Sequence Study — Translate and Inspect

MODEL "Sequence Study — Translate and Inspect"
DESCRIPTION "Read a synthetic peptide, inspect ORF coordinates and alignment differences, and reuse the Sequence workspace for file-based analysis."
VERSION "1.0.0"
AUTHOR "Grid Team"
TAGS "biology", "research", "sequence", "alignment"

# The toy coding sequence includes a stop codon. The biology functions report
# invalid alphabet symbols; they do not silently clean supplied DNA.
input CodingDna = "ATGGCTGAATTTTAA"
input AlignmentTarget = "ACGTTCGT"
input MinimumOrfAminoAcids = 2
  VALIDATE IN {1, 2, 3, 4, 5, 10, 20, 50, 100} MESSAGE "Choose a listed minimum ORF length: 1, 2, 3, 4, 5, 10, 20, 50, or 100 amino acids."

SequenceData = BIO_SEQUENCE(CodingDna, "dna")
output Protein = BIO_TRANSLATE(SequenceData, 1, TRUE)
output OpenReadingFrames = BIO_FIND_ORFS(SequenceData, MinimumOrfAminoAcids, 10)
output Alignment = BIO_ALIGN("ACGTACGT", AlignmentTarget, "global")
output AlignmentScore IS number = Alignment.score
output AlignmentMatches IS number = Alignment.matches
output AlignmentMismatches IS number = Alignment.mismatches
output Contig_N50 IS number = DNA_N50({1000, 800, 400, 200})
output Assumptions IS string = "Synthetic DNA and standard genetic code. Translation frame 1 produces MAEF and stops. ORF and alignment intervals are zero-based and end-exclusive; negative ORF frames use coordinates on the original forward strand. Motif position functions use a separate 1-based convention."
output ScenarioGuide IS string = "Select Protein, OpenReadingFrames, or Alignment in I/O and inspect the readable result. Save the study. Change AlignmentTarget to ACGTACGT for an exact match. Try ATGZ as CodingDna to inspect the alphabet error, then restore the coding sequence or reopen the saved archive."
output FileWorkflow IS string = "For a file-based analysis, open the Sequence_1 tab and import your FASTA file. Select the sequence artifact and Find ORFs. This creates an artifact separately from the inline formulas; the inline toy sequence is not automatically imported."

A1 = "Select Protein or OpenReadingFrames in I/O to inspect their full previews."
A2 = "Alignment score"
B2 = AlignmentScore
A3 = "Matches / mismatches"
B3 = AlignmentMatches
C3 = AlignmentMismatches
A4 = "Contig N50 (bases)"
B4 = Contig_N50
A6 = Assumptions
A7 = ScenarioGuide
A8 = FileWorkflow

Sequence_1!type = "sequence"
Sequence_1!config = <toml>
  version = 1
  kind = "sequence"
  title = "Import FASTA and inspect sequence artifacts"
</toml>

END MODEL