K
Kim Branson
Researcher at Vertex Pharmaceuticals
Publications - 6
Citations - 545
Kim Branson is an academic researcher from Vertex Pharmaceuticals. The author has contributed to research in topics: Computer science & Biology. The author has an hindex of 2, co-authored 2 publications receiving 479 citations.
Papers
More filters
Journal ArticleDOI
Alchemical free energy methods for drug discovery: progress and challenges
John D. Chodera,David L. Mobley,Michael R. Shirts,Dixon Richard W,Kim Branson,Vijay S. Pande +5 more
TL;DR: Many of the challenges that must be overcome for robust predictions of binding affinity to be useful in rational design are discussed and a number of promising approaches for overcoming them are suggested.
Journal ArticleDOI
Blind prediction of HIV integrase binding from the SAMPL4 challenge
David L. Mobley,David L. Mobley,Shuai Liu,Nathan M. Lim,Karisa L. Wymer,Alexander L. Perryman,Alexander L. Perryman,Stefano Forli,Nanjie Deng,Justin Su,Kim Branson,Arthur J. Olson +11 more
TL;DR: An overview of the protein-ligand binding portion of the Statistical Assessment of Modeling of Proteins and Ligands 4 (SAMPL4) challenge, which focused on predicting binding of HIV integrase inhibitors in the catalytic core domain, is given.
Posted ContentDOI
Data-Driven Modelling of Gene Expression States in Breast Cancer and their Prediction from Routine Whole Slide Images
Muhammad Dawood,Mark Eastwood,Mostafa Jahanifar,Lawrence S. Young,Asa Ben-Hur,Kim Branson,Louise Jones,Nasir M. Rajpoot,Fayyaz ul Amir Afsar Minhas +8 more
TL;DR: In this paper , a data-driven approach was used to first identify groups of genes with co-dependent expression and then predict their status from whole slide images (WSIs) using a bespoke graph neural network.
Journal ArticleDOI
Deep reinforced active learning for multi-class image classification
Emma Slade,Kim Branson +1 more
TL;DR: A new active learning framework is presented, based on deep reinforcement learning, to learn an active learning query strategy to label images based on predictions from a convolutional neural network to maximise model performance on a minimal subset from a larger pool of data.
Posted ContentDOI
Molecule-Morphology Contrastive Pretraining for Transferable Molecular Representation
TL;DR: MoCoP as discussed by the authors is a framework for learning multi-modal representation of molecular graphs and cellular morphologies, which can be used to improve quantitative structure-activity relationship (QSAR) models by introducing Molecule-Morphology Contrastive Pretraining.