User profiles for Fergus Imrie
Fergus ImrieUniversity of California, Los Angeles Verified email at ucla.edu Cited by 633 |
Protein family-specific models using deep neural networks and transfer learning improve virtual screening and highlight the need for more data
Machine learning has shown enormous potential for computer-aided drug discovery. Here
we show how modern convolutional neural networks (CNNs) can be applied to structure-…
we show how modern convolutional neural networks (CNNs) can be applied to structure-…
Deep generative models for 3D linker design
Rational compound design remains a challenging problem for both computational methods
and medicinal chemists. Computational generative methods have begun to show promising …
and medicinal chemists. Computational generative methods have begun to show promising …
[HTML][HTML] Deep generative design with 3D pharmacophoric constraints
Generative models have increasingly been proposed as a solution to the molecular design
problem. However, it has proved challenging to control the design process or incorporate …
problem. However, it has proved challenging to control the design process or incorporate …
[HTML][HTML] AutoPrognosis 2.0: Democratizing diagnostic and prognostic modeling in healthcare with automated machine learning
Diagnostic and prognostic models are increasingly important in medicine and inform many
clinical decisions. Recently, machine learning approaches have shown improvement over …
clinical decisions. Recently, machine learning approaches have shown improvement over …
Explaining latent representations with a corpus of examples
Modern machine learning models are complicated. Most of them rely on convoluted latent
representations of their input to issue a prediction. To achieve greater transparency than a …
representations of their input to issue a prediction. To achieve greater transparency than a …
Multiple stakeholders drive diverse interpretability requirements for machine learning in healthcare
Applications of machine learning are becoming increasingly common in medicine and
healthcare, enabling more accurate predictive models. However, this often comes at the cost of …
healthcare, enabling more accurate predictive models. However, this often comes at the cost of …
Continuous-time modeling of counterfactual outcomes using neural controlled differential equations
Estimating counterfactual outcomes over time has the potential to unlock personalized
healthcare by assisting decision-makers to answer ''what-iF'' questions. Existing causal inference …
healthcare by assisting decision-makers to answer ''what-iF'' questions. Existing causal inference …
Generating property-matched decoy molecules using deep learning
Motivation An essential step in the development of virtual screening methods is the use of
established sets of actives and decoys for benchmarking and training. However, the decoy …
established sets of actives and decoys for benchmarking and training. However, the decoy …
Testing the limits of SMILES-based de novo molecular generation with curriculum and deep reinforcement learning
Deep reinforcement learning methods have been shown to be potentially powerful tools for
de novo design. Recurrent-neural-network-based techniques are the most widely used …
de novo design. Recurrent-neural-network-based techniques are the most widely used …
Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data
Evaluating the performance of machine learning models on diverse and underrepresented
subgroups is essential for ensuring fairness and reliability in real-world applications. However…
subgroups is essential for ensuring fairness and reliability in real-world applications. However…