The Self-organizing Vector of Atom-pairs Proportions: Use to Develop Models for Melting Points

Atom-pairs proportions are the transparent quality of a molecule: if a molecule has two atoms of oxygen and three atoms of nitrogen, the atom-pair atom1-atom2 can be expressed as a code 'atom1-atom2-n1-n2', indicating the different atoms and their numbers. These codes for a group of atoms (nitrogen, oxygen, sulfur, phosphorus, fluorine, chlorine, bromine, as well as, double and triple covalent bonds) are applied to build up the so-called optimal molecular descriptor calculated with special coefficients named correlation weights of corresponding pairs. The numerical data on the correlation weights are calculated by the Monte Carlo technique using the CORAL software (http://www.insilico.eu/coral). The one-variable model for melting points of 8653 various organic compounds is characterized by the following statistical quality: n=6483, r2=0.6452; RMSE=61.9’C; n=2170, r2=0.7941, RMSE=39.2’C.

The Monte Carlo Method as a Tool to Build up Predictive QSPR/QSAR

Background: The Monte Carlo method has a wide application in various scientific researches. For the development of predictive models in a form of the quantitative structure-property / activity relationships (QSPRs/QSARs), the Monte Carlo approach also can be useful. The CORAL software provides the Monte Carlo calculations aimed to build up QSPR/QSAR models for different endpoints. Methods: Molecular descriptors are a mathematical function of so-called correlation weights of various molecular features. The numerical values of the correlation weights give the maximal value of a target function. The target function leads to a correlation between endpoint and optimal descriptor for the visible training set. The predictive potential of the model is estimated with the validation set, i.e. compounds that are not involved in the process of building up the model. Results: The approach gave quite good models for a large number of various physicochemical, biochemical, ecological, and medicinal endpoints. Bibliography and basic statistical characteristics of several CORAL models are collected in the present review. In addition, the extended version of the approach for more complex systems (nanomaterials and peptides), where behaviour of systems is defined by a group of conditions besides the molecular structure is demonstrated. Conclusion: The Monte Carlo technique available via the CORAL software can be a useful and convenient tool for the QSPR/QSAR analysis.

Research on FCM and NHL Based High Order Mining Driven by Big Data

In order to get the high order evaluation and correlation degree among big data with the characteristics of multidimension and multigranularity, an FCM and NHL based high order mining algorithm driven by big data is proposed, which is a kind of machine learning based on qualitative knowledge. The algorithm is applied in scientific and technical talent forecast. Driven by the big data of scientific research track of scientific and technical talents, the index system is designed and the big data is automatically acquired and processed. Accordingly, the high order evaluations in dimension level and target level can be inferred by the correlation weights mining. And the outstanding young talents in material field in 2014 have been actively recommended to review department for decision-making.

Analysis of the co-evolutions of correlations as a tool for QSAR-modeling of carcinogenicity: an unexpected good prediction based on a model that seems untrustworthy

To validate QSAR models an external test set is increasingly used. However the definition of the compounds for the test set is still debated. We studied, co-evolutions of correlations between optimal descriptors and carcinogenicity (pTD50) for the subtraining, calibration, and test set. Weak correlations for the sub-training set are sometimes accompanied by quite good correlations for the external test set. This can be explained in terms of the probability theory and can help define a suitable test set. The simplified molecular input line entry system (SMILES) was used to represent the molecular structure. Correlation weights for calculating the optimal descriptors are related to fragments of the SMILES. The statistical quality of the model is: n=170, r2=0.6638, q2=0.6554, s=0.828, F=331 (sub-training set); n=170, r2=0.6609, r2pred=0.6520, s=0.825, F=331 (calibration set); and n=61, r2=0.7796, r2pred=0.7658, Rm2=0.7448, s=0.563, F=221 (test set). The calculations were done with CORAL software (http://www.insilico.eu/coral/).

Improved QSAR modeling of anti-HIV-1 acivities by means of the optimized correlation weights of local graph invariants

We report the results derived from the use of molecular descriptors calculated with the correlation weights (CWs) of local graph invariants for modeling of anti-HIV-1 potencies of two groups of reverse transcriptase inhibitors. The presence of different chemical elements in the molecular structure of the inhibitors and the Morgan extended connectivity values of zeroth-, first-, and second order have been examined as local graph invariants in the labeled hydrogen-filled graphs. We have computed via Monte Carlo optimization procedure the values of CWs which produce the largest possible correlation coefficient between the numerical data on the anti-HIV-1 potencies and those values of the descriptors on the training set. The model of the anti-HIV-1 activity obtained with compounds of training set by means of optimization of correlation weights of chemical elements present together with Morgan extended connectivity of first order makes up a sensible model for a satisfactory prediction of the endpoints of the compounds belonging to the test set.