valuesets 0.3.1__py3-none-any.whl

valuesets/schema/bio/sequence_chemistry.yaml

@@ -0,0 +1,477 @@
+name: sequence_chemistry
+title: Sequence Chemistry Value Sets
+description: 'Value sets for nucleic acid and protein sequence chemistry, including
+
+  standard and extended alphabets, quality encodings, and molecular representations'
+id: https://w3id.org/linkml/valuesets/bio/sequence_chemistry
+imports:
+- linkml:types
+prefixes:
+  valuesets: https://w3id.org/valuesets/
+  IUPAC: http://purl.obolibrary.org/obo/IUPAC_
+  SO: http://purl.obolibrary.org/obo/SO_
+  CHEBI: http://purl.obolibrary.org/obo/CHEBI_
+default_prefix: valuesets
+slots:
+  iupac_nucleotide:
+    description: Complete IUPAC nucleotide codes including ambiguous bases for DNA/RNA sequences
+    range: IUPACNucleotideCode
+  standard_amino_acid:
+    description: The 20 standard proteinogenic amino acids with IUPAC single-letter codes
+    range: StandardAminoAcid
+  iupac_amino_acid:
+    description: Complete IUPAC amino acid codes including standard amino acids, rare amino acids, and ambiguity codes
+    range: IUPACAminoAcidCode
+  sequence_alphabet:
+    description: Types of sequence alphabets used in bioinformatics
+    range: SequenceAlphabet
+  sequence_quality_encoding:
+    description: Quality score encoding standards used in FASTQ files and sequencing data
+    range: SequenceQualityEncoding
+  genetic_code_table:
+    description: NCBI genetic code translation tables for different organisms
+    range: GeneticCodeTable
+  sequence_strand:
+    description: Strand orientation for nucleic acid sequences
+    range: SequenceStrand
+  sequence_topology:
+    description: Topological structure of nucleic acid molecules
+    range: SequenceTopology
+  sequence_modality:
+    description: Types of sequence data based on experimental method
+    range: SequenceModality
+enums:
+  IUPACNucleotideCode:
+    title: IUPAC Nucleotide Ambiguity Codes
+    description: 'Complete IUPAC nucleotide codes including ambiguous bases for DNA/RNA sequences.
+
+      Used in FASTA and other sequence formats to represent uncertain nucleotides.'
+    permissible_values:
+      A:
+        title: A
+        description: Adenine
+      T:
+        title: T
+        description: Thymine (DNA)
+      U:
+        title: U
+        description: Uracil (RNA)
+      G:
+        title: G
+        description: Guanine
+      C:
+        title: C
+        description: Cytosine
+      R:
+        title: R
+        description: Purine (A or G)
+      Y:
+        title: Y
+        description: Pyrimidine (C or T/U)
+      S:
+        description: Strong interaction (G or C)
+      W:
+        description: Weak interaction (A or T/U)
+      K:
+        description: Keto (G or T/U)
+      M:
+        description: Amino (A or C)
+      B:
+        description: Not A (C or G or T/U)
+      D:
+        description: Not C (A or G or T/U)
+      H:
+        description: Not G (A or C or T/U)
+      V:
+        description: Not T/U (A or C or G)
+      N:
+        description: Any nucleotide (A or C or G or T/U)
+      GAP:
+        title: '-'
+        description: Gap or deletion in alignment
+  StandardAminoAcid:
+    title: Standard Amino Acids
+    description: The 20 standard proteinogenic amino acids with IUPAC single-letter codes
+    permissible_values:
+      A:
+        title: A
+        description: Alanine
+      R:
+        title: R
+        description: Arginine
+      N:
+        title: N
+        description: Asparagine
+      D:
+        title: D
+        description: Aspartic acid
+      C:
+        title: C
+        description: Cysteine
+      E:
+        title: E
+        description: Glutamic acid
+      Q:
+        title: Q
+        description: Glutamine
+      G:
+        title: G
+        description: Glycine
+      H:
+        title: H
+        description: Histidine
+      I:
+        title: I
+        description: Isoleucine
+      L:
+        title: L
+        description: Leucine
+      K:
+        title: K
+        description: Lysine
+      M:
+        title: M
+        description: Methionine
+      F:
+        title: F
+        description: Phenylalanine
+      P:
+        title: P
+        description: Proline
+      S:
+        title: S
+        description: Serine
+      T:
+        title: T
+        description: Threonine
+      W:
+        title: W
+        description: Tryptophan
+      Y:
+        title: Y
+        description: Tyrosine
+      V:
