ProteinGym is an extensive set of Deep Mutational Scanning (DMS) assays curated to enable thorough comparisons of various mutation effect predictors indifferent regimes. It is comprised of two benchmarks: 1) a substitution benchmark which currently consists of the experimental characterisation of ∼1.5M missense variants across 87 DMS assays 2) an indel benchmark that includes ∼300k mutants across 7 DMS assays.

Each processed file in each benchmark corresponds to a single DMS assay, and contains the following variables:

• mutant (str): describes the set of substitutions to apply on the reference sequence to obtain the mutated sequence (eg., A1P:D2N implies the amino acid 'A' at position 1 should be replaced by 'P', and 'D' at position 2 should be replaced by 'N'). Present in the the ProteinGym substitution assays only (not indels).
• mutated_sequence (str): represents the full amino acid sequence for the mutated protein.
• DMS_score (float): corresponds to the experimental measurement in the DMS assay. Across all assays, the higher the DMS_score value, the higher the fitness of the mutated protein
• DMS_score_bin (int): indicates whether the DMS_score is above the fitness cutoff (1 is fit, 0 is not fit)

Additionally, we provide two reference files for each benharmk that give further details on each assay and contain in particular:

• The UniProt_ID of the corresponding protein, along with taxon and MSA depth category
• The target sequence (target_seq) used in the assay
• Details on how the DMS_score was created from the raw files and how it was binarized

To download the substitution benchmark (~867M unzipped):

curl -o ProteinGym_substitutions.zip https://marks.hms.harvard.edu/proteingym/ProteinGym_substitutions.zip 
unzip ProteinGym_substitutions.zip
rm ProteinGym_substitutions.zip

Similarly, to download the indel benchmark (~223M unzipped):

curl -o ProteinGym_indels.zip https://marks.hms.harvard.edu/proteingym/ProteinGym_indels.zip
unzip ProteinGym_indels.zip
rm ProteinGym_indels.zip

The ProteinGym benchmarks are also available on the Hugging Face Hub.

The Detailed_performance_files folder provides detailed performance files for all baselines on the two ProteinGym benchmarks, for the 3 focus performance metrics (Spearman's rank, AUC, MCC) as introduced in the original Tranception paper.

We recommand to aggregate fitness prediction performance at the Uniprot ID level to avoid biasing results towards proteins for which several DMS assays are available in ProteinGym. The corresponding aggregated files are suffixed with "_Uniprot_level", while the non aggregated performance files are suffixed with "_DMS_level". Note that there is at most one DMS per Uniprot_ID for the ProteinGym indel benchmark (ie., no difference between "_Uniprot_level" and "_DMS_level"). We thus only provide one set of performance metrics for that benchmark.

The full ProteinGym benchmarks performance files are also accessible via our dedicated website: https://www.proteingym.org/. It includes leaderboards for the substitution and indel benchmarks, as well as detailed DMS-level performance files for all baselines. The current version of the substitution benchmark includes the following baselines:

Except for the Wavenet model (which only uses alignments to recover a set of homologous protein sequences to train on, but then trains on non-aligned sequences), all alignment-based methods are unable to score indels given the fixed coordinate system they are trained on. Similarly, the masking procedure to generate the masked-marginals for ESM-1v and MSA Transformer requires the position to exist in the wild-type sequence. All the other model architectures listed above (eg., Tranception, RITA, Progen2) are included in the indel benchmark.

The scores for all DMS assays in the ProteinGym substitution benchmark for all baselines (eg., Tranception, EVE, Wavenet, ESM-1v, MSA Transformer) may be downloaded as follows;

curl -o scores_all_models_proteingym_substitutions.zip https://marks.hms.harvard.edu/proteingym/scores_all_models_proteingym_substitutions.zip
unzip scores_all_models_proteingym_substitutions.zip
rm scores_all_models_proteingym_substitutions.zip

Similarly for the indel benchmark, all scoring files may be downloaded as follows:

curl -o scores_all_models_proteingym_indels.zip https://marks.hms.harvard.edu/proteingym/scores_all_models_proteingym_indels.zip
unzip scores_all_models_proteingym_indels.zip
rm scores_all_models_proteingym_indels.zip

The MSAs used to train alignment-based methods or used at inference in Tranception with retrieval and MSA Transformer may be downloaded as follows (~2.2GB unzipped):

curl -o MSA_ProteinGym.zip https://marks.hms.harvard.edu/proteingym/MSA_ProteinGym.zip
unzip MSA_ProteinGym.zip
rm MSA_ProteinGym.zip

If you would like to suggest new assays to be part of ProteinGym, please raise an issue on this repository with a `new_assay' label. The criteria we typically consider for inclusion are as follows:

1. The corresponding raw dataset needs to be publicly available
2. The assay needs to be protein-related (ie., exclude UTR, tRNA, promoter, etc.)
3. The dataset needs to have a sufficient number of measurements (ie., a couple hundred mutants at a minimum, ideally several thousands)
4. The assay needs to have a sufficiently high dynamic range
5. The assay has to be relevant to fitness prediction

If you would like new baselines to be included in ProteinGym (ie., website, performance files, detailed scoring files), please raise an issue on this repository with a 'new_model' label. At this point we are only considering models satisfying the following conditions:

1. The approach is unsupervised (the DMS measurements should not be used to train the model);
2. The model is able to score all mutants across all the assays (to ensure all models are compared exactly on the same set of mutants everywhere);
3. The corresponding code is open source (we should be able to reproduce scores if needed). At this stage, we are only considering requests for which all model scores for all mutants in a given benchmark (substitution or indel) are provided by the requester; but we are planning on regularly scoring new baselines ourselves for methods with wide adoption by the community and/or suggestions with many upvotes.

This project is available under the MIT license.

If you use ProteinGym in your work, please cite the following paper:

Notin, P., Dias, M., Frazer, J., Marchena-Hurtado, J., Gomez, A., Marks, D.S., Gal, Y. (2022). Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval. ICML.

• Original paper: https://proceedings.mlr.press/v162/notin22a.html
• Website: https://www.proteingym.org/
• HuggingFace: https://huggingface.co/datasets/OATML-Markslab/ProteinGym