DEVELOPMENT OF AN EXPERT-SYSTEM FOR AMINO-ACID-SEQUENCE IDENTIFICATION

An expert system for amino acid sequence identification has been devel oped. The algorithm uses heuristic rules developed by human expel ts i n protein sequencing, The system is applied to the chromatographic dat a of phenylthiohydantoin-amino acids acquired fi om an automated seque ncer. The peak intensities in the current cycle are compared with thos e in the previous cycle, while the calibration and succeeding cycles a re used as ancillary identification criteria when necessary. The reten tion time for each chromatographic peak in each cycle is corrected by the corresponding peak in the calibration cycle at the same run. The m ain improvement of our system compared with the onboard software used by the Applied Biosystems 477 A Protein/Peptide Sequencer is that each peak in each cycle is assigned an identification name according to th e corrected retention time to be used for the comparison with differen t cycles. The system was developed from analyses of ribonuclease A and evaluated by runs of four other protein samples that were not used in rule development. This paper demonstrates that rules developed by hum an experts can be automatically applied to sequence assignment. The ex pert system performed more accurately than the onboard software of the protein sequencer, in that the misidentification rates for the expert system were around 7%, whereas those for the onboard software were be tween 13 and 21%.