Search

Type 2 diabetes leads to premature death and reduced quality of life for 8% of Americans. Nutrition management is critical to maintaining glycemic control, yet it is difficult to achieve due to the high individual differences in glycemic response to nutrition. Anticipating glycemic impact of different meals can be challenging not only for individuals with diabetes, but also for expert diabetes educators. Personalized computational models that can accurately forecast an impact of a given meal on an individual’s blood glucose levels can serve as the engine for a new generation of decision support tools for individuals with diabetes. However, to be useful in practice, these computational engines need to generate accurate forecasts based on limited datasets consistent with typical self-monitoring practices of individuals with type 2 diabetes. This paper uses three forecasting machines: (i) data assimilation, a technique borrowed from atmospheric physics and engineering that uses Bayesian modeling to infuse data with human knowledge represented in a mechanistic model, to generate real-time, personalized, adaptable glucose forecasts; (ii) model averaging of data assimilation output; and (iii) dynamical Gaussian process model regression. The proposed data assimilation machine, the primary focus of the paper, uses a modified dual unscented Kalman filter to estimate states and parameters, personalizing the mechanistic models. Model selection is used to make a personalized model selection for the individual and their measurement characteristics. The data assimilation forecasts are empirically evaluated against actual postprandial glucose measurements captured by individuals with type 2 diabetes, and against predictions generated by experienced diabetes educators after reviewing a set of historical nutritional records and glucose measurements for the same individual. The evaluation suggests that the data assimilation forecasts compare well with specific glucose measurements and match or exceed in accuracy expert forecasts. We conclude by examining ways to present predictions as forecast-derived range quantities and evaluate the comparative advantages of these ranges. [ABSTRACT FROM AUTHOR]

The ability to produce timely and accurate flu forecasts in the United States can significantly impact public health. Augmenting forecasts with internet data has shown promise for improving forecast accuracy and timeliness in controlled settings, but results in practice are less convincing, as models augmented with internet data have not consistently outperformed models without internet data. In this paper, we perform a controlled experiment, taking into account data backfill, to improve clarity on the benefits and limitations of augmenting an already good flu forecasting model with internet-based nowcasts. Our results show that a good flu forecasting model can benefit from the augmentation of internet-based nowcasts in practice for all considered public health-relevant forecasting targets. The degree of forecast improvement due to nowcasting, however, is uneven across forecasting targets, with short-term forecasting targets seeing the largest improvements and seasonal targets such as the peak timing and intensity seeing relatively marginal improvements. The uneven forecasting improvements across targets hold even when “perfect” nowcasts are used. These findings suggest that further improvements to flu forecasting, particularly seasonal targets, will need to derive from other, non-nowcasting approaches. [ABSTRACT FROM AUTHOR]

To eliminate and eradicate gambiense human African trypanosomiasis (HAT), maximizing the effectiveness of active case finding is of key importance. The progression of the epidemic is largely influenced by the planning of these operations. This paper introduces and analyzes five models for predicting HAT prevalence in a given village based on past observed prevalence levels and past screening activities in that village. Based on the quality of prevalence level predictions in 143 villages in Kwamouth (DRC), and based on the theoretical foundation underlying the models, we consider variants of the Logistic Model—a model inspired by the SIS epidemic model—to be most suitable for predicting HAT prevalence levels. Furthermore, we demonstrate the applicability of this model to predict the effects of planning policies for screening operations. Our analysis yields an analytical expression for the screening frequency required to reach eradication (zero prevalence) and a simple approach for determining the frequency required to reach elimination within a given time frame (one case per 10000). Furthermore, the model predictions suggest that annual screening is only expected to lead to eradication if at least half of the cases are detected during the screening rounds. This paper extends knowledge on control strategies for HAT and serves as a basis for further modeling and optimization studies. [ABSTRACT FROM AUTHOR]

Emerging evidence has shown microRNAs (miRNAs) play an important role in human disease research. Identifying potential association among them is significant for the development of pathology, diagnose and therapy. However, only a tiny portion of all miRNA-disease pairs in the current datasets are experimentally validated. This prompts the development of high-precision computational methods to predict real interaction pairs. In this paper, we propose a new model of Logistic Model Tree for predicting miRNA-Disease Association (LMTRDA) by fusing multi-source information including miRNA sequences, miRNA functional similarity, disease semantic similarity, and known miRNA-disease associations. In particular, we introduce miRNA sequence information and extract its features using natural language processing technique for the first time in the miRNA-disease prediction model. In the cross-validation experiment, LMTRDA obtained 90.51% prediction accuracy with 92.55% sensitivity at the AUC of 90.54% on the HMDD V3.0 dataset. To further evaluate the performance of LMTRDA, we compared it with different classifier and feature descriptor models. In addition, we also validate the predictive ability of LMTRDA in human diseases including Breast Neoplasms, Breast Neoplasms and Lymphoma. As a result, 28, 27 and 26 out of the top 30 miRNAs associated with these diseases were verified by experiments in different kinds of case studies. These experimental results demonstrate that LMTRDA is a reliable model for predicting the association among miRNAs and diseases. [ABSTRACT FROM AUTHOR]

Robustly predicting outcome for cancer patients from gene expression is an important challenge on the road to better personalized treatment. Network-based outcome predictors (NOPs), which considers the cellular wiring diagram in the classification, hold much promise to improve performance, stability and interpretability of identified marker genes. Problematically, reports on the efficacy of NOPs are conflicting and for instance suggest that utilizing random networks performs on par to networks that describe biologically relevant interactions. In this paper we turn the prediction problem around: instead of using a given biological network in the NOP, we aim to identify the network of genes that truly improves outcome prediction. To this end, we propose SyNet, a gene network constructed ab initio from synergistic gene pairs derived from survival-labelled gene expression data. To obtain SyNet, we evaluate synergy for all 69 million pairwise combinations of genes resulting in a network that is specific to the dataset and phenotype under study and can be used to in a NOP model. We evaluated SyNet and 11 other networks on a compendium dataset of >4000 survival-labelled breast cancer samples. For this purpose, we used cross-study validation which more closely emulates real world application of these outcome predictors. We find that SyNet is the only network that truly improves performance, stability and interpretability in several existing NOPs. We show that SyNet overlaps significantly with existing gene networks, and can be confidently predicted (~85% AUC) from graph-topological descriptions of these networks, in particular the breast tissue-specific network. Due to its data-driven nature, SyNet is not biased to well-studied genes and thus facilitates post-hoc interpretation. We find that SyNet is highly enriched for known breast cancer genes and genes related to e.g. histological grade and tamoxifen resistance, suggestive of a role in determining breast cancer outcome. [ABSTRACT FROM AUTHOR]

