Sarraf, S. | Search bioRxiv

bioRxiv2022

NAK associated protein 1 is required to activate Tank binding kinase 1 to regulate mitosis

Subcellular location and activation of Tank Binding Kinase 1 (TBK1) govern precise progression through mitosis. Either loss of activated TBK1 or its sequestration from the centrosomes causes error in mitosis and growth defects. Yet, what regulates its recruitment and activation on the centrosomes is unknown. We identified that NAK Associated Protein 1 (NAP1) is essential for mitosis which binds to TBK1 on the centrosomes to activate it. Loss of NAP1 causes several mitotic and cytokinetic defects due to inactivation of TBK1. Our quantitative phosphoproteomics identified numerous TBK1 substrates that are not only confined to the centrosomes but also are associated with microtubules. Substrate motifs analysis indicates that TBK1 acts upstream of other essential cell cycle kinases like Aurora and PAK kinases. We also identified NAP1 as a TBK1 substrate at S318 promoting its degradation by ubiquitin proteasomal system acting as a negative regulatory step. These data uncover an important distinct function for the NAP1-TBK1 complex during cell division.

cell biology↗

bioRxiv2021

OViTAD: Optimized Vision Transformer to Predict Various Stages of Alzheimer's Disease Using Resting-State fMRI and Structural MRI Data

Advances in applied machine learning techniques for neuroimaging have encouraged scientists to implement models to diagnose brain disorders such as Alzheimers disease at early stages. Predicting the exact stage of Alzheimers disease is challenging; however, complex deep learning techniques can manage this with precision. While successful, these complex architectures are difficult to interrogate and computationally expensive. Therefore, using novel, simpler architectures with more efficient pattern extraction capabilities, such as transformers, is of interest to neuroscientists. This study introduced an optimized vision transformer architecture to predict the group membership by separating healthy adults, mild cognitive impairment, and Alzheimers brains within the same age group (>75 years) using resting-state functional (rs-fMRI) and structural magnetic resonance imaging (sMRI) data. Our optimized architecture known as OViTAD is currently the sole vision transformer-based end-to-end pipeline and outperformed the existing transformer models and most state-of-the-art solutions. Our model achieved F1-scores of 97%{+/-}0.0 and 99.55%{+/-}0.39 from the testing sets for the rs-fMRI and sMRI modalities in the triple-class prediction experiments. Furthermore, our model reached these performances using 30% fewer parameters than a vanilla transformer. The model was robust and repeatable, producing similar estimates across three runs (we reported the averaged evaluation metrics). Finally, to challenge the model, we observed how it handled increasing noise levels by inserting varying numbers of healthy brains into the two dementia groups. Our findings suggest that optimized vision transformers are a promising and exciting new approach for neuroimaging applications, especially for Alzheimers disease prediction.

neuroscience↗