Protify Paper

GleghornLab 's Collections

Protify Paper

Platonic Protein Space

Exhaustive hidden-state probing

DSM

Protein Language Models

Annotation Vocabulary

Protify

updated 2 days ago

Every dataset and model used in the Protify paper: benchmark datasets, pretrained protein language models and pH probes.

Upvote

GleghornLab/EC_reg

Viewer • Updated Nov 21, 2023 • 16.2k • 19

Note Protify dataset name: EC
GleghornLab/CC_reg

Viewer • Updated Nov 22, 2023 • 32.5k • 9

Note Protify dataset name: GO-CC
GleghornLab/BP_reg

Viewer • Updated Nov 22, 2023 • 32.5k • 15

Note Protify dataset name: GO-BP
GleghornLab/MF_reg

Viewer • Updated Nov 24, 2023 • 32.5k • 9

Note Protify dataset name: GO-MF
GleghornLab/SL_13

Viewer • Updated Jun 18, 2025 • 34.6k • 23

Note Protify dataset name: Subcellular
GleghornLab/ppi_SHS27k_bfs_2025

Viewer • Updated Oct 28, 2025 • 7.4k • 7

Note Protify dataset name: shs27-ppi-bfs
GleghornLab/ppi_SHS148k_bfs_2025

Viewer • Updated Oct 28, 2025 • 43.4k • 5

Note Protify dataset name: shs148-ppi-bfs
GleghornLab/ppi_STRING_bfs_2025

Viewer • Updated Oct 28, 2025 • 573k • 16

Note Protify dataset name: string-ppi-bfs
GleghornLab/DL10_reg

Viewer • Updated Nov 15, 2023 • 13.7k • 11

Note Protify dataset name: DeepLoc-10
lhallee/ec_active

Viewer • Updated Jun 2, 2025 • 82.2k • 19

Note Protify dataset name: ec-active
GleghornLab/taxonomy_species_0.4_clusters

Viewer • Updated Sep 11, 2025 • 285k • 16

Note Protify dataset name: taxon_species
GleghornLab/fold_prediction

Viewer • Updated Aug 14, 2024 • 16.3k • 13

Note Protify dataset name: number-of-folds
GleghornLab/MB_reg

Viewer • Updated Nov 15, 2023 • 6.4k • 12

Note Protify dataset name: MB
GleghornLab/DL2_reg

Viewer • Updated Nov 15, 2023 • 8.54k • 13

Note Protify dataset name: DeepLoc-2
GleghornLab/solubility_prediction

Viewer • Updated Aug 14, 2024 • 69.4k • 45

Note Protify dataset name: solubility
GleghornLab/diff_phylo

Viewer • Updated Sep 16, 2025 • 102k • 13

Note Protify dataset name: diff_phylogeny
GleghornLab/temperature_stability

Viewer • Updated Sep 15, 2025 • 419k • 30

Note Protify dataset name: temperature-stability
GleghornLab/material_production

Viewer • Updated Aug 14, 2024 • 28.1k • 7

Note Protify dataset name: material-production
GleghornLab/cloning_clf

Viewer • Updated Aug 14, 2024 • 28.2k • 4

Note Protify dataset name: cloning-clf
GleghornLab/ecoli_expression

Viewer • Updated Jan 12 • 6.81k • 19

Note Protify dataset name: ecoli_expression
GleghornLab/soluprot

Viewer • Updated Nov 24, 2025 • 14.5k • 14 • 1

Note Protify dataset name: soluprot
GleghornLab/plm_interact_human_train_cross_ppi

