Locating Protein-Coding Regions in Human DNA Sequences by a Multiple Sensor-Neural Network Approach

• Published in: Proceedings of the National Academy of Sciences - PNAS Vol. 88; no. 24; pp. 11261 - 11265
• Main Authors: Uberbacher, E C, Mural, R J
• Format: Journal Article
• Language: English
• Published: Washington, DC National Academy of Sciences of the United States of America 15.12.1991; National Acad Sciences
• Subjects: 550200 - Biochemistry; Algorithms; ALKALINE PHOSPHATASE; ANIMALS; Base Sequence; BASIC BIOLOGICAL SCIENCES; Biological and medical sciences; BIOLOGICAL MARKERS; BLOOD COAGULATION FACTORS; Chromosome Mapping; Chromosomes, Human; COAGULANTS; coding; Databases, Factual; DNA; DNA - genetics; DNA SEQUENCING; DRUGS; ENZYMES; Enzymes - genetics; ESTERASES; Exons; False positive errors; Fundamental and applied biological sciences. Psychology; GENES; Genes, ras; genetics; HEMATOLOGIC AGENTS; Hominidae - genetics; Humans; HYDROLASES; MAMMALS; MAN; Models, Genetic; Molecular and cellular biology; Molecular genetics; Molecular Sequence Data; MOLECULAR STRUCTURE; Murals; neural networks; Neural Networks (Computer); Nucleic acids; Nucleotide sequences; Open reading frames; ORGANIC COMPOUNDS; PATTERN RECOGNITION; PHOSPHATASES; PHOSPHORUS-GROUP TRANSFERASES; PHOSPHOTRANSFERASES; PRIMATES; PROTEINS; Proteins - genetics; PROTHROMBIN; Reading frames; Sensors; STRUCTURAL CHEMICAL ANALYSIS; TRANSFERASES; VERTEBRATES; Human; Exon; Nucleotide sequence; Localization; DNA; Recognition
• ISSN: 0027-8424; 1091-6490
• DOI: 10.1073/pnas.88.24.11261

Genes in higher eukaryotes may span tens or hundreds of kilobases with the protein-coding regions accounting for only a few percent of the total sequence. Identifying genes within large regions of uncharacterized DNA is a difficult undertaking and is currently the focus of many research efforts. We describe a reliable computational approach for locating protein-coding portions of genes in anonymous DNA sequence. Using a concept suggested by robotic environmental sensing, our method combines a set of sensor algorithms and a neural network to localize the coding regions. Several algorithms that report local characteristics of the DNA sequence, and therefore act as sensors, are also described. In its current configuration the "coding recognition module" identifies 90% of coding exons of length 100 bases or greater with less than one false positive coding exon indicated per five coding exons indicated. This is a significantly lower false positive rate than any method of which we are aware. This module demonstrates a method with general applicability to sequence-pattern recognition problems and is available for current research efforts.