Lucas Benjamin, Ana Fló ... Ghislaine Dehaene-Lambertz
When exposed to sound sequences, humans compute biased transition probabilities between elements, extract the underlying network structure, and even generalize missing data.
Eric Kenji Lee, Hymavathy Balasubramanian ... Chandramouli Chandrasekaran
WaveMAP is a novel approach that combines nonlinear dimensionality reduction with graph clustering on extracellular waveforms to reveal previously obscured cell type diversity in monkey cortex.
It provides evidence for the feasibility of using combined graph convolutional neural network and transformers’ based systems with patient demographics, and CT-derived imaging features as inputs into the transformer model for survival prediction in early stage lung cancer patients.
Temporally delayed linear modelling provides a domain-general linear framework for sequence detection and statistical testing, and is able to detect replays in both human neuroimaging and animal electrophysiology.
Joshua T Vogelstein, Eric W Bridgeford ... Cencheng Shen
Multiscale Graph Correlation, an interpretable hypothesis test with strong theoretical guarantees for discerning relationships in complex data, requires about half the sample size as other methods, whilst maintaining computational tractability.
Felipe Aedo-Jury, Miriam Schwalm ... Albrecht Stroh
Distinct brain states govern resting state functional architecture revealed by neurophysiologically defined simultaneous optic-fiber-based calcium recordings and task-free functional magnetic resonance imaging (fMRI) in rats.
Convolutional neural networks and graph partitioning algorithms can be combined into an easy-to-use tool for segmentation of cells in dense plant tissue volumes imaged with light microscopy.
Fast and flexible estimation of effective migration surfaces (FEEMS) is a new statistical method that can quickly infer and visualize patterns of migration from genetic data with spatial coordinates.
A novel method for factorizing complex cellular trajectories into interpretable bifurcation processes enhances the understanding of cell fate determination through the identification of key biological determinants in scRNA-seq data.