B cells develop high affinity receptors during the course of affinity maturation, a cyclic process of mutation and selection. At the end of affinity maturation, a number of cells sharing the same ancestor (i.e. in the same “clonal family”) are released from the germinal center; their amino acid frequency profile reflects the allowed and disallowed substitutions at each position. These clonal-family-specific frequency profiles, called “substitution profiles”, are useful for studying the course of affinity maturation as well as for antibody engineering purposes. However, most often only a single sequence is recovered from each clonal family in a sequencing experiment, making it impossible to construct a clonal-family-specific substitution profile. Given the public release of many high-quality large B cell receptor datasets, one may ask whether it is possible to use such data in a prediction model for clonal-family-specific substitution profiles. In this paper, we present the method “Substitution Profiles Using Related Families” (SPURF), a penalized tensor regression framework that integrates information from a rich assemblage of datasets to predict the clonal-family-specific substitution profile for any single input sequence. Using this framework, we show that substitution profiles from similar clonal families can be leveraged together with simulated substitution profiles and germline gene sequence information to improve prediction. We fit this model on a large public dataset and validate the robustness of our approach on two external datasets. Furthermore, we provide a command-line tool in an open-source software package () implementing these ideas and providing easy prediction using our pre-fit models. [ABSTRACT FROM AUTHOR]

Shotgun metagenomic analysis of the human associated microbiome provides a rich set of microbial features for prediction and biomarker discovery in the context of human diseases and health conditions. However, the use of such high-resolution microbial features presents new challenges, and validated computational tools for learning tasks are lacking. Moreover, classification rules have scarcely been validated in independent studies, posing questions about the generality and generalization of disease-predictive models across cohorts. In this paper, we comprehensively assess approaches to metagenomics-based prediction tasks and for quantitative assessment of the strength of potential microbiome-phenotype associations. We develop a computational framework for prediction tasks using quantitative microbiome profiles, including species-level relative abundances and presence of strain-specific markers. A comprehensive meta-analysis, with particular emphasis on generalization across cohorts, was performed in a collection of 2424 publicly available metagenomic samples from eight large-scale studies. Cross-validation revealed good disease-prediction capabilities, which were in general improved by feature selection and use of strain-specific markers instead of species-level taxonomic abundance. In cross-study analysis, models transferred between studies were in some cases less accurate than models tested by within-study cross-validation. Interestingly, the addition of healthy (control) samples from other studies to training sets improved disease prediction capabilities. Some microbial species (most notably Streptococcus anginosus) seem to characterize general dysbiotic states of the microbiome rather than connections with a specific disease. Our results in modelling features of the “healthy” microbiome can be considered a first step toward defining general microbial dysbiosis. The software framework, microbiome profiles, and metadata for thousands of samples are publicly available at . [ABSTRACT FROM AUTHOR]

In pharmaceutical sciences, a crucial step of the drug discovery process is the identification of drug-target interactions. However, only a small portion of the drug-target interactions have been experimentally validated, as the experimental validation is laborious and costly. To improve the drug discovery efficiency, there is a great need for the development of accurate computational approaches that can predict potential drug-target interactions to direct the experimental verification. In this paper, we propose a novel drug-target interaction prediction algorithm, namely neighborhood regularized logistic matrix factorization (NRLMF). Specifically, the proposed NRLMF method focuses on modeling the probability that a drug would interact with a target by logistic matrix factorization, where the properties of drugs and targets are represented by drug-specific and target-specific latent vectors, respectively. Moreover, NRLMF assigns higher importance levels to positive observations (i.e., the observed interacting drug-target pairs) than negative observations (i.e., the unknown pairs). Because the positive observations are already experimentally verified, they are usually more trustworthy. Furthermore, the local structure of the drug-target interaction data has also been exploited via neighborhood regularization to achieve better prediction accuracy. We conducted extensive experiments over four benchmark datasets, and NRLMF demonstrated its effectiveness compared with five state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Genetic risk prediction is an important goal in human genetics research and precision medicine. Accurate prediction models will have great impacts on both disease prevention and early treatment strategies. Despite the identification of thousands of disease-associated genetic variants through genome wide association studies (GWAS), genetic risk prediction accuracy remains moderate for most diseases, which is largely due to the challenges in both identifying all the functionally relevant variants and accurately estimating their effect sizes in the presence of linkage disequilibrium. In this paper, we introduce AnnoPred, a principled framework that leverages diverse types of genomic and epigenomic functional annotations in genetic risk prediction for complex diseases. AnnoPred is trained using GWAS summary statistics in a Bayesian framework in which we explicitly model various functional annotations and allow for linkage disequilibrium estimated from reference genotype data. Compared with state-of-the-art risk prediction methods, AnnoPred achieves consistently improved prediction accuracy in both extensive simulations and real data. [ABSTRACT FROM AUTHOR]

Seasonal influenza is a sometimes surprisingly impactful disease, causing thousands of deaths per year along with much additional morbidity. Timely knowledge of the outbreak state is valuable for managing an effective response. The current state of the art is to gather this knowledge using in-person patient contact. While accurate, this is time-consuming and expensive. This has motivated inquiry into new approaches using internet activity traces, based on the theory that lay observations of health status lead to informative features in internet data. These approaches risk being deceived by activity traces having a coincidental, rather than informative, relationship to disease incidence; to our knowledge, this risk has not yet been quantitatively explored. We evaluated both simulated and real activity traces of varying deceptiveness for influenza incidence estimation using linear regression. We found that deceptiveness knowledge does reduce error in such estimates, that it may help automatically-selected features perform as well or better than features that require human curation, and that a semantic distance measure derived from the Wikipedia article category tree serves as a useful proxy for deceptiveness. This suggests that disease incidence estimation models should incorporate not only data about how internet features map to incidence but also additional data to estimate feature deceptiveness. By doing so, we may gain one more step along the path to accurate, reliable disease incidence estimation using internet data. This capability would improve public health by decreasing the cost and increasing the timeliness of such estimates. [ABSTRACT FROM AUTHOR]

