ProGen2
Suite of protein language models of up to 6.4 billion parameters trained on sequence datasets drawn from over a billion proteins, which generate sequences and predict fitness without fine-tuning; ProteinGym scores it as a zero-shot single-sequence substitution baseline.
15 evaluations · 100 results1 configuration with further results
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluations and results
15 evaluations · 100 results. Different protocols are not a single leaderboard.
Sorted by AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.
| Tested configuration | Protocol and dataset | AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) | Spearman | Spearman (ProteinGym zero-shot DMS substitutions, Activity assays: mean over proteins of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, Binding assays: mean over proteins of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, Expression assays: mean over proteins of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, High MSA depth proteins: mean over proteins of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, Human proteins: mean over proteins of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, Low MSA depth proteins: mean over proteins of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)) | Spearman (ProteinGym zero-shot DMS substitutions, Medium MSA depth proteins: mean over proteins of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, Organismal fitness assays: mean over proteins of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, Other eukaryote proteins: mean over proteins of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, Prokaryote proteins: mean over proteins of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, Stability assays: mean over proteins of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, variants with 1 substitution: mean over protein and selection-type groups of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, variants with 2 substitutions: mean over protein and selection-type groups of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, variants with 3 substitutions: mean over protein and selection-type groups of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, variants with 4 substitutions: mean over protein and selection-type groups of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, variants with 5 or more substitutions: mean over protein and selection-type groups of assay-level Spearman) | Spearman (ProteinGym zero-shot DMS substitutions, Virus proteins: mean over proteins of assay-level Spearman) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Progen2 L [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22), ProteinGym clinical indel benchmark at commit 144fe22 | 0.851 (best in column) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Progen2 M [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22), ProteinGym clinical indel benchmark at commit 144fe22 | 0.846 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Progen2 Base [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22), ProteinGym clinical indel benchmark at commit 144fe22 | 0.844 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Progen2 XL [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22), ProteinGym clinical indel benchmark at commit 144fe22 | 0.842 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Progen2 S [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22), ProteinGym clinical indel benchmark at commit 144fe22 | 0.763 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Progen2 Base [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym AMFR official zero-shot Spearman snapshot, ProteinGym AMFR 4G3O official snapshot cohort | Not reported | -0.05 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Progen2 L [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym AMFR official zero-shot Spearman snapshot, ProteinGym AMFR 4G3O official snapshot cohort | Not reported | -0.121 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Progen2 M [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym AMFR official zero-shot Spearman snapshot, ProteinGym AMFR 4G3O official snapshot cohort | Not reported | -0.089 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Progen2 S [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym AMFR official zero-shot Spearman snapshot, ProteinGym AMFR 4G3O official snapshot cohort | Not reported | -0.317 | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Progen2 XL [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym AMFR official zero-shot Spearman snapshot, ProteinGym AMFR 4G3O official snapshot cohort | Not reported | 0.056 (best in column) | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported | Not reported |
| Progen2 Base [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym v1.3 zero-shot DMS substitutions, ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | Not reported | Not reported | 0.396 | 0.294 | 0.437 (best in column) | 0.421 | 0.422 (best in column) | 0.327 | 0.378 | 0.379 | 0.381 | 0.422 | 0.333 | 0.383 | 0.371 | 0.131 | 0.149 | 0.156 | 0.208 | 0.316 |
