Illinois Data Bank

Data for ESMDynamic: Fast and Accurate Prediction of Protein Dynamic Contact Maps from Single Sequences

This repository contains data and model weights associated with the publication "ESMDynamic: Fast and Accurate Prediction of Protein Dynamic Contact Maps from Single Sequences". It includes the datasets used for training and evaluating a dynamic contact prediction model, ESMDynamic, as well as a script for conversion and usage.

Life Sciences
Computational biology; Structural biology; Molecular dynamics; Machine learning; Protein modeling; Bioinformatics; Biophysics; Artificial intelligence
CC BY
U.S. National Science Foundation (NSF)-Grant:MCB-1845606
U.S. National Science Foundation (NSF)-Grant:CHE-2136142
Diwakar Shukla
Version DOI Comment Publication Date
2 10.13012/B2IDB-3773897_V2 Made substantial changes to the data after the peer review 2026-04-17
1 10.13012/B2IDB-3773897_V1 2025-06-23
Files associated with this dataset are being processed for availability via Globus. This is expected to complete within a few hours of publication. Contact the Research Data Service with any questions.
README.md 3.79 KB File
atlas_test.zip 1.21 MB File
decompress_mdcath_dataset.py 4.15 KB File
decompress_rcsb_dataset.py 1.61 KB File
esmdynamic_model_weights_V2.pt 366 MB File
human_proteome_preds_1.tar.xz 16.9 GB File
human_proteome_preds_10.tar.xz 31.3 GB File
human_proteome_preds_11.tar.xz 35.2 GB File
human_proteome_preds_12.tar.xz 27.5 GB File
human_proteome_preds_13.tar.xz 31.4 GB File
human_proteome_preds_14.tar.xz 29.1 GB File
human_proteome_preds_15.tar.xz 26.1 GB File
human_proteome_preds_16.tar.xz 31.6 GB File
human_proteome_preds_17.tar.xz 30.2 GB File
human_proteome_preds_18.tar.xz 37.3 GB File
human_proteome_preds_19.tar.xz 2.31 GB File
human_proteome_preds_2.tar.xz 29.9 GB File
human_proteome_preds_3.tar.xz 26.7 GB File
human_proteome_preds_4.tar.xz 22.2 GB File
human_proteome_preds_5.tar.xz 30.2 GB File
human_proteome_preds_6.tar.xz 28.5 GB File
human_proteome_preds_7.tar.xz 28.5 GB File
human_proteome_preds_8.tar.xz 35.1 GB File
human_proteome_preds_9.tar.xz 31.2 GB File
human_proteome_structs_1.tar.xz 25.3 MB File
human_proteome_structs_10.tar.xz 37.6 MB File
human_proteome_structs_11.tar.xz 40.4 MB File
human_proteome_structs_12.tar.xz 35.9 MB File
human_proteome_structs_13.tar.xz 37.7 MB File
human_proteome_structs_14.tar.xz 36.7 MB File
human_proteome_structs_15.tar.xz 34.4 MB File
human_proteome_structs_16.tar.xz 38.2 MB File
human_proteome_structs_17.tar.xz 37.2 MB File
human_proteome_structs_18.tar.xz 39.3 MB File
human_proteome_structs_19.tar.xz 3.88 MB File
human_proteome_structs_2.tar.xz 36.4 MB File
human_proteome_structs_3.tar.xz 34 MB File
human_proteome_structs_4.tar.xz 30 MB File
human_proteome_structs_5.tar.xz 37.5 MB File
human_proteome_structs_6.tar.xz 35.8 MB File
human_proteome_structs_7.tar.xz 34.6 MB File
human_proteome_structs_8.tar.xz 39.9 MB File
human_proteome_structs_9.tar.xz 37.1 MB File
human_proteome_uniprot_to_file.csv 943 KB File
mdcath.zip 210 MB File
mdcath_to_rcsb_mapping.csv 44.9 KB File
rcsb.zip 65.2 MB File

Contact the Research Data Service for help interpreting this log.