Prediction of compounds that are active against a desired biological target is a common step in drug discovery efforts. Virtual screening methods seek some active-enriched fraction of a library for experimental testing. Where data are too scarce to train supervised learning models for compound prioritization, initial screening must provide the necessary data. Commonly, such an initial library is selected on the basis of chemical diversity by some pseudo-random process (for example, the first few plates of a larger library) or by selecting an entire smaller library. These approaches may not produce a sufficient number or diversity of actives. An alternative approach is to select an informer set of screening compounds on the basis of chemogenomic information from previous testing of compounds against a large number of targets. We compare different ways of using chemogenomic data to choose a small informer set of compounds based on previously measured bioactivity data. We develop this Informer-Based-Ranking (IBR) approach using the Published Kinase Inhibitor Sets (PKIS) as the chemogenomic data to select the informer sets. We test the informer compounds on a target that is not part of the chemogenomic data, then predict the activity of the remaining compounds based on the experimental informer data and the chemogenomic data. Through new chemical screening experiments, we demonstrate the utility of IBR strategies in a prospective test on three kinase targets not included in the PKIS. [ABSTRACT FROM AUTHOR]

Estimation of influenza-like illness (ILI) using search trends activity was intended to supplement traditional surveillance systems, and was a motivation behind the development of Google Flu Trends (GFT). However, several studies have previously reported large errors in GFT estimates of ILI in the US. Following recent release of time-stamped surveillance data, which better reflects real-time operational scenarios, we reanalyzed GFT errors. Using three data sources—GFT: an archive of weekly ILI estimates from Google Flu Trends; ILIf: fully-observed ILI rates from ILINet; and, ILIp: ILI rates available in real-time based on partial reporting—five influenza seasons were analyzed and mean square errors (MSE) of GFT and ILIp as estimates of ILIf were computed. To correct GFT errors, a random forest regression model was built with ILI and GFT rates from the previous three weeks as predictors. An overall reduction in error of 44% was observed and the errors of the corrected GFT are lower than those of ILIp. An 80% reduction in error during 2012/13, when GFT had large errors, shows that extreme failures of GFT could have been avoided. Using autoregressive integrated moving average (ARIMA) models, one- to four-week ahead forecasts were generated with two separate data streams: ILIp alone, and with both ILIp and corrected GFT. At all forecast targets and seasons, and for all but two regions, inclusion of GFT lowered MSE. Results from two alternative error measures, mean absolute error and mean absolute proportional error, were largely consistent with results from MSE. Taken together these findings provide an error profile of GFT in the US, establish strong evidence for the adoption of search trends based 'nowcasts' in influenza forecast systems, and encourage reevaluation of the utility of this data source in diverse domains. [ABSTRACT FROM AUTHOR]

Cancer is mainly caused by somatic genome alterations (SGAs). Precision oncology involves identifying and targeting tumor-specific aberrations resulting from causative SGAs. We developed a novel tumor-specific computational framework that finds the likely causative SGAs in an individual tumor and estimates their impact on oncogenic processes, which suggests the disease mechanisms that are acting in that tumor. This information can be used to guide precision oncology. We report a tumor-specific causal inference (TCI) framework, which estimates causative SGAs by modeling causal relationships between SGAs and molecular phenotypes (e.g., transcriptomic, proteomic, or metabolomic changes) within an individual tumor. We applied the TCI algorithm to tumors from The Cancer Genome Atlas (TCGA) and estimated for each tumor the SGAs that causally regulate the differentially expressed genes (DEGs) in that tumor. Overall, TCI identified 634 SGAs that are predicted to cause cancer-related DEGs in a significant number of tumors, including most of the previously known drivers and many novel candidate cancer drivers. The inferred causal relationships are statistically robust and biologically sensible, and multiple lines of experimental evidence support the predicted functional impact of both the well-known and the novel candidate drivers that are predicted by TCI. TCI provides a unified framework that integrates multiple types of SGAs and molecular phenotypes to estimate which genome perturbations are causally influencing one or more molecular/cellular phenotypes in an individual tumor. By identifying major candidate drivers and revealing their functional impact in an individual tumor, TCI sheds light on the disease mechanisms of that tumor, which can serve to advance our basic knowledge of cancer biology and to support precision oncology that provides tailored treatment of individual tumors. [ABSTRACT FROM AUTHOR]

Differentiation between phenotypically neutral and disease-causing genetic variation remains an open and relevant problem. Among different types of variation, non-frameshifting insertions and deletions (indels) represent an understudied group with widespread phenotypic consequences. To address this challenge, we present a machine learning method, MutPred-Indel, that predicts pathogenicity and identifies types of functional residues impacted by non-frameshifting insertion/deletion variation. The model shows good predictive performance as well as the ability to identify impacted structural and functional residues including secondary structure, intrinsic disorder, metal and macromolecular binding, post-translational modifications, allosteric sites, and catalytic residues. We identify structural and functional mechanisms impacted preferentially by germline variation from the Human Gene Mutation Database, recurrent somatic variation from COSMIC in the context of different cancers, as well as de novo variants from families with autism spectrum disorder. Further, the distributions of pathogenicity prediction scores generated by MutPred-Indel are shown to differentiate highly recurrent from non-recurrent somatic variation. Collectively, we present a framework to facilitate the interrogation of both pathogenicity and the functional effects of non-frameshifting insertion/deletion variants. The MutPred-Indel webserver is available at . [ABSTRACT FROM AUTHOR]

