• Corpus ID: 219179876

Regression Enrichment Surfaces: a Simple Analysis Technique for Virtual Drug Screening Models

@article{Clyde2020RegressionES,
  title={Regression Enrichment Surfaces: a Simple Analysis Technique for Virtual Drug Screening Models},
  author={Austin R. Clyde and Xiaotian Duan and Rick L. Stevens},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.01171}
}
We present a new method for understanding the performance of a model in virtual drug screening tasks. While most virtual screening problems present as a mix between ranking and classification, the models are typically trained as regression models presenting a problem requiring either a choice of a cutoff or ranking measure. Our method, regression enrichment surfaces (RES), is based on the goal of virtual screening: to detect as many of the top-performing treatments as possible. We outline… 
Protein-Ligand Docking Surrogate Models: A SARS-CoV-2 Benchmark for Deep Learning Accelerated Virtual Screening
TLDR
This work shows surrogate docking models have six orders of magnitude more throughput than standard docking protocols on the same supercomputer node types, and proposes a benchmark to study surrogate model accuracy for protein-ligand docking.
Scaffold-Induced Molecular Graph (SIMG): Effective Graph Sampling Methods for High-Throughput Computational Drug Discovery
TLDR
The utility of scaffold based networks for chemical space is highlighted as a potential solution to the intractable enumeration problem of chemical space by working inductively on local neighborhoods.
IMPECCABLE: Integrated Modeling PipelinE for COVID Cure by Assessing Better LEads
TLDR
Development and deployment of computational infrastructure at scale integrates multiple artificial intelligence and simulation-based approaches to overcome this fundamental limitation of the drug discovery process.
Scalable HPC and AI Infrastructure for COVID-19 Therapeutics
TLDR
This work describes several methods that integrate artificial intelligence and simulation-based approaches, and the design of computational infrastructure to support these methods at scale, and discusses their implementation and characterize their performance.
Scalable HPC & AI infrastructure for COVID-19 therapeutics
TLDR
Several methods that integrate artificial intelligence and simulation-based approaches, and the design of computational infrastructure to support these methods at scale are described.

References

SHOWING 1-10 OF 53 REFERENCES
Comparison of Ranking Methods for Virtual Screening in Lead-Discovery Programs
This paper discusses the use of several rank-based virtual screening methods for prioritizing compounds in lead-discovery programs, given a training set for which both structural and bioactivity data
Prediction of Biological Activity for High-Throughput Screening Using Binary Kernel Discrimination
TLDR
Binary kernel discrimination is shown to perform robustly with varying quantities of training data and also in the presence of noisy data, highlighting the importance of the judicious use of general pattern recognition techniques for compound selection.
Machine Learning Consensus Scoring Improves Performance Across Targets in Structure-Based Virtual Screening.
TLDR
Traditional consensus scoring methods are compared with a novel, unsupervised gradient boosting approach that observed increased score variation among active ligands and developed a statistical mixture model consensus score based on combining score means and variances.
Structure-based virtual screening: an overview.
  • P. Lyne
  • Computer Science, Medicine
    Drug discovery today
  • 2002
TLDR
The current strengths and weaknesses of the technology are discussed, and emphasis is placed on aspects of the work-flow of a virtual screening campaign, from preparation through to post-screening analysis.
Machine‐learning scoring functions to improve structure‐based binding affinity prediction and virtual screening
TLDR
The emerging picture from these studies is that the classical approach of using linear regression with a small number of expert‐selected structural features can be strongly improved by a machine‐learning approach based on nonlinear regression allied with comprehensive data‐driven feature selection.
A Discussion of Measures of Enrichment in Virtual Screening: Comparing the Information Content of Descriptors with Increasing Levels of Sophistication
TLDR
Surprisingly, structure-unaware atom count vectors as descriptors in combination with the Euclidean distance measure are able to achieve "enrichment factors" over random selection of around 4 (depending on the particular class of active compounds), putting the enrichment factors reported for more sophisticated virtual screening methods in a different light.
Screening Drug-Like Compounds by Docking to Homology Models: A Systematic Study
TLDR
Questions regarding the choice of the template to use in constructing the model, the accuracy of the screening results, and the importance of allowing for protein flexibility are addressed with compound screening calculations for multiple homology models of five drug targets.
Evaluating Virtual Screening Methods: Good and Bad Metrics for the "Early Recognition" Problem
TLDR
This work formally generalizes the ROC metric to the early recognition problem and proposes a novel metric called Boltzmann-enhanced discrimination of receiver operating characteristic that turns out to contain the discrimination power of the RIE metric but incorporates the statistical significance from ROC and its well-behaved boundaries.
Structure-based virtual screening of chemical libraries for drug discovery.
TLDR
Virtual screening is being increasingly used as a complement to high-throughput screening to improve the speed and efficiency of the drug discovery and development process.
Virtual screening of chemical libraries
TLDR
Interest in virtual screening is re-ignited, which is now widely used in drug discovery, albeit on a more limited scale than empirical screening.
...
1
2
3
4
5
...