PFMBench BINDING-DB: BindingDB
BindingDB. Scored with Spearman on BindingDB. Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
Overview
BindingDB. Scored with Spearman on BindingDB. 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 BINDING-DB: BindingDB
- ESM-2 on PFMBench BINDING-DB: BindingDB
- ESM-C on PFMBench BINDING-DB: BindingDB
- ESM3 on PFMBench BINDING-DB: BindingDB
- PGLM on PFMBench BINDING-DB: BindingDB
- ProstT5 on PFMBench BINDING-DB: BindingDB
- ProtGPT2 on PFMBench BINDING-DB: BindingDB
- ProTrek on PFMBench BINDING-DB: BindingDB
- ProtST on PFMBench BINDING-DB: BindingDB
- ProtT5 on PFMBench BINDING-DB: BindingDB
- SaProt on PFMBench BINDING-DB: BindingDB
- VenusPLM on PFMBench BINDING-DB: BindingDB
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 BINDING-DB: BindingDB
spearman (correlation) · Higher values are better for this metric.
Every method PFMBench reports on BindingDB, scored with Spearman on BindingDB.
- ESM-2 · Configuration · Author-reported evaluation0.13692
- VenusPLM · Configuration · Author-reported evaluation0.16834
- ESM-C · Configuration · Author-reported evaluation0 .20716
- ProtGPT2 · Configuration · Author-reported evaluation0.17169
- PGLM · Configuration · Author-reported evaluation0.16884
- ProtT5 · Configuration · Author-reported evaluation0.19730
- DPLM · Configuration · Author-reported evaluation0.17408
- SaProt · Configuration · Author-reported evaluation0.16557
- ProstT5 · Configuration · Author-reported evaluation0.16642
- ProtST · Configuration · Author-reported evaluation0.18886
- ESM3 · Configuration · Author-reported evaluation0.22519
- ProTrek · Configuration · Author-reported evaluation0.19230
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(BindingDB)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| ESM-2 · Configuration | 0.13692 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(Bind. DB) |
| VenusPLM · Configuration | 0.16834 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(Bind. DB) |
| ESM-C · Configuration | 0 .20716 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(Bind. DB) |
| ProtGPT2 · Configuration | 0.17169 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(Bind. DB) |
| PGLM · Configuration | 0.16884 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(Bind. DB) |
| ProtT5 · Configuration | 0.19730 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(Bind. DB) |
| DPLM · Configuration | 0.17408 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(Bind. DB) |
| SaProt · Configuration | 0.16557 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(Bind. DB) |
| ProstT5 · Configuration | 0.16642 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(Bind. DB) |
| ProtST · Configuration | 0.18886 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(Bind. DB) |
| ESM3 · Configuration | 0.22519 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(Bind. DB) |
| ProTrek · Configuration | 0.19230 correlation | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(Bind. DB) |
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 BINDING-DB: BindingDB 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 | ||
| 0.17408 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(Bind. DB) Source checking is not independent reproduction. |
| ESM-2 on PFMBench BINDING-DB: BindingDB 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 | ||
| 0.13692 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(Bind. DB) Source checking is not independent reproduction. |
| ESM-C on PFMBench BINDING-DB: BindingDB 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 .20716 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(Bind. DB) Source checking is not independent reproduction. |
| ESM3 on PFMBench BINDING-DB: BindingDB 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 | ||
| 0.22519 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(Bind. DB) Source checking is not independent reproduction. |
| PGLM on PFMBench BINDING-DB: BindingDB 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 | ||
| 0.16884 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(Bind. DB) Source checking is not independent reproduction. |
| ProstT5 on PFMBench BINDING-DB: BindingDB Configuration: ProstT5Task: PFMBench BINDING-DB: BindingDBDataset subset: BindingDB (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 | ||
| 0.16642 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(Bind. DB) Source checking is not independent reproduction. |
| ProtGPT2 on PFMBench BINDING-DB: BindingDB Configuration: ProtGPT2Task: PFMBench BINDING-DB: BindingDBDataset subset: BindingDB (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 | ||
| 0.17169 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(Bind. DB) Source checking is not independent reproduction. |
| ProTrek on PFMBench BINDING-DB: BindingDB Configuration: ProTrekTask: PFMBench BINDING-DB: BindingDBDataset subset: BindingDB (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 | ||
| 0.19230 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(Bind. DB) Source checking is not independent reproduction. |
| ProtST on PFMBench BINDING-DB: BindingDB 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 | ||
| 0.18886 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(Bind. DB) Source checking is not independent reproduction. |
| ProtT5 on PFMBench BINDING-DB: BindingDB 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 | ||
| 0.19730 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(Bind. DB) Source checking is not independent reproduction. |
| SaProt on PFMBench BINDING-DB: BindingDB 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 | ||
| 0.16557 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(Bind. DB) Source checking is not independent reproduction. |
| VenusPLM on PFMBench BINDING-DB: BindingDB Configuration: VenusPLMTask: PFMBench BINDING-DB: BindingDBDataset subset: BindingDB (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 | ||
| 0.16834 spearman Unit: correlation · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(Bind. DB) 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(BindingDB) 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-binding-db 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-binding-db
- areas
- proteins-complexes
- tasks
- BindingDB
- metric
- Spearman
- metric direction
- higher
- dataset
- BindingDB
- protocol
- Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
- source locator
- Table 1, row(BindingDB)
- comparison panels
- id: pfmbench-panel-binding-db; title: PFMBench BINDING-DB: BindingDB; protocol id: pfmbench-task-binding-db; dataset id: pfmbench-dataset-bindingdb; metric: spearman; unit: correlation; direction: higher; result ids: pfmbench-result-esm-2-binding-db-spearman; pfmbench-result-venusplm-binding-db-spearman; pfmbench-result-esm-c-binding-db-spearman; pfmbench-result-protgpt2-binding-db-spearman; pfmbench-result-pglm-binding-db-spearman; pfmbench-result-prott5-binding-db-spearman; pfmbench-result-dplm-binding-db-spearman; pfmbench-result-saprot-binding-db-spearman; pfmbench-result-prostt5-binding-db-spearman; pfmbench-result-protst-binding-db-spearman; pfmbench-result-esm3-binding-db-spearman; pfmbench-result-protrek-binding-db-spearman; source ids: expansion-p3-pfmbench; source locator: Table 1, row(BindingDB); context: Every method PFMBench reports on BindingDB, scored with Spearman on BindingDB.; 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 BINDING-DB: part of discovery-benchmark-pfmbench
- benchmark: DPLM on PFMBench BINDING-DB: BindingDB
- benchmark: ESM-2 on PFMBench BINDING-DB: BindingDB
- benchmark: ESM-C on PFMBench BINDING-DB: BindingDB
- benchmark: ESM3 on PFMBench BINDING-DB: BindingDB
- benchmark: PGLM on PFMBench BINDING-DB: BindingDB
- benchmark: ProstT5 on PFMBench BINDING-DB: BindingDB
- benchmark: ProtGPT2 on PFMBench BINDING-DB: BindingDB
- benchmark: ProTrek on PFMBench BINDING-DB: BindingDB
- benchmark: ProtST on PFMBench BINDING-DB: BindingDB
- benchmark: ProtT5 on PFMBench BINDING-DB: BindingDB
- benchmark: SaProt on PFMBench BINDING-DB: BindingDB
- benchmark: VenusPLM on PFMBench BINDING-DB: BindingDB