Route Designer: a retrosynthetic analysis tool utilizing automated retrosynthetic rule generation.

Route Designer, version 1.0, is a new retrosynthetic analysis package that generates complete synthetic routes for target molecules starting from readily available starting materials. Rules describing retrosynthetic transformations are automatically generated from reaction databases, which ensure that the rules can be easily updated to reflect the latest reaction literature. These rules are used to carry out an exhaustive retrosynthetic analysis of the target molecule, in which heuristics are used to mitigate the combinatorial explosion. Proposed routes are prioritized by an empirical rating algorithm to present a diverse profile of the most promising solutions. The program runs on a server with a web-based user interface. An overview of the system is presented together with examples that illustrate Route Designer's utility.

On-the-fly selection of a training set for aqueous solubility prediction.

Training sets are usually chosen so that they represent the database as a whole; random selection helps to maintain this integrity. In this study, the prediction of aqueous solubility was used as a specific example of using the individual molecule for which solubility is desired, the target molecule, as the basis for choosing a training set. Similarity of the training set to the target molecule rather than a random allocation was used as the selection criteria. The Tanimoto coefficients derived from Daylight's binary fingerprints were used as the molecular similarity selection tool. Prediction models derived from this type of customization will be designated as "on-the-fly local" models because a new model is generated for each target molecule which is necessarily local. Such models will be compared with "global" models which are derived from a one-time "preprocessed" partitioning of training and test sets which use fixed fitted parameters for each target molecule prediction. Although both fragment and molecular descriptors were examined, a minimum set of MOE (molecular operating environment) molecular descriptors were found to be more efficient and were use for both on-the-fly local and preprocessed global models. It was found that on-the-fly local predictions were more accurate (r2=0.87) than the preprocessed global predictions (r2=0.74) for the same test set. In addition, their precision was shown to increase as the degree of similarity increases. Correlation and distribution plots were used to visualize similarity cutoff groupings and their chemical structures. In summary, rapid "on-the-fly" similarity selection can enable the customization of a training set to each target molecule for which solubility is desired. In addition, the similarity information and the model's fitting statistics give the user criteria to judge the validity of the prediction since it is always possible that good prediction cannot be obtained because the database and the target molecule are too dissimilar. Although the rapid processing speed of binary fingerprints enable the "on-the-fly" real time prediction, slower but more feature rich similarity measures may improve follow-up predictions.

Prediction of drug degradants using DELPHI: an expert system for focusing knowledge.

DELPHI is an expert system that has been developed to predict possible degradants of pharmaceutical compounds under stress testing conditions. It has been programmed with the objective of finding relevant degradation pathways, identifying degradant structures, and providing tools to the analytical chemist to assist in degradation identification. The system makes degradant predictions based on the chemical structure of the drug molecule and precedent from a broad survey of the literature. A description of DELPHI's treatment of molecular perception is described as are many features of the heuristic degradation rules it uses to capture and apply chemical degradation knowledge. DELPHI's utility for capturing institutional knowledge is discussed in relation to an analysis of degradation prediction results for 250 molecules of diverse chemical structure collected over 5 years of use. As such, it provides a reliable, convenient, and rapid tool for evaluating potential pathways of chemical instability of pharmaceuticals.

Discovering H-bonding rules in crystals with inductive logic programming.

In the domain of crystal engineering, various schemes have been proposed for the classification of hydrogen bonding (H-bonding) patterns observed in 3D crystal structures. In this study, the aim is to complement these schemes with rules that predict H-bonding in crystals from 2D structural information only. Modern computational power and the advances in inductive logic programming (ILP) can now provide computational chemistry with the opportunity for extracting structure-specific rules from large databases that can be incorporated into expert systems. ILP technology is here applied to H-bonding in crystals to develop a self-extracting expert system utilizing data in the Cambridge Structural Database of small molecule crystal structures. A clear increase in performance was observed when the ILP system DMax was allowed to refer to the local structural environment of the possible H-bond donor/acceptor pairs. This ability distinguishes ILP from more traditional approaches that build rules on the basis of global molecular properties.

Semi-empirical relationships between effective mobility, charge, and molecular weight of pharmaceuticals by pressure-assisted capillary electrophoresis: applications in drug discovery.

Relationships between effective mobility (m(eff)), calculated charge (Z(c)), and molecular weight (MW) are semi-empirically derived for pharmaceuticals using pressure-assisted capillary electrophoresis (PACE). We determined the m(eff) at 12 different pH points (2.0-11.4) of 66 pharmaceutical-like compounds ranging in MW from 79 to 825 g/mol. Plots of the observed m(eff) values versus Z(c)/MW(x ) (where x is a fractional coefficient) gave linear relationships. For anions, it was found that the best correlation (R(2) = 0.9666) exists when the fractional coefficient is equal to 0.4920, resulting in the equation m(eff) = 0.1853 (Z(c)/MW (0.4920)). For cations, the best linear relationship (R(2) = 0.9861) gave the equation m(eff) = 0.3888 (Z(c)/MW (0.6330)). The m(eff), Z(c)/MW(x) relationships were then applied to: (i) developing a technique for selecting an appropriate pH to achieve optimal separation of pharmaceuticals and (ii) determining the maximum charge of a molecule in the pH range of determination of negative log of the dissociation constants (pK(a)) by PACE, thus enabling the correct choice of model equation to be automated without structure analysis.