to-do list (mainly for text analysis)

[jokergoo]

• [ ] n-gram, (e.g. cell cycle)
• [ ] words (or abbreviations) with two letters, or to distinguish abbreviations that are the same as normal words, but all in upper case.
• [x] "enrichment" of words (using all gene descriptions/GO definitions as background, maybe more sources)
• [ ] stemming of words

[jokergoo]

I prefer to construct a white word list for GO/gene descriptions that contain single words and phrases.