Biomedical subjects

J Shirazi

Publications and source records attributed to J Shirazi.

4 recordsLinked to original sources

PubMed1994

On the use of machine learning to identify topological rules in the packing of beta-strands.

The machine learning program GOLEM was applied to discover topological rules in the packing of beta-sheets in alpha/beta-domain proteins. Rules (constraints) were determined for four features of beta-sheet packing: (i) whether a beta-strand is at an edge; (ii) whether two consecutive beta-strands pack parallel or anti-parallel; (iii) whether two beta-strands pack adjacently; and (iv) the winding direction of two consecutive beta-strands. Rules were found with high predictive accuracy and coverage. The errors were generally associated with complications in domain folds, especially in one doubly would domains. Investigation of the rules revealed interesting patterns, some of which were known previously, others that are novel. Novel features include (i) the relationship between pairs of sequential strands is in general one of decreasing size; (ii) more sequential pairs of strands wind in the direction out than in; and (iii) it takes a larger alteration in hydrophobicity to change a strand from winding in the direction out than in. These patterns in the data may be the result of folding pathways in the domains. The rules found are of predictive value and could be used in the combinatorial prediction of protein structure, or as a general test of model structures, e.g. those produced by threading. We conclude that machine learning has a useful role in the analysis of protein structures.

Amino Acid Sequence↗

PubMed1994

Inductive logic programming used to discover topological constraints in protein structures.

This paper describes the application of the Inductive Logic Programming (ILP) program GOLEM to the discovery of constraints in the packing of beta-sheets in alpha/beta proteins. These constraints (rules) have a role in understanding the protein folding problem. Constraints were learnt for four features of beta-sheet packing: the winding direction of two sequential strands, whether two consecutive strands pack parallel or anti-parallel, whether two strands pack adjacently, and whether a beta-strand is at an edge. Investigation of the learnt constraints revealed interesting patterns, some of which were previously known, others that were novel. Novel features include the discovery: that the relationship between pairs of sequential strands is in general one of decreasing size, and that more sequential pairs of strands wind in the direction out than the direction in. We conclude that machine learning has a useful place in molecular biology as a pattern discovery tool.

Animals↗

PubMed1993

Protein topology prediction through parallel constraint logic programming.

In this paper, two programs are described (CBS1e and CBS2e). These are implemented in the parallel constraint logic programming language ElipSys. These predict protein alpha/beta-sheet and beta-sheet topologies from secondary structure assignments and topological folding rules (constraints). These programs illustrate how recent developments in logic programming environments can be applied to solve large-scale combinatorial problems in molecular biology. We demonstrate that parallel constraint logic programming is able to overcome some of the important limitations of more established logic programming languages i.e. Prolog. This is particularly the case in providing features that enhance the declarative nature of the program and also in addressing directly the problems of scaling-up logic programs to solve scientifically realistic problems. Moreover, we show that for large topological problems CBS1e was approximately 60 times faster than an equivalent Prolog implementation (CBS1) on a sequential device with further performance enhancements possible on parallel computer architectures. CBS2e is an extension of CBS1e that addresses the important problem of integrating the use of uncertain (weighted) protein folding constraints with categorical ones, through the use of a cost function that is minimized. CBS2e achieves this with a relatively minor reduction of performance. These results significantly extend the range and complexity of protein structure prediction methods that can reasonably be addressed using AI languages.

Artificial Intelligence↗

PubMed1991

Protein topology prediction through constraint-based search and the evaluation of topological folding rules.

An algorithm for predicting protein alpha/beta-sheet topologies from secondary structure and topological folding rules (constraints) has been developed and implemented in Prolog. This algorithm (CBS1) is based on constraint satisfaction and employs forward pruned breadth-first search and rotational invariance. CBS1 showed a 37-fold increase in efficiency over an exhaustive generate and test algorithm giving the same solution for a typical sheet of five strands whose topology was predicted from secondary structure with four topological folding constraints. Prolog specifications of a range of putative protein folding rules were then used to (i) replicate published protein topology predictions and (ii) validate these rules against known protein structures of nucleotide-binding domains. This demonstrated that (i) manual techniques for topology prediction can lead to non-exhaustive search and (ii) most of these protein folding principles were violated by specific proteins. Various extensions to the algorithm are discussed.

Algorithms↗