Task

clathrin protein classification

Clathrin classification uses cross-validation and multiple independent benchmark datasets with different redundancy filters.

Sources

14 evaluations · 79 results

Overview

Datasets

Le2019 and Zhang2020-derived clathrin/non-clathrin sequence collections.

Sources

Metrics

Accuracy, AUC, Matthews correlation coefficient, F1, sensitivity and specificity are reported. The Performance evaluation subsection describes ten-fold evaluation and early stopping but does not specify a universal probability threshold for every comparator.

Sources

Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Materials and methods: Performance evaluation

Allowed inputs

Protein amino-acid sequences represented by protein language models.

Sources

Evaluation procedure diagram

How it worksComputational evaluation flow

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

Sources

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Results

Each comparison retains its reviewed evaluation scope, dataset and metric. Results are shown without a pooled ranking.

Evaluation scope and datasetMetric and reported setup

Clathrin independent test: selected-embedding classifiers · Table 3

ACC (fraction) · Higher values are better.

Clathrin independent test: selected-embedding classifiers (clathrin protein classification) · Clathrin independent test: selected-embedding classifiers

Evidence origin: Author-reported evaluation.

Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3: ACC, Clathrin independent test: selected-embedding classifiers

Source prose has inconsistent dataset sizes; exact cohort counts left unresolved, not inferred.
Feature-selection and evaluation leakage cannot be excluded by this table alone.

Comparison details and limitations

Conventional classifiers and PLM-CLA compared using paper-selected features. CLA-IND 0.6 independent test from Shoombuatong 2024 dataset; source Table 1 carries cohort counts.

No interval assigned unless printed in source cell.

Automated source review: 2026-09-17. Numerical source review does not establish independent reproduction.

Dots show point estimates. Whiskers show only explicitly defined uncertainty (standard deviation, standard error or a labelled interval); their definitions remain in Table. Unresolved uncertainty is not plotted. Differences do not establish statistical significance.

Find a tested model or method

Showing 12 of 13 matching rows.

Zoom to observed range

Tested configuration

00.250.50.751

Reported score

Methods and evaluation design

Procedure, tasks and evaluated configurations

How it works

Evaluation methodology

Le2019 and Zhang2020-derived clathrin/non-clathrin sequence collections. Ten-fold cross-validation on training data plus named independent CLA test sets. Accuracy, AUC, Matthews correlation coefficient, F1, sensitivity and specificity are reported. The Performance evaluation subsection describes ten-fold evaluation and early stopping but does not specify a universal probability threshold for every comparator. deep-clathrin includes literature-reported scores; DeepCLA is reimplemented for comparison. The Zhang2020-derived collection uses BLAST redundancy filtering at 0.7, and the new dataset uses CD-HIT at 0.6. These dataset filters do not establish absence from the pretrained protein encoders’ corpora. Feature subsets are evaluated on both cross-validation and independent-test performance, which limits treating that test as untouched model selection.

Sources

Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54; Materials and methods: Performance evaluation; Materials and methods: Dataset construction and Overall framework of PLM-CLA; Results: The effect of feature selection methods on the predictive performance

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Protocols

Clathrin independent test: selected-embedding classifiers (clathrin protein classification)

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

Recorded evaluations

Each evaluation records what was tested and under which conditions.

ESM-2 embedding + paper classifier: clathrin protein classification

Run this benchmark

Choose a concrete protocol before running an evaluation. Its inputs, split and scoring rules determine which results can be compared.

Clathrin independent test: selected-embedding classifiers (clathrin protein classification)

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.

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

No source-reviewed explanatory claims are recorded here yet.

