Comparing approaches to predict transmembrane domains in protein sequences

Davidsson, PaulBlekinge Tekniska Högskola,Sektionen för datavetenskap och kommunikation (författare)

There are today several systems for predicting transmembrane domains in membrane protein sequences. As they are based on different classifiers as well as different pre- and post-processing techniques, it is very difficult to evaluate the performance of the particular classifier used. We have developed a system called MemMiC for predicting transmembrane domains in protein se-quences with the possibility to choose between different ap-proaches to pre- and post-processing as well as different classifiers. Therefore it is possible to compare the performance of each classifier in a certain environment as well as the different approaches to pre- and post-processing. We have demonstrated the usefulness of MemMiC in a set of experiments, which shows, e.g., that the performance of a classifier is very dependent on which pre- and post-processing techniques are used.

Hagelbäck, Johan,1977-Travelstart Nordic, Sweden,Travelstart Nordic, SWE(Swepub:bth)jhg (författare)
Svensson, KennyEricsson, Sweden,Ericsson AB, SWE (författare)
Blekinge Tekniska HögskolaSektionen för datavetenskap och kommunikation (creator_code:org_t)

Ingår i:ProceedingSAC '05 Proceedings of the 2005 ACM symposium on Applied computingNew York, NY, USA : ACM Press, s. 185-1891581139640

Av författaren/redakt...: Davidsson, Paul; Hagelbäck, Johan ...; Svensson, Kenny

Om ämnet

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.