Development of NEural network simulator for structure-activity COrrelation of molecules: Neco.

Isu, Yoshimi; Nagashima, Umpei; Hosoya, Haruo; Ohshima, Shigeru; Sakamoto, Yohko; Aoyama, Tomoo

doi:10.2477/jchemsoft.2.76

Cited by 16 publications

(26 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We examined the relevance of the features to the estimated presence by using the parameter scan method [23]. In the method, the values of a specific input-feature are changed in 0.1 steps and the outputs of the neural network are observed.…”

Section: Relevance Of the Features To Presencementioning

confidence: 99%

Development of an Estimation Model for Instantaneous Presence in Audio-Visual Content

Ozawa

Tsukahara

Kinoshita

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThe sense of presence is often used to evaluate the performances of audio-visual (AV) content and systems. However, a presence meter has yet to be realized. We consider that the sense of presence can be divided into two aspects: system presence and content presence. In this study we focused on content presence. To estimate the overall presence of a content item, we have developed estimation models for the sense of presence in audio-only and audio-visual content. In this study, the audio-visual model is expanded to estimate the instantaneous presence in an AV content item. Initially, we conducted an evaluation experiment of the presence with 40 content items to investigate the relationship between the features of the AV content and the instantaneous presence. Based on the experimental data, a neural-network-based model was developed by expanding the previous model. To express the variation in instantaneous presence, 6 audiorelated features and 14 visual-related features, which are extracted from the content items in 500-ms intervals, are used as inputs for the model. The audio-related features are loudness, sharpness, roughness, dynamic range and standard deviation in sound pressure levels, and movement of sound images. The visual-related features involve hue, lightness, saturation, and movement of visual images. After constructing the model, a generalization test confirmed that the model is sufficiently accurate to estimate the instantaneous presence. Hence, the model should contribute to the development of a presence meter.

show abstract

Section: Relevance Of the Features To Presencementioning

confidence: 99%

Development of an Estimation Model for Instantaneous Presence in Audio-Visual Content

Ozawa

Tsukahara

Kinoshita

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…A number of NN analyses have been performed for predicting the NMR chemical shifts from the topological structure of molecules. [25][26][27][28][29] Contrary to these studies we have undertaken to predict several molecular properties by NN analysis using 13 C-NMR chemical shifts of a series of compounds. Namely, to test the predictability of Neco, the exo or endo branching of norbornane and norbornene derivatives was predicted from the set of the 13 C-NMR chemical shifts of ring carbon atoms by using the same data 30 which were chosen by Sasaki et al in their learning machine and cluster analysis.…”

Section: Relationship Between 13 C-nmr Chemical Shifts and Exo/endo B...mentioning

confidence: 99%

“…1,11,12 The numberings of carbon atoms of the norbornane skeleton are given in the bottom right of Figure 3. The structures, 13 C-NMR data, and exo/endo branchings of 38 compounds are given in Figure 3 and Table 1. The upper 25 (nos.…”

Section: Relationship Between 13 C-nmr Chemical Shifts and Exo/endo B...mentioning

confidence: 99%

“…15 Use of Graph-theoretical technique has accelerated the elucidation of QSAR problems. [16][17][18][19][20][21] On the other hand, we have applied our neural network simulator, Neco, to two problems in which some specific property of a given substance, i.e., a set of 13 C-NMR chemical shifts of the component carbon atoms, has a crucial role in determining another specificity, such as molecular conformation or carcinogenicity.…”

Section: Introductionmentioning

confidence: 99%

“…11 In the following chapter the applied NN will briefly be explained. Analysis of the 13 C-NMR chemical shifts and the branching of norbornane and norbornene derivatives † Ochanomizu University. ‡ Miyazaki University.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Development of Neural Network Simulator for Structure−Activity Correlation of Molecules (NECO). Prediction of Endo/Exo Substitution of Norbornane Derivatives and of Carcinogenic Activity of PAHs from ¹³C-NMR Shifts

Isu

Nagashima

Aoyama

et al. 1996

J. Chem. Inf. Comput. Sci.

Self Cite

View full text Add to dashboard Cite

A perceptron type neural network simulator for structure--activity correlation of molecules has been developed with two different learning methods, i.e., back-propagation and reconstruction methods. First by use of the back-propagation method the exo/endo branching of norbornane and norbornene derivatives was correctly predicted from the set of 13C NMR chemical shifts for various ring carbon atoms. Then the obtained correlation was analyzed by the reconstruction learning method. It was shown in this case that the NMR shifts for two carbon atoms out of seven have strong correlation with the exo/endo branching. Further, structure--activity correlation between the 13C NMR chemical shifts and carcinogenicity of 11 polycyclic aromatic hydrocarbons was also analyzed using the reconstruction method. It was demonstrated that neural network analysis is suitable for the elucidation of complicated structure--activity problems where many factors are nonlinearly entangled.

show abstract

Virtual Screening of Phytochemicals

Choudhury

Atteya

Dahal

et al. 2018

Computational Phytochemistry

View full text Add to dashboard Cite

Development of NEural network simulator for structure-activity COrrelation of molecules: Neco.

Cited by 16 publications

References 2 publications

Development of an Estimation Model for Instantaneous Presence in Audio-Visual Content

Development of an Estimation Model for Instantaneous Presence in Audio-Visual Content

Development of Neural Network Simulator for Structure−Activity Correlation of Molecules (NECO). Prediction of Endo/Exo Substitution of Norbornane Derivatives and of Carcinogenic Activity of PAHs from ¹³C-NMR Shifts

Virtual Screening of Phytochemicals

Contact Info

Product

Resources

About

Development of NEural network simulator for structure-activity COrrelation of molecules: Neco.

Cited by 16 publications

References 2 publications

Development of an Estimation Model for Instantaneous Presence in Audio-Visual Content

Development of an Estimation Model for Instantaneous Presence in Audio-Visual Content

Development of Neural Network Simulator for Structure−Activity Correlation of Molecules (NECO). Prediction of Endo/Exo Substitution of Norbornane Derivatives and of Carcinogenic Activity of PAHs from 13C-NMR Shifts

Virtual Screening of Phytochemicals

Contact Info

Product

Resources

About

Development of Neural Network Simulator for Structure−Activity Correlation of Molecules (NECO). Prediction of Endo/Exo Substitution of Norbornane Derivatives and of Carcinogenic Activity of PAHs from ¹³C-NMR Shifts