Limitations and conditions

Literature scores and newly executed comparisons have different provenance. The several CLA datasets must not be treated as interchangeable.
Sources
Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54

Profile review details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Stable record: reported-task-786c09824e9bf5

Specifications

Inputs, training, access and other details

Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Data, procedure and scoring
Property	Description and evidence
Datasets	Le2019 and Zhang2020-derived clathrin/non-clathrin sequence collections. Sources Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54
Splits	Ten-fold cross-validation on training data plus named independent CLA test sets. Sources Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54
Metrics	Accuracy, AUC, Matthews correlation coefficient, F1, sensitivity and specificity are reported. The Performance evaluation subsection describes ten-fold evaluation and early stopping but does not specify a universal probability threshold for every comparator. Sources Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Materials and methods: Performance evaluation
Baselines	deep-clathrin includes literature-reported scores; DeepCLA is reimplemented for comparison. Sources Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54
Leakage controls	The Zhang2020-derived collection uses BLAST redundancy filtering at 0.7, and the new dataset uses CD-HIT at 0.6. These dataset filters do not establish absence from the pretrained protein encoders’ corpora. Feature subsets are evaluated on both cross-validation and independent-test performance, which limits treating that test as untouched model selection. Sources Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Materials and methods: Dataset construction and Overall framework of PLM-CLA; Results: The effect of feature selection methods on the predictive performance
Uncertainty	The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. · Not reported in inspected sources Sources Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54
Entity type	Paper-specific computational evaluation protocol. Sources Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54
Organisms	The paper does not enumerate organisms. Its pinned released CSVs contain sequence identifiers and amino-acid sequences, without organism columns; one dataset uses synthetic row identifiers. Consequently, a complete source-species inventory is not established by the supplied benchmark metadata. · Not reported in inspected sources Sources (5) Advancing the accuracy of clathrin protein prediction through multi-source protein language models; clathrin__Dataset__Clathrin0.6.csv; clathrin__Dataset__Clathrin0.7.csv; clathrin__Dataset__Clathrin1.0.csv; clathrin__README.md · Dataset construction; pinned repository README and Dataset/Clathrin0.6.csv, Clathrin0.7.csv and Clathrin1.0.csv headers
Assays	Clathrin/non-clathrin sequence labels. Sources Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54
Allowed inputs	Protein amino-acid sequences represented by protein language models. Sources Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54
Adaptation	Supervised classification with cross-validation and independent test collections. Sources Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.

Paper or primary resource	Version	Reference
Advancing the accuracy of clathrin protein prediction through multi-source protein language models	journal full text in PMC	Read source DOI: 10.1038/s41598-025-08510-4

Historical gaps recorded on 2026-09-17

The catalogue now holds 79 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.

Independent batch review before import; preserve existing observation identities.

Search and extraction details

complete comparison tables extracted pending publication review

Searches

Advancing the accuracy of clathrin protein prediction through multi-source protein language models primary paper benchmark results

Evidence locations

Tables2–5; independent-test and dataset-construction sections

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.

