John Bradshaw
YOU?
Author Swipe
View article: Challenging Reaction Prediction Models to Generalize to Novel Chemistry
Challenging Reaction Prediction Models to Generalize to Novel Chemistry Open
Deep learning models for anticipating the products of organic reactions have found many use cases, including validating retrosynthetic pathways and constraining synthesis-based molecular design tools. Despite compelling performance on popu…
View article: Reproducing Reaction Mechanisms with Machine‐Learning Models Trained on a Large‐Scale Mechanistic Dataset
Reproducing Reaction Mechanisms with Machine‐Learning Models Trained on a Large‐Scale Mechanistic Dataset Open
Mechanistic understanding of organic reactions can facilitate reaction development, impurity prediction, and in principle, reaction discovery. While several machine learning models have sought to address the task of predicting reaction pro…
View article: Reproducing Reaction Mechanisms with Machine‐Learning Models Trained on a Large‐Scale Mechanistic Dataset
Reproducing Reaction Mechanisms with Machine‐Learning Models Trained on a Large‐Scale Mechanistic Dataset Open
Mechanistic understanding of organic reactions can facilitate reaction development, impurity prediction, and in principle, reaction discovery. While several machine learning models have sought to address the task of predicting reaction pro…
View article: Beyond Major Product Prediction: Reproducing Reaction Mechanisms with Machine Learning Models Trained on a Large-Scale Mechanistic Dataset
Beyond Major Product Prediction: Reproducing Reaction Mechanisms with Machine Learning Models Trained on a Large-Scale Mechanistic Dataset Open
Mechanistic understanding of organic reactions can facilitate reaction development, impurity prediction, and in principle, reaction discovery. While several machine learning models have sought to address the task of predicting reaction pro…
View article: Machine Learning Methods for Modeling Synthesizable Molecules
Machine Learning Methods for Modeling Synthesizable Molecules Open
The search for new molecules often involves cycles of design-make-test-analyze steps, where new molecules are designed, synthesized in a lab, tested, and then analyzed to inform what is to be designed next. This thesis proposes new machine…
View article: Barking up the right tree: an approach to search over molecule synthesis DAGs
Barking up the right tree: an approach to search over molecule synthesis DAGs Open
When designing new molecules with particular properties, it is not only important what to make but crucially how to make it. These instructions form a synthesis directed acyclic graph (DAG), describing how a large vocabulary of simple buil…
View article: Barking up the right tree: an approach to search over molecule synthesis DAGs
Barking up the right tree: an approach to search over molecule synthesis DAGs Open
When designing new molecules with particular properties, it is not only important what to make but crucially how to make it. These instructions form a synthesis directed acyclic graph (DAG), describing how a large vocabulary of simple buil…
View article: Communication
Communication Open
Introduction: When a caregiver is fully present with a person with intellectual disability, it leads to a rich relationship of greater understanding. The purpose of this research was to gain a better understanding of Presence through an ex…
View article: A Model to Search for Synthesizable Molecules
A Model to Search for Synthesizable Molecules Open
Deep generative models are able to suggest new organic molecules by generating strings, trees, and graphs representing their structure. While such models allow one to generate molecules with desirable properties, they give no guarantees th…
View article: The role of G-quadruplex structures of LIGS-generated aptamers R1.2 and R1.3 in IgM specific recognition
The role of G-quadruplex structures of LIGS-generated aptamers R1.2 and R1.3 in IgM specific recognition Open
View article: A generative model for electron paths
A generative model for electron paths Open
Chemical reactions can be described as the stepwise redistribution of electrons in molecules. As such, reactions are often depicted using “arrow-pushing” diagrams which show this movement as a sequence of arrows. We propose an electron pat…
View article: Predicting Electron Paths.
Predicting Electron Paths. Open
Chemical reactions can be described as the stepwise redistribution of electrons in molecules. As such, reactions are often depicted using arrow-pushing diagrams which show this movement as a sequence of arrows. We propose an electron path …
View article: Are Generative Classifiers More Robust to Adversarial Attacks
Are Generative Classifiers More Robust to Adversarial Attacks Open
View article: Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks Open
Deep neural networks (DNNs) have excellent representative power and are state of the art classifiers on many tasks. However, they often do not capture their own uncertainties well making them less robust in the real world as they overconfi…