Correlation weighting of valence shells in QSAR analysis of toxicity

In the rainbow trout (Oncorhynchus mykiss), we studied the acute toxicity LC50-96h of 274 organic pesticides with a wide variety of molecular structures. Optimization of correlation weights of local and global graph invariants (OCWLGI) gave quantitative structure-activity relationships (QSARs) for predicting toxicity. We used a labeled hydrogen-filled graph (LHFG) to elucidate the molecular structure. We also used the extended connectivity of zero (0ECk), first (1ECk), and second (2ECk) order, numbers of path lengths 2 (P2k) and 3 (P3k) starting from a given vertex in the LHFG, and valence shells of second order (S2k). S2k is the sum of the degree of vertices at distance 2 from a given vertex k. The presence of three-, five-, and six-member cycles and hydrogen bond indices suggested they might be used as global LHFG invariants. We applied this method to a broad set of pesticides, to predict toxicity for the trout. The best model used weighted S2k and global LHFG invariants. Statistical characteristics of this model are as follows: n = 233, r2 = 0.7689, r2(pred) = 0.7688, s = 0.75, F = 769 (training set); n = 41, r2 = 0.6421, r2(pred) = 0.4241, s = 1.14, F = 70 (test set).