21 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims	Advancing the accuracy of clathrin protein prediction through multi-source protein language models Original source ↗ Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54; Materials and methods: Performance evaluation Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558194+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `2edc86b25707c1b737d26117093ce8d856e79cc5d0b335f27c1c341f887f1c7e` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps Input: Protein amino-acid sequences represented by protein language models. Evaluation: Ten-fold cross-validation on training data plus named independent CLA test sets. Readout: Accuracy, AUC, Matthews correlation coefficient, F1, sensitivity and specificity are reported. The Performance evaluation subsection describes ten-fold evaluation and early stopping but does not specify a universal probability threshold for every comparator. Individual claims	Advancing the accuracy of clathrin protein prediction through multi-source protein language models Original source ↗ Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54; Materials and methods: Performance evaluation Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558194+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `2edc86b25707c1b737d26117093ce8d856e79cc5d0b335f27c1c341f887f1c7e` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Computational evaluation flow Individual claims	Advancing the accuracy of clathrin protein prediction through multi-source protein language models Original source ↗ Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54; Materials and methods: Performance evaluation Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558194+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `2edc86b25707c1b737d26117093ce8d856e79cc5d0b335f27c1c341f887f1c7e` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Datasets Le2019 and Zhang2020-derived clathrin/non-clathrin sequence collections. Individual claims	Advancing the accuracy of clathrin protein prediction through multi-source protein language models Original source ↗ Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54 Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558194+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `2edc86b25707c1b737d26117093ce8d856e79cc5d0b335f27c1c341f887f1c7e` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Splits Ten-fold cross-validation on training data plus named independent CLA test sets. Individual claims	Advancing the accuracy of clathrin protein prediction through multi-source protein language models Original source ↗ Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54 Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558194+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `2edc86b25707c1b737d26117093ce8d856e79cc5d0b335f27c1c341f887f1c7e` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Adaptation Supervised classification with cross-validation and independent test collections. Individual claims	Advancing the accuracy of clathrin protein prediction through multi-source protein language models Original source ↗ Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54 Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558194+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `2edc86b25707c1b737d26117093ce8d856e79cc5d0b335f27c1c341f887f1c7e` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Metrics Accuracy, AUC, Matthews correlation coefficient, F1, sensitivity and specificity are reported. The Performance evaluation subsection describes ten-fold evaluation and early stopping but does not specify a universal probability threshold for every comparator. Individual claims	Advancing the accuracy of clathrin protein prediction through multi-source protein language models Original source ↗ Materials and methods: Performance evaluation Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558194+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `2edc86b25707c1b737d26117093ce8d856e79cc5d0b335f27c1c341f887f1c7e` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Baselines deep-clathrin includes literature-reported scores; DeepCLA is reimplemented for comparison. Individual claims	Advancing the accuracy of clathrin protein prediction through multi-source protein language models Original source ↗ Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54 Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558194+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `2edc86b25707c1b737d26117093ce8d856e79cc5d0b335f27c1c341f887f1c7e` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Leakage controls The Zhang2020-derived collection uses BLAST redundancy filtering at 0.7, and the new dataset uses CD-HIT at 0.6. These dataset filters do not establish absence from the pretrained protein encoders’ corpora. Feature subsets are evaluated on both cross-validation and independent-test performance, which limits treating that test as untouched model selection. Individual claims	Advancing the accuracy of clathrin protein prediction through multi-source protein language models Original source ↗ Materials and methods: Dataset construction and Overall framework of PLM-CLA; Results: The effect of feature selection methods on the predictive performance Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558194+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `2edc86b25707c1b737d26117093ce8d856e79cc5d0b335f27c1c341f887f1c7e` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Uncertainty The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. Individual claims	Advancing the accuracy of clathrin protein prediction through multi-source protein language models Original source ↗ Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54 Version: journal full text in PMC Retrieved: 2026-09-16T10:38:57.558194+00:00	unreported automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.5.value` Source artifact SHA-256: `2edc86b25707c1b737d26117093ce8d856e79cc5d0b335f27c1c341f887f1c7e` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

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

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: needs review

6 source records and release history

Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Original source · journal full text in PMC
Advancing the accuracy of clathrin protein prediction through multi-source protein language models · Original source · journal full text in PMC
clathrin__Dataset__Clathrin0.6.csv · Original source · 9a8f55bc008401180152864560d8c8528600fe71
clathrin__Dataset__Clathrin0.7.csv · Original source · 9a8f55bc008401180152864560d8c8528600fe71
clathrin__Dataset__Clathrin1.0.csv · Original source · 9a8f55bc008401180152864560d8c8528600fe71
clathrin__README.md · Original source · 9a8f55bc008401180152864560d8c8528600fe71

