PFMBench EC: Enzyme Commission
Enzyme Commission. Scored with F1 score on Enzyme Commission. Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
Overview
Enzyme Commission. Scored with F1 score on Enzyme Commission. Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluation design
Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.
Benchmarks
These source-backed links do not make different protocols or scores interchangeable.
Recorded evaluations
Each evaluation records what was tested and under which conditions.
- DPLM on PFMBench EC: Enzyme Commission
- ESM-2 on PFMBench EC: Enzyme Commission
- ESM-C on PFMBench EC: Enzyme Commission
- ESM3 on PFMBench EC: Enzyme Commission
- PGLM on PFMBench EC: Enzyme Commission
- ProstT5 on PFMBench EC: Enzyme Commission
- ProtGPT2 on PFMBench EC: Enzyme Commission
- ProTrek on PFMBench EC: Enzyme Commission
- ProtST on PFMBench EC: Enzyme Commission
- ProtT5 on PFMBench EC: Enzyme Commission
- SaProt on PFMBench EC: Enzyme Commission
- VenusPLM on PFMBench EC: Enzyme Commission
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Published comparisons
Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies. The pooled view gathers every source table that reports the same metric and names what it does not hold constant.
PFMBench EC: Enzyme Commission
f1 (fraction) · Higher values are better for this metric.
Every method PFMBench reports on Enzyme Commission, scored with F1 score on Enzyme Commission.
- ESM-2 · Configuration · Author-reported evaluation0.73578
- VenusPLM · Configuration · Author-reported evaluation0.75194
- ESM-C · Configuration · Author-reported evaluation0.71694
- ProtGPT2 · Configuration · Author-reported evaluation0.69687
- PGLM · Configuration · Author-reported evaluation0.74659
- ProtT5 · Configuration · Author-reported evaluation0.76201
- DPLM · Configuration · Author-reported evaluation0.75521
- SaProt · Configuration · Author-reported evaluation0.75144
- ProstT5 · Configuration · Author-reported evaluation0.76829
- ProtST · Configuration · Author-reported evaluation0.71761
- ESM3 · Configuration · Author-reported evaluation0.64830
- ProTrek · Configuration · Author-reported evaluation0 .76408
Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.
pfmbench primary benchmark evidence · Table 1, row(Enzyme Commission)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| ESM-2 · Configuration | 0.73578 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(EC) |
| VenusPLM · Configuration | 0.75194 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(EC) |
| ESM-C · Configuration | 0.71694 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(EC) |
| ProtGPT2 · Configuration | 0.69687 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(EC) |
| PGLM · Configuration | 0.74659 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(EC) |
| ProtT5 · Configuration | 0.76201 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(EC) |
| DPLM · Configuration | 0.75521 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(EC) |
| SaProt · Configuration | 0.75144 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(EC) |
| ProstT5 · Configuration | 0.76829 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(EC) |
| ProtST · Configuration | 0.71761 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(EC) |
| ESM3 · Configuration | 0.64830 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(EC) |
| ProTrek · Configuration | 0 .76408 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(EC) |
Scope and limitations
- Author-reported numbers, source checked but not independently reproduced.
- The metric differs by task, taken from Table 1, so these figures cannot be averaged into one score.
- Table 3 scores come from adapter fine-tuning; the ProteinGym figure is zero-shot and is not comparable to them.
Source transcription and grouping reviewed by automated source review on 2026-09-18. These experiments were not independently reproduced by rewire.
