Task

PFMBench DEEPLOC2: DeepLoc2 Multi

DeepLoc2 Multi. Scored with F1 score on DeepLoc2 Multi. Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.

12 evaluations · 12 metric rows

Overview

DeepLoc2 Multi. Scored with F1 score on DeepLoc2 Multi. 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

PFMBench

These source-backed links do not make different protocols or scores interchangeable.

Recorded evaluations

Each evaluation records what was tested and under which conditions.

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.

Comparison and metric

PFMBench DEEPLOC2: DeepLoc2 Multi

f1 (fraction) · Higher values are better for this metric.

Every method PFMBench reports on DeepLoc2 Multi, scored with F1 score on DeepLoc2 Multi.

Evaluation protocol · DeepLoc2 Multi (PFMBench split)

ESM-2 · Configuration · Author-reported evaluation0 .76191
VenusPLM · Configuration · Author-reported evaluation0.73814
ESM-C · Configuration · Author-reported evaluation0.75395
ProtGPT2 · Configuration · Author-reported evaluation0.70341
PGLM · Configuration · Author-reported evaluation0.74772
ProtT5 · Configuration · Author-reported evaluation0.72624
DPLM · Configuration · Author-reported evaluation0.75759
SaProt · Configuration · Author-reported evaluation0.74006
ProstT5 · Configuration · Author-reported evaluation0.73190
ProtST · Configuration · Author-reported evaluation0.74886
ESM3 · Configuration · Author-reported evaluation0.65853
ProTrek · Configuration · Author-reported evaluation0.83944

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(DeepLoc2 Multi)

Values, uncertainty and evidence

f1: original source values
Tested entity	Printed value	Uncertainty	Evidence
ESM-2 · Configuration	0 .76191 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-2 [ 35 ]), column(DL2 M.)
VenusPLM · Configuration	0.73814 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(VenusPLM [ 59 ]), column(DL2 M.)
ESM-C · Configuration	0.75395 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM-C), column(DL2 M.)
ProtGPT2 · Configuration	0.70341 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtGPT2 [ 12 ]), column(DL2 M.)
PGLM · Configuration	0.74772 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(PGLM [ 5 ]), column(DL2 M.)
ProtT5 · Configuration	0.72624 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtT5 [ 11 ]), column(DL2 M.)
DPLM · Configuration	0.75759 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(DPLM [ 68 ]), column(DL2 M.)
SaProt · Configuration	0.74006 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(SaProt [ 55 ]), column(DL2 M.)
ProstT5 · Configuration	0.73190 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProstT5 [ 21 ]), column(DL2 M.)
ProtST · Configuration	0.74886 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProtST [ 71 ]), column(DL2 M.)
ESM3 · Configuration	0.65853 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ESM3 [ 18 ]), column(DL2 M.)
ProTrek · Configuration	0.83944 fraction	Not reported	Author-reported evaluation · source checkedpfmbench primary benchmark evidence · Table 3, row(ProTrek [ 56 ]), column(DL2 M.)

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.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
DPLM on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: DPLMTask: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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
0.75759 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(DL2 M.) Source checking is not independent reproduction.
ESM-2 on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: ESM-2Task: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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 .76191 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(DL2 M.) Source checking is not independent reproduction.
ESM-C on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: ESM-CTask: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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
0.75395 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(DL2 M.) Source checking is not independent reproduction.
ESM3 on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: ESM3Task: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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
0.65853 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(DL2 M.) Source checking is not independent reproduction.
PGLM on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: PGLMTask: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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
0.74772 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(DL2 M.) Source checking is not independent reproduction.
ProstT5 on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: ProstT5Task: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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
0.73190 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(DL2 M.) Source checking is not independent reproduction.
ProtGPT2 on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: ProtGPT2Task: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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
0.70341 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(DL2 M.) Source checking is not independent reproduction.
ProTrek on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: ProTrekTask: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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
0.83944 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(DL2 M.) Source checking is not independent reproduction.
ProtST on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: ProtSTTask: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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
0.74886 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(DL2 M.) Source checking is not independent reproduction.
ProtT5 on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: ProtT5Task: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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
0.72624 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(DL2 M.) Source checking is not independent reproduction.
SaProt on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: SaProtTask: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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
0.74006 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(DL2 M.) Source checking is not independent reproduction.
VenusPLM on PFMBench DEEPLOC2: DeepLoc2 Multi Configuration: VenusPLMTask: PFMBench DEEPLOC2: DeepLoc2 MultiDataset subset: DeepLoc2 Multi (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
0.73814 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(DL2 M.) 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