+        title: V
+        description: Valine
+  IUPACAminoAcidCode:
+    title: IUPAC Amino Acid Codes
+    description: 'Complete IUPAC amino acid codes including standard amino acids,
+
+      rare amino acids, and ambiguity codes'
+    permissible_values:
+      A:
+        title: A
+        description: Alanine
+      R:
+        title: R
+        description: Arginine
+      N:
+        title: N
+        description: Asparagine
+      D:
+        title: D
+        description: Aspartic acid
+      C:
+        title: C
+        description: Cysteine
+      E:
+        title: E
+        description: Glutamic acid
+      Q:
+        title: Q
+        description: Glutamine
+      G:
+        title: G
+        description: Glycine
+      H:
+        title: H
+        description: Histidine
+      I:
+        title: I
+        description: Isoleucine
+      L:
+        title: L
+        description: Leucine
+      K:
+        title: K
+        description: Lysine
+      M:
+        title: M
+        description: Methionine
+      F:
+        title: F
+        description: Phenylalanine
+      P:
+        title: P
+        description: Proline
+      S:
+        title: S
+        description: Serine
+      T:
+        title: T
+        description: Threonine
+      W:
+        title: W
+        description: Tryptophan
+      Y:
+        title: Y
+        description: Tyrosine
+      V:
+        title: V
+        description: Valine
+      U:
+        title: U
+        description: Selenocysteine (21st amino acid)
+        aliases:
+        - Sec
+      O:
+        title: O
+        description: Pyrrolysine (22nd amino acid)
+        aliases:
+        - Pyl
+      B:
+        description: Asparagine or Aspartic acid (N or D)
+      Z:
+        description: Glutamine or Glutamic acid (Q or E)
+      J:
+        description: Leucine or Isoleucine (L or I)
+      X:
+        description: Any amino acid
+      STOP:
+        title: '*'
+        description: Translation stop codon
+      GAP:
+        title: '-'
+        description: Gap or deletion in alignment
+  SequenceAlphabet:
+    title: Sequence Alphabet Types
+    description: Types of sequence alphabets used in bioinformatics
+    permissible_values:
+      DNA:
+        description: Deoxyribonucleic acid alphabet (A, T, G, C)
+      RNA:
+        description: Ribonucleic acid alphabet (A, U, G, C)
+      PROTEIN:
+        description: Protein/amino acid alphabet (20 standard AAs)
+      IUPAC_DNA:
+        description: Extended DNA with IUPAC ambiguity codes
+      IUPAC_RNA:
+        description: Extended RNA with IUPAC ambiguity codes
+      IUPAC_PROTEIN:
+        description: Extended protein with ambiguity codes and rare AAs
+      RESTRICTED_DNA:
+        description: Unambiguous DNA bases only (A, T, G, C)
+      RESTRICTED_RNA:
+        description: Unambiguous RNA bases only (A, U, G, C)
+      BINARY:
+        description: Binary encoding of sequences
+  SequenceQualityEncoding:
+    title: Sequence Quality Score Encodings
+    description: 'Quality score encoding standards used in FASTQ files and sequencing data.
+
+      Different platforms and software versions use different ASCII offsets.'
+    permissible_values:
+      SANGER:
+        description: Sanger/Phred+33 (PHRED scores, ASCII offset 33)
+        annotations:
+          ascii_offset: 33
+          score_range: 0-93
+          platforms: NCBI SRA, Illumina 1.8+
+      SOLEXA:
+        description: Solexa+64 (Solexa scores, ASCII offset 64)
+        annotations:
+          ascii_offset: 64
+          score_range: -5-62
+          platforms: Early Solexa/Illumina
+      ILLUMINA_1_3:
+        description: Illumina 1.3+ (PHRED+64, ASCII offset 64)
+        annotations:
+          ascii_offset: 64
+          score_range: 0-62
+          platforms: Illumina 1.3-1.7
+      ILLUMINA_1_5:
+        description: Illumina 1.5+ (PHRED+64, special handling for 0-2)
+        annotations:
+          ascii_offset: 64
+          score_range: 3-62
+          platforms: Illumina 1.5-1.7
+      ILLUMINA_1_8:
+        description: Illumina 1.8+ (PHRED+33, modern standard)
+        annotations:
+          ascii_offset: 33
+          score_range: 0-41
+          platforms: Illumina 1.8+, modern sequencers
+  GeneticCodeTable:
+    title: NCBI Genetic Code Translation Tables
+    description: 'NCBI genetic code translation tables for different organisms.
+
+      Table 1 is the universal genetic code used by most organisms.'
