Concepedia

Expert system for predicting protein localization sites in gram‐negative bacteria

Proteins Structure Function and Bioinformatics · 1991 · 753 citations · 29 references

TL;DR

We developed an expert system that uses if‑then rules to predict protein localization sites in Gram‑negative bacteria from amino‑acid sequences alone. The system considers four sites—cytoplasm, inner membrane, periplasm, and outer membrane—and applies experimentally derived rules such as hydrophobic stretches or uncleavable N‑terminal signals for inner membrane proteins, consensus patterns for lipoproteins, and acidic residues in the mature N‑terminal region to discriminate between inner and outer membrane lipoproteins. The system achieved an 83 % accuracy, with an empirical rule that distinguishes periplasmic from outer membrane proteins based on amino‑acid composition.

Abstract

Abstract We have developed an expert system that makes use of various kinds of knowledge organized as “if‐then” rules for predicting protein localization sites in Gram‐negative bacteria, given the amino acid sequence information alone. We considered four localization sites: the cytoplasm, the inner (cytoplasmic) membrane, the periplasm, and the outer membrane. Most rules were derived from experimental observations. For example, the rule to recognize an inner membrane protein is the presence of either a hydrophobic stretch in the predicted mature protein or an uncleavable N‐terminal signal sequence. Lipoproteins are first recognized by a consensus pattern and then assumed present at either the inner or outer membrane. These two possibilities are further discriminated by examining an acidic residue in the mature N‐terminal portion. Furthermore, we found an empirical rule that periplasmic and outer membrane proteins were successfully discriminated by their different amino acid composition. Overall, our system could predict 83% of the localization sites of proteins in our database.