30 August 2022 in Nature Communications
Design of de novo synthetic regulatory DNA is a promising avenue to control gene expression in biotechnology and medicine. Using mutagenesis typically requires screening sizable random DNA libraries, which limits the designs to span merely a short section of the promoter and restricts their control of gene expression. Here, we prototype a deep learning strategy based on generative adversarial networks (GAN) by learning directly from genomic and transcriptomic data. Our ExpressionGAN can traverse the entire regulatory sequence-expression landscape in a gene-specific manner, generating regulatory DNA with prespecified target mRNA levels spanning the whole gene regulatory structure including coding and adjacent non-coding regions. Despite high sequence divergence from natural DNA, in vivo measurements show that 57% of the highly-expressed synthetic sequences surpass the expression levels of highly-expressed natural controls. This demonstrates the applicability and relevance of deep generative design to expand our knowledge and control of gene expression regulation in any desired organism, condition or tissue.
23 April 2024 in Nature Biotechnology
In recent years, generative protein sequence models have been developed to sample novel sequences. However, predicting whether generated proteins will fold and function remains challenging. We evaluate a set of 20 diverse computational metrics to assess the quality of enzyme sequences produced by three contrasting generative models: ancestral sequence reconstruction, a generative adversarial network and a protein language model. Focusing on two enzyme families, we expressed and purified over 500 natural and generated sequences with 70–90% identity to the most similar natural sequences to benchmark computational metrics for predicting in vitro enzyme activity. Over three rounds of experiments, we developed a computational filter that improved the rate of experimental success by 50–150%. The proposed metrics and models will drive protein engineering research by serving as a benchmark for generative protein sequence models and helping to select active variants for experimental testing.
9 October 2024 in Nature Communications
Protoberberine alkaloids and benzophenanthridine alkaloids (BZDAs) are subgroups of benzylisoquinoline alkaloids (BIAs), which represent a diverse class of plant-specialized natural metabolites with many pharmacological properties. Microbial biosynthesis has been allowed for accessibility and scalable production of high-value BIAs. Here, we engineer Saccharomyces cerevisiae to de novo produce a series of protoberberines and BZDAs, including palmatine, berberine, chelerythrine, sanguinarine and chelirubine. An ER compartmentalization strategy is developed to improve vacuole protein berberine bridge enzyme (BBE) activity, resulting in >200% increase on the production of the key intermediate (S)-scoulerine. Another promiscuous vacuole protein dihydrobenzophenanthridine oxidase (DBOX) has been identified to catalyze two-electron oxidation on various tetrahydroprotoberberines at N7-C8 position and dihydrobenzophenanthridine alkaloids. Furthermore, cytosolically expressed DBOX can alleviate the limitation on BBE. This study highlights the potential of microbial cell factories for the biosynthesis of a diverse group of BIAs through engineering of heterologous plant enzymes.
21 September 2023 in ACS Sustainable Chemistry & Engineering
12 December 2024 in Protein Science
Understanding what drives protein abundance is essential to biology, medicine, and biotechnology. Driven by evolutionary selection, an amino acid sequence is tailored to meet the required abundance of a proteome, underscoring the intricate relationship between sequence and functional demand. Yet, the specific role of amino acid sequences in determining proteome abundance remains elusive. Here we show that the amino acid sequence alone encodes over half of protein abundance variation across all domains of life, ranging from bacteria to mouse and human. With an attempt to go beyond predictions, we trained a manageable‐size Transformer model to interpret latent factors predictive of protein abundances. Intuitively, the model's attention focused on the protein's structural features linked to stability and metabolic costs related to protein synthesis. To probe these relationships, we introduce MGEM (Mutation Guided by an Embedded Manifold), a methodology for guiding protein abundance through sequence modifications. We find that mutations which increase predicted abundance have significantly altered protein polarity and hydrophobicity, underscoring a connection between protein structural features and abundance. Through molecular dynamics simulations we revealed that abundance‐enhancing mutations possibly contribute to protein thermostability by increasing rigidity, which occurs at a lower synthesis cost.