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.

Open PDF

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

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Chemistry
  • Computational Biology
  • Computational Science
  • Computer Languages
  • Computer Programming
  • Computers
  • Convolutional Neural Networks
  • Covid-19
  • Data Mining
  • Data Science
  • Dimensionality Reduction
  • Information Science
  • Machine Learning
  • Neural Networks
  • Ontologies
  • Synthetic Biology

Fields of Study

  • Biology
  • Computer science

Readers

  • Computational Modeling and Simulation
  • Molecular Genetics
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks