Advances in computational methods to predict the biological activity of compounds

  title={Advances in computational methods to predict the biological activity of compounds},
  author={Chanin Nantasenamat and Chartchalerm Isarankura-Na-Ayudhya and Virapong Prachayasittikul},
  journal={Expert Opinion on Drug Discovery},
  pages={633 - 654}
Importance of the field: The past decade had witnessed remarkable advances in computer science which had given rise to many new possibilities including the ability to simulate and model life's phenomena. Among one of the greatest gifts computer science had contributed to drug discovery is the ability to predict the biological activity of compounds and in doing so drives new prospects and possibilities for the development of novel drugs with robust properties. Areas covered in this review: This… 

Use of machine learning approaches for novel drug discovery

An important application of ML techniques is related to the calculation of scoring functions used in docking and virtual screening assays from a consensus, combining traditional and ML techniques in order to improve the prediction of binding sites and docking solutions.

Maximizing computational tools for successful drug discovery

The authors explore the available computational tools in the context of the extant of big data that has borne out via advents of the Omics revolution in order to give drug discovery scientists the best opportunity.

Construction of machine learning models to predict pharmacology properties of molecules

This work tried to optimize the process of building QSAR models using the feature selection technique, resulting in a reduction in the set of variables used by the algorithm resulting in the construction of more robust models, maintaining the same performance.

Towards reproducible computational drug discovery

This article provides an in-depth coverage on the reproducibility of computational drug discovery and explores the current state-of-the-art on reproducible research.

Computational modeling in melanoma for novel drug discovery

This review discusses the basics of computational modeling in melanoma drug discovery and development and includes the in silico discovery of novel molecular drug targets, the optimization of immunotherapies and personalized medicine trials.

A New Big-Data Paradigm for Target Identification and Drug Discovery

BANDIT is developed, a novel paradigm that integrates multiple data types within a Bayesian machine-learning framework to predict the targets and mechanisms for small molecules with unprecedented accuracy and versatility that can be used as a resource to accelerate drug discovery and direct the clinical application of small molecule therapeutics with improved precision.

Quantitative structure activity relationships in computer aided molecular design

CAMD and QSAR are considered to be extremely efficient instruments in molecular design and accelerate the initial steps of drug development process and enhance the effectiveness and reduce the cost of newly developed drugs.

Chemoinformatics and chemical genomics: potential utility of in silico methods

This review will describe in silico chemoinformatics methods such as (quantitative) structure–activity relationship modeling and will overview how chemoinformatic technologies are considered in applied regulatory research.

A Bayesian machine learning approach for drug target identification using diverse data types

A Bayesian machine learning framework that integrates multiple data types to predict the targets of small molecules is introduced, enabling identification of a new set of microtubule inhibitors and the target of the anti-cancer molecule ONC201.



Computational systems approach for drug target discovery

  • N. Chandra
  • Biology
    Expert opinion on drug discovery
  • 2009
Systems thinking has now come of age enabling a ‘bird's eye view’ of the biological systems under study, at the same time allowing us to ‘zoom in’, where necessary, for a detailed description of individual components.

Drug discovery: past, present and future.

  • P. N. Kaul
  • Biology
    Progress in drug research. Fortschritte der Arzneimittelforschung. Progres des recherches pharmaceutiques
  • 1998
As the authors understand more about the co-ordinating and regulating powers of the cerebral cortex during the next century, man may be able to use bio-feedback training to voluntarily regulate the release of neurotransmitters, hormones, and other molecules involved in the regulation of various physiological processes in health as well as in disease.

Applications of 2D descriptors in drug design: a DRAGON tale.

This review attempts to summarize present knowledge related to the computational biological activity prediction based in 2D molecular descriptors implemented in the DRAGON software.

A practical overview of quantitative structure-activity relationship

This review aims to cover the essential concepts and techniques that are relevant for performing QSAR/QSPR studies through the use of selected examples from the authors' previous work.

Drug design by machine learning: ensemble learning for QSAR modeling

  • Y. Liu
  • Computer Science
    Fourth International Conference on Machine Learning and Applications (ICMLA'05)
  • 2005
This study introduced the ensemble machine learning, a set of classifiers whose individual decisions are combined in some way (typically by weighted or unweighted voting) to improve the performance of the overall system.

Modelling mutagenicity using properties calculated by computational chemistry

A study of mutagenicity data for a diverse set of 90 compounds using good discriminant models built for this data set using properties calculated by the techniques of computational chemistry.

AI and SAR approaches for predicting chemical carcinogenicity: Survey and status report

A survey of AI and SAR approaches applied to the prediction of rodent carcinogenicity is presented, and it is concluded that the definitions of biological activity and nature of chemicals in the training set are important determinants of the predictive success and specificity/sensitivity characteristics of a derived model.

Prediction of drug absorption: different modeling approaches from discovery to clinical development

  • M. Kuentz
  • Biology
    Expert review of clinical pharmacology
  • 2009
Drug absorption modeling is a task that requires different tools depending on the drug development stage. Scientific progress and increased computer power have initiated a veritable revolution of

Considerations and recent advances in QSAR models for cytochrome P450-mediated drug metabolism prediction

Some considerations to be taken into account by QSAR for modeling drug metabolism, such as the accuracy/consistency of the entire data set, representation and diversity of the training and test sets, and variable selection are described.

Finding more needles in the haystack: A simple and efficient method for improving high-throughput docking results.

The application of naïve Bayes to enrich HTD results can be carried out without a priori knowledge of the activity of compounds and results in superior enrichment of known actives compared to the use of scoring methods alone.