Dataset update: {"publication_state"=>["version candidate under curator review", "released"], "release_date"=>[nil, Fri, 17 Apr 2026]} 2026-04-17T21:53:55Z
Dataset update: {"version_comment"=>["The paper has been peer-reviewed for journal publication and substantial changes, including to the dataset, have been requested.", "Made substantial changes to the data after the peer review"]} 2026-04-17T20:47:46Z
RelatedMaterial update: {"note"=>[nil, ""]} 2026-04-17T20:10:44Z
Dataset update: {"hold_state"=>["version candidate under curator review", "none"]} 2026-04-09T20:28:36Z
Dataset update: {"version_comment"=>[nil, "The paper has been peer-reviewed for journal publication and substantial changes, including to the dataset, have been requested."]} 2026-04-09T20:27:38Z
RelatedMaterial create: {"material_type"=>"Dataset", "availability"=>nil, "link"=>"https://doi.org/10.13012/B2IDB-3773897_V1", "uri"=>"10.13012/B2IDB-3773897_V1", "uri_type"=>"DOI", "citation"=>"Kleiman, Diego; Feng, Jiangyan; Xue, Zhengyuan; Shukla, Diwakar (2025): Data for ESMDynamic: Fast and Accurate Prediction of Protein Dynamic Contact Maps from Single Sequences. University of Illinois Urbana-Champaign. https://doi.org/10.13012/B2IDB-3773897_V1", "dataset_id"=>3391, "selected_type"=>"Dataset", "datacite_list"=>"IsNewVersionOf", "note"=>nil, "feature"=>nil} 2026-04-09T20:26:21Z
RelatedMaterial create: {"material_type"=>"Preprint", "availability"=>nil, "link"=>"https://doi.org/10.1101/2025.08.20.671365", "uri"=>"10.1101/2025.08.20.671365", "uri_type"=>"DOI", "citation"=>" Kleiman, D. E., Feng, J., Xue, Z. & Shukla, D. ESMDynamic: A Fast and Accurate Prediction of Protein Dynamic Contact Maps from Single Sequences. (2025). doi:10.1101/2025.08.20.671365.", "dataset_id"=>3391, "selected_type"=>"Other", "datacite_list"=>"IsSupplementTo", "note"=>"", "feature"=>nil} 2026-04-09T20:26:21Z
RelatedMaterial create: {"material_type"=>"Code", "availability"=>nil, "link"=>"https://github.com/ShuklaGroup/esmdynamic", "uri"=>"https://github.com/ShuklaGroup/esmdynamic", "uri_type"=>"URL", "citation"=>"https://github.com/ShuklaGroup/esmdynamic", "dataset_id"=>3391, "selected_type"=>"Code", "datacite_list"=>"IsSupplementedBy", "note"=>"", "feature"=>nil} 2026-04-09T20:26:21Z
Funder create: {"name"=>"U.S. National Science Foundation (NSF)", "identifier"=>"10.13039/100000001", "identifier_scheme"=>"DOI", "grant"=>"CHE-2136142", "dataset_id"=>3391, "code"=>"NSF"} 2026-04-09T20:26:21Z
Funder create: {"name"=>"U.S. National Science Foundation (NSF)", "identifier"=>"10.13039/100000001", "identifier_scheme"=>"DOI", "grant"=>"MCB-1845606", "dataset_id"=>3391, "code"=>"NSF"} 2026-04-09T20:26:21Z
Creator create: {"family_name"=>"Shukla", "given_name"=>"Diwakar", "identifier"=>"0000-0003-4079-5381", "email"=>"diwakar@illinois.edu", "is_contact"=>true, "row_position"=>4} 2026-04-09T20:26:21Z
Dataset update: {"corresponding_creator_name"=>[nil, "Diwakar Shukla"], "corresponding_creator_email"=>[nil, "diwakar@illinois.edu"]} 2026-04-09T20:26:21Z
Creator create: {"family_name"=>"Xue", "given_name"=>"Zhengyuan", "identifier"=>"0009-0004-4738-4395", "email"=>"zxue8@illinois.edu", "is_contact"=>false, "row_position"=>3} 2026-04-09T20:26:21Z
Creator create: {"family_name"=>"Feng", "given_name"=>"Jiangyan", "identifier"=>"0000-0003-0292-6758", "email"=>"jyfeng20@gmail.com", "is_contact"=>false, "row_position"=>2} 2026-04-09T20:26:21Z
Creator create: {"family_name"=>"Kleiman", "given_name"=>"Diego", "identifier"=>"0000-0002-3833-5872", "email"=>"diegoek2@illinois.edu", "is_contact"=>false, "row_position"=>1} 2026-04-09T20:26:21Z
Research Data Service Illinois Data Bank
Access and Use Policies Web Privacy Notice Contact Us