Search PubMed⌕ Search

Biomedical subjects

W P Walters

Publications and source records attributed to W P Walters.

6 recordsLinked to original sources
PubMed1999

Consensus scoring: A method for obtaining improved hit rates from docking databases of three-dimensional structures into proteins.

We present the results of an extensive computational study in which we show that combining scoring functions in an intersection-based consensus approach results in an enhancement in the ability to discriminate between active and inactive enzyme inhibitors. This is illustrated in the context of docking collections of three-dimensional structures into three different enzymes of pharmaceutical interest: p38 MAP kinase, inosine monophosphate dehydrogenase, and HIV protease. An analysis of two different docking methods and thirteen scoring functions provides insights into which functions perform well, both singly and in combination. Our data shows that consensus scoring further provides a dramatic reduction in the number of false positives identified by individual scoring functions, thus leading to a significant enhancement in hit-rates.

Algorithms↗
PubMed1999

Recognizing molecules with drug-like properties.

A variety of successful approaches to the problem of recognizing 'drug-like' molecules have been employed. These range from simple counting schemes such as the Lipinski 'rule of five' to the analysis of the multidimensional 'chemistry space' occupied by drugs, to neural network learning systems. With this variety of tools, it now appears possible to design libraries that are enriched in compounds which have desirable or 'drug-like' properties. Verifying the robustness of these methods, and extending them, will form the basis of research in this field during the next few years.

Administration, Oral↗
PubMed1998

Can we learn to distinguish between "drug-like" and "nondrug-like" molecules?

We have used a Bayesian neural network to distinguish between drugs and nondrugs. For this purpose, the CMC acts as a surrogate for drug-like molecules while the ACD is a surrogate for nondrug-like molecules. This task is performed by using two different set of 1D and 2D parameters. The 1D parameters contain information about the entire molecule like the molecular weight and the the 2D parameters contain information about specific functional groups within the molecule. Our best results predict correctly on over 90% of the compounds in the CMC while classifying about 10% of the molecules in the ACD as drug-like. Excellent generalization ability is shown by the models in that roughly 80% of the molecules in the MDDR are classified as drug-like. We propose to use the models to design combinatorial libraries. In a computer experiment on generating a drug-like library of size 100 from a set of 10 000 molecules we obtain at least a 3 or 4 order of magnitude improvement over random methods. The neighborhoods defined by our models are not similar to the ones generated by standard Tanimoto similarity calculations. Therefore, new and different information is being generated by our models, and so it can supplement standard diversity approaches to library design.

Bayes Theorem↗
PubMed1994

MOUSE-III: learning rules of conformational analysis from X-ray data.

MOUSE-III is learning program that finds rules of conformational analysis from raw crystallographic data. The program perceives molecular features, finds conformational classes in the data and then learns rules that link features to classes. The rules that MOUSE learns are capable of correctly assigning conformations to ring systems that were not used for training with greater than 95% accuracy, when MOUSE was presented with sufficient data. The rules also show a compression of as much as 99% when compared to the raw data. This is accomplished through abstraction and generalization. The algorithm is presented along with a carefully worked example. An example of a learned rule is also presented and analyzed. Some conclusions about the scope and limitations of the learning process are presented.

Algorithms↗
PubMed1993

Short-term learning in conformational analysis.

A method for learning short-term rules of conformational analysis is introduced. The technique works by discovering problems during the building of a conformation in Cartesian coordinate space, and builds an abstract critic suitable for reasoning in abstract symbolic space. The methods not only afford speed increases ranging from 1.0- to 2.3-fold in WIZARD (analysis completed in 100% to 43% of original run time), but can be modified to provide similar increases in other programs that use "template joining" and distance geometry. These methods also provide the basis for a long-term learning project.

Artificial Intelligence↗