Dataset Information

A kernel machine method for detecting higher order interactions in multimodal datasets: Application to schizophrenia.

ABSTRACT:

Background

Technological advances are enabling us to collect multimodal datasets at an increasing depth and resolution while with decreasing labors. Understanding complex interactions among multimodal datasets, however, is challenging.

New method

In this study, we tested the interaction effect of multimodal datasets using a novel method called the kernel machine for detecting higher order interactions among biologically relevant multimodal data. Using a semiparametric method on a reproducing kernel Hilbert space, we formulated the proposed method as a standard mixed-effects linear model and derived a score-based variance component statistic to test higher order interactions between multimodal datasets.

Results

The method was evaluated using extensive numerical simulation and real data from the Mind Clinical Imaging Consortium with both schizophrenia patients and healthy controls. Our method identified 13-triplets that included 6 gene-derived SNPs, 10 ROIs, and 6 gene-specific DNA methylations that are correlated with the changes in hippocampal volume, suggesting that these triplets may be important for explaining schizophrenia-related neurodegeneration.

Comparison with existing method(s)

The performance of the proposed method is compared with the following methods: test based on only first and first few principal components followed by multiple regression, and full principal component analysis regression, and the sequence kernel association test.

Conclusions

With strong evidence (p-value ≤0.000001), the triplet (MAGI2, CRBLCrus1.L, FBXO28) is a significant biomarker for schizophrenia patients. This novel method can be applicable to the study of other disease processes, where multimodal data analysis is a common task.

SUBMITTER: Alam MA

PROVIDER: S-EPMC6415770 | biostudies-literature | 2018 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A kernel machine method for detecting higher order interactions in multimodal datasets: Application to schizophrenia.

Alam Md Ashad MA Lin Hui-Yi HY Deng Hong-Wen HW Calhoun Vince D VD Wang Yu-Ping YP

Journal of neuroscience methods 20180902

<h4>Background</h4>Technological advances are enabling us to collect multimodal datasets at an increasing depth and resolution while with decreasing labors. Understanding complex interactions among multimodal datasets, however, is challenging.<h4>New method</h4>In this study, we tested the interaction effect of multimodal datasets using a novel method called the kernel machine for detecting higher order interactions among biologically relevant multimodal data. Using a semiparametric method on a ...[more]

PMID: 30184473

Similar Datasets

Project description:In brain imaging, accurate alignment of cortical surfaces is fundamental to the statistical sensitivity and spatial localisation of group studies, and cortical surface-based alignment has generally been accepted to be superior to volume-based approaches at aligning cortical areas. However, human subjects have considerable variation in cortical folding, and in the location of functional areas relative to these folds. This makes alignment of cortical areas a challenging problem. The Multimodal Surface Matching (MSM) tool is a flexible, spherical registration approach that enables accurate registration of surfaces based on a variety of different features. Using MSM, we have previously shown that driving cross-subject surface alignment, using areal features, such as resting state-networks and myelin maps, improves group task fMRI statistics and map sharpness. However, the initial implementation of MSM's regularisation function did not penalize all forms of surface distortion evenly. In some cases, this allowed peak distortions to exceed neurobiologically plausible limits, unless regularisation strength was increased to a level which prevented the algorithm from fully maximizing surface alignment. Here we propose and implement a new regularisation penalty, derived from physically relevant equations of strain (deformation) energy, and demonstrate that its use leads to improved and more robust alignment of multimodal imaging data. In addition, since spherical warps incorporate projection distortions that are unavoidable when mapping from a convoluted cortical surface to the sphere, we also propose constraints that enforce smooth deformation of cortical anatomies. We test the impact of this approach for longitudinal modelling of cortical development for neonates (born between 31 and 43 weeks of post-menstrual age) and demonstrate that the proposed method increases the biological interpretability of the distortion fields and improves the statistical significance of population-based analysis relative to other spherical methods.