| Progen2 L [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym v1.3 zero-shot DMS substitutions, ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | Not reported | Not reported | 0.406 (best in column) | 0.293 | 0.427 | 0.414 | 0.411 | 0.339 (best in column) | 0.38 | 0.39 | 0.379 | 0.432 | 0.364 | 0.396 | 0.371 | 0.142 | 0.225 | 0.207 | 0.258 | 0.323 |
| Progen2 M [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym v1.3 zero-shot DMS substitutions, ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | Not reported | Not reported | 0.393 | 0.295 | 0.433 | 0.422 | 0.413 | 0.307 | 0.38 | 0.391 | 0.383 | 0.417 | 0.356 | 0.396 | 0.373 | 0.131 | 0.152 | 0.137 | 0.177 | 0.335 |
| Progen2 S [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym v1.3 zero-shot DMS substitutions, ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | Not reported | Not reported | 0.333 | 0.275 | 0.384 | 0.39 | 0.385 | 0.293 | 0.336 | 0.321 | 0.338 | 0.358 | 0.291 | 0.349 | 0.328 | 0.114 | 0.117 | 0.123 | 0.187 | 0.271 |
| Progen2 XL [ProteinGym 144fe22b snapshot]Evaluation | ProteinGym v1.3 zero-shot DMS substitutions, ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | Not reported | Not reported | 0.402 | 0.302 (best in column) | 0.418 | 0.442 (best in column) | 0.386 | 0.323 | 0.391 (best in column) | 0.412 (best in column) | 0.387 (best in column) | 0.458 (best in column) | 0.418 (best in column) | 0.445 (best in column) | 0.384 (best in column) | 0.182 (best in column) | 0.271 (best in column) | 0.234 (best in column) | 0.28 (best in column) | 0.402 (best in column) |
All 100 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort | -0.05 Spearman unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base AMFR official snapshot Not reported Aggregation: Not reported ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=Progen2 Base |
| Configuration: Progen2 L [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort | -0.121 Spearman unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 L AMFR official snapshot Not reported Aggregation: Not reported ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=Progen2 L |
| Configuration: Progen2 M [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort | -0.089 Spearman unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 M AMFR official snapshot Not reported Aggregation: Not reported ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=Progen2 M |
| Configuration: Progen2 S [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort | -0.317 Spearman unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 S AMFR official snapshot Not reported Aggregation: Not reported ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=Progen2 S |
| Configuration: Progen2 XL [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort | 0.056 Spearman unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 XL AMFR official snapshot Not reported Aggregation: Not reported ProteinGym AMFR assay-level Spearman comparison · DMS_substitutions_Spearman_DMS_level.csv line 15, DMS ID=AMFR_HUMAN_Tsuboyama_2023_4G3O, column=Progen2 XL |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22 | 0.844 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 10, row 'Progen2 Base', column 'Average_AUC' |
| Configuration: Progen2 L [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22 | 0.851 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 L: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 8, row 'Progen2 L', column 'Average_AUC' |
| Configuration: Progen2 M [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22 | 0.846 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 M: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 9, row 'Progen2 M', column 'Average_AUC' |
| Configuration: Progen2 S [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22 | 0.763 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 S: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 16, row 'Progen2 S', column 'Average_AUC' |
| Configuration: Progen2 XL [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Dataset subset: ProteinGym clinical indel benchmark at commit 144fe22 | 0.842 AUROC (ProteinGym clinical indels, zero-shot, Average_AUC over proteins) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 XL: ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) ProteinGym clinical indels, zero-shot, average AUC (commit 144fe22) Aggregation: Not reported ProteinGym clinical zero-shot indels AUC summary at commit 144fe22 · benchmarks/clinical_zero_shot/indels/AUC/Summary_performance_clinical_indels_AUC.csv line 12, row 'Progen2 XL', column 'Average_AUC' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.378 Spearman (ProteinGym zero-shot DMS substitutions, mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)) unitless · higher Uncertainty: SE 0.01. From compute_bootstrap_standard_error_functional_categories in performance_DMS_benchmarks.py at 144fe22 (default 10,000 resamples, lines 95-111 and 310-315); not an absolute standard error of the model's own average. Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Average_Spearman' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.371 Spearman (ProteinGym zero-shot DMS substitutions, variants with 1 substitution: mean over protein and selection-type groups of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Depth_1' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.131 Spearman (ProteinGym zero-shot DMS substitutions, variants with 2 substitutions: mean over protein and selection-type groups of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Depth_2' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.149 Spearman (ProteinGym zero-shot DMS substitutions, variants with 3 substitutions: mean over protein and selection-type groups of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Depth_3' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.156 Spearman (ProteinGym zero-shot DMS substitutions, variants with 4 substitutions: mean over protein and selection-type groups of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Depth_4' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.208 Spearman (ProteinGym zero-shot DMS substitutions, variants with 5 or more substitutions: mean over protein and selection-type groups of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Depth_5+' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.396 Spearman (ProteinGym zero-shot DMS substitutions, Activity assays: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Function_Activity' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.294 Spearman (ProteinGym zero-shot DMS substitutions, Binding assays: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Function_Binding' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.437 Spearman (ProteinGym zero-shot DMS substitutions, Expression assays: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Function_Expression' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.381 Spearman (ProteinGym zero-shot DMS substitutions, Organismal fitness assays: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Function_OrganismalFitness' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.383 Spearman (ProteinGym zero-shot DMS substitutions, Stability assays: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Function_Stability' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.421 Spearman (ProteinGym zero-shot DMS substitutions, High MSA depth proteins: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'High_MSA_depth' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.327 Spearman (ProteinGym zero-shot DMS substitutions, Low MSA depth proteins: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Low_MSA_depth' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.379 Spearman (ProteinGym zero-shot DMS substitutions, Medium MSA depth proteins: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Medium_MSA_depth' |
| Configuration: Progen2 Base [ProteinGym 144fe22b snapshot] | Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays) | 0.422 Spearman (ProteinGym zero-shot DMS substitutions, Human proteins: mean over proteins of assay-level Spearman) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Evaluation origin not reported · Source checkedMethods, coverage and sourceProgen2 Base: ProteinGym zero-shot DMS substitutions summary (144fe22) ProteinGym zero-shot DMS substitutions, Spearman summary Aggregation: Not reported ProteinGym zero-shot DMS substitutions Spearman summary at commit 144fe22 · benchmarks/DMS_zero_shot/substitutions/Spearman/Summary_performance_DMS_substitutions_Spearman.csv line 68, row 'Progen2 Base', column 'Taxa_Human' |
Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.
Further results on linked records
One linked record has results that are not included above, because no reviewed claim yet ties the link to this model. Each record keeps its own settings and evaluations, and its scores are on its own page.
- ProGen2 (Livesey and Marsh 2025) Configuration · configuration · 5 evaluations · 6 results
Use this model
How it works, versions and access
Versions and evaluated configurations
- Progen2 Base [ProteinGym 144fe22b snapshot] · configuration of
- Progen2 L [ProteinGym 144fe22b snapshot] · configuration of
- Progen2 M [ProteinGym 144fe22b snapshot] · configuration of
- Progen2 S [ProteinGym 144fe22b snapshot] · configuration of
- Progen2 XL [ProteinGym 144fe22b snapshot] · configuration of
Strengths, limitations and unresolved questions
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
3 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Description Suite of protein language models of up to 6.4 billion parameters trained on sequence datasets drawn from over a billion proteins, which generate sequences and predict fitness without fine-tuning; ProteinGym scores it as a zero-shot single-sequence substitution baseline. Individual claims | Abstract: ProGen2: Exploring the boundaries of protein language models uc20260930-source-proteingym-amfr-spearman: Benchmark CSV header (model scored in the zero-shot DMS substitution benchmark); run-doc-proteingym-readme-md-144fe22b: README 'Leaderboard' baseline table (model name, input modalities, reference); qa-descriptions-20261010-source-progen2: abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Europe PMC core record MED/37909046 (title and abstract), Cell systems 2023 | source checked ["automated-source-review","ai-assisted-source-review"] · 2026-10-10 Audit detailsDescription written from the cited source text; provenance text was generic and is kept here as previous_value. Independent review 2026-10-10: corrected. 'trained on over a billion protein sequences' changed to the abstract's 'sequence datasets drawn from over a billion proteins'. Field: Claim: metadata-correction-d07cca550523d5ebb924 Source artifact SHA-256: Hash scope: SHA-256 of one retrieval of a Europe PMC REST search response. The response is not byte-stable: on 2026-10-10 a second retrieval of 10 of these 31 records differed only in JSON key order and parsed to identical content. The title and abstractText fields are the evidence. |
