scispace - formally typeset
N

Nicolas Coudray

Researcher at New York University

Publications -  63
Citations -  2562

Nicolas Coudray is an academic researcher from New York University. The author has contributed to research in topics: Bacterial outer membrane & Cell envelope. The author has an hindex of 13, co-authored 54 publications receiving 1490 citations. Previous affiliations of Nicolas Coudray include University of Upper Alsace & University of York.

Papers
More filters
Journal ArticleDOI

Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning.

TL;DR: A deep convolutional neural network model is trained on whole-slide images obtained from The Cancer Genome Atlas to accurately and automatically classify them into LUAD, LUSC or normal lung tissue and predicts the ten most commonly mutated genes in LUAD.
Journal ArticleDOI

Inward-facing conformation of the zinc transporter YiiP revealed by cryoelectron microscopy

TL;DR: Cryoelectron microscopy and molecular dynamics simulation of YiiP in a lipid environment were used to address the feasibility of a conformational change that involves pivoting of a transmembrane, four-helix bundle relative to the M3-M6 helix pair.
Journal ArticleDOI

Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma

TL;DR: A pipeline that integrates deep learning on histology specimens with clinical data to predict ICI response in advanced melanoma is developed that has potential for integration into clinical practice.
Journal ArticleDOI

Structural basis for the alternating access mechanism of the cation diffusion facilitator YiiP

TL;DR: The physical changes that a bacterial transporter uses to carry Zn2+ across cell membranes are deduced and dimer stability was not compromised by mutagenesis of elements in the cytoplasmic domain, suggesting that the extensive interface between membrane domains is a strong determinant of dimerization.
Journal ArticleDOI

Robust threshold estimation for images with unimodal histograms

TL;DR: The proposed technique is based on a piecewise linear regression to fit the whole descending slope of the histogram, rather than the search of some specific points, and gives a reliable estimation of the threshold.