Graphical abstract template · Drug discovery & proteins · Protein language models
From coevolution to protein language models
Residues in contact mutate together, so an alignment holds the fold (direct-coupling analysis). Language models trained only on sequences learn the same: ESM-2 scaled to 15 billion parameters predicts structures directly, and ESMFold built an atlas of more than 617 million metagenomic proteins.
Updated 4 cited papers41 editable layers
At a glance
- Category
- Drug discovery & proteins
- Method
- Protein language models
- Starting materials
- Protein sequences (and their alignments)
- Product
- Contacts, embeddings and structures
- Key result
- Alignment and contact map are synthetic examples
- Figure
- 1920 × 1080 px (16:9), 41 editable layers, 5 generated objects
Step by step
- CoevolutionDirect-coupling analysis of alignments predicts residue contacts across many protein families (Morcos 2011)
- Language modelTrained on 86 billion amino acids in 250 million sequences, by filling in masked residues (Rives 2021)
- StructureESM-2 scaled to 15 billion parameters; ESMFold predicts structure from a single sequence (Lin 2023)
- AtlasMore than 617 million metagenomic structures, over 225 million with high confidence (Lin 2023)
- GenerationESM3 generated a fluorescent protein 58% identical to the nearest known one (Hayes 2025)
Strengths
- No alignment needed at prediction time
- Fast enough for whole metagenomes
- Embeddings reused for many tasks
Limitations
- Less accurate than alignment-based models on some proteins
- Large models need large compute to train
Uses
- Structure prediction at scale
- Variant effect prediction
- Protein design
Papers this template follows
- Morcos et al., “Direct-coupling analysis of residue coevolution captures native contacts across many protein families”, PNAS 2011. doi:10.1073/pnas.1111471108primary
- Rives et al., “Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences”, PNAS 2021. doi:10.1073/pnas.2016239118primary
- Lin et al., “Evolutionary-scale prediction of atomic-level protein structure with a language model”, Science 2023. doi:10.1126/science.ade2574primary
- Hayes et al., “Simulating 500 million years of evolution with a language model”, Science 2025. doi:10.1126/science.ads0018primary
After Morcos et al., PNAS 2011 (doi:10.1073/pnas.1111471108), Rives et al., PNAS 2021 (doi:10.1073/pnas.2016239118), Lin et al., Science 2023 (doi:10.1126/science.ade2574) and Hayes et al., Science 2025 (doi:10.1126/science.ads0018). Alignment and contacts synthetic; numbers from the abstracts.
How templates are written and checked: editorial guidelines.
Questions
What does the “From coevolution to protein language models” template show?
Residues in contact mutate together, so an alignment holds the fold (direct-coupling analysis). Language models trained only on sequences learn the same: ESM-2 scaled to 15 billion parameters predicts structures directly, and ESMFold built an atlas of more than 617 million metagenomic proteins.
What are the steps shown in “From coevolution to protein language models”?
1. Coevolution: Direct-coupling analysis of alignments predicts residue contacts across many protein families (Morcos 2011). 2. Language model: Trained on 86 billion amino acids in 250 million sequences, by filling in masked residues (Rives 2021). 3. Structure: ESM-2 scaled to 15 billion parameters; ESMFold predicts structure from a single sequence (Lin 2023). 4. Atlas: More than 617 million metagenomic structures, over 225 million with high confidence (Lin 2023). 5. Generation: ESM3 generated a fluorescent protein 58% identical to the nearest known one (Hayes 2025).
What are the starting materials and the product?
Starting materials: Protein sequences (and their alignments). Product: Contacts, embeddings and structures.
Which papers is “From coevolution to protein language models” based on?
Morcos et al., “Direct-coupling analysis of residue coevolution captures native contacts across many protein families”, PNAS 2011 (doi:10.1073/pnas.1111471108); Rives et al., “Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences”, PNAS 2021 (doi:10.1073/pnas.2016239118); Lin et al., “Evolutionary-scale prediction of atomic-level protein structure with a language model”, Science 2023 (doi:10.1126/science.ade2574); Hayes et al., “Simulating 500 million years of evolution with a language model”, Science 2025 (doi:10.1126/science.ads0018).
Can I edit the “From coevolution to protein language models” template?
Yes. Open it in the LabCanvas editor: all 41 layers are editable, including 5 generated objects (structures, plots, equipment) with their own settings. Change the text, colours and layout, then export PNG, TIFF, SVG or PDF.
Do I need an account to use this template?
Not to view it here. To open and edit it, sign in to LabCanvas or create a free account (the free plan keeps up to 3 designs). Downloading the figure is part of LabCanvas Pro (US$19 a month or US$199 a year).
