ArticleBioinformatics (Oxford, England)2021
Unsupervised protein embeddings outperform hand-crafted sequence and structure features at predicting molecular function.
Article in Bioinformatics (Oxford, England), 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 65 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
65 citing papers in PubMed.
- Predicting protein-nucleic acid interactions via protein language models with biophysical and evolutionary priors.iScience · 2026Article
- Compressing the collective knowledge of ESM into a single protein language model.Nature methods · 2026Article
- Contrastive representation learning and capsule networks enable accurate identification of ferroptosis-related proteins.Journal of cheminformatics · 2026Article
- A Novel Weighted Ensemble Framework of Transformer and Deep Q-Network for ATP-Binding Site Prediction Using Protein Language Model Features.International journal of molecular sciences · 2026Article
- Exploring the limits of pre-trained embeddings in machine-guided protein design: a case study on predicting AAV vector viability.Scientific reports · 2026Article
- Intrinsic dataset features drive mutational effect prediction by protein language models.bioRxiv : the preprint server for biology · 2026Article
- Artificial intelligence drives the identification and screening of novel antibiotics and antimicrobial peptides.Briefings in bioinformatics · 2026Review
- Protein language models enable accurate viral host range prediction.Scientific reports · 2026Article
- Comprehensive review and assessment of machine learning approaches for host-pathogen protein-protein interaction prediction.Briefings in bioinformatics · 2026Review
- Lab to codes: multimodel advanced AI-driven pipelines to drive antimicrobial peptide design for the post-antibiotic era.Frontiers in cellular and infection microbiology · 2026Review
- Predicting Protein-Protein Interactions from Machine-Learned Representations.Advances in experimental medicine and biology · 2026Review
- Article
- Antimicrobial peptide prediction based on contrastive learning and gated convolutional neural network.Scientific reports · 2025Article
- ProGraphTrans: multimodal dynamic collaborative framework for protein representation learning.BMC biology · 2025Article
- Computational function prediction of bacteria and phage proteins.Microbiology and molecular biology reviews : MMBR · 2025Review
- Predicting nucleic acid binding sites by attention map-guided graph convolutional network with protein language embeddings and physicochemical information.Briefings in bioinformatics · 2025Article
- Exo-Tox: Identifying Exotoxins from secreted bacterial proteins.BioData mining · 2025Article
- DrugTar improves druggability prediction by integrating large language models and gene ontologies.Bioinformatics (Oxford, England) · 2025Article
- Medium-sized protein language models perform well at transfer learning on realistic datasets.Scientific reports · 2025Article
- Medium-sized protein language models perform well at transfer learning on realistic datasets.bioRxiv : the preprint server for biology · 2025Article
5 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.
Funding
No grant is acknowledged in the PubMed record.
Abstract
motivationProtein function prediction is a difficult bioinformatics problem. Many recent methods use deep neural networks to learn complex sequence representations and predict function from these. Deep supervised models require a lot of labeled training data which are not available for this task. However, a very large amount of protein sequences without functional labels is available.
resultsWe applied an existing deep sequence model that had been pretrained in an unsupervised setting on the supervised task of protein molecular function prediction. We found that this complex feature representation is effective for this task, outperforming hand-crafted features such as one-hot encoding of amino acids, k-mer counts, secondary structure and backbone angles. Also, it partly negates the need for complex prediction models, as a two-layer perceptron was enough to achieve competitive performance in the third Critical Assessment of Functional Annotation benchmark. We also show that combining this sequence representation with protein 3D structure information does not lead to performance improvement, hinting that 3D structure is also potentially learned during the unsupervised pretraining. AVAILABILITY AND IMPLEMENTATION: Implementations of all used models can be found at https://github.com/stamakro/GCN-for-Structure-and-Function. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
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.