| Description Suite of protein language models of up to 6.4 billion parameters trained on sequence datasets drawn from over a billion proteins, which generate sequences and predict fitness without fine-tuning; ProteinGym scores it as a zero-shot single-sequence substitution baseline. Individual claims | OATML-Markslab/ProteinGym / README.md uc20260930-source-proteingym-amfr-spearman: Benchmark CSV header (model scored in the zero-shot DMS substitution benchmark); run-doc-proteingym-readme-md-144fe22b: README 'Leaderboard' baseline table (model name, input modalities, reference); qa-descriptions-20261010-source-progen2: abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c | source checked ["automated-source-review","ai-assisted-source-review"] · 2026-10-10 Audit detailsDescription written from the cited source text; provenance text was generic and is kept here as previous_value. Independent review 2026-10-10: corrected. 'trained on over a billion protein sequences' changed to the abstract's 'sequence datasets drawn from over a billion proteins'. Field: Claim: metadata-correction-d07cca550523d5ebb924 Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Description Suite of protein language models of up to 6.4 billion parameters trained on sequence datasets drawn from over a billion proteins, which generate sequences and predict fitness without fine-tuning; ProteinGym scores it as a zero-shot single-sequence substitution baseline. Individual claims | ProteinGym AMFR assay-level Spearman comparison uc20260930-source-proteingym-amfr-spearman: Benchmark CSV header (model scored in the zero-shot DMS substitution benchmark); run-doc-proteingym-readme-md-144fe22b: README 'Leaderboard' baseline table (model name, input modalities, reference); qa-descriptions-20261010-source-progen2: abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 144fe22b07dfaeec2b366f2346203a9838a55b4c | source checked ["automated-source-review","ai-assisted-source-review"] · 2026-10-10 Audit detailsDescription written from the cited source text; provenance text was generic and is kept here as previous_value. Independent review 2026-10-10: corrected. 'trained on over a billion protein sequences' changed to the abstract's 'sequence datasets drawn from over a billion proteins'. Field: Claim: metadata-correction-d07cca550523d5ebb924 Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
3 source records and release history
- ProteinGym AMFR assay-level Spearman comparison · Original source · 144fe22b07dfaeec2b366f2346203a9838a55b4c
- OATML-Markslab/ProteinGym / README.md · Original source · Git commit 144fe22b07dfaeec2b366f2346203a9838a55b4c
- Abstract: ProGen2: Exploring the boundaries of protein language models · Original source · Europe PMC core record MED/37909046 (title and abstract), Cell systems 2023
Technical metadata and extraction receipts
Stable ID: uc20260930-model-progen2
- areas
- proteins-complexes
- source locator
- Pinned ProteinGym Spearman CSV header: Progen2 S
- review
- method: automated-source-review; reviewer: codex; reviewed at: 2026-09-30T21:40:59.576893+00:00; scope: Primary-source transcription and catalogue applicability audit; not human scientific review or independent experimental reproduction.; reviewer note: role: experimental use-case curation
- entity level
- family
- identity scope
- Family/method identity only; no undocumented checkpoint equivalence.
Related records
- uses model: GCN with ProGen2 protein embeddings (sequence) (PPI embeddings study)
- uses model: GraphSAGE with ProGen2 protein embeddings (sequence) (PPI embeddings study)
- uses model: MLP on concatenated protein embeddings (protein-only baseline, no network) with ProGen2 protein embeddings (sequence) (PPI embeddings study)
- uses model: NGNN with GCN combined with SEAL with ProGen2 protein embeddings (sequence) (PPI embeddings study)
- uses model: NGNN with GCN with ProGen2 protein embeddings (sequence) (PPI embeddings study)
- uses model: NGNN with GraphSAGE combined with SEAL with ProGen2 protein embeddings (sequence) (PPI embeddings study)
- uses model: NGNN with GraphSAGE with ProGen2 protein embeddings (sequence) (PPI embeddings study)
- subject: ProGen2: description
- configuration of: Progen2 Base [ProteinGym 144fe22b snapshot]
- configuration of: Progen2 L [ProteinGym 144fe22b snapshot]
- configuration of: Progen2 M [ProteinGym 144fe22b snapshot]
- configuration of: Progen2 S [ProteinGym 144fe22b snapshot]
- configuration of: Progen2 XL [ProteinGym 144fe22b snapshot]
- configuration of: ProGen2 (Livesey and Marsh 2025)