Viewer • Updated Oct 28, 2025 • 717k • 22

Note Protify dataset name: plm-interact
Synthyra/bernett_gold_ppi

Viewer • Updated Feb 7, 2025 • 275k • 95 • 2

Note Protify dataset name: gold-ppi
GleghornLab/KSmo_fixed

Viewer • Updated Feb 18 • 78.9k • 10

Note Protify dataset name: KSMoFinder
GleghornLab/KSmo_clustered

Viewer • Updated Feb 18 • 51.2k • 74

Note Protify dataset name: KSMoFinder-clustered
GleghornLab/fitness_prediction

Viewer • Updated Aug 15, 2024 • 8.73k • 8

Note Protify dataset name: fitness-prediction
GleghornLab/stability_prediction

Viewer • Updated Aug 14, 2024 • 69k • 43

Note Protify dataset name: stability-prediction
GleghornLab/enzyme_kcat

Viewer • Updated Sep 21, 2024 • 7.8k • 269

Note Protify dataset name: enzyme-kcat
GleghornLab/optimal_temperature

Viewer • Updated Aug 14, 2024 • 1.9k • 7

Note Protify dataset name: optimal-temperature
GleghornLab/optimal_ph

Viewer • Updated Apr 15 • 9.86k • 33

Note Protify dataset name: optimal-ph
GleghornLab/millionfull_round_1_oct_2025

Viewer • Updated Oct 28, 2025 • 117k • 2

Note Protify dataset name: million_full
Synthyra/ppi_affinity

Viewer • Updated Sep 15, 2025 • 11k • 17

Note Protify dataset name: PPA-ppi
GleghornLab/SS3

Viewer • Updated Jan 16, 2024 • 11.5k • 30

Note Protify dataset name: SecondaryStructure-3
GleghornLab/SS8

Viewer • Updated Jan 16, 2024 • 11.5k • 18

Note Protify dataset name: SecondaryStructure-8
lhallee/foldseek_dataset

Viewer • Updated May 29, 2025 • 17.1M • 35 • 1

Note Protify dataset name: foldseek-fold, foldseek-inverse
GleghornLab/af2_plddt

Viewer • Updated Sep 14, 2025 • 100k • 29

Note Protify dataset name: plddt
GleghornLab/ppi_SHS27k_random_2025

Viewer • Updated Oct 28, 2025 • 7.4k • 4

Note Protify dataset name: shs27-ppi-random
GleghornLab/ppi_SHS27k_dfs_2025

Viewer • Updated Oct 28, 2025 • 7.4k • 26

Note Protify dataset name: shs27-ppi-dfs
GleghornLab/ppi_SHS148k_random_2025

Viewer • Updated Oct 28, 2025 • 43.4k • 8

Note Protify dataset name: shs148-ppi-random
GleghornLab/ppi_SHS148k_dfs_2025

Viewer • Updated Oct 28, 2025 • 43.4k • 11

Note Protify dataset name: shs148-ppi-dfs
GleghornLab/ppi_STRING_random_2025

Viewer • Updated Oct 28, 2025 • 573k • 23

Note Protify dataset name: string-ppi-random
GleghornLab/ppi_STRING_dfs_2025

Viewer • Updated Oct 28, 2025 • 573k • 19

Note Protify dataset name: string-ppi-dfs
Synthyra/SHS27k

Viewer • Updated Apr 15, 2025 • 26.9k • 17

Note Protify dataset name: shs27-ppi-raw
Synthyra/SHS148k

Viewer • Updated Apr 15, 2025 • 148k • 11 • 1

Note Protify dataset name: shs148-ppi-raw
GleghornLab/localization_prediction

Viewer • Updated Nov 11, 2025 • 8.46k • 6

Note Protify dataset name: localization
GleghornLab/taxonomy_domain_0.4_clusters

Viewer • Updated Sep 11, 2025 • 464k • 14

Note Protify dataset name: taxon_domain
GleghornLab/taxonomy_kingdom_0.4_clusters

Viewer • Updated Sep 11, 2025 • 470k • 8

Note Protify dataset name: taxon_kingdom
GleghornLab/taxonomy_phylum_0.4_clusters

