PFMBench METAL-ION: Metal ion binding
Metal ion binding. Scored with Accuracy on Metal ion binding. Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
Overview
Metal ion binding. Scored with Accuracy on Metal ion binding. 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 METAL-ION: Metal ion binding
- ESM-2 on PFMBench METAL-ION: Metal ion binding
- ESM-C on PFMBench METAL-ION: Metal ion binding
- ESM3 on PFMBench METAL-ION: Metal ion binding
- PGLM on PFMBench METAL-ION: Metal ion binding
- ProstT5 on PFMBench METAL-ION: Metal ion binding
- ProtGPT2 on PFMBench METAL-ION: Metal ion binding
- ProTrek on PFMBench METAL-ION: Metal ion binding
- ProtST on PFMBench METAL-ION: Metal ion binding
- ProtT5 on PFMBench METAL-ION: Metal ion binding
- SaProt on PFMBench METAL-ION: Metal ion binding
- VenusPLM on PFMBench METAL-ION: Metal ion binding
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 METAL-ION: Metal ion binding
accuracy (fraction) · Higher values are better for this metric.
Every method PFMBench reports on Metal ion binding, scored with Accuracy on Metal ion binding.
- ESM-2 · Configuration · Author-reported evaluation0.71170
- VenusPLM · Configuration · Author-reported evaluation0.70195
- ESM-C · Configuration · Author-reported evaluation0.70195
- ProtGPT2 · Configuration · Author-reported evaluation0.71170
- PGLM · Configuration · Author-reported evaluation0 .74513
- ProtT5 · Configuration · Author-reported evaluation0.72145
- DPLM · Configuration · Author-reported evaluation0.70056
- SaProt · Configuration · Author-reported evaluation0.71031
- ProstT5 · Configuration · Author-reported evaluation0.72145
- ProtST · Configuration · Author-reported evaluation0.51532
- ESM3 · Configuration · Author-reported evaluation0.70334
- ProTrek · Configuration · Author-reported evaluation0.80362
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(Metal ion binding)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| ESM-2 · Configuration | 0.71170 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(M. I. Bin.) |
| VenusPLM · Configuration | 0.70195 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(M. I. Bin.) |
| ESM-C · Configuration | 0.70195 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(M. I. Bin.) |
| ProtGPT2 · Configuration | 0.71170 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(M. I. Bin.) |
| PGLM · Configuration | 0 .74513 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(M. I. Bin.) |
| ProtT5 · Configuration | 0.72145 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(M. I. Bin.) |
| DPLM · Configuration | 0.70056 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(M. I. Bin.) |
| SaProt · Configuration | 0.71031 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(M. I. Bin.) |
| ProstT5 · Configuration | 0.72145 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(M. I. Bin.) |
| ProtST · Configuration | 0.51532 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(M. I. Bin.) |
| ESM3 · Configuration | 0.70334 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(M. I. Bin.) |
| ProTrek · Configuration | 0.80362 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(M. I. Bin.) |
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 METAL-ION: Metal ion binding Configuration: DPLMTask: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 | ||
| 0.70056 accuracy Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(M. I. Bin.) Source checking is not independent reproduction. |
| ESM-2 on PFMBench METAL-ION: Metal ion binding Configuration: ESM-2Task: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 | ||
| 0.71170 accuracy 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(M. I. Bin.) Source checking is not independent reproduction. |
| ESM-C on PFMBench METAL-ION: Metal ion binding Configuration: ESM-CTask: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 | ||
| 0.70195 accuracy Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(M. I. Bin.) Source checking is not independent reproduction. |
| ESM3 on PFMBench METAL-ION: Metal ion binding Configuration: ESM3Task: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 | ||
| 0.70334 accuracy Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(M. I. Bin.) Source checking is not independent reproduction. |
