ArticlePLoS computational biology2025
Benchmarking uncertainty quantification for protein engineering.
Article in PLoS computational biology, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 14 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
14 citing papers in PubMed.
- Deep learning architectures achieve state-of-the-art (SOTA) accuracy in protein secondary structure prediction.Molecular diversity · 2026Review
- Optimizing protein design through uncertainty-weighted steering of protein language models.Bioinformatics (Oxford, England) · 2026Article
- Deciphering key factors of active learning performance in biomolecular design.Bioinformatics (Oxford, England) · 2026Article
- How far can you go? Extrapolating values of catalytic activity from known protein landscapes in natural and directed evolution.Chemical Society reviews · 2026Review
- Compressing the collective knowledge of ESM into a single protein language model.Nature methods · 2026Article
- Quantifying uncertainty in protein representations across models and tasks.Nature methods · 2026Article
- Generative design of synthetic gene circuits for functional and evolutionary properties.NPJ systems biology and applications · 2026Article
- AI-Driven De Novo Binder Design: From Structure Prediction to Closed-Loop Optimization.Computational and structural biotechnology journal · 2026Review
- Leveraging uncertainty estimates for drug response prediction in cancer cell lines.Bioinformatics advances · 2026Article
- ImmUQBench: a benchmark on uncertainty quantification of protein immunogenicity prediction.Oxford open immunology · 2026Article
- Best Practices for Machine Learning-Assisted Protein Engineering.Journal of chemical information and modeling · 2025Review
- Active learning-assisted directed evolution.Nature communications · 2025Article
- Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering.ACS central science · 2024Review
- Accelerating Biocatalysis Discovery with Machine Learning: A Paradigm Shift in Enzyme Engineering, Discovery, and Design.ACS catalysis · 2023Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
Abstract
Machine learning sequence-function models for proteins could enable significant advances in protein engineering, especially when paired with state-of-the-art methods to select new sequences for property optimization and/or model improvement. Such methods (Bayesian optimization and active learning) require calibrated estimations of model uncertainty. While studies have benchmarked a variety of deep learning uncertainty quantification (UQ) methods on standard and molecular machine-learning datasets, it is not clear if these results extend to protein datasets. In this work, we implemented a panel of deep learning UQ methods on regression tasks from the Fitness Landscape Inference for Proteins (FLIP) benchmark. We compared results across different degrees of distributional shift using metrics that assess each UQ method's accuracy, calibration, coverage, width, and rank correlation. Additionally, we compared these metrics using one-hot encoding and pretrained language model representations, and we tested the UQ methods in retrospective active learning and Bayesian optimization settings. Our results indicate that there is no single best UQ method across all datasets, splits, and metrics, and that uncertainty-based sampling is often unable to outperform greedy sampling in Bayesian optimization. These benchmarks enable us to provide recommendations for more effective design of biological sequences using machine learning.
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.