PFMBench CLONING-CLF: Cloning CLF
Cloning CLF. Scored with AUROC on Cloning CLF. Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
Overview
Cloning CLF. Scored with AUROC on Cloning CLF. 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 CLONING-CLF: Cloning CLF
- ESM-2 on PFMBench CLONING-CLF: Cloning CLF
- ESM-C on PFMBench CLONING-CLF: Cloning CLF
- ESM3 on PFMBench CLONING-CLF: Cloning CLF
- PGLM on PFMBench CLONING-CLF: Cloning CLF
- ProstT5 on PFMBench CLONING-CLF: Cloning CLF
- ProtGPT2 on PFMBench CLONING-CLF: Cloning CLF
- ProTrek on PFMBench CLONING-CLF: Cloning CLF
- ProtST on PFMBench CLONING-CLF: Cloning CLF
- ProtT5 on PFMBench CLONING-CLF: Cloning CLF
- SaProt on PFMBench CLONING-CLF: Cloning CLF
- VenusPLM on PFMBench CLONING-CLF: Cloning CLF
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 CLONING-CLF: Cloning CLF
auroc (fraction) · Higher values are better for this metric.
Every method PFMBench reports on Cloning CLF, scored with AUROC on Cloning CLF.
- ESM-2 · Configuration · Author-reported evaluation0.80586
- VenusPLM · Configuration · Author-reported evaluation0 .83172
- ESM-C · Configuration · Author-reported evaluation0.81033
- ProtGPT2 · Configuration · Author-reported evaluation0.77730
- PGLM · Configuration · Author-reported evaluation0.83638
- ProtT5 · Configuration · Author-reported evaluation0.78485
- DPLM · Configuration · Author-reported evaluation0.81247
- SaProt · Configuration · Author-reported evaluation0.81206
- ProstT5 · Configuration · Author-reported evaluation0.79853
- ProtST · Configuration · Author-reported evaluation0.80714
- ESM3 · Configuration · Author-reported evaluation0.77391
- ProTrek · Configuration · Author-reported evaluation0.82612
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(Cloning CLF)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| ESM-2 · Configuration | 0.80586 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(Clo. CLF) |
| VenusPLM · Configuration | 0 .83172 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(Clo. CLF) |
| ESM-C · Configuration | 0.81033 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(Clo. CLF) |
| ProtGPT2 · Configuration | 0.77730 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(Clo. CLF) |
| PGLM · Configuration | 0.83638 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(Clo. CLF) |
| ProtT5 · Configuration | 0.78485 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(Clo. CLF) |
| DPLM · Configuration | 0.81247 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(Clo. CLF) |
| SaProt · Configuration | 0.81206 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(Clo. CLF) |
| ProstT5 · Configuration | 0.79853 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(Clo. CLF) |
| ProtST · Configuration | 0.80714 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(Clo. CLF) |
| ESM3 · Configuration | 0.77391 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(Clo. CLF) |
| ProTrek · Configuration | 0.82612 fraction | Not reported | Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(Clo. CLF) |
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 CLONING-CLF: Cloning CLF Configuration: DPLMTask: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 | ||
| 0.81247 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(Clo. CLF) Source checking is not independent reproduction. |
| ESM-2 on PFMBench CLONING-CLF: Cloning CLF Configuration: ESM-2Task: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 | ||
| 0.80586 auroc 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(Clo. CLF) Source checking is not independent reproduction. |
| ESM-C on PFMBench CLONING-CLF: Cloning CLF Configuration: ESM-CTask: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 | ||
| 0.81033 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(Clo. CLF) Source checking is not independent reproduction. |
| ESM3 on PFMBench CLONING-CLF: Cloning CLF Configuration: ESM3Task: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 | ||
| 0.77391 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(Clo. CLF) Source checking is not independent reproduction. |
| PGLM on PFMBench CLONING-CLF: Cloning CLF Configuration: PGLMTask: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 | ||
| 0.83638 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(Clo. CLF) Source checking is not independent reproduction. |
| ProstT5 on PFMBench CLONING-CLF: Cloning CLF Configuration: ProstT5Task: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 | ||
| 0.79853 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(Clo. CLF) Source checking is not independent reproduction. |
| ProtGPT2 on PFMBench CLONING-CLF: Cloning CLF Configuration: ProtGPT2Task: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 | ||
| 0.77730 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(Clo. CLF) Source checking is not independent reproduction. |
| ProTrek on PFMBench CLONING-CLF: Cloning CLF Configuration: ProTrekTask: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 | ||
| 0.82612 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(Clo. CLF) Source checking is not independent reproduction. |
| ProtST on PFMBench CLONING-CLF: Cloning CLF Configuration: ProtSTTask: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 | ||
| 0.80714 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(Clo. CLF) Source checking is not independent reproduction. |
| ProtT5 on PFMBench CLONING-CLF: Cloning CLF Configuration: ProtT5Task: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 | ||
| 0.78485 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(Clo. CLF) Source checking is not independent reproduction. |
| SaProt on PFMBench CLONING-CLF: Cloning CLF Configuration: SaProtTask: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 | ||
| 0.81206 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(Clo. CLF) Source checking is not independent reproduction. |
| VenusPLM on PFMBench CLONING-CLF: Cloning CLF Configuration: VenusPLMTask: PFMBench CLONING-CLF: Cloning CLFDataset subset: Cloning CLF (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 .83172 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(Clo. CLF) 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(Cloning CLF) 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-cloning-clf 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-cloning-clf
- areas
- proteins-complexes
- tasks
- Cloning CLF
- metric
- AUROC
- metric direction
- higher
- dataset
- Cloning CLF
- protocol
- Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
- source locator
- Table 1, row(Cloning CLF)
- comparison panels
- id: pfmbench-panel-cloning-clf; title: PFMBench CLONING-CLF: Cloning CLF; protocol id: pfmbench-task-cloning-clf; dataset id: pfmbench-dataset-cloning-clf; metric: auroc; unit: fraction; direction: higher; result ids: pfmbench-result-esm-2-cloning-clf-auroc; pfmbench-result-venusplm-cloning-clf-auroc; pfmbench-result-esm-c-cloning-clf-auroc; pfmbench-result-protgpt2-cloning-clf-auroc; pfmbench-result-pglm-cloning-clf-auroc; pfmbench-result-prott5-cloning-clf-auroc; pfmbench-result-dplm-cloning-clf-auroc; pfmbench-result-saprot-cloning-clf-auroc; pfmbench-result-prostt5-cloning-clf-auroc; pfmbench-result-protst-cloning-clf-auroc; pfmbench-result-esm3-cloning-clf-auroc; pfmbench-result-protrek-cloning-clf-auroc; source ids: expansion-p3-pfmbench; source locator: Table 1, row(Cloning CLF); context: Every method PFMBench reports on Cloning CLF, scored with AUROC on Cloning CLF.; 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 CLONING-CLF: part of discovery-benchmark-pfmbench
- benchmark: DPLM on PFMBench CLONING-CLF: Cloning CLF
- benchmark: ESM-2 on PFMBench CLONING-CLF: Cloning CLF
- benchmark: ESM-C on PFMBench CLONING-CLF: Cloning CLF
- benchmark: ESM3 on PFMBench CLONING-CLF: Cloning CLF
- benchmark: PGLM on PFMBench CLONING-CLF: Cloning CLF
- benchmark: ProstT5 on PFMBench CLONING-CLF: Cloning CLF
- benchmark: ProtGPT2 on PFMBench CLONING-CLF: Cloning CLF
- benchmark: ProTrek on PFMBench CLONING-CLF: Cloning CLF
- benchmark: ProtST on PFMBench CLONING-CLF: Cloning CLF
- benchmark: ProtT5 on PFMBench CLONING-CLF: Cloning CLF
- benchmark: SaProt on PFMBench CLONING-CLF: Cloning CLF
- benchmark: VenusPLM on PFMBench CLONING-CLF: Cloning CLF