BioVec
代表生物序列的新方法。 该算法来自本文:“ ”
安装
克隆后在本地安装。
快速开始
import biovec
pv = biovec.models.ProtVec("some_fasta_file.fasta", corpus_fname="output_corpusfile_path.txt", n=3)
# The n-gram "QAT" should be trained in advance
pv["QAT"]
# convert whole amino acid sequence into vector
pv.to_vecs("ATATQSQSMTEEL")
# convert multi-sequence FASTA file to a numpy array of protvec vectors (axis 0 = sample axis)
# seqty
1