of sleep patterns across individuals calls for personalized models of sleep-wake states prediction that could be potentially better suited to individual-level data and yield more accurate estimation of sleep. PURPOSE: To investigate the validity of developing personalized machine learning models, trained and tested on individual-level actigraphy data, for improved prediction of sleep-wake states and reliable estimation of nightly sleep parameters. PARTICIPANTS AND METHODS: We used a dataset including 54 participants and systematically trained and tested 5 different personalized machine learning models as well as their generalized counterparts. We evaluated model performance compared to concurrent PSG through extensive machine learning experiments and statistical analyses. RESULTS: Our experiments show the superiority of personalized models over their generalized counterparts in estimating PSG-derived sleep parameters. Personalized models of regularized logistic regression, random forest, adaptive boosting, and extreme gradient boosting achieve estimates of total sleep time, wake after sleep onset, sleep efficiency, and number of awakenings that are closer to those obtained by PSG, in absolute difference, than the same estimates from their generalized counterparts. We further show that the difference between estimates of sleep parameters obtained by personalized models and those of PSG is statistically non-significant. CONCLUSION: Personalized machine learning models of sleep-wake states outperform their generalized counterparts in terms of estimating sleep parameters and are indistinguishable from PSG labeled sleep-wake states. Personalized machine learning models can be used in actigraphy studies of sleep health and potentially screening for some sleep disorders.

Partner-specific prediction of RNA-binding residues in proteins: A critical assessment.

RNA-protein interactions play essential roles in regulating gene expression. While some RNA-protein interactions are "specific", that is, the RNA-binding proteins preferentially bind to particular RNA sequence or structural motifs, others are "non-RNA specific." Deciphering the protein-RNA recognition code is essential for comprehending the functional implications of these interactions and for developing new therapies for many diseases. Because of the high cost of experimental determination of protein-RNA interfaces, there is a need for computational methods to identify RNA-binding residues in proteins. While most of the existing computational methods for predicting RNA-binding residues in RNA-binding proteins are oblivious to the characteristics of the partner RNA, there is growing interest in methods for partner-specific prediction of RNA binding sites in proteins. In this work, we assess the performance of two recently published partner-specific protein-RNA interface prediction tools, PS-PRIP, and PRIdictor, along with our own new tools. Specifically, we introduce a novel metric, RNA-specificity metric (RSM), for quantifying the RNA-specificity of the RNA binding residues predicted by such tools. Our results show that the RNA-binding residues predicted by previously published methods are oblivious to the characteristics of the putative RNA binding partner. Moreover, when evaluated using partner-agnostic metrics, RNA partner-specific methods are outperformed by the state-of-the-art partner-agnostic methods. We conjecture that either (a) the protein-RNA complexes in PDB are not representative of the protein-RNA interactions in nature, or (b) the current methods for partner-specific prediction of RNA-binding residues in proteins fail to account for the differences in RNA partner-specific versus partner-agnostic protein-RNA interactions, or both.

Sequence-Based Prediction of RNA-Binding Residues in Proteins.

Identifying individual residues in the interfaces of protein-RNA complexes is important for understanding the molecular determinants of protein-RNA recognition and has many potential applications. Recent technical advances have led to several high-throughput experimental methods for identifying partners in protein-RNA complexes, but determining RNA-binding residues in proteins is still expensive and time-consuming. This chapter focuses on available computational methods for identifying which amino acids in an RNA-binding protein participate directly in contacting RNA. Step-by-step protocols for using three different web-based servers to predict RNA-binding residues are described. In addition, currently available web servers and software tools for predicting RNA-binding sites, as well as databases that contain valuable information about known protein-RNA complexes, RNA-binding motifs in proteins, and protein-binding recognition sites in RNA are provided. We emphasize sequence-based methods that can reliably identify interfacial residues without the requirement for structural information regarding either the RNA-binding protein or its RNA partner.

In Silico Prediction of Linear B-Cell Epitopes on Proteins.

Antibody-protein interactions play a critical role in the humoral immune response. B-cells secrete antibodies, which bind antigens (e.g., cell surface proteins of pathogens). The specific parts of antigens that are recognized by antibodies are called B-cell epitopes. These epitopes can be linear, corresponding to a contiguous amino acid sequence fragment of an antigen, or conformational, in which residues critical for recognition may not be contiguous in the primary sequence, but are in close proximity within the folded protein 3D structure.Identification of B-cell epitopes in target antigens is one of the key steps in epitope-driven subunit vaccine design, immunodiagnostic tests, and antibody production. In silico bioinformatics techniques offer a promising and cost-effective approach for identifying potential B-cell epitopes in a target vaccine candidate. In this chapter, we show how to utilize online B-cell epitope prediction tools to identify linear B-cell epitopes from the primary amino acid sequence of proteins.

Predicting RNA-protein interactions using only sequence information.

