Nonlinear prediction of quantitative structure-activity relationships

Predicting the log of the partition coefficient P is a long-standing benchmark problem in Quantitative Structure-Activity Relationships (QSAR). In this paper we show that a relatively simple molecular representation (using 14 variables) can be combined with leading edge machine learning algorithms to predict logP on new compounds more accurately than existing benchmark algorithms which use complex molecular representations.     

Stereocontrolled synthesis of clerodin homolog A synthetic approach to structure-activity relationships

In order to elucidate the structure-activity relationships of the antifeeding diterpenes having a $\text{neo}$-clerodane skeleton, clerodin homolog $\text{5}$ was stereoselectively synthesized through 18 steps $\text{via}$ a key intermediate $\text{11}$. Perhydrofuro[2,3-b]furan ring in the synthesized homolog was more unstable than that of the natural product, and gave a $\text{tri}$-MeOH adduct $\text{3}$ in a similar behavior to that of the model compounds $\text{1}$ and $\text{2}$.     

Stereocontrolled synthesis of clerodin homolog: A Synthetic approach to structure-activity relationships

In order to elucidate the structure-activity relationships of the antifeeding di-terpenes, clerodin homolog $\text{5}$ was stereoselectively synthesized through 18 steps $\text{via}$ a key intermediate $\text{12}$. The perhydrofuro[2,3-b]furan ring in the synthesized homolog was less stable than that of the natural product, and its reactivity on methanolysis and potency of the antifeeding activity were almost the same as those of a 2,6-di-methylphenyl derivative $\text{10}$ which is more sterically restricted than a phenyl derivative $\text{2}$. The findings supported the hypothesis for the relationships on the structure (stereostructure) and activity of biological active substances. The methodology is conceptually termed “Dynamic structure-activity relationships,” and is effective from the standpoint of drug design.     

Three-dimensional quantitative structure-activity relationships of steroid aromatase inhibitors

Summary Inhibition of aromatase, a cytochrome P450 that converts androgens to estrogens, is relevant in the therapeutic control of breast cancer. We investigate this inhibition using a three-dimensional quantitative structure-activity relationship (3D QSAR) method known as Comparative Molecular Field Analysis, CoMFA [Cramer III, R.D. et al., J. Am. Chem. Soc., 110 (1988) 5959]. We analyzed the data for 50 steroid inhibitors [Numazawa, M. et al., J. Med. Chem., 37 (1994) 2198, and references cited therein] assayed against androstenedione on human placental microsomes. An initial CoMFA resulted in a three-component model for log(1/K_i), with an explained variance r² of 0.885, and a cross-validated q² of 0.673. Chemometric studies were performed using GOLPE [Baroni, M. et al., Quant. Struct.-Act. Relatsh., 12 (1993) 9]. The CoMFA/GOLPE model is discussed in terms of robustness, predictivity, explanatory power and simplicity. After randomized exclusion of 25 or 10 compounds (repeated 25 times), the q² for one component was 0.62 and 0.61, respectively, while r² was 0.674. We demonstrate that the predictive r² based on the mean activity (Y_m) of the training set is misleading, while the test set Y_m-based predictive r² index gives a more accurate estimate of external predictivity. Using CoMFA, the observed differences in aromatase inhibition among C6-substituted steroids are rationalized at the atomic level. The CoMFA fields are consistent with known, potent inhibitors of aromatase, not included in the model. When positioned in the same alignment, these compounds have distinct features that overlap with the steric and electrostatic fields obtained in the CoMFA model. The presence of two hydrophobic binding pockets near the aromatase active site is discussed: a steric bulk tolerant one, common for C4, C6-alpha and C7-alpha substitutents, and a smaller one at the C6-beta region.     

Parabolic quantitative structure-activity relationships and photodynamic therapy: application of a three-compartment model with clearance to the in vivo quantitative structure-activity relationships of a congeneric series of pyropheophorbide derivatives used as photosensitizers for photodynamic therapy

