scispace - formally typeset
T

Timothy Hopper

Researcher at Amgen

Publications -  5
Citations -  1138

Timothy Hopper is an academic researcher from Amgen. The author has contributed to research in topics: Graph (abstract data type) & Artificial neural network. The author has an hindex of 5, co-authored 5 publications receiving 456 citations.

Papers
More filters
Journal ArticleDOI

Analyzing Learned Molecular Representations for Property Prediction.

TL;DR: In this article, a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary data sets is presented.
Posted Content

Analyzing Learned Molecular Representations for Property Prediction

TL;DR: A graph convolutional model is introduced that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary data sets.
Journal ArticleDOI

Correction to Analyzing Learned Molecular Representations for Property Prediction.

TL;DR: Property Prediction Kevin Yang,*, Kyle Swanson,*,† Wengong Jin,† Connor Coley,‡ Philipp Eiden, Hua Gao, Angel Guzman-Perez, Timothy Hopper, Brian Kelley, Miriam Mathea, Andrew Palmer, Volker Settels, Tommi Jaakkola and Regina Barzilay.
Posted Content

Are Learned Molecular Representations Ready For Prime Time

TL;DR: A graph convolutional model is introduced that consistently outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets.
Posted ContentDOI

Are Learned Molecular Representations Ready for Prime Time

TL;DR: In this article, a graph convolutional neural network (GCNN) was proposed for molecular property prediction in industrial workflows and compared with existing graph neural network architectures on both public and proprietary datasets.