| PGLM on PFMBench METAL-ION: Metal ion binding Configuration: PGLMTask: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 .74513 accuracy Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(M. I. Bin.) Source checking is not independent reproduction. |
| ProstT5 on PFMBench METAL-ION: Metal ion binding Configuration: ProstT5Task: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 | ||
| 0.72145 accuracy Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(M. I. Bin.) Source checking is not independent reproduction. |
| ProtGPT2 on PFMBench METAL-ION: Metal ion binding Configuration: ProtGPT2Task: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 | ||
| 0.71170 accuracy Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(M. I. Bin.) Source checking is not independent reproduction. |
| ProTrek on PFMBench METAL-ION: Metal ion binding Configuration: ProTrekTask: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 | ||
| 0.80362 accuracy Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(M. I. Bin.) Source checking is not independent reproduction. |
| ProtST on PFMBench METAL-ION: Metal ion binding Configuration: ProtSTTask: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 | ||
| 0.51532 accuracy Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(M. I. Bin.) Source checking is not independent reproduction. |
| ProtT5 on PFMBench METAL-ION: Metal ion binding Configuration: ProtT5Task: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 | ||
| 0.72145 accuracy Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(M. I. Bin.) Source checking is not independent reproduction. |
| SaProt on PFMBench METAL-ION: Metal ion binding Configuration: SaProtTask: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 | ||
| 0.71031 accuracy Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(M. I. Bin.) Source checking is not independent reproduction. |
| VenusPLM on PFMBench METAL-ION: Metal ion binding Configuration: VenusPLMTask: PFMBench METAL-ION: Metal ion bindingDataset subset: Metal ion binding (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 | ||
| 0.70195 accuracy Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(M. I. Bin.) 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(Metal ion binding) 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-metal-ion 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-metal-ion
- areas
- proteins-complexes
- tasks
- Metal ion binding
- metric
- Accuracy
- metric direction
- higher
- dataset
- Metal ion binding
- protocol
- Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
- source locator
- Table 1, row(Metal ion binding)
- comparison panels
- id: pfmbench-panel-metal-ion; title: PFMBench METAL-ION: Metal ion binding; protocol id: pfmbench-task-metal-ion; dataset id: pfmbench-dataset-metal-ion-binding; metric: accuracy; unit: fraction; direction: higher; result ids: pfmbench-result-esm-2-metal-ion-accuracy; pfmbench-result-venusplm-metal-ion-accuracy; pfmbench-result-esm-c-metal-ion-accuracy; pfmbench-result-protgpt2-metal-ion-accuracy; pfmbench-result-pglm-metal-ion-accuracy; pfmbench-result-prott5-metal-ion-accuracy; pfmbench-result-dplm-metal-ion-accuracy; pfmbench-result-saprot-metal-ion-accuracy; pfmbench-result-prostt5-metal-ion-accuracy; pfmbench-result-protst-metal-ion-accuracy; pfmbench-result-esm3-metal-ion-accuracy; pfmbench-result-protrek-metal-ion-accuracy; source ids: expansion-p3-pfmbench; source locator: Table 1, row(Metal ion binding); context: Every method PFMBench reports on Metal ion binding, scored with Accuracy on Metal ion binding.; 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 METAL-ION: part of discovery-benchmark-pfmbench
- benchmark: DPLM on PFMBench METAL-ION: Metal ion binding
- benchmark: ESM-2 on PFMBench METAL-ION: Metal ion binding
- benchmark: ESM-C on PFMBench METAL-ION: Metal ion binding
- benchmark: ESM3 on PFMBench METAL-ION: Metal ion binding
- benchmark: PGLM on PFMBench METAL-ION: Metal ion binding
- benchmark: ProstT5 on PFMBench METAL-ION: Metal ion binding
- benchmark: ProtGPT2 on PFMBench METAL-ION: Metal ion binding
- benchmark: ProTrek on PFMBench METAL-ION: Metal ion binding
- benchmark: ProtST on PFMBench METAL-ION: Metal ion binding
- benchmark: ProtT5 on PFMBench METAL-ION: Metal ion binding
- benchmark: SaProt on PFMBench METAL-ION: Metal ion binding
- benchmark: VenusPLM on PFMBench METAL-ION: Metal ion binding