Project description:BackgroundEpistasis, the interaction between genetic loci where the effect of one locus is influenced by one or more other loci, plays a crucial role in the genetic architecture of complex traits. However, as the number of loci considered increases, the investigation of epistasis becomes exponentially more complex, making the selection of key features vital for effective downstream analyses. Relief-Based Algorithms (RBAs) are often employed for this purpose due to their reputation as "interaction-sensitive" algorithms and uniquely non-exhaustive approach. However, the limitations of RBAs in detecting interactions, particularly those involving multiple loci, have not been thoroughly defined. This study seeks to address this gap by evaluating the efficiency of RBAs in detecting higher-order epistatic interactions. Motivated by previous findings that suggest some RBAs may rank predictive features involved in higher-order epistasis negatively, we explore the potential of absolute value ranking of RBA feature weights as an alternative approach for capturing complex interactions. In this study, we assess the performance of ReliefF, MultiSURF, and MultiSURFstar on simulated genetic datasets that model various patterns of genotype-phenotype associations, including 2-way to 5-way genetic interactions, and compare their performance to two control methods: a random shuffle and mutual information.ResultsOur findings indicate that while RBAs effectively identify lower-order (2 to 3-way) interactions, their capability to detect higher-order interactions is significantly limited, primarily by large feature count but also by signal noise. Specifically, we observe that RBAs are successful in detecting fully penetrant 4-way XOR interactions using an absolute value ranking approach, but this is restricted to datasets with only 20 total features.ConclusionsThese results highlight the inherent limitations of current RBAs and underscore the need for the development of Relief-based approaches with enhanced detection capabilities for the investigation of epistasis, particularly in datasets with large feature counts and complex higher-order interactions.

Project description:Understanding neural mechanisms in design and creativity processes remains a challenging endeavor. To address this gap, we present two electroencephalography (EEG) datasets recorded in design and creativity experiments. We have discussed the details, similarities, differences, and corresponding cognitive tasks of the two datasets in the following sections. The design dataset (Dataset A) comprises EEG recordings of 27 participants during loosely controlled design creation experiments. Each experiment included six design problems. In each design problem, participants performed five cognitive tasks, including problem understanding, idea generation, rating idea generation, idea evaluation, and rating idea evaluation. The NASA Task Load Index was used in rating tasks. The creativity dataset (Dataset B) includes EEG signals recorded from 28 participants in creativity experiments which were based on a modified variant of the Torrance Test of Creative Thinking (TTCT-F). Participants were presented with three incomplete sketches and were asked to perform three creativity tasks for each sketch: idea generation, idea evolution, and idea evaluation. In both datasets, we structured the experiments into predefined steps, primarily to ensure participants' comfort and task clarity. This was the only control applied to the experiments. All the tasks were loosely controlled: open-ended (up to 3 min) and self-paced. 64-channel EEG signals were recorded at 500 Hz based on the international 10-10 system by the Brain Vision EEG recording system while the participants were performing their assigned tasks. EEG channels were pre-processed and finally referenced to the Cz channel to remove artifacts. EEGs were pre-processed using popular pipelines widely used in previous studies. Preprocessed EEG signals were finally segmented according to the tasks to facilitate future analyses. The EEG signals are stored in the .mat format. While the present paper mainly addresses pre-processed datasets, it also cites raw EEG recordings in the following sections. We aim to promote research and facilitate the development of experimental protocols and methodologies in design and creativity cognition by sharing these resources. There exist important points regarding the datasets which are worth mentioning. These datasets represent a novel contribution to the field, offering insights into design and creativity neurocognition. To our knowledge, publicly accessible datasets of this nature are scarce, and, to the best of our knowledge, our datasets are the first publicly available ones in design and creativity. Researchers can utilize these datasets directly or draw upon the considerations and technical insights provided to inform their studies. Furthermore, we introduce the concept of loosely controlled cognitive experiments in design and creativity cognition. These experiments strike a balance between flexibility and control, allowing participants to incubate creative ideas over extended response times while maintaining structured experimental sections. Such an approach fosters more natural data recording procedures and holds the potential to enhance the accuracy and reliability of future studies. The loosely controlled approach can be employed in future cognitive studies. This paper also conducts a comparative analysis of the two datasets, offering a holistic view of design and creativity tasks. By exploring various aspects of these cognitive processes, we provide an understanding for future researchers.

Dataset Information

A kernel machine method for detecting higher order interactions in multimodal datasets: Application to schizophrenia.

Background

New method

Results

Comparison with existing method(s)

Conclusions

Publications

A kernel machine method for detecting higher order interactions in multimodal datasets: Application to schizophrenia.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets