Model

ESM-IF1

ESM-IF1 designs protein sequences conditioned on backbone coordinates.

Sources

facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models

How it worksESM-IF1 workflow

Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.

Sources

facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models

Overview

Model type

Geometric encoder and inverse-folding transformer

Inputs

Protein backbone atom coordinates; the model supports missing backbone spans.

Outputs

Sampled protein sequences or conditional sequence likelihoods.

Access

Official project documentation and implementation: https://github.com/facebookresearch/esm

Sources

facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Evaluations and results

13 evaluations · 34 results. Different protocols are not a single leaderboard.

Sorted by Plddt (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	Plddt	Sctm	Spearman	AUROC	MCC	NDCG at 10%	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)	Top 10% recall
ESM-IF1Evaluation	ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-PLDDT: De novo backbones based sequence design, length 100 pLDDT, CASP, CAMEO and de novo backbones (ProteinBench split)	88.8 (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	Not reported	Not reported	Not reported	Not reported	Not reported
ESM-IF1Evaluation	ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-PLDDT: De novo backbones based sequence design, length 300 pLDDT, CASP, CAMEO and de novo backbones (ProteinBench split)	74.4	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	Not reported	Not reported	Not reported	Not reported	Not reported
ESM-IF1Evaluation	ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-PLDDT: De novo backbones based sequence design, length 200 pLDDT, CASP, CAMEO and de novo backbones (ProteinBench split)	69.7	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	Not reported	Not reported	Not reported	Not reported	Not reported
ESM-IF1Evaluation	ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-PLDDT: De novo backbones based sequence design, length 400 pLDDT, CASP, CAMEO and de novo backbones (ProteinBench split)	64.6	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	Not reported	Not reported	Not reported	Not reported	Not reported
ESM-IF1Evaluation	ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-PLDDT: De novo backbones based sequence design, length 500 pLDDT, CASP, CAMEO and de novo backbones (ProteinBench split)	59	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	Not reported	Not reported	Not reported	Not reported	Not reported
ESM-IF1Evaluation	ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM: De novo backbones based sequence design, length 100 scTM, CASP, CAMEO and de novo backbones (ProteinBench split)	Not reported	0.81 (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	Not reported	Not reported	Not reported	Not reported
ESM-IF1Evaluation	ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-SCTM: De novo backbones based sequence design, length 200 scTM, CASP, CAMEO and de novo backbones (ProteinBench split)	Not reported	0.635	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	Not reported	Not reported	Not reported	Not reported
ESM-IF1Evaluation	ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-SCTM: De novo backbones based sequence design, length 300 scTM, CASP, CAMEO and de novo backbones (ProteinBench split)	Not reported	0.336	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	Not reported	Not reported	Not reported	Not reported
ESM-IF1Evaluation	ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-SCTM: De novo backbones based sequence design, length 400 scTM, CASP, CAMEO and de novo backbones (ProteinBench split)	Not reported	0.449	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	Not reported	Not reported	Not reported	Not reported
ESM-IF1Evaluation	ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-SCTM: De novo backbones based sequence design, length 500 scTM, CASP, CAMEO and de novo backbones (ProteinBench split)	Not reported	0.462	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	Not reported	Not reported	Not reported	Not reported
ESM-IF1Evaluation	ProteinGym ZS-SUB-AUC: Zero-shot substitutions, AUC, ProteinGym substitution DMS assays (ProteinGym split)	Not reported	Not reported	Not reported	0.73	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	Not reported	Not reported
ESM-IF1Evaluation	ProteinGym ZS-SUB-MCC: Zero-shot substitutions, MCC, ProteinGym substitution DMS assays (ProteinGym split)	Not reported	Not reported	Not reported	Not reported	0.331	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	Not reported
ESM-IF1Evaluation	ProteinGym ZS-SUB-NDCG: Zero-shot substitutions, NDCG@10%, ProteinGym substitution DMS assays (ProteinGym split)	Not reported	Not reported	Not reported	Not reported	Not reported	0.748	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
ESM-IF1Evaluation	ProteinGym ZS-SUB-RECALL: Zero-shot substitutions, top 10% recall, ProteinGym substitution DMS assays (ProteinGym split)	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	Not reported	Not reported	Not reported	Not reported	Not reported	0.223
ESM-IF1Evaluation	ProteinGym ZS-SUB-SPEARMAN: Zero-shot substitutions, Spearman, ProteinGym substitution DMS assays (ProteinGym split)	Not reported	Not reported	0.422	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	Not reported	Not reported	Not reported
ESM-IF1 [ProteinGym 144fe22b snapshot]Evaluation	ProteinGym AMFR official zero-shot Spearman snapshot, ProteinGym AMFR 4G3O official snapshot cohort	Not reported	Not reported	0.433 (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	Not reported	Not reported	Not reported
ESM-IF1 [ProteinGym 144fe22b snapshot]Evaluation	ProteinGym v1.3 zero-shot DMS substitutions, ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.368	0.389	0.407	0.549	0.417	0.292	0.422	0.427	0.324	0.502	0.498	0.624	0.44	0.35	0.301	0.294	0.358	0.389	Not reported