BACKGROUND: RNA-protein interactions (RPIs) play important roles in a wide variety of cellular processes, ranging from transcriptional and post-transcriptional regulation of gene expression to host defense against pathogens. High throughput experiments to identify RNA-protein interactions are beginning to provide valuable information about the complexity of RNA-protein interaction networks, but are expensive and time consuming. Hence, there is a need for reliable computational methods for predicting RNA-protein interactions. RESULTS: We propose RPISeq, a family of classifiers for predicting RNA-protein interactions using only sequence information. Given the sequences of an RNA and a protein as input, RPIseq predicts whether or not the RNA-protein pair interact. The RNA sequence is encoded as a normalized vector of its ribonucleotide 4-mer composition, and the protein sequence is encoded as a normalized vector of its 3-mer composition, based on a 7-letter reduced alphabet representation. Two variants of RPISeq are presented: RPISeq-SVM, which uses a Support Vector Machine (SVM) classifier and RPISeq-RF, which uses a Random Forest classifier. On two non-redundant benchmark datasets extracted from the Protein-RNA Interface Database (PRIDB), RPISeq achieved an AUC (Area Under the Receiver Operating Characteristic (ROC) curve) of 0.96 and 0.92. On a third dataset containing only mRNA-protein interactions, the performance of RPISeq was competitive with that of a published method that requires information regarding many different features (e.g., mRNA half-life, GO annotations) of the putative RNA and protein partners. In addition, RPISeq classifiers trained using the PRIDB data correctly predicted the majority (57-99%) of non-coding RNA-protein interactions in NPInter-derived networks from E. coli, S. cerevisiae, D. melanogaster, M. musculus, and H. sapiens. CONCLUSIONS: Our experiments with RPISeq demonstrate that RNA-protein interactions can be reliably predicted using only sequence-derived information. RPISeq offers an inexpensive method for computational construction of RNA-protein interaction networks, and should provide useful insights into the function of non-coding RNAs. RPISeq is freely available as a web-based server at http://pridb.gdcb.iastate.edu/RPISeq/.

Characterization of the retinal proteome during rod photoreceptor genesis.

BACKGROUND: The process of rod photoreceptor genesis, cell fate determination and differentiation is complex and multi-factorial. Previous studies have defined a model of photoreceptor differentiation that relies on intrinsic changes within the presumptive photoreceptor cells as well as changes in surrounding tissue that are extrinsic to the cell. We have used a proteomics approach to identify proteins that are dynamically expressed in the mouse retina during rod genesis and differentiation. FINDINGS: A series of six developmental ages from E13 to P5 were used to define changes in retinal protein expression during rod photoreceptor genesis and early differentiation. Retinal proteins were separated by isoelectric focus point and molecular weight. Gels were analyzed for changes in protein spot intensity across developmental time. Protein spots that peaked in expression at E17, P0 and P5 were picked from gels for identification. There were 239 spots that were picked for identification based on their dynamic expression during the developmental period of maximal rod photoreceptor genesis and differentiation. Of the 239 spots, 60 of them were reliably identified and represented a single protein. Ten proteins were represented by multiple spots, suggesting they were post-translationally modified. Of the 42 unique dynamically expressed proteins identified, 16 had been previously reported to be associated with the developing retina. CONCLUSIONS: Our results represent the first proteomics study of the developing mouse retina that includes prenatal development. We identified 26 dynamically expressed proteins in the developing mouse retina whose expression had not been previously associated with retinal development.

Using a seed-network to query multiple large-scale gene expression datasets from the developing retina in order to identify and prioritize experimental targets.

Understanding the gene networks that orchestrate the differentiation of retinal progenitors into photoreceptors in the developing retina is important not only due to its therapeutic applications in treating retinal degeneration but also because the developing retina provides an excellent model for studying CNS development. Although several studies have profiled changes in gene expression during normal retinal development, these studies offer at best only a starting point for functional studies focused on a smaller subset of genes. The large number of genes profiled at comparatively few time points makes it extremely difficult to reliably infer gene networks from a gene expression dataset. We describe a novel approach to identify and prioritize from multiple gene expression datasets, a small subset of the genes that are likely to be good candidates for further experimental investigation. We report progress on addressing this problem using a novel approach to querying multiple large-scale expression datasets using a 'seed network' consisting of a small set of genes that are implicated by published studies in rod photoreceptor differentiation. We use the seed network to identify and sort a list of genes whose expression levels are highly correlated with those of multiple seed network genes in at least two of the five gene expression datasets. The fact that several of the genes in this list have been demonstrated, through experimental studies reported in the literature, to be important in rod photoreceptor function provides support for the utility of this approach in prioritizing experimental targets for further experimental investigation. Based on Gene Ontology and KEGG pathway annotations for the list of genes obtained in the context of other information available in the literature, we identified seven genes or groups of genes for possible inclusion in the gene network involved in differentiation of retinal progenitor cells into rod photoreceptors. Our approach to querying multiple gene expression datasets using a seed network constructed from known interactions between specific genes of interest provides a promising strategy for focusing hypothesis-driven experiments using large-scale 'omics' data.

A proteomic analysis of maize chloroplast biogenesis.

Proteomics studies to explore global patterns of protein expression in plant and green algal systems have proliferated within the past few years. Although most of these studies have involved mapping of the proteomes of various organs, tissues, cells, or organelles, comparative proteomics experiments have also led to the identification of proteins that change in abundance in various developmental or physiological contexts. Despite the growing use of proteomics in plant studies, questions of reproducibility have not generally been addressed, nor have quantitative methods been widely used, for example, to identify protein expression classes. In this report, we use the de-etiolation ("greening") of maize (Zea mays) chloroplasts as a model system to explore these questions, and we outline a reproducible protocol to identify changes in the plastid proteome that occur during the greening process using techniques of two-dimensional gel electrophoresis and mass spectrometry. We also evaluate hierarchical and nonhierarchical statistical methods to analyze the patterns of expression of 526 "high-quality," unique spots on the two-dimensional gels. We conclude that Adaptive Resonance Theory 2-a nonhierarchical, neural clustering technique that has not been previously applied to gene expression data-is a powerful technique for discriminating protein expression classes during greening. Our experiments provide a foundation for the use of proteomics in the design of experiments to address fundamental questions in plant physiology and molecular biology.