Machine learning techniques and drug design.

The interest in the application of machine learning techniques (MLT) as drug design tools is growing in the last decades. The reason for this is related to the fact that the drug design is very complex and requires the use of hybrid techniques. A brief review of some MLT such as self-organizing maps, multilayer perceptron, bayesian neural networks, counter-propagation neural network and support vector machines is described in this paper. A comparison between the performance of the described methods and some classical statistical methods (such as partial least squares and multiple linear regression) shows that MLT have significant advantages. Nowadays, the number of studies in medicinal chemistry that employ these techniques has considerably increased, in particular the use of support vector machines. The state of the art and the future trends of MLT applications encompass the use of these techniques to construct more reliable QSAR models. The models obtained from MLT can be used in virtual screening studies as well as filters to develop/discovery new chemicals. An important challenge in the drug design field is the prediction of pharmacokinetic and toxicity properties, which can avoid failures in the clinical phases. Therefore, this review provides a critical point of view on the main MLT and shows their potential ability as a valuable tool in drug design.

Excitation energies from ground-state density-functionals by means of generator coordinates.

The generator-coordinate method is a flexible and powerful reformulation of the variational principle. Here we show that by introducing a generator coordinate in the Kohn-Sham equation of density-functional theory, excitation energies can be obtained from ground-state density functionals. As a viability test, the method is applied to ground-state energies and various types of excited-state energies of atoms and ions from the He and the Li isoelectronic series. Results are compared to a variety of alternative DFT-based approaches to excited states, in particular time-dependent density-functional theory with exact and approximate potentials.

Generator coordinate method in time-dependent density-functional theory: memory made simple.

The generator coordinate (GC) method is a variational approach to the quantum many-body problem in which interacting many-body wave functions are constructed as superpositions of (generally nonorthogonal) eigenstates of auxiliary Hamiltonians containing a deformation parameter. This paper presents a time-dependent extension of the GC method as a new approach to improve existing approximations of the exchange-correlation (XC) potential in time-dependent density-functional theory (TDDFT). The time-dependent GC method is shown to be a conceptually and computationally simple tool to build memory effects into any existing adiabatic XC potential. As an illustration, the method is applied to driven parametric oscillations of two interacting electrons in a harmonic potential (Hooke's atom). It is demonstrated that a proper choice of time-dependent generator coordinates in conjunction with the adiabatic local-density approximation reproduces the exact linear and nonlinear two-electron dynamics quite accurately, including features associated with double excitations that cannot be captured by TDDFT in the adiabatic approximation.

A chemometric study of megazol derivatives with activity against Trypanosoma equiperdum.

The AM1 semiempirical method was employed to study megazol and 13 of its analogues where their activity against Trypanosoma equiperdum was obtained from in vitro tests. Several molecular properties (descriptors or variables) were calculated for the 14 compounds studied to be correlated with the biological activity. For a practical analysis of large data sets, it is necessary to reduce the dimensionality and select the most relevant descriptors related to the biological activity under study. For this purpose, the following chemometric methods were employed: principal component analysis (PCA), hierarchical cluster analysis (HCA), K-nearest neighbour (KNN), stepwise discriminant analysis (SDA) and soft independent modelling of class analogy (SIMCA). These methods showed that the descriptors molecular electronic energy (Eelet), charge on the first nitrogen at substituent 2 (qN), volume of substituent at C5 position (V-S5), dihedral angle (D3) and bond length between atom C4 and its substituents (L4) are responsible for the separation between active and inactive compounds against T. equiperdum.

A structure-activity relationship study of quinone compounds with trypanocidal activity.

A set of 25 quinone compounds with anti-trypanocidal activity was studied by using the density functional theory (DFT) method in order to calculate atomic and molecular properties to be correlated with the biological activity. The chemometric methods principal component analysis (PCA), hierarchical cluster analysis (HCA), stepwise discriminant analysis (SDA), Kth nearest neighbor (KNN) and soft independent modeling of class analogy (SIMCA) were used to obtain possible relationships between the calculated descriptors and the biological activity studied and to predict the anti-trypanocidal activity of new quinone compounds from a prediction set. Four descriptors were responsible for the separation between the active and inactive compounds: T5 (torsion angle), QTS1 (sum of absolute values of the atomic charges), VOLS2 (volume of the substituent at region B) and HOMO-1 (energy of the molecular orbital below HOMO). These descriptors give information on the kind of interaction that occurs between the compounds and the biological receptor. The prediction study was done with a set of three new compounds by using the PCA, HCA, SDA, KNN and SIMCA methods and two of them were predicted as active against the Trypanosoma cruzi.

Synthesis, structure, electronic and vibrational spectra of 9-(Diethylamino)-benzo(a)phenoxazin-7-ium-5-N-methacrylamide.

The electronic and vibrational spectra of 9-(Diethylamino)-benzo(a)phenoxazin-7-ium-5-N-methacrylamide (Nile Blue-5-N-methacrylamide) are measured, and the results are compared with the theoretical values obtained by quantum chemical calculations. The geometry, electronic transitions, charge distribution, and the IR normal modes of this new dye and of its precursor Nile Blue have been computed by using Density Functional Theory (DFT) method with the functional B3LYP and the 6-31G(d) Gaussian basis set. The molecular properties of the two dyes, predicted and observed, are very similar in the electronic ground state. In the excited state, however, the longer lifetime and larger fluorescence quantum yield of the Nile Blue-5-methacrylamide is ascribed to an inhibition of the twisted intramolecular charge transfer (TICT) process, when the NH2 is substituted by the methacrylamide in the 5-position of the aromatic extended ring of the dye. The change in charge density of the N atom in 5-position, as well as the difference in dipole moment and ionization potential of the two dyes molecules, explain the attenuation of TICT process. The vibration spectra of both dyes are simulated properly by using the DFT method.

Immunohistochemical characterization of intraocular metastasis of a canine transmissible venereal tumor.

Little has been published on intraocular metastasis of transmissible venereal tumors (TVT) in dogs. This report presents a 4-year-old male Labrador Retriever with a previous history of subcutaneous TVT which underwent total remission after treatment with vincristine. The dog presented with clinical signs of uveitis and increased intraocular pressure (IOP) in both eyes. After enucleation of the left eye, a diagnosis of TVT was made based on morphology, histology and immunohistochemistry (IHC). IHC staining for vimentin, S-100 protein, cytokeratin and HMB45 was performed to differentiate this lesion from TVT, lymphoma, melanoma, carcinomas, neurogenic tumors and fibrosarcoma. The IHC findings supported the diagnosis of TVT for this round cell tumor.