Extract features from fasta sequences
I am new to the bioinformatics field. I have positive and negative protein sequences for acetylation PTM. Now, I want to train a classifier, say SVM. What will be the next step? How can I convert these sequences into usable features? Any information or links would help.
>P31327_55|1|testing
KAQTAHIVLEDGTKMKGYSFGHPSSVA
>P31327_57|1|testing
QTAHIVLEDGTKMKGYSFGHPSSVAGE
>P31327_119|1|testing
APDTTALDELGLSKYLESNGIKVSGLL
>P31327_157|1|testing
LATKSLGQWLQEEKVPAIYGVDTRMLT
• 903 views
•
link
written
by
suresh.wrc •
0 answers
No answers yet.
Log in to answer this question.
More posts like this
-
cutpointr package in R for finding the optimal cut of a predictive model
written by AlexStar •
-
SVM: why am I getting different results?
written by lizabe •
-
Gene Expression Analysis Steps ?
written by ali •
-
Job: Senior Computational Biologist I
written by rons.shah
-
News: Metabarcoding: Transforming the way in which biodiversity can be surveyed
written by Physalia-courses
-
Job: Bioinformatics Scientist II (Philadelphia, USA)
written by Skolc •
-
evaluation distance in Eukaryotic
written by disimos89 •
-
Classifier Optimization In Weka!
written by kandoigaurav
-
Extracting The Features From Genbank File
written by ancient_learner
-
Is There A Pathway Database With Directed Gene-Gene Edges
written by Lyco
Maybe you can start with extracting features like PseAAC:
https://en.wikipedia.org/wiki/Pseudo_amino_acid_composition