All 34 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: ESM-IF1	Task: ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-PLDDT: De novo backbones based sequence design, length 100 pLDDT Dataset subset: CASP, CAMEO and de novo backbones (ProteinBench split)	88.8 Plddt unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-PLDDT: De novo backbones based sequence design, length 100 pLDDT Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 100 pLDDT ↑)
Configuration: ESM-IF1	Task: ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM: De novo backbones based sequence design, length 100 scTM Dataset subset: CASP, CAMEO and de novo backbones (ProteinBench split)	0.81 Sctm unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-100-SCTM: De novo backbones based sequence design, length 100 scTM Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 100 scTM ↑)
Configuration: ESM-IF1	Task: ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-PLDDT: De novo backbones based sequence design, length 200 pLDDT Dataset subset: CASP, CAMEO and de novo backbones (ProteinBench split)	69.7 Plddt unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-PLDDT: De novo backbones based sequence design, length 200 pLDDT Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 200 pLDDT ↑)
Configuration: ESM-IF1	Task: ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-SCTM: De novo backbones based sequence design, length 200 scTM Dataset subset: CASP, CAMEO and de novo backbones (ProteinBench split)	0.635 Sctm unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-200-SCTM: De novo backbones based sequence design, length 200 scTM Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 200 scTM ↑)
Configuration: ESM-IF1	Task: ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-PLDDT: De novo backbones based sequence design, length 300 pLDDT Dataset subset: CASP, CAMEO and de novo backbones (ProteinBench split)	74.4 Plddt unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-PLDDT: De novo backbones based sequence design, length 300 pLDDT Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 300 pLDDT ↑)
Configuration: ESM-IF1	Task: ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-SCTM: De novo backbones based sequence design, length 300 scTM Dataset subset: CASP, CAMEO and de novo backbones (ProteinBench split)	0.336 Sctm unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-300-SCTM: De novo backbones based sequence design, length 300 scTM Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 300 scTM ↑)
Configuration: ESM-IF1	Task: ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-PLDDT: De novo backbones based sequence design, length 400 pLDDT Dataset subset: CASP, CAMEO and de novo backbones (ProteinBench split)	64.6 Plddt unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-PLDDT: De novo backbones based sequence design, length 400 pLDDT Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 400 pLDDT ↑)
Configuration: ESM-IF1	Task: ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-SCTM: De novo backbones based sequence design, length 400 scTM Dataset subset: CASP, CAMEO and de novo backbones (ProteinBench split)	0.449 Sctm unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-400-SCTM: De novo backbones based sequence design, length 400 scTM Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 400 scTM ↑)
Configuration: ESM-IF1	Task: ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-PLDDT: De novo backbones based sequence design, length 500 pLDDT Dataset subset: CASP, CAMEO and de novo backbones (ProteinBench split)	59 Plddt unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-PLDDT: De novo backbones based sequence design, length 500 pLDDT Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 500 pLDDT ↑)
Configuration: ESM-IF1	Task: ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-SCTM: De novo backbones based sequence design, length 500 scTM Dataset subset: CASP, CAMEO and de novo backbones (ProteinBench split)	0.462 Sctm unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinBench IF-DE-NOVO-BACKBONES-BASED-SEQUENCE-DESIGN-LENGTH-500-SCTM: De novo backbones based sequence design, length 500 scTM Inverse folding: recover a sequence for a given backbone. Values are the median over repeated runs. Aggregation: Not reported proteinbench primary benchmark evidence · Table 2, row(ESM-IF1), column(De novo backbones based sequence design, length 500 scTM ↑)
Configuration: ESM-IF1	Task: ProteinGym ZS-SUB-AUC: Zero-shot substitutions, AUC Dataset subset: ProteinGym substitution DMS assays (ProteinGym split)	0.73 AUROC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinGym ZS-SUB-AUC: Zero-shot substitutions, AUC Zero-shot scoring of substitution assays, averaged over assays with the correction the paper describes. Aggregation: Not reported ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 2, row(Inverse ESM-IF1), column(Zero-shot substitutions, AUC)
