Structure/Response Correlations and Similarity/Diversity Analysis by GETAWAY Descriptors. 1. Theory of the Novel 3D Molecular Descriptors

Consonni, Viviana; Todeschini, Roberto; Pavan, Manuela

doi:10.1021/ci015504a

Cited by 421 publications

(291 citation statements)

References 39 publications

Supporting

Mentioning

278

Contrasting

Unclassified

Order By: Relevance

“…28 Polarized continuum model (PCM) was applied to consider the non-specific solvent effect, and all molecules were optimized in H 2 O solvent. 3226 molecular descriptors in topological, geometrical, MoRSE, 30,31 RDF, 31,32 GETAWAY, 33,23 auto-correlations 34 and WHIM 35,36 groups were calculated using the Dragon program. 29 In three steps, the number of descriptors was reduced through an objective feature selection.…”

Section: General Methodsmentioning

confidence: 99%

A DFT and QSAR Study of Several Sulfonamide Derivatives in Gas and Solvent

Abadi¹,

Alizadehdakhel²,

Paskiabei³

2016

Journal of the Korean Chemical Society

View full text Add to dashboard Cite

ABSTRACT. The activity of 34 sulfonamide derivatives has been estimated by means of multiple linear regression (MLR), artificial neural network (ANN), simulated annealing (SA) and genetic algorithm (GA) techniques. These models were also utilized to select the most efficient subsets of descriptors in a cross-validation procedure for non-linear -log (IC50) prediction. The results obtained using GA-ANN were compared with MLR-MLR, MLR-ANN, SA-ANN and GA-ANN approaches. A high predictive ability was observed for the MLR-MLR, MLR-ANN, SA-ANN and MLR-GA models, with root mean sum square errors (RMSE) of 0.3958, 0.1006, 0.0359, 0.0326 and 0.0282 in gas phase and 0.2871, 0.0475, 0.0268, 0.0376 and 0.0097 in solvent, respectively (N=34). The results obtained using the GA-ANN method indicated that the activity of derivatives of sulfonamides depends on different parameters including DP03, BID, AAC, RDF035v, JGI9, TIE, R7e+, BELM6 descriptors in gas phase and Mor 32u, ESpm03d, RDF070v, ATS8m, MATS2e and R4p, L1u and R3m in solvent. In conclusion, the comparison of the quality of the ANN with different MLR models showed that ANN has a better predictive ability.

show abstract

Section: General Methodsmentioning

confidence: 99%

A DFT and QSAR Study of Several Sulfonamide Derivatives in Gas and Solvent

Abadi¹,

Alizadehdakhel²,

Paskiabei³

2016

Journal of the Korean Chemical Society

View full text Add to dashboard Cite

show abstract

“…(ii) Use appropriated atomic properties in order to weight and differentiate the molecular bonds. In this study, the used properties are those previously proposed for the calculation of the DRAGON descriptors [113,125,126], i.e., atomic mass (M), atomic polarizability (P), atomic Sanderson electronegativity (K), van der Waals atomic volume (V), and the atomic electronegativity in Pauling scale (G) [114]. The values of these atomic labels are shown in Table 1.…”

Section: Work Methodologymentioning

confidence: 99%

Discovery of Novel Trichomonacidals Using LDA‐Driven QSAR Models and Bond‐Based Bilinear Indices as Molecular Descriptors

