An approach to the interpretation of backpropagation neural network models in QSAR studies.

Abstract:

:An approach to the interpretation of backpropagation neural network models for quantitative structure-activity and structure-property relationships (QSAR/QSPR) studies is proposed. The method is based on analyzing the first and second moments of distribution of the values of the first and the second partial derivatives of neural network outputs with respect to inputs calculated at data points. The use of such statistics makes it possible not only to obtain actually the same characteristics as for the case of traditional "interpretable" statistical methods, such as the linear regression analysis, but also to reveal important additional information regarding the non-linear character of QSAR/QSPR relationships. The approach is illustrated by an example of interpreting a backpropagation neural network model for predicting position of the long-wave absorption band of cyane dyes.

journal_name

SAR QSAR Environ Res

authors

Baskin II,Ait AO,Halberstam NM,Palyulin VA,Zefirov NS

doi

10.1080/10629360290002073

keywords:

subject

Has Abstract

pub_date

2002-03-01 00:00:00

pages

35-41

issue

1

eissn

1062-936X

issn

1029-046X

journal_volume

13

pub_type

杂志文章
  • QSAR Toolbox - workflow and major functionalities.

    abstract::The OECD QSAR Toolbox is a software application intended to be used by governments, the chemical industry and other stakeholders in filling gaps in (eco)toxicity data needed for assessing the hazards of chemicals. The development and release of the Toolbox is a cornerstone in the computerization of hazard assessment, ...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2015.1136680

    authors: Dimitrov SD,Diderich R,Sobanski T,Pavlov TS,Chankov GV,Chapkanov AS,Karakolev YH,Temelkov SG,Vasilev RA,Gerova KD,Kuseva CD,Todorova ND,Mehmed AM,Rasenberg M,Mekenyan OG

    更新日期:2016-03-01 00:00:00

  • Application of neural networks in the QSAR analysis of percent effect biological data: comparison with adaptive least squares and nonlinear regression analysis.

    abstract::Artificial neural networks (ANN) can be used for the direct QSAR analysis of percent effect biological data, thus avoiding the bias introduced by arbitrarily chosen classes and the loss of information due to prior classification. For two data sets the ANN results are compared with those obtained by adaptive least squa...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629369308028825

    authors: Wiese M,Schaper KJ

    更新日期:1993-01-01 00:00:00

  • Straightforward MIA-QSTR evaluation of environmental toxicities of aromatic aldehydes to Tetrahymena pyriformis.

    abstract::Aldehydes are toxic environmental contaminants which cause severe health hazards. There is a growing need by industries and regulatory agencies for the development of tools able to assess the potential hazardous effects of chemicals on living organisms. In this background, multivariate image analysis combined with qua...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2013.840678

    authors: Asadollahi-Baboli M

    更新日期:2013-01-01 00:00:00

  • QSPR checking and validation: a case study with hydroxy radical reaction rate constant.

    abstract::Traditionally, QSAR and QSPR models have been fitted by splitting the available compounds into separate learning and validation sets. The model is then fitted to the learning set and assessed using the validation set. Cross-validation (CV) uses all available compounds for both purposes, so that the full body of availa...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629360802349058

    authors: Hawkins DM,Kraker JJ,Basak SC,Mills D

    更新日期:2008-01-01 00:00:00

  • QSAR classification model for diverse series of antifungal agents based on improved binary differential search algorithm.

    abstract::An improved binary differential search (improved BDS) algorithm is proposed for QSAR classification of diverse series of antimicrobial compounds against Candida albicans inhibitors. The transfer functions is the most important component of the BDS algorithm, and converts continuous values of the donor into discrete va...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2019.1568298

    authors: Al-Fakih AM,Algamal ZY,Lee MH,Aziz M,Ali HTM

    更新日期:2019-02-01 00:00:00

  • A descriptor of amino acids: SVRG and its application to peptide quantitative structure-activity relationship.

    abstract::In this work, a descriptor, SVRG (principal component scores vector of radial distribution function descriptors and geometrical descriptors), was derived from principal component analysis (PCA) of a matrix of two structural variables of coded amino acids, including radial distribution function index (RDF) and geometri...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2011.604099

    authors: Tong J,Che T,Li Y,Wang P,Xu X,Chen Y

    更新日期:2011-07-01 00:00:00

  • First report on exploring classification and regression based QSAR modelling of Plasmodium falciparum glycogen synthase kinase (PfGSK-3) inhibitors.

    abstract::Recent advances in the knowledge of parasite biology have unveiled many new antimalarial targets for drug development. The glycogen synthase kinase-3 from Plasmodium falciparum (PfGSK-3) plays an active role in the completion of the asexual erythrocytic stage of P. falciparum life cycle. Due to the limited availabilit...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2015.1104518

    authors: Balasaheb Aher R,Roy K

    更新日期:2015-01-01 00:00:00

  • Internet resources integrating many small-molecule databases.

    abstract::()New data, tools and services recently made available on the web server (http://cactus.nci.nih.gov) of the Computer-Aided Drug Design (CADD) Group, NCI, NIH, developed in the context of chemoinformatics and drug development work, are presented. These tools are designed for searching for structures in very large datab...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629360701843540

    authors: Sitzmann M,Filippov IV,Nicklaus MC

    更新日期:2008-01-01 00:00:00

  • QSAR models for anti-androgenic effect--a preliminary study.

    abstract::Three modelling systems (MultiCase®, LeadScope® and MDL® QSAR) were used for construction of androgenic receptor antagonist models. There were 923-942 chemicals in the training sets. The models were cross-validated (leave-groups-out) with concordances of 77-81%, specificity of 78-91% and sensitivity of 51-76%. The spe...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2010.528981

    authors: Jensen GE,Nikolov NG,Wedebye EB,Ringsted T,Niemela JR

    更新日期:2011-03-01 00:00:00

  • Reactivity descriptors for the hydrogen bonding ability of pyridine bases.

    abstract::The hydrogen bonding interaction between pyridine bases and water was theoretically studied by applying density functional theory computations at the B3LYP/631G(d,p) level. The theoretically determined binding energies for the complexation process correlate well with the experimental solvatochromic parameters beta for...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629360410001724914

    authors: Dimitrova M,Ilieva S,Galabov B

    更新日期:2004-08-01 00:00:00

  • Study of local anesthetic activity of some derivatives of 3-amino-benzo-[d]-isothiazole.

    abstract::On the basis of computer prediction of biological activity by PASS and toxicity by DEREK, the most prospective 18 alkylaminoacyl derivatives of 3-amino-benzo-[d]-isothiazole were selected. Their local anesthetic action was assessed using an in vitro preparation of the isolated peroneal nerve of the frog. The local ane...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629360310001624051

    authors: Geronikaki A,Vicini P,Theophilidis G,Lagunin A,Poroikov V,Dearden JC

    更新日期:2003-10-01 00:00:00

  • Drug discovery studies on quinoline-based derivatives as potential antimalarial agents.

    abstract::Molecular modelling studies were performed to identify the essential structural requirements of quinoline-based derivatives for improving their antimalarial activity. The developed CoMFA, CoMSIA and HQSAR models for a training set comprising 37 derivatives showed good statistical significance in terms of internal cros...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2013.875484

    authors: Sharma R,Patil S,Maurya P

    更新日期:2014-01-01 00:00:00

  • Structural exploration of hydroxyethylamines as HIV-1 protease inhibitors: new features identified.

    abstract::The current study deals with chemometric modelling strategies (Naïve Bayes classification, hologram-based quantitative structure-activity relationship (HQSAR), comparative molecular field analysis (CoMFA) and comparative molecular similarity index analysis (CoMSIA)) to explore the important features of hydroxylamine d...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2018.1447511

    authors: Amin SA,Adhikari N,Bhargava S,Jha T,Gayen S

    更新日期:2018-05-01 00:00:00

  • DFT study on the structure-toxicity relationship of dioxin compounds using PLS analysis.

    abstract::Density functional theory (DFT) at B3LYP/6-311G** level was employed to optimise the dioxin compounds, i.e., 25 polychlorinated or brominated dibenzo-p-dioxins (PCDDs or PBDDs) and 34 polychlorinated dibenzofurans (PCDFs) involved in this investigation. Three groups of descriptors mainly related to chemical reactivity...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629360701428755

    authors: Gu CG,Jiang X,Ju XH,Yang XL,Yu GF

    更新日期:2007-07-01 00:00:00

  • 4D-QSAR study of HEPT derivatives by electron conformational-genetic algorithm method.

