Synthetic data generation for the optimization of strains in metabolic engineering using latent space representations derived from a Conditional Variational Autoencoder

Synthetic data generation for the optimization of strains in metabolic engineering using latent space representations derived from a Conditional Variational Autoencoder

Alwani, Neil (TU Delft Electrical Engineering, Mathematics and Computer Science)

Abeel, T.E.P.M.F. (mentor)
van Lent, P.H. (mentor)
Hanjalic, A. (graduation committee)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2024-02-02

This study investigates the application of generative models for synthetic data generation in pathway optimization experiments within the field of metabolic engineering. Conditional Variational Autoencoders (CVAEs) use neural networks and latent variable distributions to generate new, plausible data samples. We adapt this model by conditioning the training process on the target flux to acquire increased performance.

Additionally, a baseline model, namely Probabilistic Principal Component Analysis (PPCA), was selected for a comparative analysis to generate the underlying latent space to test the hypothesis that a type of Variational Autoencoder (VAE) can be used to learn a reduced-dimensional latent space for configurations of a kinetic pathway model. A dataset comprising 5000 hypothetical configurations of a kinetic pathway model was utilized to extract relationships between elements of a kinetic pathway.

The results indicate that PPCA can model the underlying distribution of the dataset when the latent space is large enough. However, the traditional CVAE might struggle to capture the underlying distribution, resulting in an entangled latent space. The study suggests that an implementation of $\beta$-CVAE could lead to a better balance between parts of the objective function during training, offering improved prospects for generating cost-efficient kinetic pathways for combinatorial pathway optimization experiments.

Metabolic Flux Analysis
Variational Autoencoder (VAE)
Probabilistic analysis
Principal Component Analysis (PCA)
Combinatorial Optimization

http://resolver.tudelft.nl/uuid:0f0fbe65-257d-491d-9fe5-5c1b3864dfd4

Student theses

bachelor thesis

© 2024 Neil Alwani