Application of neural networks in structure-activity relationships

Kövesdi, István; Dominguez‐Rodriguez, Maria Felisa; Őrfi, László; Náray‐Szabó, Gábor; Varró, András; Papp, Julius Gy.; Mátyus, Péter

doi:10.1002/(sici)1098-1128(199905)19:3<249::aid-med4>3.0.co;2-0

Cited by 60 publications

(25 citation statements)

References 192 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[12][13][14] Synthetic pathways are outlined in Schemes 1 and 2. We synthesized two novel series of 4-substituted-2,6dimethylphenoxypropyl amines, represented by compounds 5±9, and 24±34, respectively, which unify pharmacophores of class III and class Ib antiarrhythmics de®ned by 3D QSAR methods.…”

Section: R E S U L T S a N D Discussion A Chemistrymentioning

confidence: 99%

New antiarrhythmic agents: a conceptually novel approach

Mátyus¹,

Rettegi²,

Varró³

et al. 2000

Med. Res. Rev.

Self Cite

View full text Add to dashboard Cite

Section: R E S U L T S a N D Discussion A Chemistrymentioning

confidence: 99%

New antiarrhythmic agents: a conceptually novel approach

Mátyus¹,

Rettegi²,

Varró³

et al. 2000

Med. Res. Rev.

Self Cite

View full text Add to dashboard Cite

“…In this study we computed all the data produced by MARCH-INSIDE ® with the ANN techniques. ANN algorithms are well-known tools in bioinformatics and many groups use them to construct classification models [99][100][101][102][103][104]. Our groups have also used ANN models many times with good results [86,105,106].…”

Section: Ann Prediction Modelsmentioning

confidence: 99%

Review of Computer-Aided Models for Predicting Collagen Stability

Concu

Podda²,

González-Dı́az³

et al. 2011

CAD

View full text Add to dashboard Cite

Collagen is the most abundant protein in the whole human body and its instability is involved in many important diseases, such as Osteogenesis imperfecta, Ehlers-Danlos syndrome, and collagenopathy. The stability of the collagen triple helix is strictly related to its amino acid sequence, especially the main Gly-X-Y motif. Many groups have used computational methods to investigate collagen's structure and the relationship between its stability and structure. In this study, we initially reviewed the most important computational methods that have been applied in this field. We then assembled data on a large number of collagen-like peptides to build the first Markov chain model for predicting the stability of the collagen at different temperatures, simply by analyzing the amino acid sequence. We used the literature to assemble a set of 102 peptides and their relative melting temperatures were determined experimentally, indicating a great variance with the main motif of the collagen. This dataset was then split in two classes, stable and unstable, according to their melting temperatures and the dataset was then used to build artificial neural network (ANN) models to predict collagen stability. We built models to predict stability at temperatures of 38°C, 35°C, 30°C, and 25°C degrees, and all models had an accuracy between 82% and 92%. Several cross-validation procedures were performed to validate the model. This method facilitates fast and accurate predictions of collagen stability at different temperatures.

show abstract

“…In recent decades, various nonlinear analysis methods [75] , such as artificial neural network (ANN) [71,76] and support vector machine (SVM) [77,78] were also adopted in establishing QSAR models. Genetic algorithms (GA) [79,80] were used for vairable selection to obtain optimal QSAR models.…”

Section: Development Of (Q)sarsmentioning

confidence: 99%

Progress and perspectives of quantitative structure-activity relationships used for ecological risk assessment of toxic organic compounds

Chen

et al. 2008

Sci. China Ser. B-Chem.

View full text Add to dashboard Cite

Structure-activity relationship (SAR) and quantitative structure-activity relationship (QSAR), collectively referred to as (Q)SARs, play an important role in ecological risk assessment (ERA) of organic chemicals. (Q)SARs can fill the data gap for physical-chemical, environmental behavioral and ecotoxicological parameters of organic compounds; they can decrease experimental expenses and reduce the extent of experimental testing (especially animal testing); they can also be used to assess the uncertainty of the experimental data. With the development for several decades, (Q)SARs in environmental sciences show three features: application orientation, multidisciplinary integration, and intelligence. Progress of (Q)SAR technology for ERA of toxic organic compounds, including endpoint selection and mathematic methods for establishing simple, transparent, easily interpretable and portable (Q)SAR models, is reviewed. The recent development on defining application domains and diagnosing outliers is summarized. Model characterization with respect to goodness-of-fit, stability and predictive power is specially presented. The purpose of the review is to promote the development of (Q)SARs orientated to ERA of organic chemicals.(Q)SARs, ecological risk assessment, application domain, stability, predictive power

show abstract

Application of neural networks in structure-activity relationships

Cited by 60 publications

References 192 publications

New antiarrhythmic agents: a conceptually novel approach

New antiarrhythmic agents: a conceptually novel approach

Review of Computer-Aided Models for Predicting Collagen Stability

Progress and perspectives of quantitative structure-activity relationships used for ecological risk assessment of toxic organic compounds

Contact Info

Product

Resources

About