Dataset Information

Domain prediction with probabilistic directional context.

ABSTRACT:

Motivation

Protein domain prediction is one of the most powerful approaches for sequence-based function prediction. Although domain instances are typically predicted independently of each other, newer approaches have demonstrated improved performance by rewarding domain pairs that frequently co-occur within sequences. However, most of these approaches have ignored the order in which domains preferentially co-occur and have also not modeled domain co-occurrence probabilistically.

Results

We introduce a probabilistic approach for domain prediction that models 'directional' domain context. Our method is the first to score all domain pairs within a sequence while taking their order into account, even for non-sequential domains. We show that our approach extends a previous Markov model-based approach to additionally score all pairwise terms, and that it can be interpreted within the context of Markov random fields. We formulate our underlying combinatorial optimization problem as an integer linear program, and demonstrate that it can be solved quickly in practice. Finally, we perform extensive evaluation of domain context methods and demonstrate that incorporating context increases the number of domain predictions by ?15%, with our approach dPUC2 (Domain Prediction Using Context) outperforming all competing approaches.

Availability and implementation

dPUC2 is available at http://github.com/alexviiia/dpuc2.

Contact

mona@cs.princeton.edu.

Supplementary information

Supplementary data are available at Bioinformatics online.

SUBMITTER: Ochoa A

PROVIDER: S-EPMC5870623 | biostudies-literature | 2017 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Domain prediction with probabilistic directional context.

Ochoa Alejandro A Singh Mona M

Bioinformatics (Oxford, England) 20170801 16

<h4>Motivation</h4>Protein domain prediction is one of the most powerful approaches for sequence-based function prediction. Although domain instances are typically predicted independently of each other, newer approaches have demonstrated improved performance by rewarding domain pairs that frequently co-occur within sequences. However, most of these approaches have ignored the order in which domains preferentially co-occur and have also not modeled domain co-occurrence probabilistically.<h4>Resul ...[more]

PMID: 28407137

Similar Datasets

Project description:In predicting hierarchical protein function annotations, such as terms in the Gene Ontology (GO), the simplest approach makes predictions for each term independently. However, this approach has the unfortunate consequence that the predictor may assign to a single protein a set of terms that are inconsistent with one another; for example, the predictor may assign a specific GO term to a given protein ('purine nucleotide binding') but not assign the parent term ('nucleotide binding'). Such predictions are difficult to interpret. In this work, we focus on methods for calibrating and combining independent predictions to obtain a set of probabilistic predictions that are consistent with the topology of the ontology. We call this procedure 'reconciliation'. We begin with a baseline method for predicting GO terms from a collection of data types using an ensemble of discriminative classifiers. We apply the method to a previously described benchmark data set, and we demonstrate that the resulting predictions are frequently inconsistent with the topology of the GO. We then consider 11 distinct reconciliation methods: three heuristic methods; four variants of a Bayesian network; an extension of logistic regression to the structured case; and three novel projection methods - isotonic regression and two variants of a Kullback-Leibler projection method. We evaluate each method in three different modes - per term, per protein and joint - corresponding to three types of prediction tasks. Although the principal goal of reconciliation is interpretability, it is important to assess whether interpretability comes at a cost in terms of precision and recall. Indeed, we find that many apparently reasonable reconciliation methods yield reconciled probabilities with significantly lower precision than the original, unreconciled estimates. On the other hand, we find that isotonic regression usually performs better than the underlying, unreconciled method, and almost never performs worse; isotonic regression appears to be able to use the constraints from the GO network to its advantage. An exception to this rule is the high precision regime for joint evaluation, where Kullback-Leibler projection yields the best performance.

Project description:Predicting future reward is paramount to performing an optimal action. Although a number of brain areas are known to encode such predictions, a detailed account of how the associated representations evolve over time is lacking. Here, we address this question using human magnetoencephalography (MEG) and multivariate analyses of instantaneous activity in reconstructed sources. We overtrained participants on a simple instrumental reward learning task where geometric cues predicted a distribution of possible rewards, from which a sample was revealed 2000 ms later. We show that predicted mean reward (i.e., expected value), and predicted reward variability (i.e., economic risk), are encoded distinctly. Early on, representations of mean reward are seen in parietal and visual areas, and later in frontal regions with orbitofrontal cortex emerging last. Strikingly, an encoding of reward variability emerges simultaneously in parietal/sensory and frontal sources and later than mean reward encoding. An orbitofrontal variability encoding emerged around the same time as that seen for mean reward. Crucially, cross-prediction showed that mean reward and variability representations are distinct and also revealed that instantaneous representations become more stable over time. Across sources, the best fitting metric for variability signals was coefficient of variation (rather than SD or variance), but distinct best metrics were seen for individual brain regions. Our data demonstrate how a dynamic encoding of probabilistic reward prediction unfolds in the brain both in time and space.SIGNIFICANCE STATEMENT Predicting future reward is paramount to optimal behavior. To gain insight into the underlying neural computations, we investigate how reward representations in the brain arise over time. Using magnetoencephalography, we show that a representation of predicted mean reward emerges early in parietal/sensory regions and later in frontal cortex. In contrast, predicted reward variability representations appear in most regions at the same time, and slightly later than for mean reward. For both features, representations dynamically change >1000 ms before stabilizing. The best metric for encoding variability is coefficient of variation, with heterogeneity in this encoding seen between brain areas. The results provide novel insights into the emergence of predictive reward representations.

Project description:One of the most important sources of predictability that human beings can exploit to create an internal representation of the external environment is the ability to implicitly build up subjective statistics of events' temporal structure and, consequently, use this knowledge to prepare for future actions. Stimulus expectancy can be subjectively shaped by hierarchically nested sources of prediction, capitalizing on either local or global probabilistic rules. In order to better understand the nature of local-global proactive motor control in Down Syndrome, in the present study a group of participants with Down Syndrome (DS group; n = 28; mean age 29.5 ± 13 years; range 10-54) and a group of typically developing participants matched by either gender or mental age (TD-MA group; n = 28; 5.6 ± 1 years; range 4-8) were administered a novel motor preparation task, defined as the Dynamic Temporal Prediction (DTP) task. In the DTP, the temporal preparation to imperative stimuli is implicitly shaped by the local increase of expectancy. This is manipulated trial-by-trial as a function of the preparatory foreperiod interval (Stimulus-Onset Asynchrony or SOA). In addition, temporal preparation can be also implicitly adjusted as a function of global predictive context, so that a block-wise SOA-distribution bias toward a given preparatory interval might determine a high-order source of expectancy, with functional consequences on proactive motor control adjustment. Results showed that in both groups motor preparation was biased by temporal expectancy when this was locally manipulated within-trials. By contrast, only the TD-MA group was sensitive to global rule changes: only in this cohort was behavioral performance overall impacted by the SOA probabilistic distribution manipulated between-blocks. The evidence of a local-global dissociation in DS suggests that the use of flexible cognitive mechanisms to implicitly extract high-order probabilistic rules in order to build-up an internal model of the temporal properties of events is disrupted in this developmental disorder. Moreover, since the content of the information to be processed in the DTP task was neither verbal nor spatial, we suggest that atypical global processing in Down Syndrome is a domain-general rather than specific aspect characterizing the cognitive profile of this population.

Dataset Information

Domain prediction with probabilistic directional context.

Motivation

Results

Availability and implementation

Contact

Supplementary information

Publications

Domain prediction with probabilistic directional context.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets