Applications of genetic algorithms on the structure-activity relationship analysis of some cinnamamides

Towards an Enrichment Optimization Algorithm (EOA)-based Target Specific Docking Functions for Virtual Screening

Docking-based virtual screening (VS) is a common starting point in many drug discovery projects. While ligand-based approaches may sometimes provide better results, the advantage of docking lies in its ability to provide reliable ligand binding modes and approximated binding free energies, two factors that are important for hit selection and optimization. Most docking programs were developed to be as general as possible and consequently their performances on specific targets may be sub-optimal. With this in mind, in this work we present a method for the development of target-specific scoring functions using our recently reported Enrichment Optimization Algorithm (EOA). EOA derives QSAR models in the form of multiple linear regression (MLR) equations by optimizing an enrichment-like metric. Since EOA requires target-specific active and inactive (or decoy) compounds, we retrieved such data for six targets from the DUD-E database, and used them to re-derive the weights associated with the components that make up GOLD's ChemPLP scoring function yielding target-specific, modified functions. We then used the original ChemPLP function in small-scale VS experiments on the six targets and subsequently rescored the resulting poses with the modified functions. In addition, we used the modified functions for compounds re-docking. We found that in many although not all cases, either rescoring the original ChemPLP poses or repeating the entire docking process with the modified functions, yielded better results in terms of AUC and EF_1% , two metrics, common for the evaluation of VS performances. While work on additional datasets and docking tools is clearly required, we propose that the results obtained thus far hint to the potential benefits in using EOA-based optimization for the derivation of target-specific functions in the context of virtual screening. To this end, we discuss the downsides of the methods and how it could be improved.

MolAICal: a soft tool for 3D drug design of protein targets by artificial intelligence and classical algorithm

Deep learning is an important branch of artificial intelligence that has been successfully applied into medicine and two-dimensional ligand design. The three-dimensional (3D) ligand generation in the 3D pocket of protein target is an interesting and challenging issue for drug design by deep learning. Here, the MolAICal software is introduced to supply a way for generating 3D drugs in the 3D pocket of protein targets by combining with merits of deep learning model and classical algorithm. The MolAICal software mainly contains two modules for 3D drug design. In the first module of MolAICal, it employs the genetic algorithm, deep learning model trained by FDA-approved drug fragments and Vinardo score fitting on the basis of PDBbind database for drug design. In the second module, it uses deep learning generative model trained by drug-like molecules of ZINC database and molecular docking invoked by Autodock Vina automatically. Besides, the Lipinski's rule of five, Pan-assay interference compounds (PAINS), synthetic accessibility (SA) and other user-defined rules are introduced for filtering out unwanted ligands in MolAICal. To show the drug design modules of MolAICal, the membrane protein glucagon receptor and non-membrane protein SARS-CoV-2 main protease are chosen as the investigative drug targets. The results show MolAICal can generate the various and novel ligands with good binding scores and appropriate XLOGP values. We believe that MolAICal can use the advantages of deep learning model and classical programming for designing 3D drugs in protein pocket. MolAICal is freely for any nonprofit purpose and accessible at https://molaical.github.io.

Evaluation of QSAR Equations for Virtual Screening

Quantitative Structure Activity Relationship (QSAR) models can inform on the correlation between activities and structure-based molecular descriptors. This information is important for the understanding of the factors that govern molecular properties and for designing new compounds with favorable properties. Due to the large number of calculate-able descriptors and consequently, the much larger number of descriptors combinations, the derivation of QSAR models could be treated as an optimization problem. For continuous responses, metrics which are typically being optimized in this process are related to model performances on the training set, for example, R2 and QCV2. Similar metrics, calculated on an external set of data (e.g., QF1/F2/F32), are used to evaluate the performances of the final models. A common theme of these metrics is that they are context -” ignorant”. In this work we propose that QSAR models should be evaluated based on their intended usage. More specifically, we argue that QSAR models developed for Virtual Screening (VS) should be derived and evaluated using a virtual screening-aware metric, e.g., an enrichment-based metric. To demonstrate this point, we have developed 21 Multiple Linear Regression (MLR) models for seven targets (three models per target), evaluated them first on validation sets and subsequently tested their performances on two additional test sets constructed to mimic small-scale virtual screening campaigns. As expected, we found no correlation between model performances evaluated by “classical” metrics, e.g., R2 and QF1/F2/F32 and the number of active compounds picked by the models from within a pool of random compounds. In particular, in some cases models with favorable R2 and/or QF1/F2/F32 values were unable to pick a single active compound from within the pool whereas in other cases, models with poor R2 and/or QF1/F2/F32 values performed well in the context of virtual screening. We also found no significant correlation between the number of active compounds correctly identified by the models in the training, validation and test sets. Next, we have developed a new algorithm for the derivation of MLR models by optimizing an enrichment-based metric and tested its performances on the same datasets. We found that the best models derived in this manner showed, in most cases, much more consistent results across the training, validation and test sets and outperformed the corresponding MLR models in most virtual screening tests. Finally, we demonstrated that when tested as binary classifiers, models derived for the same targets by the new algorithm outperformed Random Forest (RF) and Support Vector Machine (SVM)-based models across training/validation/test sets, in most cases. We attribute the better performances of the Enrichment Optimizer Algorithm (EOA) models in VS to better handling of inactive random compounds. Optimizing an enrichment-based metric is therefore a promising strategy for the derivation of QSAR models for classification and virtual screening.

Discovery of potential Toxoplasma gondii CDPK1 inhibitors with new scaffolds based on the combination of QSAR and scaffold-hopping method with in vitro validation

To discover drugs for toxoplasmosis with less side-effects and less probability to get drug resistance is eagerly appealed for pregnant women, infant or immunocompromised patients. In this work, using TgCDPK1 as drug target, we design a method to discover new inhibitors for CDPK1 as potential drug lead for toxoplasmosis with novel scaffolds based on the combination of 2D/3D-QSAR and scaffold-hopping methods. All the binding sites of the potential inhibitors were checked by docking method, and only the ones that docked to the most conserved sites of TgCDPK1, which make them have less probability to get drug resistance, were remained. As a result, 10 potential inhibitors within two new scaffolds were discovered for TgCDPK1 with experimentally verified inhibitory activities in micromole level. The discovery of these inhibitors may contribute to the drug development for toxoplasmosis. Besides, the pipeline which is composed in this work as the combination of QSAR and scaffold-hopping is simple, easy to repeat for researchers without need of in-depth knowledge of pharmacology to get inhibitors with novel scaffolds, which will accelerate the procedure of drug discovery and contribute to the drug repurposing study.

QSAR Analysis of a Series of Hydantoin-based Androgen Receptor Modulators and Corresponding Binding Affinities

Androgen receptor (AR), a member of the nuclear hormone receptor superfamily of intracellular ligand-dependent transcription factors, plays an indispensable role in normal male development through the regulation of androgen through the binding with endogenous androgens. Inappropriate amounts of androgens have a severe adverse effect on men. Excessive androgen may contribute to accelerate prostatic hypertrophy, even prostate cancer, while the absence of androgen may result in reduced muscle mass and strength, decreased bone mass, low energy, diminished sexual function and an increased risk of osteoporosis and fracture. In these cases, androgen receptor modulators are important to maintain the normal biological function of AR. So androgen receptor modulators are necessary for human being to improve their happy life index. To explore the relationships between molecular structures and corresponding binding abilities to aid the new AR modulator design, multiple linear regressions (MLR) are employed to analyze a series of hydantoin analogues, which can bind to androgen receptor acting as AR modulators. The obtained optimum model presents wonderful reliabilities and strong predictive abilities with R² =0.858, Q L O O 2 =0.822, Q L M O 2 =0.813, Q F 1 2 =0.840, Q F 2 2 =0.807, Q F 3 2 =0.814, CCC=0.893, respectively. The derived model can be used to predict the binding abilities of unknown chemicals and may help to design novel molecules with better AR affinity activity.

New insights into the selective inhibition of the β-carbonic anhydrases of pathogenic bacteria Burkholderia pseudomallei and Francisella tularensis: a proteochemometrics study

Nowadays, antibiotic resistance has turned into one of the most important worldwide health problems. Biological end point of critical enzymes induced by potent inhibitors is recently being considered as a highly effective and popular strategy to defeat antibiotic-resistant pathogens. For instance, the simple but critical β-carbonic anhydrase has recently been in the center of attention for anti-pathogen drug discoveries. However, no β-carbonic anhydrase selective inhibitor has yet been developed. Available β-carbonic anhydrase inhibitors are also highly potent with regard to human carbonic anhydrases, leading to severe inevitable side effects in case of usage. Therefore, developing novel inhibitors with high selectivity against pathogenic β-carbonic anhydrases is of great essence. Herein, for the first time, we have conducted a proteochemometric study to explore the structural and the chemical aspects of the interactions governed by bacterial β-carbonic anhydrases and their inhibitors. We have found valuable information which can lead to designing novel inhibitors with better selectivity for bacterial β-carbonic anhydrases.

Exploring the origin of phosphodiesterase inhibition via proteochemometric modeling

A proteochemometric study of a set of phosphodiesterase 4B and 4D inhibitors sheds light on the origin of their inhibition and selectivities.

Proteochemometric Modeling of the Interaction Space of Carbonic Anhydrase and its Inhibitors: An Assessment of Structure-based and Sequence-based Descriptors

Due to its physiological and clinical roles, carbonic anhydrase (CA) is one of the most interesting case studies. There are different classes of CAinhibitors including sulfonamides, polyamines, coumarins and dithiocarbamates (DTCs). However, many of them hardly act as a selective inhibitor against a specific isoform. Therefore, finding highly selective inhibitors for different isoforms of CA is still an ongoing project. Proteochemometrics modeling (PCM) is able to model the bioactivity of multiple compounds against different isoforms of a protein. Therefore, it would be extremely applicable when investigating the selectivity of different ligands towards different receptors. Given the facts, we applied PCM to investigate the interaction space and structural properties that lead to the selective inhibition of CA isoforms by some dithiocarbamates. Our models have provided interesting structural information that can be considered to design compounds capable of inhibiting different isoforms of CA in an improved selective manner. Validity and predictivity of the models were confirmed by both internal and external validation methods; while Y-scrambling approach was applied to assess the robustness of the models. To prove the reliability and the applicability of our findings, we showed how ligands-receptors selectivity can be affected by removing any of these critical findings from the modeling process.

ADME evaluation in drug discovery. 9. Prediction of oral bioavailability in humans based on molecular properties and structural fingerprints

Oral bioavailability is an essential parameter in drug screening cascades and a good indicator of the capability of the delivery of a given compound to the systemic circulation by oral administration. In the present work, we report a database of oral bioavailability of 1014 molecules determined in humans. A systematic examination of the relationships between various physicochemical properties and oral bioavailability were carried out to investigate the influence of these properties on oral bioavailability. A number of property-based rules for bioavailability classification were generated and evaluated. We found that no rule was an effective predictor for oral bioavailability because these simple rules cannot characterize the influence of important metabolic processes on bioavailability. Finally, the genetic function approximation (GFA) technique was employed to construct the multiple linear regression models for oral bioavailability using structural fingerprints as the basic parameters, together with several important molecular properties. The best model is able to predict human oral bioavailability with an r of 0.79, a q of 0.72, and a RMSE (root-mean-square error) of 22.30% of the compounds from the training set. The analysis of the descriptors chosen by GFA shows that the important structural fingerprints are primarily related to important intestinal absorption and well-known metabolic processes. The predictive power of the models was further evaluated using a separate test set of 80 compounds, and the consensus model can predict the oral bioavailability with r(test) = 0.71 and RMSE = 23.55% for the tested compounds. Since the necessary molecular properties and structural fingerprints can be calculated easily and quickly, the models we proposed here may help speed up the process of finding or designing compounds with improved oral bioavailability.

QSAR models for CXCR2 receptor antagonists based on the genetic algorithm for data preprocessing prior to application of the PLS linear regression method and design of the new compounds using in silico virtual screening

The CXCR2 receptors play a pivotal role in inflammatory disorders and CXCR2 receptor antagonists can in principle be used in the treatment of inflammatory and related diseases. In this study, quantitative relationships between the structures of 130 antagonists of the CXCR2 receptors and their activities were investigated by the partial least squares (PLS) method. The genetic algorithm (GA) has been proposed for improvement of the performance of the PLS modeling by choosing the most relevant descriptors. The results of the factor analysis show that eight latent variables are able to describe about 86.77% of the variance in the experimental activity of the molecules in the training set. Power prediction of the QSAR models developed with SMLR, PLS and GA-PLS methods were evaluated using cross-validation, and validation through an external prediction set. The results showed satisfactory goodness-of-fit, robustness and perfect external predictive performance. A comparison between the different developed methods indicates that GA-PLS can be chosen as supreme model due to its better prediction ability than the other two methods. The applicability domain was used to define the area of reliable predictions. Furthermore, the in silico screening technique was applied to the proposed QSAR model and the structure and potency of new compounds were predicted. The developed models were found to be useful for the estimation of pIC₅₀ of CXCR2 receptors for which no experimental data is available.

Global antifungal profile optimization of chlorophenyl derivatives against Botrytis cinerea and Colletotrichum gloeosporioides

Twenty-two aromatic derivatives bearing a chlorine atom and a different chain in the para or meta position were prepared and evaluated for their in vitro antifungal activity against the phytopathogenic fungi Botrytis cinerea and Colletotrichum gloeosporioides. The results showed that maximum inhibition of the growth of these fungi was exhibited for enantiomers S and R of 1-(4'-chlorophenyl)-2-phenylethanol (3 and 4). Furthermore, their antifungal activity showed a clear structure-activity relationship (SAR) trend confirming the importance of the benzyl hydroxyl group in the inhibitory mechanism of the compounds studied. Additionally, a multiobjective optimization study of the global antifungal profile of chlorophenyl derivatives was conducted in order to establish a rational strategy for the filtering of new fungicide candidates from combinatorial libraries. The MOOP-DESIRE methodology was used for this purpose providing reliable ranking models that can be used later.

Desirability-based multiobjective optimization for global QSAR studies: application to the design of novel NSAIDs with improved analgesic, antiinflammatory, and ulcerogenic profiles

Up to now, very few reports have been published concerning the application of multiobjective optimization (MOOP) techniques to quantitative structure-activity relationship (QSAR) studies. However, none reports the optimization of objectives related directly to the desired pharmaceutical profile of the drug. In this work, for the first time, it is proposed a MOOP method based on Derringer's desirability function that allows conducting global QSAR studies considering simultaneously the pharmacological, pharmacokinetic and toxicological profile of a set of molecule candidates. The usefulness of the method is demonstrated by applying it to the simultaneous optimization of the analgesic, antiinflammatory, and ulcerogenic properties of a library of fifteen 3-(3-methylphenyl)-2-substituted amino-3H-quinazolin-4-one compounds. The levels of the predictor variables producing concurrently the best possible compromise between these properties is found and used to design a set of new optimized drug candidates. Our results also suggest the relevant role of the bulkiness of alkyl substituents on the C-2 position of the quinazoline ring over the ulcerogenic properties for this family of compounds. Finally, and most importantly, the desirability-based MOOP method proposed is a valuable tool and shall aid in the future rational design of novel successful drugs.

Prediction of fungicidal activities of rice blast disease based on least-squares support vector machines and project pursuit regression

Three machine learning methods, genetic algorithm-multilinear regression (GA-MLR), least-squares support vector machine (LS-SVM), and project pursuit regression (PPR), were used to investigate the relationship between thiazoline derivatives and their fungicidal activities against the rice blast disease. The GA-MLR method was used to select the most appropriate molecular descriptors from a large set of descriptors, which were only calculated from molecular structures, and develop a linear quantitative structure-activity relationship (QSAR) model at the same time. On the basis of the selected descriptors, the other two more accurate models (LS-SVM and PPR) were built. Both the linear and nonlinear modes gave good prediction results, but the nonlinear models afforded better prediction ability, which meant that the LS-SVM and PPR methods could simulate the relationship between the structural descriptors and fungicidal activities more accurately. The results show that the nonlinear methods (LS-SVM and PPR) could be used as good modeling tools for the study of rice blast. Moreover, this study provides a new and simple but efficient approach, which should facilitate the design and development of new compounds to resist the rice blast disease.

Desirability-based methods of multiobjective optimization and ranking for global QSAR studies. Filtering safe and potent drug candidates from combinatorial libraries

Up to now, very few applications of multiobjective optimization (MOOP) techniques to quantitative structure-activity relationship (QSAR) studies have been reported in the literature. However, none of them report the optimization of objectives related directly to the final pharmaceutical profile of a drug. In this paper, a MOOP method based on Derringer's desirability function that allows conducting global QSAR studies, simultaneously considering the potency, bioavailability, and safety of a set of drug candidates, is introduced. The results of the desirability-based MOOP (the levels of the predictor variables concurrently producing the best possible compromise between the properties determining an optimal drug candidate) are used for the implementation of a ranking method that is also based on the application of desirability functions. This method allows ranking drug candidates with unknown pharmaceutical properties from combinatorial libraries according to the degree of similarity with the previously determined optimal candidate. Application of this method will make it possible to filter the most promising drug candidates of a library (the best-ranked candidates), which should have the best pharmaceutical profile (the best compromise between potency, safety and bioavailability). In addition, a validation method of the ranking process, as well as a quantitative measure of the quality of a ranking, the ranking quality index (Psi), is proposed. The usefulness of the desirability-based methods of MOOP and ranking is demonstrated by its application to a library of 95 fluoroquinolones, reporting their gram-negative antibacterial activity and mammalian cell cytotoxicity. Finally, the combined use of the desirability-based methods of MOOP and ranking proposed here seems to be a valuable tool for rational drug discovery and development.

QSAR study of selective ligands for the thyroid hormone receptor β

In this paper, an accurate and reliable QSAR model of 87 selective ligands for the thyroid hormone receptor beta 1 (TRbeta1) was developed, based on theoretical molecular descriptors to predict the binding affinity of compounds with receptor. The structural characteristics of compounds were described wholly by a large amount of molecular structural descriptors calculated by DRAGON. Six most relevant structural descriptors to the studied activity were selected as the inputs of QSAR model by a robust optimization algorithm Genetic Algorithm. The built model was fully assessed by various validation methods, including internal and external validation, Y-randomization test, chemical applicability domain, and all the validations indicate that the QSAR model we proposed is robust and satisfactory. Thus, the built QSAR model can be used to fast and accurately predict the binding affinity of compounds (in the defined applicability domain) to TRbeta1. At the same time, the model proposed could also identify and provide some insight into what structural features are related to the biological activity of these compounds and provide some instruction for further designing the new selective ligands for TRbeta1 with high activity.

Computational modeling tools for the design of potent antimalarial bisbenzamidines: Overcoming the antimalarial potential of pentamidine

Malaria is nowadays a worldwide and serious problem with a significant social, economic, and human cost, mainly in developing countries. In addition, the emergence and spread of resistance to existing antimalarial therapies deteriorate the global malaria situation, and lead thus to an urgent need toward the design and discovery of new antimalarial drugs. In this work, a QSAR predictive model based on GETAWAY descriptors was developed which is able to explain with, only three variables, more than 77% of the variance in antimalarial potency and displays a good internal predictive ability (of 73.3% and 72.9% from leave-one-out cross-validation and bootstrapping analyses, respectively). The performance of the proposed model was judged against other five methodologies providing evidence of the superiority of GETAWAY descriptors in predicting the antimalarial potency of the bisbenzamidine family. Moreover, a desirability analysis based on the final QSAR model showed that to be a useful way of selecting the predictive variable level necessary to obtain potent bisbenzamidines. From the proposed model it is also possible to infer that elevated high atomic masses/polarizabilities/van der Waals volumes could play a negative/positive/positive role in the molecular interactions responsible for the desired drug conformation, which is required for the optimal binding to the macromolecular target. The results obtained point out that our final QSAR model is statistically significant and robust as well as possessing a high predictive effectiveness. Thus, the model provides a feasible and practical tool for looking for new and potent antimalarial bisbenzamidines.