Tested entities and results
Release 2026-09-17-134cd1815de8 · 12 evaluations · 12 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| DPLM on PFMBench EC: Enzyme Commission Configuration: DPLMTask: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.75521 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(EC) Source checking is not independent reproduction. |
| ESM-2 on PFMBench EC: Enzyme Commission Configuration: ESM-2Task: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.73578 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(EC) Source checking is not independent reproduction. |
| ESM-C on PFMBench EC: Enzyme Commission Configuration: ESM-CTask: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.71694 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(EC) Source checking is not independent reproduction. |
| ESM3 on PFMBench EC: Enzyme Commission Configuration: ESM3Task: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.64830 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(EC) Source checking is not independent reproduction. |
| PGLM on PFMBench EC: Enzyme Commission Configuration: PGLMTask: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.74659 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(EC) Source checking is not independent reproduction. |
| ProstT5 on PFMBench EC: Enzyme Commission Configuration: ProstT5Task: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.76829 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(EC) Source checking is not independent reproduction. |
| ProtGPT2 on PFMBench EC: Enzyme Commission Configuration: ProtGPT2Task: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.69687 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(EC) Source checking is not independent reproduction. |
| ProTrek on PFMBench EC: Enzyme Commission Configuration: ProTrekTask: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0 .76408 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(EC) Source checking is not independent reproduction. |
| ProtST on PFMBench EC: Enzyme Commission Configuration: ProtSTTask: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.71761 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(EC) Source checking is not independent reproduction. |
| ProtT5 on PFMBench EC: Enzyme Commission Configuration: ProtT5Task: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.76201 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(EC) Source checking is not independent reproduction. |
| SaProt on PFMBench EC: Enzyme Commission Configuration: SaProtTask: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.75144 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(EC) Source checking is not independent reproduction. |
| VenusPLM on PFMBench EC: Enzyme Commission Configuration: VenusPLMTask: PFMBench EC: Enzyme CommissionDataset subset: Enzyme Commission (PFMBench split) Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.75194 f1 Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(EC) Source checking is not 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.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of discovery-benchmark-pfmbench Individual claims | pfmbench primary benchmark evidence Table 1, row(Enzyme Commission) Version: 2506.14796v1 | source checked automated source review · 2026-09-18 Audit detailsPrimary-source transcription with no human sign-off and no independent reproduction. Field: Claim: pfmbench-association-ec Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-09-17-134cd1815de8 · Record review: source checked
1 source records and release history
- pfmbench primary benchmark evidence · Original source · 2506.14796v1
Technical metadata and extraction receipts
Stable ID: pfmbench-task-ec
- areas
- proteins-complexes
- tasks
- Enzyme Commission
- metric
- F1 score
- metric direction
- higher
- dataset
- Enzyme Commission
- protocol
- Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
- source locator
- Table 1, row(Enzyme Commission)
- comparison panels
- id: pfmbench-panel-ec; title: PFMBench EC: Enzyme Commission; protocol id: pfmbench-task-ec; dataset id: pfmbench-dataset-enzyme-commission; metric: f1; unit: fraction; direction: higher; result ids: pfmbench-result-esm-2-ec-f1; pfmbench-result-venusplm-ec-f1; pfmbench-result-esm-c-ec-f1; pfmbench-result-protgpt2-ec-f1; pfmbench-result-pglm-ec-f1; pfmbench-result-prott5-ec-f1; pfmbench-result-dplm-ec-f1; pfmbench-result-saprot-ec-f1; pfmbench-result-prostt5-ec-f1; pfmbench-result-protst-ec-f1; pfmbench-result-esm3-ec-f1; pfmbench-result-protrek-ec-f1; source ids: expansion-p3-pfmbench; source locator: Table 1, row(Enzyme Commission); context: Every method PFMBench reports on Enzyme Commission, scored with F1 score on Enzyme Commission.; caveats: Author-reported numbers, source checked but not independently reproduced.; The metric differs by task, taken from Table 1, so these figures cannot be averaged into one score.; Table 3 scores come from adapter fine-tuning; the ProteinGym figure is zero-shot and is not comparable to them.; review: method: automated_source_review; date: 2026-09-18
Related records
- part of: PFMBench
- subject: PFMBench EC: part of discovery-benchmark-pfmbench
- benchmark: DPLM on PFMBench EC: Enzyme Commission
- benchmark: ESM-2 on PFMBench EC: Enzyme Commission
- benchmark: ESM-C on PFMBench EC: Enzyme Commission
- benchmark: ESM3 on PFMBench EC: Enzyme Commission
- benchmark: PGLM on PFMBench EC: Enzyme Commission
- benchmark: ProstT5 on PFMBench EC: Enzyme Commission
- benchmark: ProtGPT2 on PFMBench EC: Enzyme Commission
- benchmark: ProTrek on PFMBench EC: Enzyme Commission
- benchmark: ProtST on PFMBench EC: Enzyme Commission
- benchmark: ProtT5 on PFMBench EC: Enzyme Commission
- benchmark: SaProt on PFMBench EC: Enzyme Commission
- benchmark: VenusPLM on PFMBench EC: Enzyme Commission