Table 1 Orthographic Feature
From: Recognition of protein/gene names from text using an ensemble of classifiers
Features 1–11 | e.g. | Features 12–21 | e.g. |
|---|---|---|---|
Comma | , | OneCap | T |
Dot | . | AllCaps | CSF |
Parenthesis | () [] | CapLowAlpha | All |
RomanDigit | II | CapMixAlpha | IgM |
GreekLetter | Beta | LowMixAlpha | kDa |
StopWord | in, at | AlphaDigitAlpha | H2A |
ATCGsequence | ACAG | AlphaDigit | T4 |
OneDigit | 5 | DigitAlphaDigit | 6C2 |
AllDigits | 60 | DigitAlpha | 19D |
DigitCommaDigit | 1,25 | Others | Other |
DigitDotDigit | 0.5 | Â | Â |