    abstract::In this work, the EC-GA method, a hybrid 4D-QSAR approach that combines the electron conformational (EC) and genetic algorithm optimization (GA) methods, was applied in order to explain pharmacophore (Pha) and predict anti-HIV-1 activity by studying 115 compounds in the class of 1-[(2-hydroxyethoxy)-methyl]-6-(phenylt...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2012.665082

    authors: Akyüz L,Sarıpınar E,Kaya E,Yanmaz E

    更新日期:2012-07-01 00:00:00

  • Effects of chemical reactivity of the toxicity of phosphorus fluoridates.

    abstract::Semiempirical quantum calculations were performed on a series of organophosphorus fluoridates to determine the relative reactivity for hydrolysis. This value was determined by subtracting the energy of the metastable intermediate from the energy of the stable molecule. Plotting this relative reactivity for each compou...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629369908039176

    authors: White WE

    更新日期:1999-01-01 00:00:00

  • Identification of potential HIV-1 integrase strand transfer inhibitors: in silico virtual screening and QM/MM docking studies.

    abstract::HIV-1 integrase (IN) is a retroviral enzyme that catalyses integration of the reverse-transcribed viral DNA into the host genome, which is necessary for efficient viral replication. In this study, we have performed an in silico virtual screening for the identification of potential HIV-1 IN strand transfer (ST) inhibit...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2013.772919

    authors: Reddy KK,Singh SK,Tripathi SK,Selvaraj C

    更新日期:2013-01-01 00:00:00

  • Variable selection using pair-correlation method. Environmental applications.

    abstract::Pair-correlation method (PCM) has been developed for selecting between two, correlated descriptor variables. PCM utilizes systematic information present in the scatter of QSAR applications. The data are suitably ordered in a 2 x 2 contingency table. Statistical tests are used to discriminate between the descriptor var...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629360290023368

    authors: Héberger K,Rajkó R

    更新日期:2002-07-01 00:00:00

  • Mechanism-based common reactivity pattern (COREPA) modelling of aryl hydrocarbon receptor binding affinity.

    abstract::The aryl hydrocarbon receptor is a ligand-activated transcription factor responsive to both natural and synthetic environmental compounds, with the most potent agonist being 2,3,7,8-tetrachlotrodibenzo-p-dioxin. The aim of this work was to develop a categorical COmmon REactivity PAttern (COREPA)-based structure-activi...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629360903570933

    authors: Petkov PI,Rowlands JC,Budinsky R,Zhao B,Denison MS,Mekenyan O

    更新日期:2010-01-01 00:00:00

  • Integration of genomic data for pharmacology and toxicology using Internet resources.

    abstract::Genome based technologies such as sequencing and gene expression profiling using microarrays are creating massive amounts of data. Results from these studies have provided unique insights into targets, biochemical pathways, and biological systems affected by drug or xenobiotic chemical treatments. Moreover, these geno...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章,评审

    doi:10.1080/10659360600562053

    authors: Paananen J,Wong G

    更新日期:2006-02-01 00:00:00

  • Quantitative structure-toxicity relationships using TOPS-MODE. 2. Neurotoxicity of a non-congeneric series of solvents.

    abstract::Neurotoxicities of a series of solvents in rats and mice have been modeled by means of the TOPS-MODE approach. Two quantitative structure-toxicity relationship (QSTR) models were obtained explaining more than 80% of the variance in the experimental values of neurotoxicity of 45 solvents. Only one compound was detected...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629360108035384

    authors: Estrada E,Molina E,Uriarte E

    更新日期:2001-01-01 00:00:00

  • Structure-toxicity relationships for alkanones and alkenones.

    abstract::The relative toxicity (log IGC-1(50)) of 54 selected alkanones, both aliphatic and aromatic, as well as, alkenones and alkynones was evaluated in the static Tetrahymena pyriformis population growth assay. Excess toxicity, an indicator of bioreactivity, was associated only with the alpha-beta unsaturated alkenones and ...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629369508233991

    authors: Schultz TW,Sinks GD,Hunter RS

    更新日期:1995-01-01 00:00:00

  • Investigation of anticancer activity of macrocyclic Schiff bases by means of 4D-QSAR based on simplex representation of molecular structure.