Identification of drug-target interactions (DTIs) plays a key role in drug discovery. The high cost and labor-intensive nature of in vitro and in vivo experiments have highlighted the importance of in silico-based DTI prediction approaches. In several computational models, conventional protein descriptors have been shown to not be sufficiently informative to predict accurate DTIs. Thus, in this study, we propose a deep learning based DTI prediction model capturing local residue patterns of proteins participating in DTIs. When we employ a convolutional neural network (CNN) on raw protein sequences, we perform convolution on various lengths of amino acids subsequences to capture local residue patterns of generalized protein classes. We train our model with large-scale DTI information and demonstrate the performance of the proposed model using an independent dataset that is not seen during the training phase. As a result, our model performs better than previous protein descriptor-based models. Also, our model performs better than the recently developed deep learning models for massive prediction of DTIs. By examining pooled convolution results, we confirmed that our model can detect binding sites of proteins for DTIs. In conclusion, our prediction model for detecting local residue patterns of target proteins successfully enriches the protein features of a raw protein sequence, yielding better prediction results than previous approaches. Our code is available at . [ABSTRACT FROM AUTHOR]

Drug screening studies typically involve assaying the sensitivity of a range of cancer cell lines across an array of anti-cancer therapeutics. Alongside these sensitivity measurements high dimensional molecular characterizations of the cell lines are typically available, including gene expression, copy number variation and genomic mutations. We propose a sparse multitask regression model which learns discriminative latent characteristics that predict drug sensitivity and are associated with specific molecular features. We use ideas from Bayesian nonparametrics to automatically infer the appropriate number of these latent characteristics. The resulting analysis couples high predictive performance with interpretability since each latent characteristic involves a typically small set of drugs, cell lines and genomic features. Our model uncovers a number of drug-gene sensitivity associations missed by single gene analyses. We functionally validate one such novel association: that increased expression of the cell-cycle regulator C/EBPδ decreases sensitivity to the histone deacetylase (HDAC) inhibitor panobinostat. [ABSTRACT FROM AUTHOR]

Seasonal influenza surveillance is usually carried out by sentinel general practitioners (GPs) who compile weekly reports based on the number of influenza-like illness (ILI) clinical cases observed among visited patients. This traditional practice for surveillance generally presents several issues, such as a delay of one week or more in releasing reports, population biases in the health-seeking behaviour, and the lack of a common definition of ILI case. On the other hand, the availability of novel data streams has recently led to the emergence of non-traditional approaches for disease surveillance that can alleviate these issues. In Europe, a participatory web-based surveillance system called Influenzanet represents a powerful tool for monitoring seasonal influenza epidemics thanks to aid of self-selected volunteers from the general population who monitor and report their health status through Internet-based surveys, thus allowing a real-time estimate of the level of influenza circulating in the population. In this work, we propose an unsupervised probabilistic framework that combines time series analysis of self-reported symptoms collected by the Influenzanet platforms and performs an algorithmic detection of groups of symptoms, called syndromes. The aim of this study is to show that participatory web-based surveillance systems are capable of detecting the temporal trends of influenza-like illness even without relying on a specific case definition. The methodology was applied to data collected by Influenzanet platforms over the course of six influenza seasons, from 2011-2012 to 2016-2017, with an average of 34,000 participants per season. Results show that our framework is capable of selecting temporal trends of syndromes that closely follow the ILI incidence rates reported by the traditional surveillance systems in the various countries (Pearson correlations ranging from 0.69 for Italy to 0.88 for the Netherlands, with the sole exception of Ireland with a correlation of 0.38). The proposed framework was able to forecast quite accurately the ILI trend of the forthcoming influenza season (2016-2017) based only on the available information of the previous years (2011-2016). Furthermore, to broaden the scope of our approach, we applied it both in a forecasting fashion to predict the ILI trend of the 2016-2017 influenza season (Pearson correlations ranging from 0.60 for Ireland and UK, and 0.85 for the Netherlands) and also to detect gastrointestinal syndrome in France (Pearson correlation of 0.66). The final result is a near-real-time flexible surveillance framework not constrained by any specific case definition and capable of capturing the heterogeneity in symptoms circulation during influenza epidemics in the various European countries. [ABSTRACT FROM AUTHOR]

We present CoPhosK to predict kinase-substrate associations for phosphopeptide substrates detected by mass spectrometry (MS). The tool utilizes a Naïve Bayes framework with priors of known kinase-substrate associations (KSAs) to generate its predictions. Through the mining of MS data for the collective dynamic signatures of the kinases’ substrates revealed by correlation analysis of phosphopeptide intensity data, the tool infers KSAs in the data for the considerable body of substrates lacking such annotations. We benchmarked the tool against existing approaches for predicting KSAs that rely on static information (e.g. sequences, structures and interactions) using publically available MS data, including breast, colon, and ovarian cancer models. The benchmarking reveals that co-phosphorylation analysis can significantly improve prediction performance when static information is available (about 35% of sites) while providing reliable predictions for the remainder, thus tripling the KSAs available from the experimental MS data providing to a comprehensive and reliable characterization of the landscape of kinase-substrate interactions well beyond current limitations. [ABSTRACT FROM AUTHOR]

Accurate forecasts of influenza incidence can be used to inform medical and public health decision-making and response efforts. However, forecasting systems are uncommon in most countries, with a few notable exceptions. Here we use publicly available data from the World Health Organization to generate retrospective forecasts of influenza peak timing and peak intensity for 64 countries, including 18 tropical and subtropical countries. We find that accurate and well-calibrated forecasts can be generated for countries in temperate regions, with peak timing and intensity accuracy exceeding 50% at four and two weeks prior to the predicted epidemic peak, respectively. Forecasts are significantly less accurate in the tropics and subtropics for both peak timing and intensity. This work indicates that, in temperate regions around the world, forecasts can be generated with sufficient lead time to prepare for upcoming outbreak peak incidence. [ABSTRACT FROM AUTHOR]

