Designing novel functional peptides by manipulating a temperature in the softmax function coupled with variational autoencoder

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 136
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorChen, Sko
dc.contributor.authorKim, Hyun Ukko
dc.date.accessioned2020-01-11T03:20:08Z-
dc.date.available2020-01-11T03:20:08Z-
dc.date.created2019-12-24-
dc.date.created2019-12-24-
dc.date.issued2019-12-10-
dc.identifier.citation2019 IEEE International Conference on Big Data, Big Data 2019, pp.6010 - 6012-
dc.identifier.urihttp://hdl.handle.net/10203/271064-
dc.description.abstractDevelopment of an efficient peptide design method is crucial for tackling medical problems, such as designing antimicrobial peptides for combating drug-resistant pathogens and anticancer peptides for various cancers. Here, we present Variational Autoencoder (VAE) coupled with a Softmax function having a temperature factor (T) for high-throughput design of novel functional peptides. VAE is a generative machine learning model, which has proved to be useful for generating peptide sequences. In this study, we additionally use a Softmax function with T to facilitate determining the most probable amino acids at each position of peptide sequences to be generated, which is difficult to achieve using a conventional VAE. In particular, by manipulating T in the Softmax function, we select biologically most feasible peptides with a desired function. This method is demonstrated for designing novel antimicrobial and anticancer peptides in this study. The method presented herein should be useful for designing various peptides with a desired function upon availability of relevant datasets.-
dc.languageEnglish-
dc.publisherIEEE-
dc.titleDesigning novel functional peptides by manipulating a temperature in the softmax function coupled with variational autoencoder-
dc.typeConference-
dc.identifier.scopusid2-s2.0-85081323268-
dc.type.rimsCONF-
dc.citation.beginningpage6010-
dc.citation.endingpage6012-
dc.citation.publicationname2019 IEEE International Conference on Big Data, Big Data 2019-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationLos Angeles, CA-
dc.identifier.doi10.1109/BigData47090.2019.9006253-
dc.contributor.localauthorKim, Hyun Uk-
Appears in Collection
CBE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0