Function extractCodingRegion

synthesis/codon/codon.go:298–321

extractCodingRegion loops through genbank data to find all CDS (coding sequences)

(data genbank.Genbank)

// extractCodingRegion loops through genbank data to find all CDS (coding sequences)
func extractCodingRegion(data genbank.Genbank) ([]string, error) {
	codingRegions := []string{}

	// iterate through the features of the genbank file and if the feature is a coding region, append the sequence to the string builder
	for _, feature := range data.Features {
		if feature.Type == "CDS" {
			sequence, err := feature.GetSequence()
			if err != nil {
				return nil, err
			}

			// Note: sometimes, genbank files will have annotated CDSs that are pseudo genes (not having triplet codons).
			// This will shift the entire codon table, messing up the end results. To fix this, make sure to do a modulo
			// check.
			if len(sequence)%3 != 0 {
				continue
			}

			codingRegions = append(codingRegions, sequence)
		}
	}

	return codingRegions, nil
}

// getCodonFrequency takes a DNA sequence and returns a hashmap of its codons and their frequencies.
func getCodonFrequency(sequence string) map[string]int {