Real-time forecasts based on mathematical models can inform critical decision-making during infectious disease outbreaks. Yet, epidemic forecasts are rarely evaluated during or after the event, and there is little guidance on the best metrics for assessment. Here, we propose an evaluation approach that disentangles different components of forecasting ability using metrics that separately assess the calibration, sharpness and bias of forecasts. This makes it possible to assess not just how close a forecast was to reality but also how well uncertainty has been quantified. We used this approach to analyse the performance of weekly forecasts we generated in real time for Western Area, Sierra Leone, during the 2013–16 Ebola epidemic in West Africa. We investigated a range of forecast model variants based on the model fits generated at the time with a semi-mechanistic model, and found that good probabilistic calibration was achievable at short time horizons of one or two weeks ahead but model predictions were increasingly unreliable at longer forecasting horizons. This suggests that forecasts may have been of good enough quality to inform decision making based on predictions a few weeks ahead of time but not longer, reflecting the high level of uncertainty in the processes driving the trajectory of the epidemic. Comparing forecasts based on the semi-mechanistic model to simpler null models showed that the best semi-mechanistic model variant performed better than the null models with respect to probabilistic calibration, and that this would have been identified from the earliest stages of the outbreak. As forecasts become a routine part of the toolkit in public health, standards for evaluation of performance will be important for assessing quality and improving credibility of mathematical models, and for elucidating difficulties and trade-offs when aiming to make the most useful and reliable forecasts. [ABSTRACT FROM AUTHOR]

A number of machine learning-based predictors have been developed for identifying immunogenic T-cell epitopes based on major histocompatibility complex (MHC) class I and II binding affinities. Rationally selecting the most appropriate tool has been complicated by the evolving training data and machine learning methods. Despite the recent advances made in generating high-quality MHC-eluted, naturally processed ligandome, the reliability of new predictors on these epitopes has yet to be evaluated. This study reports the latest benchmarking on an extensive set of MHC-binding predictors by using newly available, untested data of both synthetic and naturally processed epitopes. 32 human leukocyte antigen (HLA) class I and 24 HLA class II alleles are included in the blind test set. Artificial neural network (ANN)-based approaches demonstrated better performance than regression-based machine learning and structural modeling. Among the 18 predictors benchmarked, ANN-based mhcflurry and nn_align perform the best for MHC class I 9-mer and class II 15-mer predictions, respectively, on binding/non-binding classification (Area Under Curves = 0.911). NetMHCpan4 also demonstrated comparable predictive power. Our customization of mhcflurry to a pan-HLA predictor has achieved similar accuracy to NetMHCpan. The overall accuracy of these methods are comparable between 9-mer and 10-mer testing data. However, the top methods deliver low correlations between the predicted versus the experimental affinities for strong MHC binders. When used on naturally processed MHC-ligands, tools that have been trained on elution data (NetMHCpan4 and MixMHCpred) shows better accuracy than pure binding affinity predictor. The variability of false prediction rate is considerable among HLA types and datasets. Finally, structure-based predictor of Rosetta FlexPepDock is less optimal compared to the machine learning approaches. With our benchmarking of MHC-binding and MHC-elution predictors using a comprehensive metrics, a unbiased view for establishing best practice of T-cell epitope predictions is presented, facilitating future development of methods in immunogenomics. [ABSTRACT FROM AUTHOR]

We have developed an easy-to-use and memory-efficient method called PhenotypeSeeker that (a) identifies phenotype-specific k-mers, (b) generates a k-mer-based statistical model for predicting a given phenotype and (c) predicts the phenotype from the sequencing data of a given bacterial isolate. The method was validated on 167 Klebsiella pneumoniae isolates (virulence), 200 Pseudomonas aeruginosa isolates (ciprofloxacin resistance) and 459 Clostridium difficile isolates (azithromycin resistance). The phenotype prediction models trained from these datasets obtained the F1-measure of 0.88 on the K. pneumoniae test set, 0.88 on the P. aeruginosa test set and 0.97 on the C. difficile test set. The F1-measures were the same for assembled sequences and raw sequencing data; however, building the model from assembled genomes is significantly faster. On these datasets, the model building on a mid-range Linux server takes approximately 3 to 5 hours per phenotype if assembled genomes are used and 10 hours per phenotype if raw sequencing data are used. The phenotype prediction from assembled genomes takes less than one second per isolate. Thus, PhenotypeSeeker should be well-suited for predicting phenotypes from large sequencing datasets. PhenotypeSeeker is implemented in Python programming language, is open-source software and is available at GitHub (). [ABSTRACT FROM AUTHOR]

Accurate and reliable forecasts of seasonal epidemics of infectious disease can assist in the design of countermeasures and increase public awareness and preparedness. This article describes two main contributions we made recently toward this goal: a novel approach to probabilistic modeling of surveillance time series based on “delta densities”, and an optimization scheme for combining output from multiple forecasting methods into an adaptively weighted ensemble. Delta densities describe the probability distribution of the change between one observation and the next, conditioned on available data; chaining together nonparametric estimates of these distributions yields a model for an entire trajectory. Corresponding distributional forecasts cover more observed events than alternatives that treat the whole season as a unit, and improve upon multiple evaluation metrics when extracting key targets of interest to public health officials. Adaptively weighted ensembles integrate the results of multiple forecasting methods, such as delta density, using weights that can change from situation to situation. We treat selection of optimal weightings across forecasting methods as a separate estimation task, and describe an estimation procedure based on optimizing cross-validation performance. We consider some details of the data generation process, including data revisions and holiday effects, both in the construction of these forecasting methods and when performing retrospective evaluation. The delta density method and an adaptively weighted ensemble of other forecasting methods each improve significantly on the next best ensemble component when applied separately, and achieve even better cross-validated performance when used in conjunction. We submitted real-time forecasts based on these contributions as part of CDC’s 2015/2016 FluSight Collaborative Comparison. Among the fourteen submissions that season, this system was ranked by CDC as the most accurate. [ABSTRACT FROM AUTHOR]

Accurate and reliable predictions of infectious disease dynamics can be valuable to public health organizations that plan interventions to decrease or prevent disease transmission. A great variety of models have been developed for this task, using different model structures, covariates, and targets for prediction. Experience has shown that the performance of these models varies; some tend to do better or worse in different seasons or at different points within a season. Ensemble methods combine multiple models to obtain a single prediction that leverages the strengths of each model. We considered a range of ensemble methods that each form a predictive density for a target of interest as a weighted sum of the predictive densities from component models. In the simplest case, equal weight is assigned to each component model; in the most complex case, the weights vary with the region, prediction target, week of the season when the predictions are made, a measure of component model uncertainty, and recent observations of disease incidence. We applied these methods to predict measures of influenza season timing and severity in the United States, both at the national and regional levels, using three component models. We trained the models on retrospective predictions from 14 seasons (1997/1998–2010/2011) and evaluated each model’s prospective, out-of-sample performance in the five subsequent influenza seasons. In this test phase, the ensemble methods showed average performance that was similar to the best of the component models, but offered more consistent performance across seasons than the component models. Ensemble methods offer the potential to deliver more reliable predictions to public health decision makers. [ABSTRACT FROM AUTHOR]

