QSAR—Origins and Present Status: A Historical Perspective

Craig, Paul N.

doi:10.1177/009286158401800203

Cited by 14 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ligand-based drug discovery approaches build predictive machine learning models from datasets that pair multiple compounds with a specific bioactivity of interest, which is often the activation, inhibition, or binding of a target protein. Ligand-based machine learning models are also known as quantitative structure activity relationship (QSAR) and date back to the 1960s (Craig, 1984). QSAR models do not take protein structures into account, and can only predict bioactivities for which there is sufficient experimental data, including both active and inactive compounds.…”

Section: Introductionmentioning

confidence: 99%

Proteome‐Scale Drug‐Target Interaction Predictions: Approaches and Applications

MacKinnon¹,

Tonekaboni²,

Windemuth³

2021

Current Protocols

View full text Add to dashboard Cite

Drug‐Target interaction predictions are an important cornerstone of computer‐aided drug discovery. While predictive methods around individual targets have a long history, the application of proteome‐scale models is relatively recent. In this overview, we will provide the context required to understand advances in this emerging field within computational drug discovery, evaluate emerging technologies for suitability to given tasks, and provide guidelines for the design and implementation of new drug‐target interaction prediction models. We will discuss the validation approaches used, and propose a set of key criteria that should be applied to evaluate their validity. We note that we find widespread deficiencies in the existing literature, making it difficult to judge the practical effectiveness of some of the techniques proposed from their publications alone. We hope that this review may help remedy this situation and increase awareness of several sources of bias that may enter into commonly used cross‐validation methods. © 2021 Cyclica Inc. Current Protocols published by Wiley Periodicals LLC.

show abstract

Section: Introductionmentioning

confidence: 99%

Proteome‐Scale Drug‐Target Interaction Predictions: Approaches and Applications

MacKinnon¹,

Tonekaboni²,

Windemuth³

2021

Current Protocols

View full text Add to dashboard Cite

show abstract

“…Chemical activity predictions continue to present a longstanding challenge with practical importance during pharmaceutical research and development. In particular, predictive tasks that associate chemical structures to their activity are known as Quantitative Structure Activity Relationships (QSARs) ( 1 ). In modern drug design programs, QSARs are used for modeling specific target biological activities or broader pharmacokinetic behaviours, including the absorption, distribution, metabolism, excretion, and toxicity of drug candidate molecules, collectively referred to as ADMET ( 2 -4 ).…”

Section: Introductionmentioning

confidence: 99%

“…In modern drug design programs, QSARs are used for modeling specific target biological activities or broader pharmacokinetic behaviours, including the absorption, distribution, metabolism, excretion, and toxicity of drug candidate molecules, collectively referred to as ADMET ( 2 -4 ). All machine learning (ML) approaches to predict chemical activity have three fundamental requirements: [1] a library of diverse reference molecules with a known property to predict (labeled examples), [2] a form of molecular representation and [3] a discriminative supervised learning algorithm. In practical drug discovery applications, multiple algorithms and molecular representations are explored and optimized on a trial-and-error basis ( 5 ), since their performance varies considerably from predictive task to predictive task.…”

Section: Introductionmentioning

confidence: 99%

“…A naive way to combine molecular representations is to append the vectors generated by each fingerprint directly onto each other, to create a new, longer fingerprint, of multiple types. This approach has at least two major disadvantages: [1] for some supervised learning algorithms, the computational costs may become prohibitive when concatenating multiple fingerprints, due to increased length of the vector; and [2], the concatenation approach is prone to the creatively named "curse of dimensionality" ( 18 -20 ). This phenomenon occurs when the ratio of training data to features is low, and overfitting becomes not just possible, but likely.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Predicting drug properties with parameter-free machine learning: pareto-optimal embedded modeling (POEM)

Brereton¹,

MacKinnon²,

Safikhani³

et al. 2020

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

The prediction of absorption, distribution, metabolism, excretion, and toxicity (ADMET) of small molecules from their molecular structure is a central problem in medicinal chemistry with great practical importance in drug discovery. Creating predictive models conventionally requires substantial trial-and-error for the selection of molecular representations, machine learning (ML) algorithms, and hyperparameter tuning. A generally applicable method that performs well on all datasets without tuning would be of great value but is currently lacking. Here, we describe Pareto-Optimal Embedded Modeling (POEM), a similarity-based method for predicting molecular properties. POEM is a non-parametric, supervised ML algorithm developed to generate reliable predictive models without need for optimization. POEM's predictive strength is obtained by combining multiple different representations of molecular structures in a context-specific manner, while maintaining low dimensionality. We benchmark POEM relative to industry-standard ML algorithms and published results across 17 classifications tasks. POEM performs well in all cases and reduces the risk of overfitting.

show abstract

“…Several molecular descriptors have been developed to describe molecules as numbers [ 1 – 3 ]. They are usually used to predict biological activities towards proteins, which are called quantitative structure–activity relationships (QSAR) [ 4 , 5 ], and physicochemical properties such as solubility or membrane permeability, which are called quantitative structure–property relationships (QSPR) [ 6 ]. They are also used to calculate the similarity of molecules for clustering or analysis of chemical libraries [ 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

A novel descriptor based on atom-pair properties

Kuroda¹

2017

J Cheminform

View full text Add to dashboard Cite

BackgroundMolecular descriptors have been widely used to predict biological activities and physicochemical properties or to analyze chemical libraries on the basis of similarity. Although fingerprints and properties are generally used as descriptors, neither is perfect for these purposes. A fingerprint can distinguish between molecules, whereas a property may not do the same in certain cases, and vice versa. When the number of the training set is especially small, the construction of good predictive models is difficult. Herein, a novel descriptor integrating mutually compensating fingerprint and property characteristics is described. The format of this descriptor is not conventional. It has two dimensions with variable length in one dimension to represent one molecule. This format is not acceptable for any machine learning methods. Therefore the distance between molecules has been newly defined for application to machine learning techniques. The evaluation of this descriptor, as applied to classification tasks, was performed using a support vector machine after the features of the descriptor had been optimized by a genetic algorithm.ResultsBecause the optimizing feature is time-intensive due to the complicated calculation of distances between molecules, the optimization was forced to stop before it was completed. As a result, no remarkable improvement was observed in the classification results for the new descriptor compared with those for other descriptors in any evaluation set used in this work. However, extremely low accuracies were also not found for any set.ConclusionsThe novel descriptor proposed in this work can potentially be used to make highly accurate predictive models. This new concept in descriptors is expected to be useful for developing novel predictive methods with quick training and high accuracy.

show abstract

QSAR—Origins and Present Status: A Historical Perspective

Cited by 14 publications

References 8 publications

Proteome‐Scale Drug‐Target Interaction Predictions: Approaches and Applications

Proteome‐Scale Drug‐Target Interaction Predictions: Approaches and Applications

Predicting drug properties with parameter-free machine learning: pareto-optimal embedded modeling (POEM)

A novel descriptor based on atom-pair properties

Contact Info

Product

Resources

About