Ligand-Based Virtual Screening with Co-regularised Support Vector Regression

Ullrich, Katrin; Kamp, Michael; Gärtner, Thomas; Vogt, Martin; Wrobel, Stefan

doi:10.1109/icdmw.2016.0044

Cited by 3 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many strategies to improve the performance of classifiers on imbalanced datasets, 130 whose application to SBVS should eventually be explored. Also, semi-supervised learning approaches, 131,132 where considering unlabeled instances circumvents the need of assuming the label of molecules untested in vitro, are still to be applied to SBVS. On the other hand, target-specific representation can be powerful, 78 but it is still largely unexplored.…”

Section: What Are the Limitations Of Commonly Used Retrospective Bencmentioning

confidence: 99%

Machine‐learning scoring functions for structure‐based virtual screening

Sze

Lü

et al. 2020

WIREs Comput Mol Sci

135

View full text Add to dashboard Cite

Molecular docking predicts whether and how small molecules bind to a macromolecular target using a suitable 3D structure. Scoring functions for structure-based virtual screening primarily aim at discovering which molecules bind to the considered target when these form part of a library with a much higher proportion of non-binders. Classical scoring functions are essentially models building a linear mapping between the features describing a proteinligand complex and its binding label. Machine learning, a major subfield of artificial intelligence, can also be used to build fast supervised learning models for this task. In this review, we analyzed such machine-learning scoring functions for structure-based virtual screening in the period 2015-2019. We have discussed what the shortcomings of current benchmarks really mean and what valid alternatives have been employed. The latter retrospective studies observed that machine-learning scoring functions were substantially more accurate, in terms of higher hit rates and potencies, than the classical scoring functions they were compared to. Several of these machine-learning scoring functions were also employed in prospective studies, in which mid-nanomolar binders with novel chemical structures were directly discovered without any potency optimization. We have thus highlighted the codes and webservers that are available to build or apply machine-learning scoring functions to prospective structure-based virtual screening studies. A discussion of prospects for future work completes this review.

show abstract

Section: What Are the Limitations Of Commonly Used Retrospective Bencmentioning

confidence: 99%

Machine‐learning scoring functions for structure‐based virtual screening

Sze

Lü

et al. 2020

WIREs Comput Mol Sci

135

View full text Add to dashboard Cite

show abstract

ALADIN: A New Approach for Drug–Target Interaction Prediction

Búza

Peška

2017

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

Implicit-descriptor ligand-based virtual screening by means of collaborative filtering

2018

View full text Add to dashboard Cite

Current ligand-based machine learning methods in virtual screening rely heavily on molecular fingerprinting for preprocessing, i.e., explicit description of ligands’ structural and physicochemical properties in a vectorized form. Of particular importance to current methods are the extent to which molecular fingerprints describe a particular ligand and what metric sufficiently captures similarity among ligands. In this work, we propose and evaluate methods that do not require explicit feature vectorization through fingerprinting, but, instead, provide implicit descriptors based only on other known assays. Our methods are based upon well known collaborative filtering algorithms used in recommendation systems. Our implicit descriptor method does not require any fingerprint similarity search, which makes the method free of the bias arising from the empirical nature of the fingerprint models. We show that implicit methods significantly outperform traditional machine learning methods, and the main strengths of implicit methods are their resilience to target-ligand sparsity and high potential for spotting promiscuous ligands.

show abstract

Ligand-Based Virtual Screening with Co-regularised Support Vector Regression

Cited by 3 publications

References 14 publications

Machine‐learning scoring functions for structure‐based virtual screening

Machine‐learning scoring functions for structure‐based virtual screening

ALADIN: A New Approach for Drug–Target Interaction Prediction

Implicit-descriptor ligand-based virtual screening by means of collaborative filtering

Contact Info

Product

Resources

About