Viewer • Updated Sep 11, 2025 • 478k • 10

Note Protify dataset name: taxon_phylum
GleghornLab/taxonomy_class_0.4_clusters

Viewer • Updated Sep 11, 2025 • 471k • 10

Note Protify dataset name: taxon_class
GleghornLab/taxonomy_order_0.4_clusters

Viewer • Updated Sep 11, 2025 • 466k • 11

Note Protify dataset name: taxon_order
GleghornLab/taxonomy_family_0.4_clusters

Viewer • Updated Sep 11, 2025 • 455k • 17

Note Protify dataset name: taxon_family
GleghornLab/taxonomy_genus_0.4_clusters

Viewer • Updated Sep 11, 2025 • 439k • 8

Note Protify dataset name: taxon_genus
GleghornLab/peptide_HLA_MHC_affinity_ppi

Viewer • Updated Aug 14, 2024 • 72.8k • 14 • 1

Note Protify dataset name: peptide-HLA-MHC-affinity
GleghornLab/HPPI

Viewer • Updated Dec 3, 2023 • 26.7k • 22

Note Protify dataset name: human-ppi-saprot
GleghornLab/HPPI_PiNUI

Viewer • Updated Jun 24, 2024 • 685k • 21

Note Protify dataset name: human-ppi-pinui
GleghornLab/YPPI_PiNUI

Viewer • Updated Jun 24, 2024 • 159k • 18

Note Protify dataset name: yeast-ppi-pinui
GleghornLab/ppi_mutation_effect

Viewer • Updated Oct 28, 2025 • 6.79k • 6

Note Protify dataset name: ppi-mutation-effect
GleghornLab/fluorescence_prediction

Viewer • Updated Aug 14, 2024 • 54k • 30

Note Protify dataset name: fluorescence-prediction
GleghornLab/optimal_ph_rigor

Viewer • Updated Apr 16 • 8.88k • 13

Note Protify dataset name: optimal-ph-rigor
OATML-Markslab/ProteinGym_v1

Updated Jul 21, 2025 • 6.84k • 9

Note ProteinGym v1.0, the source named in the Methods.
GleghornLab/ProteinGym_DMS

Viewer • Updated Aug 20, 2025 • 2.75M • 2.39k • 1

Note ProteinGym per-assay shards read by Protify's zero-shot scorer.
Synthyra/ESM2-8M

Fill-Mask • 7.52M • Updated 27 days ago • 753 • 4

Note Protify model name: ESM2-8
Synthyra/ESM2-35M

Fill-Mask • 33.5M • Updated 27 days ago • 1.2k • 2

Note Protify model name: ESM2-35
Synthyra/ESM2-150M

Fill-Mask • 0.1B • Updated 27 days ago • 322 • 1

Note Protify model name: ESM2-150
Synthyra/ESM2-650M

Fill-Mask • 0.7B • Updated 27 days ago • 1.29k • 1

Note Protify model name: ESM2-650
Synthyra/ESM2-3B

Fill-Mask • 3B • Updated 27 days ago • 200 • 1

Note Protify model name: ESM2-3B
Synthyra/ESMplusplus_small

Fill-Mask • 0.3B • Updated 27 days ago • 3.67k • 20

Note Protify model name: ESMC-300
Synthyra/ESMplusplus_large

Fill-Mask • 0.6B • Updated 27 days ago • 1.03k • 19

Note Protify model name: ESMC-600
Synthyra/Profluent-E1-150M

Fill-Mask • 0.2B • Updated 27 days ago • 478 • 1

Note Protify model name: E1-150
Synthyra/Profluent-E1-300M

Fill-Mask • 0.3B • Updated 27 days ago • 81.6k • 3

Note Protify model name: E1-300
Synthyra/Profluent-E1-600M

Fill-Mask • 0.6B • Updated 27 days ago • 2.06k • 1

Note Protify model name: E1-600
Rostlab/prot_bert

Fill-Mask • Updated Nov 16, 2023 • 207k • • 139

Note Protify model name: ProtBert
Rostlab/prot_bert_bfd

Fill-Mask • Updated Dec 11, 2020 • 6.12k • • 18

Note Protify model name: ProtBert-BFD
Rostlab/prot_t5_xl_half_uniref50-enc

Updated Jan 31, 2023 • 68.7k • 19

Note Protify model name: ProtT5
Rostlab/prot_t5_xl_uniref50

Updated Jan 31, 2023 • 105k • 63

Note Protify model name: ProtT5-XL-UniRef50-full-prec
Rostlab/prot_t5_xxl_uniref50