Configuration: ESM-IF1	Task: ProteinGym ZS-SUB-MCC: Zero-shot substitutions, MCC Dataset subset: ProteinGym substitution DMS assays (ProteinGym split)	0.331 MCC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinGym ZS-SUB-MCC: Zero-shot substitutions, MCC Zero-shot scoring of substitution assays, averaged over assays with the correction the paper describes. Aggregation: Not reported ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 2, row(Inverse ESM-IF1), column(Zero-shot substitutions, MCC)
Configuration: ESM-IF1	Task: ProteinGym ZS-SUB-NDCG: Zero-shot substitutions, NDCG@10% Dataset subset: ProteinGym substitution DMS assays (ProteinGym split)	0.748 NDCG at 10% unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinGym ZS-SUB-NDCG: Zero-shot substitutions, NDCG@10% Zero-shot scoring of substitution assays, averaged over assays with the correction the paper describes. Aggregation: Not reported ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 2, row(Inverse ESM-IF1), column(Zero-shot substitutions, NDCG@10%)
Configuration: ESM-IF1	Task: ProteinGym ZS-SUB-RECALL: Zero-shot substitutions, top 10% recall Dataset subset: ProteinGym substitution DMS assays (ProteinGym split)	0.223 Top 10% recall fraction · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinGym ZS-SUB-RECALL: Zero-shot substitutions, top 10% recall Zero-shot scoring of substitution assays, averaged over assays with the correction the paper describes. Aggregation: Not reported ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 2, row(Inverse ESM-IF1), column(Zero-shot substitutions, top 10% recall)
Configuration: ESM-IF1	Task: ProteinGym ZS-SUB-SPEARMAN: Zero-shot substitutions, Spearman Dataset subset: ProteinGym substitution DMS assays (ProteinGym split)	0.422 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source ESM-IF1 on ProteinGym ZS-SUB-SPEARMAN: Zero-shot substitutions, Spearman Zero-shot scoring of substitution assays, averaged over assays with the correction the paper describes. Aggregation: Not reported ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design · Table 2, row(Inverse ESM-IF1), column(Zero-shot substitutions, Spearman)
Configuration: ESM-IF1 [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym AMFR official zero-shot Spearman snapshot Dataset subset: ProteinGym AMFR 4G3O official snapshot cohort	0.433 Spearman unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source ESM-IF1 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=ESM-IF1
Configuration: ESM-IF1 [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, mean over selection types of the per-type mean over proteins of assay-level Spearman (all 217 assays)) unitless · higher Uncertainty: SE 0.011. 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 checked Methods, coverage and source ESM-IF1: 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 41, row 'ESM-IF1', column 'Average_Spearman'
Configuration: ESM-IF1 [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.44 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 checked Methods, coverage and source ESM-IF1: 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 41, row 'ESM-IF1', column 'Depth_1'
Configuration: ESM-IF1 [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.35 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 checked Methods, coverage and source ESM-IF1: 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 41, row 'ESM-IF1', column 'Depth_2'
Configuration: ESM-IF1 [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.301 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 checked Methods, coverage and source ESM-IF1: 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 41, row 'ESM-IF1', column 'Depth_3'
Configuration: ESM-IF1 [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, 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 checked Methods, coverage and source ESM-IF1: 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 41, row 'ESM-IF1', column 'Depth_4'
Configuration: ESM-IF1 [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.358 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 checked Methods, coverage and source ESM-IF1: 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 41, row 'ESM-IF1', column 'Depth_5+'
Configuration: ESM-IF1 [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.368 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 checked Methods, coverage and source ESM-IF1: 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 41, row 'ESM-IF1', column 'Function_Activity'
Configuration: ESM-IF1 [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.389 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 checked Methods, coverage and source ESM-IF1: 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 41, row 'ESM-IF1', column 'Function_Binding'
Configuration: ESM-IF1 [ProteinGym 144fe22b snapshot]	Protocol: ProteinGym v1.3 zero-shot DMS substitutions Dataset subset: ProteinGym DMS substitution assays at commit 144fe22 (217 assays)	0.407 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 checked Methods, coverage and source ESM-IF1: 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 41, row 'ESM-IF1', column 'Function_Expression'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Use this model

