Summary: Current deep learning methods often focus on modeling genome sequences of a fixed set of cell types and do not account for the interaction between multiple regulatory elements. They propose a simple yet effective approach for pre-training genome data in a multi-modal and self-supervised manner, which we call GeneBERT. They pre-train and evaluate GeneBERT model on regulatory downstream tasks across different cell types, including promoter classification, transaction factor binding sites prediction, disease risk estimation, and splicing sites prediction.
Summary: Static functional connectivity matrix is usually calculated using simple Pearson’s correlation coefficients. This is simple, but cannot represent the dynamic relations of our brain. Here, they applied self-attention to calculate the attention scores of each embedded region and temporal attention to compute the weighted sum of these dynamic functional connectivities. Using this architecture, called DICE, they were able to classify mental disorders, genders, and predict age in different big datasets.
summary : They proposed novel approach to incorporate dynamic graph computation and 2-hop neighbor nodes feature aggregation into graph convolution for brain network modeling. They used convolutional pooling strategy to readout the graph, which jointly integrates graph convolutional and readout functions. They could visualize model weights which showed interpretable connectomic patterns facilitating the understanding of brain functional abnormalities.
Summary: This is follow-up study of Video Vision Transformer. For multiscale modelling in video recognition task, they used multiview tubulets and applied cross-view attention over seperate transformer models. It is currently SOTA in kinetics600 and 5 other standard video benchmarks. It was introduced in CVPR2022. They also have official code in the scenic project.
Summary: Heterogeneity and case-control approaches to mental disorders have made it hard to link dimensions of psychopathology to abnormalities of neurodevelopment. In this study, they tried to find psychiatric biomarkers with normative modeling and machine learning using cortical volume. They showed that modeling cortical volume as deviations from normative models of neurodevelopment improved the prediction of overall psychopathology (p-factor). Also, they showed detailed group differences between MDD/ADHD and healthy groups, suggesting that the p-factor confounded case-control comparisons.
summary : They proposed BrainGNN, which is a graph neural network framework to analyze fMRI and discover neurological biomarkers. BrainGNN contains novel ROI-aware graph convolutional (Ra-GConv) layers that leverage the topological and functional information of fMRI. They applied the BrainGNN framework on two independent fMRI datasets(ASD fMRI dataset and HCP 900 subject release).
summary : This paper uses multi-modal bio-signals such as EEG, Eye data (Pupil diameter, eye gaze coordinates), and Facial data (using a depth camera) to recognize an individual’s emotions in valence and arousal. This paper suggests the multi-branch convolutional neural network (MBCNN) which shows the best accuracy among the state-of-the-art models while using multi-modal data, especially depth data.
summary : They examine the link between brain-wide gene expression and morphometric changes in individuals with MDD. They observe that the expression of MDD-associated genes spatially correlates with MSN differences.
Summary: Suicidal attempt or ideation is well known associated with various environmental factors and psychopathology. In this study, they examined whether genetic susceptibility to major psychiatric disorders is associated with suicidal behaviors. Using polygenic risk scores and suicide risk measures from ABCD KSADS data, they found that MDD and ADHD are heavily associated with suicidal risks, internalizing and externalizing respectively.
Summary: The aim of study is to examine the association between dispositional mindfulness and PFC neural activity during working memory and identify the dispositional mindfulness from AAMS (Adult and Adolescent Mindfulness Scale) that would be associated with greater working memory performance. The result showed the decreased BOLD signal in the right vlPFC related to higher Attention and Awareness score and reduced FC between right vlPFC and dmPFC related to higher Nonreactivity.