In silico screening of estrogen-like chemicals based on different nonlinear classification models

Increasing concern is being shown by the scientific community, government regulators, and the public about endocrine-disrupting chemicals that are adversely affecting human and wildlife health through a variety of mechanisms. There is a great need for an effective means of rapidly assessing endocrine-disrupting activity, especially estrogen-simulating activity, because of the large number of such chemicals in the environment. In this study, quantitative structure activity relationship (QSAR) models were developed to quickly and effectively identify possible estrogen-like chemicals based on 232 structurally-diverse chemicals (training set) by using several nonlinear classification methodologies (least-square support vector machine (LS-SVM), counter-propagation artificial neural network (CP-ANN), and k nearest neighbour (kNN)) based on molecular structural descriptors. The models were externally validated by 87 chemicals (prediction set) not included in the training set. All three methods can give satisfactory prediction results both for training and prediction sets, and the most accurate model was obtained by the LS-SVM approach through the comparison of performance. In addition, our model was also applied to about 58,000 discrete organic chemicals; about 76% were predicted not to bind to Estrogen Receptor. The obtained results indicate that the proposed QSAR models are robust, widely applicable and could provide a feasible and practical tool for the rapid screening of potential estrogens.

Application of genetic algorithm-kernel partial least square as a novel nonlinear feature selection method: Activity of carbonic anhydrase II inhibitors

This paper introduces the genetic algorithm-kernel partial least square (GA-KPLS), as a novel nonlinear feature selection method. This technique combines genetic algorithms (GAs) as powerful optimization methods with KPLS as a robust nonlinear statistical method for variable selection. This feature selection method is combined with artificial neural network to develop a nonlinear QSAR model for predicting activities of a series of substituted aromatic sulfonamides as carbonic anhydrase II (CA II) inhibitors. Eight simple one- and two-dimensional descriptors were selected by GA-KPLS and considered as inputs for developing artificial neural networks (ANNs). These parameters represent the role of acceptor-donor pair, hydrogen bonding, hydrosolubility and lipophilicity of the active sites and also the size of the inhibitors on inhibitor-isozyme interaction. The accuracy of 8-4-1 networks was illustrated by validation techniques of leave-one-out (LOO) and leave-multiple-out (LMO) cross-validations and Y-randomization. Superiority of this method (GA-KPLS-ANN) over the linear one (MLR) in a previous work and also the GA-PLS-ANN in which a linear feature selection method has been used indicates that the GA-KPLS approach is a powerful method for the variable selection in nonlinear systems.

Pharmacokinetics and metabolism of 3,4-dichlorophenyl-propenoyl-sec.-butylamine in rats by high performance liquid chromatography–ion trap mass spectrometry

The pharmacokinetics (PK) and metabolism of 3,4-dichlorophenyl-propenoyl-sec.-butylamine (3,4-DCPB), a novel antiepileptic drug, were investigated after its oral administration to rats (100 mg/kg) by HPLC. The absorption and elimination of 3,4-DCPB were rapid. 3,4-DCPB was found to undergo extensive metabolism as the major route of elimination. Structures of the metabolites present in rat plasma were identified with liquid chromatography-electrospray ionization-mass spectrometry (LC-ESI-MS/MS). It was concluded that 3,4-DCPB was involved in the multiple metabolic pathways (hydrolysis, dealkylation and oxidation) and the hydrolysis product, 3,4-dichloro-cinnamic acid (M1) appeared to be the major metabolite.

Quantitative structure activity relationship of benzoxazinone derivatives as neuropeptide Y Y5 receptor antagonists

Quantitative structure activity relationship (QSAR) has been established for 30 benzoxazinone derivatives acting as neuropeptide Y Y5 receptor antagonists. The genetic algorithm and multiple linear regression were used to generate the relationship between biological activity and calculated descriptors. Model with good statistical qualities was developed using four descriptors from topological, thermodynamic, spatial and electrotopological class. The validation of the model was done by cross validation, randomization and external test set prediction.

