Antibodies currently comprise the predominant treatment modality for a variety of diseases;therefore,optimizing their properties rapidly and efficiently is an indispensable step in antibody-based drug development.Insp...Antibodies currently comprise the predominant treatment modality for a variety of diseases;therefore,optimizing their properties rapidly and efficiently is an indispensable step in antibody-based drug development.Inspired by the great success of artificial intelligence-based algorithms,especially deep learning-based methods in the field of biology,various computational methods have been introduced into antibody optimization to reduce costs and increase the success rate of lead candidate generation and optimization.Herein,we briefly review recent progress in deep learning-based antibody optimization,focusing on the available datasets and algorithm input data types that are crucial for constructing appropriate deep learning models.Furthermore,we discuss the current challenges and potential solutions for the future development of general-purpose deep learning algorithms in antibody optimization.展开更多
A brief review of the importance of simulation-based engineering and science(including social sciences)is followed by a historic perspective of model-based simulation.Section 2 is on declarative modeling of component ...A brief review of the importance of simulation-based engineering and science(including social sciences)is followed by a historic perspective of model-based simulation.Section 2 is on declarative modeling of component systems as well as its advantages for self-documentation and for computer-aided checks and coupling.As an example for declarative modeling,General System Theory(GEST)implementor is given.In Sec.3,basic concepts for coupling of component models,and rules for computer-assisted coupling specification are explained.Section 4 is devoted to possible computerized checks in couplings of declarative models such as:(1)automatic unit checking to avoid meaning-less input/output matching at the time of coupling specification,(2)automatic threshold checking to provide warnings and/or to avoid disasters,and(3)automatic unit conversion for convenience of using library models.Section 5 is about several layers of nested couplings for modeling systems of systems.In Sec.6,two types of variable couplings are discussed:(1)couplings with variable connections(to allow input/output relations of models to depend on time or state conditions)and(2)coupling with variable component models(to allow component(or coupled)models to be switched based on time or state conditions).Section 7 is on the use of multimodels as component models in couplings.Section 8 is on types of inputs and their use in couplings as well as on exter-nal inputs to simulation studies.In Sec.9,conclusions and future work for complex systems are outlined.Especially,the values of simulation systems engineering as well as understanding and avoidance of misunderstanding in cognitive and emotive simulations are stressed.Appendix A is a list of almost 50 types of couplings and Appendix B lists over 50 terms related with couplings in modeling and simulation.To show the richness of“input”concept which is important in specification of input/output relations of component models,Appendix C lists almost 150 types of inputs.Information shared in this article may be useful in developing advanced modeling and simulation software,tools and environments.展开更多
基金supported by the National Natural Science Foundation of China(No.12104396)the National Key R&D Program of China(Nos.2021YFF1200404 and 2021YFA1201200)+2 种基金the National Independent Innovation Demonstration Zone Shanghai Zhangjiang Major Projects(No.ZJZX2020014)the Starry Night Science Fund at Shanghai Institute for Advanced Study of Zhejiang University(No.SN-ZJU-SIAS-003)the Shanghai Artificial Intelligence Lab(No.P22KN00272),China.
文摘Antibodies currently comprise the predominant treatment modality for a variety of diseases;therefore,optimizing their properties rapidly and efficiently is an indispensable step in antibody-based drug development.Inspired by the great success of artificial intelligence-based algorithms,especially deep learning-based methods in the field of biology,various computational methods have been introduced into antibody optimization to reduce costs and increase the success rate of lead candidate generation and optimization.Herein,we briefly review recent progress in deep learning-based antibody optimization,focusing on the available datasets and algorithm input data types that are crucial for constructing appropriate deep learning models.Furthermore,we discuss the current challenges and potential solutions for the future development of general-purpose deep learning algorithms in antibody optimization.
文摘A brief review of the importance of simulation-based engineering and science(including social sciences)is followed by a historic perspective of model-based simulation.Section 2 is on declarative modeling of component systems as well as its advantages for self-documentation and for computer-aided checks and coupling.As an example for declarative modeling,General System Theory(GEST)implementor is given.In Sec.3,basic concepts for coupling of component models,and rules for computer-assisted coupling specification are explained.Section 4 is devoted to possible computerized checks in couplings of declarative models such as:(1)automatic unit checking to avoid meaning-less input/output matching at the time of coupling specification,(2)automatic threshold checking to provide warnings and/or to avoid disasters,and(3)automatic unit conversion for convenience of using library models.Section 5 is about several layers of nested couplings for modeling systems of systems.In Sec.6,two types of variable couplings are discussed:(1)couplings with variable connections(to allow input/output relations of models to depend on time or state conditions)and(2)coupling with variable component models(to allow component(or coupled)models to be switched based on time or state conditions).Section 7 is on the use of multimodels as component models in couplings.Section 8 is on types of inputs and their use in couplings as well as on exter-nal inputs to simulation studies.In Sec.9,conclusions and future work for complex systems are outlined.Especially,the values of simulation systems engineering as well as understanding and avoidance of misunderstanding in cognitive and emotive simulations are stressed.Appendix A is a list of almost 50 types of couplings and Appendix B lists over 50 terms related with couplings in modeling and simulation.To show the richness of“input”concept which is important in specification of input/output relations of component models,Appendix C lists almost 150 types of inputs.Information shared in this article may be useful in developing advanced modeling and simulation software,tools and environments.