How it works, versions and access

Versions and evaluated configurations

ESM-IF1 · family
ESM-IF1 · family
ESM-IF1 [ProteinGym 144fe22b snapshot] · configuration of

How it works

Geometric-vector-perceptron input processing followed by a sequence-to-sequence transformer. The documented inputs are protein backbone atom coordinates; the model supports missing backbone spans. The output consists of sampled protein sequences or conditional sequence likelihoods.

Sources

facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models

Versions and reproducibility

esm_if1_gvp4_t16_142M_UR50. The applicable input limits require configuration-specific checking.

Sources

facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

Structure-conditioned design can use partially missing backbones because training included span masking.
Sources
facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models

Limitations and conditions

The public checkpoint name contains 142M but the README parameter table reports 124M. This discrepancy is retained rather than silently selecting a total.
Sources
facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models

Profile review details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Stable record: discovery-model-esm-if1

Specifications

Inputs, training, access and other details

Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Inputs, outputs and configuration
Property	Description and evidence
Model type	Geometric encoder and inverse-folding transformer Sources facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Architecture	Geometric-vector-perceptron input processing followed by a sequence-to-sequence transformer. Sources facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Inputs	Protein backbone atom coordinates; the model supports missing backbone spans. Sources facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Outputs	Sampled protein sequences or conditional sequence likelihoods. Sources facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Parameters	The official checkpoint identifier contains 142M but the same repository model table states 124M. Both values are retained as a source discrepancy, without choosing a total. Sources facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Known versions	esm_if1_gvp4_t16_142M_UR50. Sources facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Training data	CATH 4.3 and predicted UniRef50 structures; README reports 12M structures predicted by AlphaFold2. Sources facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Training cutoff	The official model table identifies CATH 4.3 and predicted UniRef50 structures, but does not state a common latest-structure or sequence date. · Not reported in inspected sources Sources facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Context limits	The reviewed inverse-folding usage and model table do not establish a universal maximum backbone length; the structural graph and selected inference configuration determine resource use. · Not reported in inspected sources Sources facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Weights licence	Separate checkpoint-distribution terms are not stated in the inspected release documentation and licence material. The source-code licence alone is not recorded as an explicit weight grant. · Not reported in inspected sources Sources (2) facebookresearch/esm: README.md; facebookresearch/esm: LICENSE · README.md: Inverse folding and Pre-trained Models; LICENSE: licence text
Access	Official project documentation and implementation: https://github.com/facebookresearch/esm Sources facebookresearch/esm: README.md · README.md: Inverse folding and Pre-trained Models
Code licence	MIT Sources facebookresearch/esm: LICENSE · LICENSE: licence text

Applicable tests and references

Applicability is distinct from a completed evaluation.

ProteinBench · Proposed association

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.

