Your browser doesn't support javascript.
loading
Extensive antibody search with whole spectrum black-box optimization.
Tucs, Andrejs; Ito, Tomoyuki; Kurumida, Yoichi; Kawada, Sakiya; Nakazawa, Hikaru; Saito, Yutaka; Umetsu, Mitsuo; Tsuda, Koji.
Afiliación
  • Tucs A; Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa, Japan.
  • Ito T; Department of Biomolecular Engineering, Graduate School of Engineering, Tohoku University, Sendai, Japan.
  • Kurumida Y; Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan.
  • Kawada S; Department of Data Science, School of Frontier Engineering, Kitasato University, Sagamihara, Japan.
  • Nakazawa H; Department of Biomolecular Engineering, Graduate School of Engineering, Tohoku University, Sendai, Japan.
  • Saito Y; Department of Biomolecular Engineering, Graduate School of Engineering, Tohoku University, Sendai, Japan.
  • Umetsu M; Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa, Japan.
  • Tsuda K; Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology (AIST), Tokyo, Japan.
Sci Rep ; 14(1): 552, 2024 01 04.
Article en En | MEDLINE | ID: mdl-38177656
ABSTRACT
In designing functional biological sequences with machine learning, the activity predictor tends to be inaccurate due to shortage of data. Top ranked sequences are thus unlikely to contain effective ones. This paper proposes to take prediction stability into account to provide domain experts with a reasonable list of sequences to choose from. In our approach, multiple prediction models are trained by subsampling the training set and the multi-objective optimization problem, where one objective is the average activity and the other is the standard deviation, is solved. The Pareto front represents a list of sequences with the whole spectrum of activity and stability. Using this method, we designed VHH (Variable domain of Heavy chain of Heavy chain) antibodies based on the dataset obtained from deep mutational screening. To solve multi-objective optimization, we employed our sequence design software MOQA that uses quantum annealing. By applying several selection criteria to 19,778 designed sequences, five sequences were selected for wet-lab validation. One sequence, 16 mutations away from the closest training sequence, was successfully expressed and found to possess desired binding specificity. Our whole spectrum approach provides a balanced way of dealing with the prediction uncertainty, and can possibly be applied to extensive search of functional sequences.
Asunto(s)
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Ingeniería de Proteínas / Anticuerpos Tipo de estudio: Prognostic_studies Idioma: En Revista: Sci Rep Año: 2024 Tipo del documento: Article País de afiliación: Japón Pais de publicación: Reino Unido
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Ingeniería de Proteínas / Anticuerpos Tipo de estudio: Prognostic_studies Idioma: En Revista: Sci Rep Año: 2024 Tipo del documento: Article País de afiliación: Japón Pais de publicación: Reino Unido