Design of molecules from quantitative structure-activity relationship models. 1. Information transfer between path and vertex degree counts

Kier, Lemont B.; Hall, Lowell H.; Frazer, Jack W.

doi:10.1021/ci00011a021

Cited by 66 publications

(65 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inverse quantitative structure-activity relationship (QSAR) analysis aims to identify values of descriptors used to generate a QSAR model that corresponds to high activity, and build structures of active compounds from these values [1][2][3][4] . The inverse QSAR process is challenging since numerical signatures of activity, if they can be determined, must be re-translated into viable chemical structures and active compounds, a task falling into the area of de novo compound design [5][6][7] .…”

Section: Introductionmentioning

confidence: 99%

“…The inverse QSAR process is challenging since numerical signatures of activity, if they can be determined, must be re-translated into viable chemical structures and active compounds, a task falling into the area of de novo compound design [5][6][7] . A predominant approach to inverse QSAR is the use of multiple linear regression (MLR) models to construct chemical graphs that correspond to an MLR equation [1][2][3][4] . Given this equation, a desired y (activity) value constrains relationships between descriptor settings.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring differential evolution for inverse QSAR analysis

2017

View full text Add to dashboard Cite

Inverse quantitative structure-activity relationship (QSAR) modeling encompasses the generation of compound structures from values of descriptors corresponding to high activity predicted with a given QSAR model. Structure generation proceeds from descriptor coordinates optimized for activity prediction. Herein, we concentrate on the first phase of the inverse QSAR process and introduce a new methodology for coordinate optimization, termed differential evolution (DE), that originated from computer science and engineering. Using simulation and compound activity data, we demonstrate that DE in combination with support vector regression (SVR) yields effective and robust predictions of optimized coordinates satisfying model constraints and requirements. For different compound activity classes, optimized coordinates are obtained that exclusively map to regions of high activity in feature space, represent novel positions for structure generation, and are chemically meaningful.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Exploring differential evolution for inverse QSAR analysis

2017

View full text Add to dashboard Cite

show abstract

“…In de novo molecular design [1] based on quantitative structure-property relationship (QSPR) and quantitative structure-activity relationship (QSAR), [2] evolutionary algorithms (EAs) [3,4] and inverse QSPR/QSAR [5][6][7][8] are promising methods for producing chemical structures with desired properties or activities. In EAs, evolutionary operations are directly applied to chemical structures, [9,10] and an evaluation function legitimizes the modified structures for next iterations (generations).…”

Section: Introductionmentioning

confidence: 99%

Finding Chemical Structures Corresponding to a Set of Coordinates in Chemical Descriptor Space

Miyao

Funatsu

2017

Mol. Inf.

View full text Add to dashboard Cite

When chemical structures are searched based on descriptor values, or descriptors are interpreted based on values, it is important that corresponding chemical structures actually exist. In order to consider the existence of chemical structures located in a specific region in the chemical space, we propose to search them inside training data domains (TDDs), which are dense areas of a training dataset in the chemical space. We investigated TDDs' features using diverse and local datasets, assuming that GDB11 is the chemical universe. These two analyses showed that considering TDDs gives higher chance of finding chemical structures than a random search-based method, and that novel chemical structures actually exist inside TDDs. In addition to those findings, we tested the hypothesis that chemical structures were distributed on the limited areas of chemical space. This hypothesis was confirmed by the fact that distances among chemical structures in several descriptor spaces were much shorter than those among randomly generated coordinates in the training data range

show abstract

“…Kier et al developed methods for reconstructing molecular structures from the count of paths of a length up to two and the count of paths of a length up to three, by combining enumeration and bounding operations [20]. Skvortsova et al developed a similar method, in which paths of the same length are further classified into several classes based on atom and bond types [28].…”

Section: Introductionmentioning

confidence: 99%

Kernel Methods for Chemical Compounds: From Classification to Design

Akutsu

Nagamochi

2011

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper, we briefly review kernel methods for analysis of chemical compounds with focusing on the authors' works. We begin with a brief review of existing kernel functions that are used for classification of chemical compounds and prediction of their activities. Then, we focus on the pre-image problem for chemical compounds, which is to infer a chemical structure that is mapped to a given feature vector, and has a potential application to design of novel chemical compounds. In particular, we consider the pre-image problem for feature vectors consisting of frequencies of labeled paths of length at most K. We present several time complexity results that include: NP-hardness result for a general case, polynomial time algorithm for tree structured compounds with fixed K, and polynomial time algorithm for K = 1 based on graph detachment. Then we review practical algorithms for the pre-image problem, which are based on enumeration of chemical structures satisfying given constraints. We also briefly review related results which include efficient enumeration of stereoisomers of tree-like chemical compounds and efficient enumeration of outerplanar graphs.

show abstract

Design of molecules from quantitative structure-activity relationship models. 1. Information transfer between path and vertex degree counts

Cited by 66 publications

References 4 publications

Exploring differential evolution for inverse QSAR analysis

Exploring differential evolution for inverse QSAR analysis

Finding Chemical Structures Corresponding to a Set of Coordinates in Chemical Descriptor Space

Kernel Methods for Chemical Compounds: From Classification to Design

Contact Info

Product

Resources

About