Gorski, B. | Search bioRxiv

bioRxiv2022

RADGENNETS: DEEP LEARNING-BASED RADIOGENOMICS MODEL FOR GENE MUTATION PREDICTION IN LUNG CANCER

AO_SCPLOWBSTRACTC_SCPLOWIn this paper, we present our methodology that can be used for predicting gene mutation in patients with non-small cell lung cancer (NSCLC). There are three major types of gene mutations that a NSCLC patients gene structure can change to: epidermal growth factor receptor (EGFR), Kirsten rat sarcoma virus (KRAS), and Anaplastic lymphoma kinase (ALK). We worked with the clinical and genomics data for each patient as well CT scans. We preprocessed all of the data and then built a novel pipeline to integrate both the image and tabular data. We built a novel pipeline that used a fusion of Convolutional Neural Networks and Dense Neural Networks. Also, using a search approach, we pick an ensemble of deep learning models to classify the separate gene mutations. These models include EfficientNets, SENet, and ResNeXt WSL, among others. Our model achieved a high area under curve (AUC) score of 94% in detecting gene mutation.

cancer biology↗

bioRxiv2021

The unique neuronal structure and neuropeptide repertoire in the ctenophore Mnemiopsis leidyi shed light on the evolution of animal nervous systems

The ctenophore nerve net represents one of the earliest evolved nervous system of animals. Due to the uncertainties of their phylogenetic placement of ctenophores and the absence of several key bilaterian neuronal genes, it has been hypothesized that their neurons have evolved independently. Whether this is indeed the case remains unclear, and thus the evolutionary history of neurons is still contentious. Here, we have characterized the neuropeptide repertoire of the ctenophore Mnemiopsis leidyi. Using the machine learning NeuroPID tool1 129 new putative neuropeptide precursors were predicted. Sixteen of them are detected in the subepithelial nerve net (SNN), aboral organ (AO) and epithelial sensory cells (ESC) of early cydippid-stage M. leidyi by in situ hybridization (ISH) and immunohistochemistry (IHC). Four of these neuropeptides increase the animals swimming velocity in a behavioral essay. The new neuropeptides were used as markers to identify neuronal cell types in single cell transcriptomic data2. To unravel the neuronal architecture, we 3D reconstructed the SNN underlying the comb plates using serial block-face scanning electron microscopy (SBF-SEM). For the first time, we confirm a more than 100 years old hypothesis about anastomoses between neurites of the same cell in ctenophores and reveal that they occur through a continuous membrane. Our findings reveal the unique neuronal structure and neuropeptide repertoire of ctenophores and are important for reconstructing the evolutionary origin of animal neurons and nervous systems.

evolutionary biology↗