본문 바로가기
HOME> 논문 > 논문 검색상세

논문 상세정보

Metabolic engineering v.44, 2017년, pp.171 - 181   SCIE
본 등재정보는 저널의 등재정보를 참고하여 보여주는 베타서비스로 정확한 논문의 등재여부는 등재기관에 확인하시기 바랍니다.

Predicting novel substrates for enzymes with minimal experimental effort with active learning

Pertusi, Dante A. (Department of Chemical and Biological Engineering, Northwestern University, Evanston, IL, United States ) ; Moura, Matthew E. (Department of Chemical and Biological Engineering, Northwestern University, Evanston, IL, United States ) ; Jeffryes, James G. (Department of Chemical and Biological Engineering, Northwestern University, Evanston, IL, United States ) ; Prabhu, Siddhant (Department of Chemical and Biological Engineering, Northwestern University, Evanston, IL, United States ) ; Walters Biggs, Bradley (Department of Chemical and Biological Engineering, Northwestern University, Evanston, IL, United States ) ; Tyo, Keith E.J. (Department of Chemical and Biological Engineering, Northwestern University, Evanston, IL, United States ) ;
  • 초록  

    Abstract Enzymatic substrate promiscuity is more ubiquitous than previously thought, with significant consequences for understanding metabolism and its application to biocatalysis. This realization has given rise to the need for efficient characterization of enzyme promiscuity. Enzyme promiscuity is currently characterized with a limited number of human-selected compounds that may not be representative of the enzyme's versatility. While testing large numbers of compounds may be impractical, computational approaches can exploit existing data to determine the most informative substrates to test next, thereby more thoroughly exploring an enzyme's versatility. To demonstrate this, we used existing studies and tested compounds for four different enzymes, developed support vector machine (SVM) models using these datasets, and selected additional compounds for experiments using an active learning approach. SVMs trained on a chemically diverse set of compounds were discovered to achieve maximum accuracies of ~80% using ~33% fewer compounds than datasets based on all compounds tested in existing studies. Active learning-selected compounds for testing resolved apparent conflicts in the existing training data, while adding diversity to the dataset. The application of these algorithms to wide arrays of metabolic enzymes would result in a library of SVMs that can predict high-probability promiscuous enzymatic reactions and could prove a valuable resource for the design of novel metabolic pathways. Highlights An algorithm for prioritizing experiments for enzyme promiscuity is proposed. The algorithm (SimAL) utilizes cheminformatics and support vector machine learning. SimAL can predict an enzyme's promiscuity with 33% less experimental observations. SimAL judiciously resolve apparent conflicts in existing data in compound selection. Improvement in SimAL predictive power is experimentally validated.


  • 주제어

    Machine learning .   Active learning .   Enzyme promiscuity.  

 활용도 분석

  • 상세보기

    amChart 영역
  • 원문보기

    amChart 영역

원문보기

무료다운로드
  • 원문이 없습니다.

유료 다운로드의 경우 해당 사이트의 정책에 따라 신규 회원가입, 로그인, 유료 구매 등이 필요할 수 있습니다. 해당 사이트에서 발생하는 귀하의 모든 정보활동은 NDSL의 서비스 정책과 무관합니다.

원문복사신청을 하시면, 일부 해외 인쇄학술지의 경우 외국학술지지원센터(FRIC)에서
무료 원문복사 서비스를 제공합니다.

NDSL에서는 해당 원문을 복사서비스하고 있습니다. 위의 원문복사신청 또는 장바구니 담기를 통하여 원문복사서비스 이용이 가능합니다.

이 논문과 함께 출판된 논문 + 더보기