Table 1.
Categories of predicates on observed tokens
| Predicate | Example | Predicate | Example | Predicate | Example |
|---|---|---|---|---|---|
| Word | proteins | Hyphen | - | Nucleoside | Thymine |
| StemmedWord | protein | BackSlash | / | Nucleotide | ATP |
| PartOfSpeech | NN | OpenSqure | [ | Roman | I, II, XI |
| InitCap | Kinase | CloseSqure | ] | MorphologyTypeI | p53→p* |
| EndCap | kappaB | Colon | : | MorphologyTypeII | p53→a1 |
| AllCaps | SOX | SemiColon | ; | MorphologyTypeIII | GnRH→AaAA |
| LowerCase | interlukin | Percent | % | WordLength | 1, 2, 3-5, 6+ |
| MixCase | RalGDS | OpenParen | ( | N-grams(2-4) | p53→{p5, 53} |
| SingleCap | kDa | CloseParen | ) | ATCGUsequece | ATCGU |
| TwoCap | IL | Comma | , | Greek | alpha |
| ThreeCap | CSF | FullStop | . | NucleicAcid | cDNA |
| MoreCap | RESULT | Apostrophe | ' | AminoAcidLong | tyrosine |
| SingleDigit | 1 | QuotationMark | ‘,’ | AminoAcidShort | Ser |
| TwoDigit | 22 | Star | * | AminoAcid+Position | Ser150 |
| FourDigit | 1983 | Equal | = | ||
| MoreDigit | 513256 | Plus | + |