Predicting novel microRNA (miRNA)-disease associations is clinically significant due to miRNAs’ potential roles of diagnostic biomarkers and therapeutic targets for various human diseases. Previous studies have demonstrated the viability of utilizing different types of biological data to computationally infer new disease-related miRNAs. Yet researchers face the challenge of how to effectively integrate diverse datasets and make reliable predictions. In this study, we presented a computational model named Laplacian Regularized Sparse Subspace Learning for MiRNA-Disease Association prediction (LRSSLMDA), which projected miRNAs/diseases’ statistical feature profile and graph theoretical feature profile to a common subspace. It used Laplacian regularization to preserve the local structures of the training data and a L1-norm constraint to select important miRNA/disease features for prediction. The strength of dimensionality reduction enabled the model to be easily extended to much higher dimensional datasets than those exploited in this study. Experimental results showed that LRSSLMDA outperformed ten previous models: the AUC of 0.9178 in global leave-one-out cross validation (LOOCV) and the AUC of 0.8418 in local LOOCV indicated the model’s superior prediction accuracy; and the average AUC of 0.9181+/-0.0004 in 5-fold cross validation justified its accuracy and stability. In addition, three types of case studies further demonstrated its predictive power. Potential miRNAs related to Colon Neoplasms, Lymphoma, Kidney Neoplasms, Esophageal Neoplasms and Breast Neoplasms were predicted by LRSSLMDA. Respectively, 98%, 88%, 96%, 98% and 98% out of the top 50 predictions were validated by experimental evidences. Therefore, we conclude that LRSSLMDA would be a valuable computational tool for miRNA-disease association prediction. [ABSTRACT FROM AUTHOR]

Novel or rare variants in mitochondrial tRNA sequences may be observed after mitochondrial DNA analysis. Determining whether these variants are pathogenic is critical, but confirmation of the effect of a variant on mitochondrial function can be challenging. We have used available databases of benign and pathogenic variants, alignment between diverse tRNAs, structural information and comparative genomics to predict the impact of all possible single-base variants and deletions. The Mitochondrial tRNA Informatics Predictor (MitoTIP) is available through MITOMAP at . The source code for MitoTIP is available at . [ABSTRACT FROM AUTHOR]

When we perform a cognitive task, multiple brain regions are engaged. Understanding how these regions interact is a fundamental step to uncover the neural bases of behavior. Most research on the interactions between brain regions has focused on the univariate responses in the regions. However, fine grained patterns of response encode important information, as shown by multivariate pattern analysis. In the present article, we introduce and apply multivariate pattern dependence (MVPD): a technique to study the statistical dependence between brain regions in humans in terms of the multivariate relations between their patterns of responses. MVPD characterizes the responses in each brain region as trajectories in region-specific multidimensional spaces, and models the multivariate relationship between these trajectories. We applied MVPD to the posterior superior temporal sulcus (pSTS) and to the fusiform face area (FFA), using a searchlight approach to reveal interactions between these seed regions and the rest of the brain. Across two different experiments, MVPD identified significant statistical dependence not detected by standard functional connectivity. Additionally, MVPD outperformed univariate connectivity in its ability to explain independent variance in the responses of individual voxels. In the end, MVPD uncovered different connectivity profiles associated with different representational subspaces of FFA: the first principal component of FFA shows differential connectivity with occipital and parietal regions implicated in the processing of low-level properties of faces, while the second and third components show differential connectivity with anterior temporal regions implicated in the processing of invariant representations of face identity. [ABSTRACT FROM AUTHOR]

Laboratory and epidemiological evidence indicate that ambient humidity modulates the survival and transmission of influenza. Here we explore whether the inclusion of humidity forcing in mathematical models describing influenza transmission improves the accuracy of forecasts generated with those models. We generate retrospective forecasts for 95 cities over 10 seasons in the United States and assess both forecast accuracy and error. Overall, we find that humidity forcing improves forecast performance (at 1–4 lead weeks, 3.8% more peak week and 4.4% more peak intensity forecasts are accurate than with no forcing) and that forecasts generated using daily climatological humidity forcing generally outperform forecasts that utilize daily observed humidity forcing (4.4% and 2.6% respectively). These findings hold for predictions of outbreak peak intensity, peak timing, and incidence over 2- and 4-week horizons. The results indicate that use of climatological humidity forcing is warranted for current operational influenza forecast. [ABSTRACT FROM AUTHOR]

Recent research has produced a number of methods for forecasting seasonal influenza outbreaks. However, differences among the predicted outcomes of competing forecast methods can limit their use in decision-making. Here, we present a method for reconciling these differences using Bayesian model averaging. We generated retrospective forecasts of peak timing, peak incidence, and total incidence for seasonal influenza outbreaks in 48 states and 95 cities using 21 distinct forecast methods, and combined these individual forecasts to create weighted-average superensemble forecasts. We compared the relative performance of these individual and superensemble forecast methods by geographic location, timing of forecast, and influenza season. We find that, overall, the superensemble forecasts are more accurate than any individual forecast method and less prone to producing a poor forecast. Furthermore, we find that these advantages increase when the superensemble weights are stratified according to the characteristics of the forecast or geographic location. These findings indicate that different competing influenza prediction systems can be combined into a single more accurate forecast product for operational delivery in real time. [ABSTRACT FROM AUTHOR]

