ArticlePLoS computational biology2021
Generating functional protein variants with variational autoencoders.
Article in PLoS computational biology, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 102 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
102 citing papers in PubMed, 194 citations in OpenAlex.
- Translating functional molecular knowledge into crop-breeding success.Nature reviews. Genetics · 2026Review
- Protein function-conditioned language models for variant effect prediction and controllable design.Biophysical journal · 2026Article
- Functional alignment of protein language models via reinforcement learning.Nature communications · 2026Article
- Generative AI for controllable protein sequence design: A survey.npj drug discovery · 2026Review
- Generative models for antimicrobial peptide design: auto-encoders and beyond.BioData mining · 2026Article
- Generative design of synthetic gene circuits for functional and evolutionary properties.NPJ systems biology and applications · 2026Article
- PHA synthase variant design using a conditional variational autoencoder.PLoS computational biology · 2026Article
- Single-round evolution of RNA aptamers with GRAPE-LM.Nature biotechnology · 2026Article
- Unveiling patterns: an exploration of machine learning techniques for unsupervised feature selection in single-cell data.Briefings in bioinformatics · 2026Review
- BlendSplice: A Frequency-Blended Generative Framework forComputational and structural biotechnology journal · 2026Article
- AI-Driven Enzyme Engineering: Emerging Models and Next-Generation Biotechnological Applications.Molecules (Basel, Switzerland) · 2025Review
- Article
- Deep Generative Model-Driven Design of Microbial Synthetic Promoters.Journal of microbiology and biotechnology · 2025Review
- Enhancing functional proteins through multimodal inverse folding with ABACUS-T.Nature communications · 2025Article
- Controllable Generation of Pathogen-Specific Antimicrobial Peptides Through Knowledge-Aware Prompt Diffusion Model.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2025Article
- Biomolecular Interaction Prediction: The Era of AI.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2025Review
- Rational protein engineering using an omni-directional multipoint mutagenesis generation pipeline.iScience · 2025Article
- PRO-LDM: A Conditional Latent Diffusion Model for Protein Sequence Design and Functional Optimization.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2025Article
- Integrating experimental feedback improves generative models for biological sequences.Nucleic acids research · 2025Article
- Generative Landscapes and Dynamics to Design Functional Multidomain Artificial Transmembrane Transporters.ACS central science · 2025Article
42 more citing papers are in PubMed but not listed here.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
6 authors at 1 institution in 1 country.
Funding
No grant is acknowledged in the PubMed record.
Abstract
The vast expansion of protein sequence databases provides an opportunity for new protein design approaches which seek to learn the sequence-function relationship directly from natural sequence variation. Deep generative models trained on protein sequence data have been shown to learn biologically meaningful representations helpful for a variety of downstream tasks, but their potential for direct use in the design of novel proteins remains largely unexplored. Here we show that variational autoencoders trained on a dataset of almost 70000 luciferase-like oxidoreductases can be used to generate novel, functional variants of the luxA bacterial luciferase. We propose separate VAE models to work with aligned sequence input (MSA VAE) and raw sequence input (AR-VAE), and offer evidence that while both are able to reproduce patterns of amino acid usage characteristic of the family, the MSA VAE is better able to capture long-distance dependencies reflecting the influence of 3D structure. To confirm the practical utility of the models, we used them to generate variants of luxA whose luminescence activity was validated experimentally. We further showed that conditional variants of both models could be used to increase the solubility of luxA without disrupting function. Altogether 6/12 of the variants generated using the unconditional AR-VAE and 9/11 generated using the unconditional MSA VAE retained measurable luminescence, together with all 23 of the less distant variants generated by conditional versions of the models; the most distant functional variant contained 35 differences relative to the nearest training set sequence. These results demonstrate the feasibility of using deep generative models to explore the space of possible protein sequences and generate useful variants, providing a method complementary to rational design and directed evolution approaches.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.