bioRxiv Science⌕ Search

Biology subjects

Fallah, A.

Publications and source records attributed to Fallah, A..

2 recordsLinked to original sources
bioRxiv2021

Refining epileptogenic high-frequency oscillations using deep learning: a reverse engineering approach

Intracranially-recorded interictal high-frequency oscillations (HFOs) have been proposed as a promising spatial biomarker of the epileptogenic zone. However, visual verification of HFOs is time-consuming and exhibits poor inter-rater reliability. Furthermore, no method is currently available to distinguish HFOs generated from the epileptogenic zone (epileptogenic HFOs: eHFOs) from those generated from other areas (non-epileptogenic HFOs: non-eHFOs). To address these issues, we constructed a deep learning (DL)-based algorithm using HFO events from chronic intracranial electroencephalogram (iEEG) data via subdural grids from 19 children with medication-resistant neocortical epilepsy to: 1) replicate human expert annotation of artifacts and HFOs with or without spikes, and 2) discover eHFOs by designing a novel weakly supervised model (HFOs from the resected brain regions are initially labeled as eHFOs, and those from the preserved brain regions as non-eHFOs). The "purification power" of DL is then used to automatically relabel the HFOs to distill eHFOs. Using 12,958 annotated HFO events from 19 patients, the model achieved 96.3% accuracy on artifact detection (F1 score = 96.8%) and 86.5% accuracy on classifying HFOs with or without spikes (F1 score = 80.8%) using patient-wise cross-validation. Based on the DL-based algorithm trained from 84,602 HFO events from nine patients who achieved seizure-freedom after resection, the majority of such DL-discovered eHFOs were found to be HFOs with spikes (78.6%, p < 0.001). While the resection ratio of detected HFOs (number of resected HFOs/number of detected HFOs) did not correlate significantly with post-operative seizure freedom (the area under the curve [AUC]=0.76, p=0.06), the resection ratio of eHFOs positively correlated with post-operative seizure freedom (AUC=0.87, p=0.01). We discovered that the eHFOs had a higher signal intensity associated with ripple (80-250 Hz) and fast ripple (250-500 Hz) bands at the HFO onset and with a lower frequency band throughout the event time window (the inverted T-shaped), compared to non-eHFOs. We then designed perturbations on the input of the trained model for non-eHFOs to determine the models decision-making logic. The model probability significantly increased towards eHFOs by the artificial introduction of signals in the inverted T-shaped frequency bands (mean probability increase: 0.285, p < 0.001), and by the artificial insertion of spike-like signals into the time domain (mean probability increase: 0.452, p < 0.001). With this DL-based framework, we reliably replicated HFO classification tasks by human experts. Using a reverse engineering technique, we distinguished eHFOs from others and identified salient features of eHFOs that aligned with current knowledge. Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=200 SRC="FIGDIR/small/458385v1_ufig1.gif" ALT="Figure 1"> View larger version (81K): org.highwire.dtl.DTLVardef@39977dorg.highwire.dtl.DTLVardef@108b182org.highwire.dtl.DTLVardef@1bdf864org.highwire.dtl.DTLVardef@fe9e57_HPS_FORMAT_FIGEXP M_FIG C_FIG

neuroscience↗
bioRxiv2021

Human Astrocytes Exhibit Tumor Microenvironment-, Age-, and Sex-Related Transcriptomic Signatures

Astrocytes are dynamic cells with important roles in brain function and neurological disease. There are notable species differences between human astrocytes and commonly used animal models. However, changes of the molecular attributes of human astrocytes across disease states, sex, and age are largely unknown, which is a barrier in understanding human astrocyte biology and its potential involvement in neurological diseases. To better understand the properties of human astrocytes, we acutely purified astrocytes from the cerebral cortices of over 40 humans across various ages, sexes, and disease states. We performed RNA sequencing to generate transcriptomic profiles of these astrocytes and identified genes associated with these biological variables. Here, we identified a robust transcriptomic signature of human astrocytes in the tumor-surrounding microenvironment, including upregulation of proliferation processes, along with downregulation of genes involved in ionic homeostasis and synaptic function, suggesting involvement of peri-tumor astrocytes in tumor-associated neural circuit dysfunction. In aging, we also found downregulation of synaptic regulators and upregulation of markers of astrocyte reactivity, while in maturation we identified changes in ionic transport with implications for calcium signaling. In addition, we identified some of the first transcriptomic evidence of sexual dimorphism in human cortical astrocytes, which has implications for observed sex differences across many neurological disorders. Overall, genes involved in synaptic function exhibited dynamic changes in multiple conditions. This data provides powerful new insights into human astrocyte biology in several biologically relevant states, that will aid in generating novel testable hypotheses about homeostatic and reactive astrocytes in humans. Significance StatementAstrocytes are an abundant class of cells playing integral roles in the central nervous system. Astrocyte dysfunction is implicated in a variety of human neurological diseases. Yet our knowledge of astrocytes is largely based on mouse studies. Direct knowledge of human astrocyte biology remains limited. Here, we present transcriptomic profiles of human cortical astrocytes, and we identified molecular differences associated with age, sex, and disease state. We found changes suggesting involvement of peritumor astrocytes in tumor-associated neural circuit dysfunction, aging-associated decline in astrocyte-synapse interactions, ionic transport changes with brain maturation, and some of the first evidence of sexual dimorphism in human astrocytes. These data provide necessary insight into human astrocyte biology that will improve our understanding of human disease.

neuroscience↗