Due to relatively high costs and labor required for experimental profiling of the full target space of chemical compounds, various machine learning models have been proposed as cost-effective means to advance this process in terms of predicting the most potent compound-target interactions for subsequent verification. However, most of the model predictions lack direct experimental validation in the laboratory, making their practical benefits for drug discovery or repurposing applications largely unknown. Here, we therefore introduce and carefully test a systematic computational-experimental framework for the prediction and pre-clinical verification of drug-target interactions using a well-established kernel-based regression algorithm as the prediction model. To evaluate its performance, we first predicted unmeasured binding affinities in a large-scale kinase inhibitor profiling study, and then experimentally tested 100 compound-kinase pairs. The relatively high correlation of 0.77 (p < 0.0001) between the predicted and measured bioactivities supports the potential of the model for filling the experimental gaps in existing compound-target interaction maps. Further, we subjected the model to a more challenging task of predicting target interactions for such a new candidate drug compound that lacks prior binding profile information. As a specific case study, we used tivozanib, an investigational VEGF receptor inhibitor with currently unknown off-target profile. Among 7 kinases with high predicted affinity, we experimentally validated 4 new off-targets of tivozanib, namely the Src-family kinases FRK and FYN A, the non-receptor tyrosine kinase ABL1, and the serine/threonine kinase SLK. Our sub-sequent experimental validation protocol effectively avoids any possible information leakage between the training and validation data, and therefore enables rigorous model validation for practical applications. These results demonstrate that the kernel-based modeling approach offers practical benefits for probing novel insights into the mode of action of investigational compounds, and for the identification of new target selectivities for drug repurposing applications. [ABSTRACT FROM AUTHOR]

In the recent few years, an increasing number of studies have shown that microRNAs (miRNAs) play critical roles in many fundamental and important biological processes. As one of pathogenetic factors, the molecular mechanisms underlying human complex diseases still have not been completely understood from the perspective of miRNA. Predicting potential miRNA-disease associations makes important contributions to understanding the pathogenesis of diseases, developing new drugs, and formulating individualized diagnosis and treatment for diverse human complex diseases. Instead of only depending on expensive and time-consuming biological experiments, computational prediction models are effective by predicting potential miRNA-disease associations, prioritizing candidate miRNAs for the investigated diseases, and selecting those miRNAs with higher association probabilities for further experimental validation. In this study, ath-ased iRNA-isease ssociation (PBMDA) prediction model was proposed by integrating known human miRNA-disease associations, miRNA functional similarity, disease semantic similarity, and Gaussian interaction profile kernel similarity for miRNAs and diseases. This model constructed a heterogeneous graph consisting of three interlinked sub-graphs and further adopted depth-first search algorithm to infer potential miRNA-disease associations. As a result, PBMDA achieved reliable performance in the frameworks of both local and global LOOCV (AUCs of 0.8341 and 0.9169, respectively) and 5-fold cross validation (average AUC of 0.9172). In the cases studies of three important human diseases, 88% (Esophageal Neoplasms), 88% (Kidney Neoplasms) and 90% (Colon Neoplasms) of top-50 predicted miRNAs have been manually confirmed by previous experimental reports from literatures. Through the comparison performance between PBMDA and other previous models in case studies, the reliable performance also demonstrates that PBMDA could serve as a powerful computational tool to accelerate the identification of disease-miRNA associations. [ABSTRACT FROM AUTHOR]

The brain constantly infers the causes of the inputs it receives and uses these inferences to generate statistical expectations about future observations. Experimental evidence for these expectations and their violations include explicit reports, sequential effects on reaction times, and mismatch or surprise signals recorded in electrophysiology and functional MRI. Here, we explore the hypothesis that the brain acts as a near-optimal inference device that constantly attempts to infer the time-varying matrix of transition probabilities between the stimuli it receives, even when those stimuli are in fact fully unpredictable. This parsimonious Bayesian model, with a single free parameter, accounts for a broad range of findings on surprise signals, sequential effects and the perception of randomness. Notably, it explains the pervasive asymmetry between repetitions and alternations encountered in those studies. Our analysis suggests that a neural machinery for inferring transition probabilities lies at the core of human sequence knowledge. [ABSTRACT FROM AUTHOR]

Transcript levels do not faithfully predict protein levels, due to post-transcriptional regulation of gene expression mediated by RNA binding proteins (RBPs) and non-coding RNAs. We developed a multivariate linear regression model integrating RBP levels and predicted RBP-mRNA regulatory interactions from matched transcript and protein datasets. RBPs significantly improved the accuracy in predicting protein abundance of a portion of the total modeled mRNAs in three panels of tissues and cells and for different methods employed in the detection of mRNA and protein. The presence of upstream translation initiation sites (uTISs) at the mRNA 5’ untranslated regions was strongly associated with improvement in predictive accuracy. On the basis of these observations, we propose that the recently discovered widespread uTISs in the human genome can be a previously unappreciated substrate of translational control mediated by RBPs. [ABSTRACT FROM AUTHOR]

Target-based screening is one of the major approaches in drug discovery. Besides the intended target, unexpected drug off-target interactions often occur, and many of them have not been recognized and characterized. The off-target interactions can be responsible for either therapeutic or side effects. Thus, identifying the genome-wide off-targets of lead compounds or existing drugs will be critical for designing effective and safe drugs, and providing new opportunities for drug repurposing. Although many computational methods have been developed to predict drug-target interactions, they are either less accurate than the one that we are proposing here or computationally too intensive, thereby limiting their capability for large-scale off-target identification. In addition, the performances of most machine learning based algorithms have been mainly evaluated to predict off-target interactions in the same gene family for hundreds of chemicals. It is not clear how these algorithms perform in terms of detecting off-targets across gene families on a proteome scale. Here, we are presenting a fast and accurate off-target prediction method, REMAP, which is based on a dual regularized one-class collaborative filtering algorithm, to explore continuous chemical space, protein space, and their interactome on a large scale. When tested in a reliable, extensive, and cross-gene family benchmark, REMAP outperforms the state-of-the-art methods. Furthermore, REMAP is highly scalable. It can screen a dataset of 200 thousands chemicals against 20 thousands proteins within 2 hours. Using the reconstructed genome-wide target profile as the fingerprint of a chemical compound, we predicted that seven FDA-approved drugs can be repurposed as novel anti-cancer therapies. The anti-cancer activity of six of them is supported by experimental evidences. Thus, REMAP is a valuable addition to the existing in silico toolbox for drug target identification, drug repurposing, phenotypic screening, and side effect prediction. The software and benchmark are available at . [ABSTRACT FROM AUTHOR]

