公开(公告)号：WO2021248060A1

公开(公告)日：2021-12-09

申请号：PCT/US2021/035990

申请日：2021-06-04

申请人： CALIFORNIA INSTITUTE OF TECHNOLOGY ,  BASF SE

发明人： LISZKA, Michael ,  WU, Zachary ,  YANG, Kevin

IPC分类号： C12N15/62 ,  G06N3/02 ,  G06N3/08

摘要： The disclosure provides systems and methods for generating a signal peptide amino acid sequence using deep learning, where a signal peptide is generated for input protein sequences, amino acids of the protein sequences are tokenized and mapped to a sequence of continuous representations to decode an output signal peptide sequence based on the input protein sequence.

公开(公告)号：WO2021248045A2

公开(公告)日：2021-12-09

申请号：PCT/US2021/035968

申请日：2021-06-04

申请人： CALIFORNIA INSTITUTE OF TECHNOLOGY ,  BASF SE

发明人： LISZKA, Michael ,  BATZILLA, Alina ,  WU, Zachary ,  ARNOLD, Frances

IPC分类号： C12N9/42 ,  C12N9/24 ,  C12N9/26 ,  C12P19/14 ,  C12P7/56 ,  C07K7/08 ,  A61P43/00 ,  C07K2319/02 ,  C12N9/14 ,  C12N9/2411 ,  C12N9/2417 ,  C12N9/2482 ,  C12N9/52 ,  C12N9/54 ,  C12Y302/01001 ,  C12Y302/01008 ,  C12Y304/21062 ,  C12Y308/01005

摘要： The disclosure provides for artificial signal peptides generated by systems and methods utilizing deep learning.