et al. 2009

View full text Add to dashboard Cite

Few years ago, the World Health Organization estimated the number of adults with trichomoniasis at 170 million worldwide, more than the combined numbers for gonorrhea, syphilis, and chlamydia. To combat this sexually transmitted disease, Metronidazole (MTZ) has emerged, since 1959, as a powerful drug for the systematic treatment of infected patients. However, increasing resistance to MTZ, adverse effects associated to high-dose MTZ therapies and very expensive conventional technologies related to the development of new trichomonacidals necessitate novel computational methods that shorten the drug discovery pipeline. Therefore, bond-based bilinear indices, new 2-D bond-based TOMOCOMD-CARDD Molecular Descriptors (MDs), and Linear Discriminant Analysis (LDA) are combined to discover novel antitrichomonal agents. Generated models, using non-stochastic and stochastic indices, are able to classify correctly the 90.11% (93.75%) and the 87.92% (87.50%) of chemicals in the training (test) sets, respectively. In addition, they show large Matthews correlation coefficients (C) of 0.80 (0.86) and 0.76 (0.71) for the training (test) sets, respectively. The result of predictions on the 10% full-out cross-validation test also evidences the quality of both models. In order to test the models predictive power, 12 compounds, already proved against Trichomonas vaginalis (Tv), are screened in a simulated virtual screening experiment. As a result, they correctly classified 9 out of 12 (75.00%) and 10 out of 12 (83.33%) of the chemicals, respectively, which were the most important criteria to validate the models. Finally, in order to prove the reach of TOMOCOMD-CARDD approach and to discover new trichomonacidals, these classification functions were applied to a set of QSAR Comb. Sci. 28, 2009, No. 1, 9 -26 2009 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim 9 * To whom correspondence should be addressed (contact for chem-and bioinformatics methods) ** Contact for biological assays *** Contact for chemical methods Full Paperseight chemicals which, in turn, were synthesized and tested toward in vitro activity against Tv. As a result, experimental observations confirm theoretical predictions to a great extent, since it is gained a correct classification of 87.50% (7/8) of chemicals. Biological tests also show several candidates as antitrichomonals, since almost all the compounds [VAM2-(3 -8)] exhibit pronounced cytocidal activities of 100% at the concentration of 100 mg/mL and at 24 h (48 h) but VAM2 -2: 99.37% (100%), and it is remarkable that these compounds do not show toxic activity in macrophage assays at this concentration. The Quantitative Structure -Activity Relationship (QSAR) models presented here could significantly reduce the number of synthesized and tested compounds as well as could act as virtual shortcuts to new chemical entities with trichomonacidal activity.

show abstract

“…The QSAR literature contains a large number of possible choices. Examples of "cheap" descriptors that may be used are Fingal [6], where the different inter-atomic distances in a molecule are coded into a hash-key fingerprint, the Weighted Holistic Invariant Molecular (WHIM) descriptors [7,8], which are based on statistical indices calculated on the projections of the atoms along principal axes, and the GEometry, Topology and Atom-Weights AssemblY (GETAWAY) descriptors [9,10], which are computed on the basis of the Molecular Influence Matrix (MIM). There are also 3D-Molecule Representation of Structures based on electron diffraction (3D-MoRSE) [11], which are based on theoretical scattering curves calculated from the same transforms as used in electron diffraction studies.…”

Section: Defining Acceptable Moleculesmentioning

confidence: 99%

A knowledge‐based approach for screening chemical structures withinde novomolecular evolution

Chu

Alsberg

2010

Journal of Chemometrics

View full text Add to dashboard Cite

Despite the advantage of employing evolutionary algorithms (EAs) for de novo creation of novel molecular structures with optimal properties, the approach is hampered by sampling chemically undesirable structures. Such structures are undesirable for different reasons, such as a critical structural pattern may be ignored or too many rotational degrees of freedom exist for conformational search. A new method is presented which creates a user-defined structure filter, here referred to as the bias filter (BF), generated from a set of molecules representing typical structure types that are allowed to evolve in the de novo process. The BF can be seen as constraining the chemical structure space according to external requirements given by the user. No explicit programming of structure rules is necessary which makes the proposed method much more intuitive and user friendly than other methods commonly used in de novo applications. We have tested the proposed method in the process of evolving a set of Factor Xa inhibitors where the aim is to create molecules with optimal logP values. The de novo GeneGear system developed in our group is responsible for the corresponding evolutionary computation and bias filtering.

show abstract

Structure/Response Correlations and Similarity/Diversity Analysis by GETAWAY Descriptors. 1. Theory of the Novel 3D Molecular Descriptors

Cited by 421 publications

References 39 publications

A DFT and QSAR Study of Several Sulfonamide Derivatives in Gas and Solvent

A DFT and QSAR Study of Several Sulfonamide Derivatives in Gas and Solvent

Discovery of Novel Trichomonacidals Using LDA‐Driven QSAR Models and Bond‐Based Bilinear Indices as Molecular Descriptors

A knowledge‐based approach for screening chemical structures withinde novomolecular evolution

Contact Info

Product

Resources

About