Hi ML,
Are there any methods or products that do a decent job of taking a list of short descriptions, and summarizing them?
The descriptions are of proteins, and some examples are:
- Chromosome segregation protein SMC
- Condensin subunit SMC
- Chromosome segregation protein (Smc1)
- Putative chromosome segregation protein, SMC ATPase superfamily
- Condensin subunit Smc
- SMC proteins Flexible Hinge Domain
Other than just the collection of text, I have information on the likely quality of the description, and I have collections of things that should be similar. (So I can say that Apoptotic peptidase activating factor 1 and APAF1 are both good names and mean roughly the same thing).
[link] [2 comments]