The activity of a biological community is the outcome of complex processes involving interactions between community members. It is often unclear how to accurately incorporate these interactions into predictive models. Previous work has shown a range of positive and negative metabolic pairwise interactions between species. Here we examine the ability of a modified general Lotka-Volterra model with cell-cell interaction coefficients to predict the overall metabolic rate of a well-mixed microbial community comprised of four heterotrophic natural isolates, experimentally quantifying the strengths of two, three, and four-species interactions. Within this community, interactions between any pair of microbial species were positive, while higher-order interactions, between 3 or more microbial species, slightly modulated community metabolism. For this simple community, the metabolic rate of can be well predicted only with taking into account pairwise interactions. Simulations using the experimentally determined interaction parameters revealed that spatial heterogeneity in the distribution of cells increased the importance of multispecies interactions in dictating function at both the local and global scales. [ABSTRACT FROM AUTHOR]

To survive, organisms must extract information from the past that is relevant for their future. How this process is expressed at the neural level remains unclear. We address this problem by developing a novel approach from first principles. We show here how to generate low-complexity representations of the past that produce optimal predictions of future events. We then illustrate this framework by studying the coding of ‘oddball’ sequences in auditory cortex. We find that for many neurons in primary auditory cortex, trial-by-trial fluctuations of neuronal responses correlate with the theoretical prediction error calculated from the short-term past of the stimulation sequence, under constraints on the complexity of the representation of this past sequence. In some neurons, the effect of prediction error accounted for more than 50% of response variability. Reliable predictions often depended on a representation of the sequence of the last ten or more stimuli, although the representation kept only few details of that sequence. [ABSTRACT FROM AUTHOR]

Recent technologies like AGO CLIP sequencing and CLASH enable direct transcriptome-wide identification of AGO binding and miRNA target sites, but the most widely used miRNA target prediction algorithms do not exploit these data. Here we use discriminative learning on AGO CLIP and CLASH interactions to train a novel miRNA target prediction model. Our method combines two SVM classifiers, one to predict miRNA-mRNA duplexes and a second to learn a binding model of AGO’s local UTR sequence preferences and positional bias in 3’UTR isoforms. The duplex SVM model enables the prediction of non-canonical target sites and more accurately resolves miRNA interactions from AGO CLIP data than previous methods. The binding model is trained using a multi-task strategy to learn context-specific and common AGO sequence preferences. The duplex and common AGO binding models together outperform existing miRNA target prediction algorithms on held-out binding data. Open source code is available at . [ABSTRACT FROM AUTHOR]

We assess how presymptomatic infection affects predictability of infectious disease epidemics. We focus on whether or not a major outbreak (i.e. an epidemic that will go on to infect a large number of individuals) can be predicted reliably soon after initial cases of disease have appeared within a population. For emerging epidemics, significant time and effort is spent recording symptomatic cases. Scientific attention has often focused on improving statistical methodologies to estimate disease transmission parameters from these data. Here we show that, even if symptomatic cases are recorded perfectly, and disease spread parameters are estimated exactly, it is impossible to estimate the probability of a major outbreak without ambiguity. Our results therefore provide an upper bound on the accuracy of forecasts of major outbreaks that are constructed using data on symptomatic cases alone. Accurate prediction of whether or not an epidemic will occur requires records of symptomatic individuals to be supplemented with data concerning the true infection status of apparently uninfected individuals. To forecast likely future behavior in the earliest stages of an emerging outbreak, it is therefore vital to develop and deploy accurate diagnostic tests that can determine whether asymptomatic individuals are actually uninfected, or instead are infected but just do not yet show detectable symptoms. [ABSTRACT FROM AUTHOR]

Systems biology offers promising approaches for identifying response-specific signatures to vaccination and assessing their predictive value. Here, we designed a modelling strategy aiming to predict the quality of late T-cell responses after vaccination from early transcriptome analysis of dendritic cells. Using standardized staining with tetramer, we first quantified antigen-specific T-cell expansion 5 to 10 days after vaccination with one of a set of 41 different vaccine vectors all expressing the same antigen. Hierarchical clustering of the responses defined sets of high and low T cell response inducers. We then compared these responses with the transcriptome of splenic dendritic cells obtained 6 hours after vaccination with the same vectors and produced a random forest model capable of predicting the quality of the later antigen-specific T-cell expansion. The model also successfully predicted vector classification as low or strong T-cell response inducers of a novel set of vaccine vectors, based on the early transcriptome results obtained from spleen dendritic cells, whole spleen and even peripheral blood mononuclear cells. Finally, our model developed with mouse datasets also accurately predicted vaccine efficacy from literature-mined human datasets. [ABSTRACT FROM AUTHOR]

The way in which single neurons transform input into output spike trains has fundamental consequences for network coding. Theories and modeling studies based on standard Integrate-and-Fire models implicitly assume that, in response to increasingly strong inputs, neurons modify their coding strategy by progressively reducing their selective sensitivity to rapid input fluctuations. Combining mathematical modeling with in vitro experiments, we demonstrate that, in L5 pyramidal neurons, the firing threshold dynamics adaptively adjust the effective timescale of somatic integration in order to preserve sensitivity to rapid signals over a broad range of input statistics. For that, a new Generalized Integrate-and-Fire model featuring nonlinear firing threshold dynamics and conductance-based adaptation is introduced that outperforms state-of-the-art neuron models in predicting the spiking activity of neurons responding to a variety of in vivo-like fluctuating currents. Our model allows for efficient parameter extraction and can be analytically mapped to a Generalized Linear Model in which both the input filter—describing somatic integration—and the spike-history filter—accounting for spike-frequency adaptation—dynamically adapt to the input statistics, as experimentally observed. Overall, our results provide new insights on the computational role of different biophysical processes known to underlie adaptive coding in single neurons and support previous theoretical findings indicating that the nonlinear dynamics of the firing threshold due to Na+-channel inactivation regulate the sensitivity to rapid input fluctuations. [ABSTRACT FROM AUTHOR]