An open three-compartment pharmacokinetic model was applied to the in vivo quantitative structure-activity relationship (QSAR) data of a homologous series of pyropheophorbide photosensitizers for photodynamic therapy (PDT). The physical model was a lipid compartment sandwiched between two identical aqueous compartments. The first compartment was assumed to clear irreversibly at a rate K0. The measured octanol-water partition coefficients, P(i) (where i is the number of carbons in the alkyl chain) and the clearance rate K0 determined the clearance kinetics of the drugs. Solving the coupled differential equations of the three-compartment model produced clearance kinetics for each of the sensitizers in each of the compartments. The third compartment was found to contain the target of PDT. This series of compounds is quite lipophilic. Therefore these drugs are found mainly in the second compartment. The drug level in the third compartment represents a small fraction of the tissue level and is thus not accessible to direct measurement by extraction. The second compartment of the model accurately predicted the clearance from the serum of mice of the hexyl ether of pyropheophorbide a, one member of this series of compounds. The diffusion and clearance rate constants were those found by fitting the pharmacokinetics of the third compartment to the QSAR data. This result validated the magnitude and mechanistic significance of the rate constants used to model the QSAR data. The PDT response to dose theory was applied to the kinetic behavior of the target compartment drug concentration. This produced a pharmacokinetic-based function connecting PDT response to dose as a function of time postinjection. This mechanistic dose-response function was fitted to published, single time point QSAR data for the pheophorbides. As a result, the PDT target threshold dose together with the predicted QSAR as a function of time postinjection was found.     

A stoichiometric approach to quantitative structure-property relationships (QSPR)

An unusual analogy between the quantitative structure-property relationships (QSPR), stoichiometry, chemical thermodynamics, and kinetics is presented. Namely, the conventional ordinary least-squares (OLS) QSPR analysis is modified so as to explicitly minimize the residuals of the species subject to a set of linear relations among the residuals. The ways the linear relations among the residuals are visualized and defined totally resemble the formalism of chemical stoichiometry and, therefore, were called isostructural reactions. It is further proved that the residuals may be uniquely partitioned into a sum of contributions associated with a set of isostructural reactions that have the same properties as the response reactions (RERs) previously deduced by us from chemical thermodynamics and kinetics. This finding is shown to be a useful tool for a deeper understanding of the QSPR. In particular, the isostructural RERs approach may be effectively used to detect the outliers.     

Inhibition of highly purified porcine kidney Na,K-ATPase by steroid glycosides of the spirostan and furostan series and a study of structure-activity relationships

A comparative investigation has been made of the action of 14 steroid glycosides of the spirostan and furostan series on highly purified Na,K-ATPase from the medullary layer of porcine kidneys (∼90% purity in terms of protein). It has been shown that alliospirosides A, B, and D, isolated from the collective fruit ofAllium sepa L., are capable of inhibiting the activity of the Na,K-ATPase The inhibition of the activity of the transport enzyme by alliospirosides A and B is of the uncompetitive type and by alliospiroside D of the competitive type. It is desirable to test alliospirosides on the intact organism. Institute of Physiology, Academy of Sciences of the Republic of Uzbekistan. Institute of the Chemistry of Plant Substances, Academy of Sciences of the Republic of Uzbekistan. Translated from Khimiya Prirodnykh Soedinenii, No. 4, pp. 558–566, July–August, 1993.     

Inhibition of highly purified porcine kidney Na,K-ATPase by steroid glycosides of the spirostan and furostan series and a study of structure-activity relationships

A comparative investigation has been made of the action of 14 steroid glycosides of the spirostan and furostan series on highly purified Na,K-ATPase from the medullary layer of porcine kidneys (90% purity in terms of protein). It has been shown that alliospirosides A, B, and D, isolated from the collective fruit ofAllium sepa L., are capable of inhibiting the activity of the Na,K-ATPase The inhibition of the activity of the transport enzyme by alliospirosides A and B is of the uncompetitive type and by alliospiroside D of the competitive type. It is desirable to test alliospirosides on the intact organism.Institute of Physiology, Academy of Sciences of the Republic of Uzbekistan. Institute of the Chemistry of Plant Substances, Academy of Sciences of the Republic of Uzbekistan. Translated from Khimiya Prirodnykh Soedinenii, No. 4, pp. 558–566, July–August, 1993.     

Applications of rule-induction in the derivation of quantitative structure-activity relationships

Summary Recently, methods have been developed in the field of Artificial Intelligence (AI), specifically in the expert systems area using rule-induction, designed to extract rules from data. We have applied these methods to the analysis of molecular series with the objective of generating rules which are predictive and reliable.The input to rule-induction consists of a number of examples with known outcomes (a training set) and the output is a tree-structured series of rules. Unlike most other analysis methods, the results of the analysis are in the form of simple statements which can be easily interpreted. These are readily applied to new data giving both a classification and a probability of correctness.Rule-induction has been applied to in-house generated and published QSAR datasets and the methodology, application and results of these analyses are discussed.The results imply that in some cases it would be advantageous to use rule-induction as a complementary technique in addition to conventional statistical and pattern-recognition methods.     

