Multi-objective Monkey Algorithm for Drug Design

Devi, R. Vasundhara; Sathya, S. Siva; Kumar, Nilabh; Coumar, Mohane Selvaraj

doi:10.5815/ijisa.2019.03.04

Cited by 3 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method proposed by Devi et al (2014) used a GA guided by the scalarisation of two objective functions, druglikeness (by Lipinski's Rule of 5 Lipinski ( 2004)) and similarity (by Tanimoto similarity Loving et al (2010)) to a known reference molecule from the e-Drug3D database. The weights of the objectives are set a priori.…”

Section: Aggregation-basedmentioning

confidence: 99%

“…The MoGADdrug method, introduced in Devi et al ( 2021), is a fragment-based GA that constructs new molecules from a set of chemical fragments and a reference molecule as inputs. Building upon previous work Devi et al (2014), which considered only two fragments (acid and amine), this method incorporates a variable-length representation to construct new solutions considering double amine fragments, thus allowing three fragment types. The objective function is a weighted sum of the oral bio-availability score Lipinski (2004), and the 2D similarity based on the Tanimoto coefficient Brown (2009), with the weights being set a priori.…”

Section: Aggregation-basedmentioning

confidence: 99%

“…In the works of Devi et al (2019Devi et al ( , 2020, two multi-objective methods were explored for dnDD of new drug-like molecules: the monkey algorithm (MoMADrug) Devi et al (2019) and the biofilm algorithm (MOBifi) Devi et al (2020). MoMADrug is inspired by the behaviour of monkeys, while MOBifi is inspired by the life cycle of bacteria in a biofilm.…”

Section: Pareto-basedmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Objective and Many-Objective Optimisation: Present and Future in de novo Drug Design

S. Angelo,

Alvim Guedes,

J. C. Barbosa

et al. 2023

Preprint

View full text Add to dashboard Cite

de novo Drug Design (dnDD) is a multi-objective optimisation problem (MultiOOP) that aims to design new molecules that satisfy multiple conflicting objectives. Since several desired properties can be considered in the optimisation process, dnDD is naturally categorised as a many-objective optimisation problem (ManyOOP), where more than three objectives must be simultaneously optimised. However, many objectives typically pose several challenges that affect the choice and the design of optimisation methodologies. Herein, we cover the application of MultiOO and ManyOO methods, particularly those based on Evolutionary Computation and Machine Learning techniques, to enlighten their potential application in dnDD. Additionally, we comprehensively analyse how molecular properties used in the optimisation process are applied as either objectives or constraints to the problem. Finally, we discuss future research in ManyOO for dnDD, highlighting two important possible impacts: i) its integration with the development of multi-target approaches to accelerate the discovery of innovative and more efficacious drug therapies and ii) its role as a catalyst for new developments in more fundamental and general methodological frameworks within the ManyOO field.

show abstract

Section: Aggregation-basedmentioning

confidence: 99%

Section: Aggregation-basedmentioning

confidence: 99%

Section: Pareto-basedmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Objective and Many-Objective Optimisation: Present and Future in de novo Drug Design

S. Angelo,

Alvim Guedes,

J. C. Barbosa

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition to these two objectives, MOBifi also employed the Veber score Veber et al (2002) as a third objective related to oral bioavailability. In Devi et al (2019) , the authors compared the MoMADrug against the MoGADdrug Devi et al (2021) , which uses a weighted sum of the objectives. Their results showed that MoMADrug could produce a more diverse set of solutions due to its multi-objective nature and its use of Pareto dominance criteria.…”

Section: Applications In De Novo Drug Designmentioning

confidence: 99%

“…In the works of Devi et al (2019Devi et al ( , 2020, two multi-objective methods were explored for dnDD of new drug-like molecules: the monkey algorithm (MoMADrug) Devi et al (2019) and the biofilm algorithm (MOBifi) Devi et al (2020). MoMADrug is inspired by the behavior of monkeys, while MOBifi is inspired by the life cycle of bacteria in a biofilm.…”

Section: Pareto-basedmentioning

confidence: 99%

Multi-and many-objective optimization: present and future in de novo drug design

Angelo,

Guedes,

Barbosa

et al. 2023

Front. Chem.

View full text Add to dashboard Cite

de novo Drug Design (dnDD) aims to create new molecules that satisfy multiple conflicting objectives. Since several desired properties can be considered in the optimization process, dnDD is naturally categorized as a many-objective optimization problem (ManyOOP), where more than three objectives must be simultaneously optimized. However, a large number of objectives typically pose several challenges that affect the choice and the design of optimization methodologies. Herein, we cover the application of multi- and many-objective optimization methods, particularly those based on Evolutionary Computation and Machine Learning techniques, to enlighten their potential application in dnDD. Additionally, we comprehensively analyze how molecular properties used in the optimization process are applied as either objectives or constraints to the problem. Finally, we discuss future research in many-objective optimization for dnDD, highlighting two important possible impacts: i) its integration with the development of multi-target approaches to accelerate the discovery of innovative and more efficacious drug therapies and ii) its role as a catalyst for new developments in more fundamental and general methodological frameworks in the field.

show abstract

Multi- and Many-Objective Optimisation: Present and Future in de novo Drug Design

S. Angelo,

A. Guedes,

J. C. Barbosa

et al. 2023

Preprint

View full text Add to dashboard Cite

de novo Drug Design (dnDD) aims to create new molecules that satisfy multiple conflicting objectives. Since several desired properties can be considered in the optimisation process, dnDD is naturally categorised as a many-objective optimisation problem (ManyOOP), where more than three objectives must be simultaneously optimised. However, a large number of objectives typically pose several challenges that affect the choice and the design of optimisation methodologies. Herein, we cover the application of multi- and many-objective optimisation methods, particularly those based on Evolutionary Computation and Machine Learning techniques, to enlighten their potential application in dnDD. Additionally, we comprehensively analyse how molecular properties used in the optimisation process are applied as either objectives or constraints to the problem. Finally, we discuss future research in many-objective optimisation for dnDD, highlighting two important possible impacts: i) its integration with the development of multi-target approaches to accelerate the discovery of innovative and more efficacious drug therapies and ii) its role as a catalyst for new developments in more fundamental and general methodological frameworks in the field.

show abstract

Multi-objective Monkey Algorithm for Drug Design

Cited by 3 publications

References 13 publications

Multi-Objective and Many-Objective Optimisation: Present and Future in de novo Drug Design

Multi-Objective and Many-Objective Optimisation: Present and Future in de novo Drug Design

Multi-and many-objective optimization: present and future in de novo drug design

Multi- and Many-Objective Optimisation: Present and Future in de novo Drug Design

Contact Info

Product

Resources

About