A Novel Method for the Inverse QSAR/QSPR to Monocyclic Chemical Compounds Based on Artificial Neural Networks and Integer Programming

Ito, Ryo; Azam, Naveed Ahmed; Wang, Chenxi; Shurbevski, Aleksandar; Nagamochi, Hiroshi; Akutsu, Tatsuya

doi:10.1007/978-3-030-71051-4_51

Cited by 5 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 A Method for Inferring Chemical Graphs We review the framework that solves the inverse QSAR/QSPR by using MILPs [9,25], which is illustrated in Figure 3. For a specified chemical property π such as boiling point, we denote by a(G) the observed value of the property π for a chemical compound G. As the first phase, we solve (I) Prediction Problem with the following three steps.…”

Section: Descriptorsmentioning

confidence: 99%

“…Theorem 1. ( [9,25]) Let N be an ANN with a piecewise-linear activation function for an input vector x ∈ R K , n A denote the number of nodes in the architecture and n B denote the total number of break-points over all activation functions. Then there is an MILP M(x, y; C 1 ) that consists of variable vectors x ∈ D (⊆ R K ), y ∈ R, and an auxiliary variable vector z ∈ R p for some integer p = O(n A + n B ) and a set C 1 of O(n A + n B ) constraints on these variables such that: ψ N (x * ) = y * if and only if there is a vector (x * , y * ) feasible to M(x, y; C 1 ).…”

Section: Phasementioning

confidence: 99%

“…In (II-a) of the above-mentioned previous methods [3,5,24], an MILP is formulated for acyclic chemical compounds. Afterwards, Ito et al [9] and Zhu et al [25] designed a method of inferring chemical graphs with cycle index 1 and 2, respectively by formulating a new MILP and using an efficient algorithm for enumerating chemical graphs with cycle index 1 [20] and cycle index 2 [21,22]. The computational results conducted on instances with n non-hydrogen atoms show that a feature vector x * can be inferred for up to around n = 40 whereas graphs G * can be enumerated for up to around n = 15.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Method for Inference of Acyclic Chemical Compounds with Bounded Branch-height Based on Artificial Neural Networks and Integer Programming

Azam¹,

Zhu²,

Sun³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Analysis of chemical graphs is becoming a major research topic in computational molecular biology due to its potential applications to drug design. One of the major approaches in such a study is inverse quantitative structure activity/property relationships (inverse QSAR/QSPR) analysis, which is to infer chemical structures from given chemical activities/properties. Recently, a novel framework has been proposed for inverse QSAR/QSPR using both artificial neural networks (ANN) and mixed integer linear programming (MILP). This method consists of a prediction phase and an inverse prediction phase. In the first phase, a feature vector f (G) of a chemical graph G is introduced and a prediction function ψ N on a chemical property π is constructed with an ANN N . In the second phase, given a target value y * of the chemical property π, a feature vector x * is inferred by solving an MILP formulated from the trained ANN N so that ψ N (x * ) is close to y * and then a set of chemical structures G * such that f (G * ) = x * is enumerated by a graph search algorithm. The framework has been applied to the case of chemical compounds with cycle index up to 2 so far. The computational results conducted on instances with n non-hydrogen atoms show that a feature vector x * can be inferred for up to around n = 40 whereas graphs G * can be enumerated for up to around n = 15. When applied to the case of chemical acyclic graphs, the maximum computable diameter of G * was around up to around 8. In this paper, we introduce a new characterization of graph structure, called "branch-height" based on which a new MILP formulation and a new graph search algorithm are designed for chemical acyclic graphs. The results of computational experiments using such chemical properties as octanol/water partition coefficient, boiling point and heat of combustion suggest that the proposed method can infer chemical acyclic graphs G * with n = 50 and diameter 30.

show abstract

Section: Descriptorsmentioning

confidence: 99%

Section: Phasementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Method for Inference of Acyclic Chemical Compounds with Bounded Branch-height Based on Artificial Neural Networks and Integer Programming

Azam¹,

Zhu²,

Sun³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…We review the framework that solves the inverse QSAR/QSPR by using MILPs [6,11,30], which is illustrated in Figure 4. For a specified chemical property π such as boiling point, we denote by a(G) the observed value of the property π for a chemical compound G. As the first phase, we solve (I) Prediction Problem with the following three steps.…”

Section: Descriptorsmentioning

confidence: 99%

“…In (II-a) of the above-mentioned previous methods [3,6,29], an MILP is formulated for acyclic chemical compounds. Afterwards, Ito et al [11] and Zhu et al [30] designed a method of inferring chemical graphs with rank (or cycle index) 1 and 2, respectively by formulating a new MILP and using an efficient algorithm for enumerating chemical graphs with rank 1 [24] and rank 2 [26,27]. The computational results conducted on instances with n non-hydrogen atoms show that a feature vector x * can be inferred for up to around n = 40 whereas graphs G * can be enumerated for up to around n = 15.…”

Section: Introductionmentioning

confidence: 99%

A novel method for inference of chemical compounds with prescribed topological substructures based on integer programming

Akutsu,

Nagamochi

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Recently, extensive studies have been done on design of chemical graphs using artificial neural networks (ANNs). However, most existing studies do not guarantee optimal or exact solutions. On the other hand, a novel framework has been proposed for design of chemical graphs using both ANNs and mixed integer linear programming (MILP). This method consists of a prediction phase and an inverse prediction phase. In the first phase, a feature vector f (G) of a chemical graph G is introduced and a prediction function ψ N on a chemical property π is constructed with an ANN N . In the second phase, given a target value y * of the chemical property π, a feature vector x * is inferred by solving an MILP formulated from the trained ANN N so that ψ N (x * ) is equal to y * and then a set of chemical structures G * such that f (G * ) = x * is enumerated by a graph enumeration algorithm. Although exact solutions are guaranteed by this framework, types of chemical graphs are restricted to such classes as trees, monocyclic graphs and graphs with a specified polymer topology with cycle index up to 2.To overcome this limitation, we propose a new flexible modeling method to the framework so that we can specify a topological substructure of graphs and a partial assignment of chemical elements and bond-multiplicity to a target graph.

show abstract

Machine Learning Approaches to Improve Prediction of Target‐Drug Interactions

Balatti¹,

Barletta²,

Pérez³

et al. 2022

Drug Design Using Machine Learning

View full text Add to dashboard Cite

A Novel Method for the Inverse QSAR/QSPR to Monocyclic Chemical Compounds Based on Artificial Neural Networks and Integer Programming

Cited by 5 publications

References 19 publications

A Novel Method for Inference of Acyclic Chemical Compounds with Bounded Branch-height Based on Artificial Neural Networks and Integer Programming

A Novel Method for Inference of Acyclic Chemical Compounds with Bounded Branch-height Based on Artificial Neural Networks and Integer Programming

A novel method for inference of chemical compounds with prescribed topological substructures based on integer programming

Machine Learning Approaches to Improve Prediction of Target‐Drug Interactions

Contact Info

Product

Resources

About