Coudray, N. | Search bioRxiv

bioRxiv2018

Stalk-mediated communication in the dynein motor domain

The movement of a molecular motor protein along a cytoskeletal track requires communication between enzymatic, polymer-binding, and mechanical elements. Such communication is particularly complex and not well understood in the dynein motor, an ATPase that is comprised of a ring of six AAA domains, a large mechanical element (linker) spanning over the ring, and a microtubule-binding domain (MTBD) that is separated from the AAA ring by a ~135 [A] coiled-coil stalk. We identified mutations in the stalk that disrupt directional motion, have microtubule-independent hyperactive ATPase activity, and nucleotide-independent low affinity for microtubules. Cryo-electron microscopy structures of a mutant that uncouples ATPase activity from directional movement reveal that nucleotide-dependent conformational changes occur normally in one half of the AAA ring, but are disrupted in the other half. The large-scale linker conformational change observed in the wild-type protein is also inhibited, revealing that this conformational change is not required for ATP hydrolysis. These results demonstrate an essential role of the stalk in regulating motor activity and coupling conformational changes across the two halves of the AAA ring.

biochemistry↗

bioRxiv2017

Classification and Mutation Prediction from Non-Small Cell Lung Cancer Histopathology Images using Deep Learning

Visual analysis of histopathology slides of lung cell tissues is one of the main methods used by pathologists to assess the stage, types and sub-types of lung cancers. Adenocarcinoma and squamous cell carcinoma are two most prevalent sub-types of lung cancer, but their distinction can be challenging and time-consuming even for the expert eye. In this study, we trained a deep learning convolutional neural network (CNN) model (inception v3) on histopathology images obtained from The Cancer Genome Atlas (TCGA) to accurately classify whole-slide pathology images into adenocarcinoma, squamous cell carcinoma or normal lung tissue. Our method slightly outperforms a human pathologist, achieving better sensitivity and specificity, with [~]0.97 average Area Under the Curve (AUC) on a held-out population of whole-slide scans. Furthermore, we trained the neural network to predict the ten most commonly mutated genes in lung adenocarcinoma. We found that six of these genes - STK11, EGFR, FAT1, SETBP1, KRAS and TP53 - can be predicted from pathology images with an accuracy ranging from 0.733 to 0.856, as measured by the AUC on the held-out population. These findings suggest that deep learning models can offer both specialists and patients a fast, accurate and inexpensive detection of cancer types or gene mutations, and thus have a significant impact on cancer treatment.

cancer biology↗