    abstract::Influence of the molecular structure of macrocyclic pyridinophanes, their analogues and some other compounds on anticancer activity (Leukemia, central nervous system (CNS) cancer, prostate cancer, breast cancer, melanoma, non-small cell lung cancer, colon cancer, ovarian cancer, renal cancer) was investigated by means...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10659360500037206

    authors: Kuz'min VE,Artemenko AG,Lozytska RN,Fedtchouk AS,Lozitsky VP,Muratov EN,Mescheriakov AK

    更新日期:2005-06-01 00:00:00

  • Antibacterial activity and QSAR of chalcones against biofilm-producing bacteria isolated from marine waters.

    abstract::Biofouling in the marine environment is a major problem. In this study, three marine organisms, namely Bacillus flexus (LD1), Pseudomonas fluorescens (MD3) and Vibrio natriegens (MD6), were isolated from biofilms formed on polymer and metal surfaces immersed in ocean water. Phylogenetic analysis of these three organis...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629361003771009

    authors: Sivakumar PM,Prabhawathi V,Doble M

    更新日期:2010-04-01 00:00:00

  • Topological structural alerts modulations of mammalian cell mutagenicity for halogenated derivatives.

    abstract::Genotoxicity is a key toxicity endpoint for current regulatory requirements regarding new and existing chemicals. However, genotoxicity testing is time-consuming and costly, and involves the use of laboratory animals. This has motivated the development of computational approaches, designed to predict genotoxicity with...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2013.820791

    authors: Pérez-Garrido A,Girón-Rodríguez F,Morales Helguera A,Borges F,Combes RD

    更新日期:2014-01-01 00:00:00

  • Comparison of global and mode of action-based models for aquatic toxicity.

    abstract::The ability to estimate aquatic toxicity is a critical need for ecological risk assessment and chemical regulation. The consensus in the literature is that mode of action (MOA) based toxicity models yield the most toxicologically meaningful and, theoretically, the most accurate results. In this study, a two-step predi...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2015.1018939

    authors: Martin TM,Young DM,Lilavois CR,Barron MG

    更新日期:2015-01-01 00:00:00

  • Can the Internet help to meet the challenges in ADME and e-ADME?

    abstract::The high-throughput screening (HTS) of large proprietary compound collections and combinatorial libraries has put an increased pressure on getting pharmacokinetic and drug metabolism data as early as possible. Properties related to absorption, distribution, metabolism and excretion (ADME) can be estimated by a range o...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/10629360290014269

    authors: Van de Waterbeemd H,De Groot M

    更新日期:2002-05-01 00:00:00

  • Experimental verification of structural alerts for the protein binding of sulfur-containing compounds.

    abstract::As often noted by Dr. Gilman Veith, a major barrier to advancing any model is defining its applicability domain. Sulfur-containing industrial organic chemicals can be grouped into several chemical classes including mercaptans (RSH), sulfides (RSR'), disulfides (RSSR'), sulfoxides (RS(=O)R'), sulfones (RS(=O)(=O)R'), s...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2014.898693

    authors: Richarz AN,Schultz TW,Cronin MT,Enoch SJ

    更新日期:2014-01-01 00:00:00

  • Partial least squares modelling of the acute toxicity of aliphatic compounds to Tetrahymena pyriformis.

    abstract::The aim of this study was to evaluate a multivariate statistical model, utilising Partial Least Squares (PLS) analysis, for the prediction of the acute toxicity of aliphatic chemicals to the ciliate Tetrahymena pyriformis. A model was developed that was capable of making a prediction regardless the mechanism of toxic ...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936032000101501

    authors: Netzeva TI,Schultz TW,Aptula AO,Cronin MT

    更新日期:2003-08-01 00:00:00

  • Multiple molecular modelling studies on some derivatives and analogues of glutamic acid as matrix metalloproteinase-2 inhibitors.

    abstract::Matrix metalloproteinase-2 (MMP-2) is a potential target in anticancer drug discovery due to its association with angiogenesis, metastasis and tumour progression. In this study, 67 glutamic acid derivatives, synthesized and evaluated as MMP-2 inhibitors, were taken into account for multi-QSAR modelling study (regressi...

    journal_title:SAR and QSAR in environmental research

    pub_type: 杂志文章

    doi:10.1080/1062936X.2017.1406986

    authors: Jha T,Adhikari N,Saha A,Amin SA

    更新日期:2018-01-01 00:00:00