Three-dimensional quantitative structure-activity and structure-selectivity relationships of dihydrofolate reductase inhibitors

Three-dimensional quantitative structure-activity relationship (3D-QSAR) modelling using comparative molecular similarity indices analysis (CoMSIA) was applied to a series of 406 structurally diverse dihydrofolate reductase (DHFR) inhibitors from Pneumocystis carinii (pc) and rat liver (rl). X-ray crystal structures of three inhibitors bound to pcDHFR were used for defining the alignment rule. For pcDHFR, a QSAR model containing 6 components was selected using leave-10%-out cross-validation (n= 240, q2 = 0.65), while a 4-component model was selected for rlDHFR (n= 237, q2 = 0.63); both include steric, electrostatic and hydrophobic contributions. The models were validated using a large test set, designed to maximise its diversity and to verify the predictive accuracy of models for extrapolation. The pcDHFR model has r2 = 0.60 and mean absolute error (MAE) = 0.57 for the test set after removing 4 outliers, and the rlDHFR model has r2 = 0.60 and MAE = 0.69 after removing 4 test set outliers. In addition, classification models predicting selectivity for pcDHFR over rlDHFR were developed using soft independent modelling by class analogy (SIMCA), with a selectivity ratio of 2 (IC50,rlDHFR/ IC50,pcDHFR) used for delimiting classes. A 5-component model including steric and electrostatic contributions has cross-validated and test set classification rates of 0.67 and 0.68 for selective inhibitors, and 0.85 and 0.72 for unselective inhibitors. The predictive accuracy of models, together with the identification of important contributions in QSAR and classification models, offer the possibility of designing potent selective inhibitors and estimating their activity prior to synthesis.     

Comparison of different partial least-squares methods in quantitative structure-activity relationships

In this paper, the partial least-squares (PLS) is discussed. A new hybrid method combining PLS with GAGP, in which selection of variables, selection of functions and optimization of parameters were carried at the same time without any foreknowledge, was studied. A number of PLS algorithms (linear PLS, QPLS, SPL-PLS, NPLSNGA) that have appeared were compared from a theoretical viewpoint. Eight practical results with all the compared methods indicated that nonlinear models are better than linear model. In nonlinear methods, GAGP-PLS is significant.     

Quantitative structure-activity relationships for a series of selective estrogen receptor-beta modulators

The estrogen receptor-beta subtype (ERbeta) is an attractive drug target for the development of novel therapeutic agents for hormone replacement therapy. Hologram quantitative structure-activity relationships (HQSAR) were conducted on a series of 6-phenylnaphthalene and 2-phenylquinoline derivatives, employing values of ERbeta binding affinity. A training set of 65 compounds served to derive the models. The best statistical HQSAR model (q(2) = 0.73 and r(2) = 0.91) was generated using atoms, bonds, connections and donor and acceptor as fragment distinction parameters, and fragment size default (4-7) with hologram length of 199. The model was used to predict the binding affinity of an external test set of 16 compounds, and the predicted values were in good agreement with the experimental results. The final HQSAR model and the information obtained from 2D contribution maps should be useful for the design of novel ERbeta modulators having improved affinity.     

Quantitative structure-activity relationships for a series of selective estrogen receptor-beta modulators

The estrogen receptor-beta subtype (ERβ) is an attractive drug target for the development of novel therapeutic agents for hormone replacement therapy. Hologram quantitative structure-activity relationships (HQSAR) were conducted on a series of 6-phenylnaphthalene and 2-phenylquinoline derivatives, employing values of ERβ binding affinity. A training set of 65 compounds served to derive the models. The best statistical HQSAR model (q ²?=?0.73 and r ²?=?0.91) was generated using atoms, bonds, connections and donor and acceptor as fragment distinction parameters, and fragment size default (4–7) with hologram length of 199. The model was used to predict the binding affinity of an external test set of 16 compounds, and the predicted values were in good agreement with the experimental results. The final HQSAR model and the information obtained from 2D contribution maps should be useful for the design of novel ERβ modulators having improved affinity.     

Predicting toxicity of benzene derivatives by molecular hologram derived quantitative structure-activity relationships (QSARS)

Holographic quantitative structure-activity relationship (HQSAR) is an emerging QSAR technique with the combined application of molecular hologram, which encodes the frequency of occurrence of various molecular fragment types, and the subsequent partial least squares (PLS) regression analysis. Based on molecular hologram, alignment-free QSAR models could be rapidly and easily developed with highly statistical significance and predictive ability. In this paper, the toxicity data for a series of 83 benzene derivatives to the autotrophic Chlorella vulgaris (IGC50, negative logarithmic form of 6-h 50% population growth inhibition concentration in mmol/l) were subjected to HQSAR analysis and this resulted in a model with a high predictive ability. The robustness and predictive ability of the model were validated by "leave-one-out" (LOO) cross-validation procedure and an external testing set. The influence of fragment distinction parameters and fragment size on the quality of the HQSAR model have been also discussed.