+    permissible_values:
+      TABLE_1:
+        description: Standard genetic code (universal)
+        annotations:
+          ncbi_id: 1
+          name: Standard
+      TABLE_2:
+        description: Vertebrate mitochondrial code
+        annotations:
+          ncbi_id: 2
+          name: Vertebrate Mitochondrial
+      TABLE_3:
+        description: Yeast mitochondrial code
+        annotations:
+          ncbi_id: 3
+          name: Yeast Mitochondrial
+      TABLE_4:
+        description: Mold, protozoan, coelenterate mitochondrial
+        annotations:
+          ncbi_id: 4
+          name: Mold Mitochondrial
+      TABLE_5:
+        description: Invertebrate mitochondrial code
+        annotations:
+          ncbi_id: 5
+          name: Invertebrate Mitochondrial
+      TABLE_6:
+        description: Ciliate, dasycladacean, hexamita nuclear code
+        annotations:
+          ncbi_id: 6
+          name: Ciliate Nuclear
+      TABLE_9:
+        description: Echinoderm and flatworm mitochondrial code
+        annotations:
+          ncbi_id: 9
+          name: Echinoderm Mitochondrial
+      TABLE_10:
+        description: Euplotid nuclear code
+        annotations:
+          ncbi_id: 10
+          name: Euplotid Nuclear
+      TABLE_11:
+        description: Bacterial, archaeal and plant plastid code
+        annotations:
+          ncbi_id: 11
+          name: Bacterial
+      TABLE_12:
+        description: Alternative yeast nuclear code
+        annotations:
+          ncbi_id: 12
+          name: Alternative Yeast Nuclear
+      TABLE_13:
+        description: Ascidian mitochondrial code
+        annotations:
+          ncbi_id: 13
+          name: Ascidian Mitochondrial
+      TABLE_14:
+        description: Alternative flatworm mitochondrial code
+        annotations:
+          ncbi_id: 14
+          name: Alternative Flatworm Mitochondrial
+      TABLE_16:
+        description: Chlorophycean mitochondrial code
+        annotations:
+          ncbi_id: 16
+          name: Chlorophycean Mitochondrial
+      TABLE_21:
+        description: Trematode mitochondrial code
+        annotations:
+          ncbi_id: 21
+          name: Trematode Mitochondrial
+      TABLE_22:
+        description: Scenedesmus obliquus mitochondrial code
+        annotations:
+          ncbi_id: 22
+          name: Scenedesmus Mitochondrial
+      TABLE_23:
+        description: Thraustochytrium mitochondrial code
+        annotations:
+          ncbi_id: 23
+          name: Thraustochytrium Mitochondrial
+      TABLE_24:
+        description: Rhabdopleuridae mitochondrial code
+        annotations:
+          ncbi_id: 24
+          name: Rhabdopleuridae Mitochondrial
+      TABLE_25:
+        description: Candidate division SR1 and gracilibacteria code
+        annotations:
+          ncbi_id: 25
+          name: Candidate Division SR1
+      TABLE_26:
+        description: Pachysolen tannophilus nuclear code
+        annotations:
+          ncbi_id: 26
+          name: Pachysolen Nuclear
+      TABLE_27:
+        description: Karyorelict nuclear code
+        annotations:
+          ncbi_id: 27
+          name: Karyorelict Nuclear
+      TABLE_28:
+        description: Condylostoma nuclear code
+        annotations:
+          ncbi_id: 28
+          name: Condylostoma Nuclear
+      TABLE_29:
+        description: Mesodinium nuclear code
+        annotations:
+          ncbi_id: 29
+          name: Mesodinium Nuclear
+      TABLE_30:
+        description: Peritrich nuclear code
+        annotations:
+          ncbi_id: 30
+          name: Peritrich Nuclear
+      TABLE_31:
+        description: Blastocrithidia nuclear code
+        annotations:
+          ncbi_id: 31
+          name: Blastocrithidia Nuclear
+  SequenceStrand:
+    title: DNA/RNA Strand Orientation
+    description: Strand orientation for nucleic acid sequences
+    permissible_values:
+      PLUS:
+        title: PLUS
+        description: Plus/forward/sense strand (5' to 3')
+      MINUS:
+        title: MINUS
+        description: Minus/reverse/antisense strand (3' to 5')
+      BOTH:
+        description: Both strands
+      UNKNOWN:
+        description: Strand not specified or unknown
+  SequenceTopology:
+    title: Sequence Topology
+    description: Topological structure of nucleic acid molecules
+    permissible_values:
+      LINEAR:
+        description: Linear sequence molecule
+        meaning: SO:0000987
+      CIRCULAR:
+        description: Circular sequence molecule
+        meaning: SO:0000988
+      BRANCHED:
+        description: Branched sequence structure
+      UNKNOWN:
+        description: Topology not specified
+  SequenceModality:
+    title: Sequence Data Modality
+    description: Types of sequence data based on experimental method
+    permissible_values:
+      SINGLE_CELL:
+        description: Single-cell sequencing data
+      BULK:
+        description: Bulk/population sequencing data
+      SPATIAL:
+        description: Spatially-resolved sequencing
+      LONG_READ:
+        description: Long-read sequencing (PacBio, Oxford Nanopore)
+      SHORT_READ:
+        description: Short-read sequencing (Illumina)
+      PAIRED_END:
+        description: Paired-end sequencing reads
+      SINGLE_END:
+        description: Single-end sequencing reads
+      MATE_PAIR:
+        description: Mate-pair sequencing libraries