Updated Mar 30, 2021 • 317 • 1

Note Protify model name: ProtT5-XXL-UniRef50
Rostlab/prot_t5_xl_bfd

Text Generation • Updated Dec 11, 2020 • 2.85k • 10

Note Protify model name: ProtT5-XL-BFD
Rostlab/prot_t5_xxl_bfd

Feature Extraction • Updated Dec 11, 2020 • 76 • 1

Note Protify model name: ProtT5-XXL-BFD
Synthyra/ANKH_base

0.7B • Updated 27 days ago • 336

Note Protify model name: ANKH-Base
Synthyra/ANKH_large

2B • Updated 27 days ago • 261 • 2

Note Protify model name: ANKH-Large
Synthyra/ANKH2_large

2B • Updated 27 days ago • 230 • 1

Note Protify model name: ANKH2-Large
tattabio/gLM2_150M

0.2B • Updated Feb 11 • 2.06k • 3

Note Protify model name: GLM2-150
tattabio/gLM2_650M

0.7B • Updated Feb 11 • 3.08k • 7

Note Protify model name: GLM2-650
tattabio/gLM2_650M_embed

0.3B • Updated Feb 11 • 441 • 3

Note Protify model name: GLM2-GAIA
Synthyra/DPLM-150M

0.1B • Updated 27 days ago • 379

Note Protify model name: DPLM-150
Synthyra/DPLM-650M

0.7B • Updated 27 days ago • 165

Note Protify model name: DPLM-650
Synthyra/DPLM-3B

3B • Updated 27 days ago • 164

Note Protify model name: DPLM-3B
Synthyra/DPLM2-150M

0.2B • Updated 27 days ago • 186 • 1

Note Protify model name: DPLM2-150
Synthyra/DPLM2-650M

0.7B • Updated 27 days ago • 178 • 1

Note Protify model name: DPLM2-650
Synthyra/DPLM2-3B

3B • Updated 27 days ago • 286 • 1

Note Protify model name: DPLM2-3B
GleghornLab/DSM_150

0.1B • Updated Sep 24 • 22

Note Protify model name: DSM-150
GleghornLab/DSM_650

0.7B • Updated Sep 24 • 586

Note Protify model name: DSM-650
Synthyra/DSM_ppi_full

Updated Sep 24 • 64 • 1

Note Protify model name: DSM-PPI
GleghornLab/AMPLIFY_120M

0.1B • Updated Sep 30, 2024 • 8

Note Protify model name: AMPLIFY-120
GleghornLab/AMPLIFY_350M

0.4B • Updated Sep 30, 2024 • 8

Note Protify model name: AMPLIFY-350
multimolecule/calm

Fill-Mask • 85.7M • Updated May 31 • 114

Note Protify model name: CaLM
facebook/esm2_t12_35M_UR50D

Fill-Mask • 34M • Updated Mar 21, 2023 • 256k • • 30

Note Configuration and tokenizer of the Random-Transformer control.
GleghornLab/optimal_ph_DPLM2-3B_2026-04-27-19-40_RTHS

Text Classification • 5.45M • Updated Apr 27 • 7

Note pH transformer probe on DPLM2-3B, EpHod split: test R2 0.482.
GleghornLab/optimal_ph_rigor_DPLM2-3B_2026-04-27-19-40_RTHS

Text Classification • 5.45M • Updated Apr 27 • 7

Note pH transformer probe on DPLM2-3B, rigor split: test R2 0.248.
GleghornLab/optimal_ph_rigor_DPLM2-3B_2026-04-27-19-29_BWNH

Text Classification • 5.45M • Updated Apr 27 • 10

Note pH transformer probe on DPLM2-3B, rigor split: test R2 0.248.

Upvote