Carmody, T. | bioRxiv Science

bioRxiv2024

A brain-enriched circRNA blood biomarker can predict response to SSRI antidepressants

Major Depressive Disorder (MDD) is a debilitating psychiatric disorder that currently affects more than 20% of the adult US population and is a leading cause of disability worldwide. Although treatment with antidepressants, such as Selective Serotonin Reuptake Inhibitors (SSRIs), has demonstrated clinical efficacy, the inherent complexity and heterogeneity of the disease and the "trial and error" approach in choosing the most effective antidepressant treatment for each patient, allows for only a subset of patients to achieve response to the first line of treatment. Circular RNAs (circRNAs), are highly stable and brain-enriched non-coding RNAs that are mainly derived from the backsplicing and covalent joining of exons and introns of protein-coding genes. They are known to be important for brain development and function, to cross the blood-brain-barrier, and to be highly sensitive to changes in neuronal activity or activation of various neuronal receptors. Here we present evidence of a brain-enriched circRNA that is regulated by Serotonin 5-HT2A and Brain-Derived Neurotrophic Factor (BDNF) receptor activity and whose expression in the blood can predict response to SSRI treatment. We present data using circRNA-specific PCR in baseline whole blood samples from the Establishing moderators and biosignatures of antidepressant response in clinical care (EMBARC) study, showing that before treatment this circRNA is differentially expressed between future responders and non-responders to sertraline. We further show that the expression of this circRNA is upregulated following sertraline treatment and that its trajectory of change post-treatment is associated with long-term remission. Furthermore, we show that the biomarker potential of this circRNA is specific to SSRIs, and not associated with prediction of response or remission after Placebo or Bupropion treatment. Lastly, we provide evidence in animal mechanistic and neuronal culture studies, suggesting that the same circRNA is enriched in the brain and is regulated by 5-HT2A and BDNF receptor signaling. Taken together, our data identify a brain-enriched circRNA associated with known mechanisms of antidepressant response that can serve as a blood biomarker for predicting response and remission with SSRI treatment.

neuroscience↗

bioRxiv2021

The BLENDS Method for Data Augmentation of 4-Dimensional Brain Images

PurposeData augmentation improves the accuracy of deep learning models when training data is scarce by synthesizing additional samples. This work addresses the lack of validated augmentation methods specific for synthesizing anatomically realistic 4D (3D+time) images for neuroimaging, such as fMRI, by proposing a new augmentation method. Materials and MethodsThe proposed method, BLENDS, generates new nonlinear warp fields by combining intersubject coregistration maps, computed using symmetric normalization, through spatial blending. These new warp fields can be applied to existing 4D fMRI to create new augmented images. BLENDS is tested on two neuroimaging problems using de-identified datasets: 1) the prediction of antidepressant response from task-based fMRI in the EMBARC dataset (n = 163), and 2) the prediction of Parkinsons Disease symptom trajectory from baseline resting-state fMRI regional homogeneity in the PPMI dataset (n = 43). ResultsBLENDS readily generates hundreds of new fMRI from existing images, with unique anatomical variations from the source images, that significantly improve prediction performance. For antidepressant response prediction, augmenting each original image once (2x the original training data) significantly increased prediction R2 from 0.055 to 0.098 (p < 1e-6), while at 10x augmentation R2 increased to 0.103. For the prediction of Parkinsons Disease trajectory, 10x augmentation R2 increased from 0.294 to 0.548 (p < 1e-6). ConclusionAugmentation of fMRI through nonlinear transformations with BLENDS significantly improves the performance of deep learning models on clinically relevant predictive tasks. This method will help neuroimaging researchers overcome dataset size limitations and achieve more accurate predictive models.

bioengineering↗