Claims, original sources and review scope · Release 2026-09-17-134cd1815de8
Property and statement	Original source and location	Review and provenance
Relationship: part of discovery-benchmark-pfmbench Individual claims	pfmbench primary benchmark evidence Original source ↗ Table 1, row(DeepLoc2 Multi) Version: 2506.14796v1 Retrieved: 2026-09-16T21:06:29.716004+00:00	source checked automated source review · 2026-09-18 Audit details Primary-source transcription with no human sign-off and no independent reproduction. Field: `links:part_of:discovery-benchmark-pfmbench` Claim: pfmbench-association-deeploc2 Source artifact SHA-256: `59c7bbb888e8e91f33c1e2cabfde062c32381d6ca727d23b6655c977aabf97a2` Hash scope: Exact retrieved primary paper artifact bytes. Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

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

Download this release

Technical metadata and extraction receipts

Stable ID: pfmbench-task-deeploc2

areas: proteins-complexes
tasks: DeepLoc2 Multi
metric: F1 score
metric direction: higher
dataset: DeepLoc2 Multi
protocol: Fine-tuned with an adapter under the PFMBench harness; train, validation and test counts are in Table 1.
source locator: Table 1, row(DeepLoc2 Multi)
comparison panels: id: pfmbench-panel-deeploc2; title: PFMBench DEEPLOC2: DeepLoc2 Multi; protocol id: pfmbench-task-deeploc2; dataset id: pfmbench-dataset-deeploc2-multi; metric: f1; unit: fraction; direction: higher; result ids: pfmbench-result-esm-2-deeploc2-f1; pfmbench-result-venusplm-deeploc2-f1; pfmbench-result-esm-c-deeploc2-f1; pfmbench-result-protgpt2-deeploc2-f1; pfmbench-result-pglm-deeploc2-f1; pfmbench-result-prott5-deeploc2-f1; pfmbench-result-dplm-deeploc2-f1; pfmbench-result-saprot-deeploc2-f1; pfmbench-result-prostt5-deeploc2-f1; pfmbench-result-protst-deeploc2-f1; pfmbench-result-esm3-deeploc2-f1; pfmbench-result-protrek-deeploc2-f1; source ids: expansion-p3-pfmbench; source locator: Table 1, row(DeepLoc2 Multi); context: Every method PFMBench reports on DeepLoc2 Multi, scored with F1 score on DeepLoc2 Multi.; 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 DEEPLOC2: part of discovery-benchmark-pfmbench
benchmark: DPLM on PFMBench DEEPLOC2: DeepLoc2 Multi
benchmark: ESM-2 on PFMBench DEEPLOC2: DeepLoc2 Multi
benchmark: ESM-C on PFMBench DEEPLOC2: DeepLoc2 Multi
benchmark: ESM3 on PFMBench DEEPLOC2: DeepLoc2 Multi
benchmark: PGLM on PFMBench DEEPLOC2: DeepLoc2 Multi
benchmark: ProstT5 on PFMBench DEEPLOC2: DeepLoc2 Multi
benchmark: ProtGPT2 on PFMBench DEEPLOC2: DeepLoc2 Multi
benchmark: ProTrek on PFMBench DEEPLOC2: DeepLoc2 Multi
benchmark: ProtST on PFMBench DEEPLOC2: DeepLoc2 Multi
benchmark: ProtT5 on PFMBench DEEPLOC2: DeepLoc2 Multi
benchmark: SaProt on PFMBench DEEPLOC2: DeepLoc2 Multi
benchmark: VenusPLM on PFMBench DEEPLOC2: DeepLoc2 Multi

Suggest a correction