Dataset Information

Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability.

ABSTRACT: Variation in cognitive ability arises from subtle differences in underlying neural architecture. Understanding and predicting individual variability in cognition from the differences in brain networks requires harnessing the unique variance captured by different neuroimaging modalities. Here we adopted a multi-level machine learning approach that combines diffusion, functional, and structural MRI data from the Human Connectome Project (N = 1050) to provide unitary prediction models of various cognitive abilities: global cognitive function, fluid intelligence, crystallized intelligence, impulsivity, spatial orientation, verbal episodic memory and sustained attention. Out-of-sample predictions of each cognitive score were first generated using a sparsity-constrained principal component regression on individual neuroimaging modalities. These individual predictions were then aggregated and submitted to a LASSO estimator that removed redundant variability across channels. This stacked prediction led to a significant improvement in accuracy, relative to the best single modality predictions (approximately 1% to more than 3% boost in variance explained), across a majority of the cognitive abilities tested. Further analysis found that diffusion and brain surface properties contribute the most to the predictive power. Our findings establish a lower bound to predict individual differences in cognition using multiple neuroimaging measures of brain architecture, both structural and functional, quantify the relative predictive power of the different imaging modalities, and reveal how each modality provides unique and complementary information about individual differences in cognitive function.

SUBMITTER: Rasero J

PROVIDER: S-EPMC7984650 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundGenomic prediction (GP) based on single nucleotide polymorphisms (SNP) has become a broadly used tool to increase the gain of selection in plant breeding. However, using predictors that are biologically closer to the phenotypes such as transcriptome and metabolome may increase the prediction ability in GP. The objectives of this study were to (i) assess the prediction ability for three yield-related phenotypic traits using different omic datasets as single predictors compared to a SNP array, where these omic datasets included different types of sequence variants (full-SV, deleterious-dSV, and tolerant-tSV), different types of transcriptome (expression presence/absence variation-ePAV, gene expression-GE, and transcript expression-TE) sampled from two tissues, leaf and seedling, and metabolites (M); (ii) investigate the improvement in prediction ability when combining multiple omic datasets information to predict phenotypic variation in barley breeding programs; (iii) explore the predictive performance when using SV, GE, and ePAV from simulated 3'end mRNA sequencing of different lengths as predictors.ResultsThe prediction ability from genomic best linear unbiased prediction (GBLUP) for the three traits using dSV information was higher than when using tSV, all SV information, or the SNP array. Any predictors from the transcriptome (GE, TE, as well as ePAV) and metabolome provided higher prediction abilities compared to the SNP array and SV on average across the three traits. In addition, some (di)-similarity existed between different omic datasets, and therefore provided complementary biological perspectives to phenotypic variation. Optimal combining the information of dSV, TE, ePAV, as well as metabolites into GP models could improve the prediction ability over that of the single predictors alone.ConclusionsThe use of integrated omic datasets in GP model is highly recommended. Furthermore, we evaluated a cost-effective approach generating 3'end mRNA sequencing with transcriptome data extracted from seedling without losing prediction ability in comparison to the full-length mRNA sequencing, paving the path for the use of such prediction methods in commercial breeding programs.

Project description:BACKGROUND: Genomic prediction (GP) based on single nucleotide polymorphisms (SNP) has become a broadly used tool to increase the gain of selection in plant breeding. However, using predictors that are biologically closer to the phenotypes such as transcriptome and metabolome may increase the prediction ability in GP. The objectives of this study were to (i) assess the prediction ability for three phenotypic traits using different omic datasets including sequence variants (SV), deleterious SV (dSV), tolerant SV (tSV), expression presence/absence variation (ePAV), gene expression (GE), transcript expression (TE), and metabolites (M) as single predictors in comparison to those using a SNP array; (ii) investigate the improvement in prediction ability when combining multiple omic datasets information to predict phenotypic variation in barley breeding programs; (iii) explore the relationship between genes and metabolites to unravel the metabolic pathway of the three above mentioned phenotypic traits.RESULTS: The prediction ability from genomic best linear unbiased prediction (GBLUP) for the three traits using dSV information was higher than when using tSV, all SV information, or the SNP array. Any predictors from the transcriptome (GE, TE, as well as ePAV) and metabolome provided higher prediction abilities compared to the SNP array and SV on average across the three traits. In addition, some (di)-similarity existed between different omic datasets, and therefore provided complementary biological perspectives to phenotypic variation. Optimal combining the information of dSV, TE, ePAV, as well as metabolites into GP models could improve the prediction ability over that of the single predictors alone.CONCLUSIONS: The use of integrated omic datasets in GP model is highly recommended. Furthermore, we evaluated a cost-effective approach generating 3’end mRNA sequencing with transcriptome data extracted from seedling without losing prediction ability in comparison to the full-length mRNA sequencing, paving the path for the use of such prediction methods in commercial breeding programs.

Project description:In this study, we examined the role that cognitive control and language regulation ability play in mediating readers' susceptibility to prediction error costs when reading in the native language (L1) or a second language (L2). Twenty-four English monolinguals (Experiment 1) and 28 Chinese-English bilinguals (Experiment 2) read sentences in English while their EEG was recorded. The sentences varied in the predictability of an upcoming expected word and in whether that prediction was confirmed. Monolinguals showed sensitivity to sentence contexts in which expectations were not met (i.e., when unexpected words were encountered) in the form of a late, frontally-distributed positivity, but for bilinguals this effect was more complex. For both groups, performance on the prediction task was modulated by individual differences on the AX-CPT, a measure of inhibitory control. However, the bilinguals' reading performance in the L2 was affected not only by inhibitory control, but also by their performance on an L1 verbal fluency task that indexed language regulation and production capability, related to their language dominance and immersion context. Bilinguals with better regulation of the L1 generated a larger frontal positivity in response to unexpected words in the L2, an effect that was attenuated by inhibitory control ability. In contrast, bilinguals with lower regulatory ability generated a larger, late negativity, which was also mediated by control. These findings suggest that the ability to regulate the native language when immersed in a second language environment can influence mechanisms underlying the prediction process when reading in the L2. In addition, cognitive control ability, specifically inhibitory control, appears to mediate the difficulty readers incur when predictions are disconfirmed, not only in the native language, but also for proficient bilinguals reading in the L2. We argue that the mechanisms engaged during prediction in the L1 and L2 are fundamentally the same, and that what differs for bilinguals are the additional demands imposed by their language experience and language use.

Dataset Information

Integrating across neuroimaging modalities boosts prediction accuracy of cognitive ability.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets