Integration of Top-Down and Bottom-Up Methodologies for Accurate Modeling of Biological Networks
Abstract
First, we developed STORM/NuSpeak as a tool to leverage big data and machine learning to automate the prediction and design of toehold switches more reliably. Second, we engineered BioSeqML as a biological sequence-based automated machine learning framework to automate development and interpretation of a range of machine learning architectures on biological data types. Finally, we created DeepInducer to generate novel inducible promoters in bacterial organisms, classify them, and predict their strength, all in a tunable manner. Furthermore, we've outlined some auxiliary work we've done in gene regulatory networks using various machine learning and statistical analysis methods.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 2022
- Accession Number
- AD1163047
Entities
People
- Diogo M Camach
- George Steven
- Jacqueline A Valeri
- James J. Collins
- Rani Powers
Organizations
- President and Fellows of Harvard College