21 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims	facebookresearch/esm: README.md Original source ↗ README.md: Inverse folding and Pre-trained Models Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T19:46:19.090082+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps Backbone coordinates Geometric processing Sequence transformer Designed sequence or likelihood Individual claims	facebookresearch/esm: README.md Original source ↗ README.md: Inverse folding and Pre-trained Models Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T19:46:19.090082+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram title ESM-IF1 workflow Individual claims	facebookresearch/esm: README.md Original source ↗ README.md: Inverse folding and Pre-trained Models Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T19:46:19.090082+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Model type Geometric encoder and inverse-folding transformer Individual claims	facebookresearch/esm: README.md Original source ↗ README.md: Inverse folding and Pre-trained Models Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T19:46:19.090082+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Architecture Geometric-vector-perceptron input processing followed by a sequence-to-sequence transformer. Individual claims	facebookresearch/esm: README.md Original source ↗ README.md: Inverse folding and Pre-trained Models Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T19:46:19.090082+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Access Official project documentation and implementation: https://github.com/facebookresearch/esm Individual claims	facebookresearch/esm: README.md Original source ↗ README.md: Inverse folding and Pre-trained Models Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T19:46:19.090082+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Code licence MIT Individual claims	facebookresearch/esm: LICENSE Original source ↗ LICENSE: licence text Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T19:46:19.090082+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.facts.11.value` Source artifact SHA-256: `da6d3703ed11cbe42bd212c725957c98da23cbff1998c05fa4b3d976d1a58e93` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Inputs Protein backbone atom coordinates; the model supports missing backbone spans. Individual claims	facebookresearch/esm: README.md Original source ↗ README.md: Inverse folding and Pre-trained Models Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T19:46:19.090082+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Outputs Sampled protein sequences or conditional sequence likelihoods. Individual claims	facebookresearch/esm: README.md Original source ↗ README.md: Inverse folding and Pre-trained Models Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T19:46:19.090082+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Parameters The official checkpoint identifier contains 142M but the same repository model table states 124M. Both values are retained as a source discrepancy, without choosing a total. Individual claims	facebookresearch/esm: README.md Original source ↗ README.md: Inverse folding and Pre-trained Models Version: 2b369911bb5b4b0dda914521b9475cad1656b2ac Retrieved: 2026-09-16T19:46:19.090082+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `8b273c21a322fc9473d1b68d0dd40c8166ab2f89e4a190aa26ca87251b97cba9` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: discovered

3 source records and release history

facebookresearch/esm official source · Original source · 2b369911bb5b4b0dda914521b9475cad1656b2ac
facebookresearch/esm: README.md · Original source · 2b369911bb5b4b0dda914521b9475cad1656b2ac
facebookresearch/esm: LICENSE · Original source · 2b369911bb5b4b0dda914521b9475cad1656b2ac

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: discovery-model-esm-if1

areas: protein-structure
access: official_source_linked
candidate benchmark ids: discovery-benchmark-proteinbench
entity level: family
reported name: ESM-IF1
entity classification: review date: 2026-09-17; rationale: The cited profile describes a named learned biological predictor or representation model/family. Preserve this identity separately from task-specific fitting, individual checkpoints, pipelines and hosted access.; source ids: evidence-official-29d4b229a3aa426a6dfb; source locator: README.md: Inverse folding and Pre-trained Models; ambiguities: None recorded
missing metadata: version: reason: unextracted

Related records

applicable to: ProteinBench
uses model: GCN with ESM-IF1 protein embeddings (structure) (PPI embeddings study)
uses model: GraphSAGE with ESM-IF1 protein embeddings (structure) (PPI embeddings study)
uses model: MLP on concatenated protein embeddings (protein-only baseline, no network) with ESM-IF1 protein embeddings (structure) (PPI embeddings study)
uses model: NGNN with GCN with ESM-IF1 protein embeddings (structure) (PPI embeddings study)
uses model: NGNN with GCN combined with SEAL with ESM-IF1 protein embeddings (structure) (PPI embeddings study)
uses model: NGNN with GraphSAGE with ESM-IF1 protein embeddings (structure) (PPI embeddings study)
uses model: NGNN with GraphSAGE combined with SEAL with ESM-IF1 protein embeddings (structure) (PPI embeddings study)
family: ESM-IF1
family: ESM-IF1
configuration of: ESM-IF1 [ProteinGym 144fe22b snapshot]

Suggest a correction