A new set of amino acid descriptors and its application in peptide QSARs

In this work, a new set of amino acid descriptors, i.e., VHSE (principal components score Vectors of Hydrophobic, Steric, and Electronic properties), is derived from principal components analysis (PCA) on independent families of 18 hydrophobic properties, 17 steric properties, and 15 electronic properties, respectively, which are included in total 50 physicochemical variables of 20 coded amino acids. Using the stepwise multiple regression (SMR) method combined with partial least squares (PLS), the VHSE scales are then applied to QSAR studies of bitter-tasting dipeptides (BTD), angiotensin-converting enzyme (ACE) inhibitors, and bradykinin-potentiating pentapeptides (BPP). To validate the predictive power of resulting models, external validation are also performed. A comparison of the results to those obtained with z scores and other two-dimensional (2D) or three-dimensional(3D) descriptors shows that the VHSE scales are comparable for parameterizing the structural variability of the peptide series.

A QSAR toxicity study of a series of alkaloids with the lycoctonine skeleton

A QSAR toxicity analysis has been performed for a series of 19 alkaloids with the lycoctonine skeleton. GA-MLRA (Genetic Algorithm combined with Multiple Linear Regression Analysis) technique was applied for the generation of two types of QSARs: first, models containing exclusively 3D-descriptors and second, models consisting of physicochemical descriptors. As expected, 3D-descriptor QSARs have better statistical fits. Physicochemical-descriptor containing models, that are in a good agreement with the mode of toxic action exerted by the alkaloids studied, have also been identified and discussed. In particular, TPSA (Topological Polar Surface Area) and nC=O (number of -C(O)- fragments) parameters give the best statistically significant mono- and bidescriptor models (when combined with lipophilicity, MlogP) confirming the importance of H-bonding capability of the alkaloids for binding at the receptor site.

A new molecular simulation software package--Peking University Drug Design System (PKUDDS) for structure-based drug design

We present a comprehensive molecular simulation program package, the Peking University Drug Design System (PKUDDS), which runs on personal computers. PKUDDS has been developed mainly for computer-aided drug design using the methods of two-dimensional quantitative structure-activity relationships, three-dimensional quantitative structure-activity relationships, molecular docking, and database screening. This study presents an overview of its functionality, especially of methods developed in our group. PKUDDS uses genetic algorithms in molecular docking, conformational analysis, and quantitative structure-activity relationships as the most useful optimization technique. A user-friendly graphical interface provides easy access to many functions of PKUDDS. We report some examples of our considerable research using PKUDDS.

Enhancement of binary QSAR analysis by a GA-based variable selection method

Binary quantitative structure-activity relationship (QSAR) is an approach for the analysis of high throughput screening (HTS) data by correlating structural properties of compounds with a "binary" expression of biological activity (1 = active and 0 = inactive) and calculating a probability distribution for active and inactive compounds in a training set. Successfully deriving a predictive binary or any QSAR model largely depends on the selection of a preferred set of molecular descriptors that can capture the chemico-biological interaction for a particular biological target. In this study, a genetic algorithm (GA) was applied as a variable selection method in binary QSAR analysis. This GA-based variable selection method was applied to the analysis of three diverse sets of compounds, estrogen receptor (ER) ligands, carbonic anhydrase II inhibitors, and monoamine oxidase (MAO) inhibitors. Out of a variable pool of 150 molecular descriptors, predictive binary QSAR models were obtained for all three sets of compounds within a reasonable number of GA generations. The results indicate that the GA is a very effective variable selection approach for binary QSAR analysis.

Application of BCUT metrics and genetic algorithm in binary QSAR analysis

The application of three-dimensional H-suppressed BCUT metrics (BCUTs) in binary QSAR analysis was investigated using carbonic anhydrase II inhibitors and estrogen receptor ligands as test cases. Variable selection was accomplished with a genetic algorithm (GA). Highly predictive binary QSAR models were obtained for both sets of compounds within 200 GA generations. The derived binary QSAR models were validated with two sets of compounds not included in the training sets. The results indicate that BCUTs are very useful molecular descriptors, and the genetic algorithm is a very efficient variable selection tool in binary QSAR analysis.