Download this release

Technical metadata and extraction receipts

Stable ID: reported-task-786c09824e9bf5

areas: proteins-complexes
tasks: clathrin protein classification
entity level: task
version: Not reported
task: clathrin protein classification
scope note: Paper-specific evaluation task; protocol completeness requires further extraction.
comparison panels: id: part2-clathrin-plm-2025-Tab3-7ef65949fa; title: Clathrin independent test: selected-embedding classifiers · Table 3; protocol id: paper-protocol-bbffa94da73852557b; dataset id: paper-dataset-a1836de18515f3ab55; metric: ACC; unit: fraction; direction: higher; result ids: paper-result-0730029c96e20b98de; paper-result-a55f9924436b4f2946; paper-result-6d26a3281ddec02ba6; paper-result-199f6ba07b9c097f4f; paper-result-644ae2f042fb2f5b23; paper-result-36ae69af478636d799; paper-result-7ed01313e3f4c28c40; paper-result-7195f65c3684098379; paper-result-a969b52eed01ab25da; paper-result-4cf9ff8fa7d95ed4ce; paper-result-e677c183db2fc0a6fe; paper-result-f444ed165adbeb9c85; paper-result-48b062f1f39640cb79; source ids: part2-clathrin-plm-2025; source locator: Table 3: ACC, Clathrin independent test: selected-embedding classifiers; context: Conventional classifiers and PLM-CLA compared using paper-selected features. CLA-IND 0.6 independent test from Shoombuatong 2024 dataset; source Table 1 carries cohort counts.; caveats: Source prose has inconsistent dataset sizes; exact cohort counts left unresolved, not inferred.; Feature-selection and evaluation leakage cannot be excluded by this table alone.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-clathrin-plm-2025-Tab3-9059dcb8eb; title: Clathrin independent test: selected-embedding classifiers · Table 3; protocol id: paper-protocol-bbffa94da73852557b; dataset id: paper-dataset-a1836de18515f3ab55; metric: SN; unit: fraction; direction: higher; result ids: paper-result-7e844e0a18dfd2a35b; paper-result-1d8775900e322544d5; paper-result-14af9ff7e7145d4d29; paper-result-2691b7b496a2b70805; paper-result-8a421ada6b63ee530d; paper-result-9824c5bbad9176ec8e; paper-result-5667de2e439b758d52; paper-result-c5b318cd60d0cdb4a7; paper-result-ac6a602d275b3fea3c; paper-result-5a7ce3c38ddae8961d; paper-result-a2a2ddd6bf8f13daef; paper-result-387a61f6d26366959d; paper-result-d62014e2f2c00f0b19; source ids: part2-clathrin-plm-2025; source locator: Table 3: SN, Clathrin independent test: selected-embedding classifiers; context: Conventional classifiers and PLM-CLA compared using paper-selected features. CLA-IND 0.6 independent test from Shoombuatong 2024 dataset; source Table 1 carries cohort counts.; caveats: Source prose has inconsistent dataset sizes; exact cohort counts left unresolved, not inferred.; Feature-selection and evaluation leakage cannot be excluded by this table alone.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-clathrin-plm-2025-Tab3-1637766aec; title: Clathrin independent test: selected-embedding classifiers · Table 3; protocol id: paper-protocol-bbffa94da73852557b; dataset id: paper-dataset-a1836de18515f3ab55; metric: SP; unit: fraction; direction: higher; result ids: paper-result-21feace8cb2ce5e3eb; paper-result-e33d8392c76daadbc3; paper-result-97cc71a9c8b17a8bc1; paper-result-667c1dd0ce262e830c; paper-result-f1e415b2cfba651012; paper-result-0ce650036f050c2762; paper-result-21c44a4182b8225eb1; paper-result-a2d81dd3a62697406b; paper-result-7c339a10051c86a7c0; paper-result-ea67a0b7b24f3bb052; paper-result-9bdbc84d434b285e04; paper-result-87b08711535c28932a; paper-result-d04ecf04da1004cff8; source ids: part2-clathrin-plm-2025; source locator: Table 3: SP, Clathrin independent test: selected-embedding classifiers; context: Conventional classifiers and PLM-CLA compared using paper-selected features. CLA-IND 0.6 independent test from Shoombuatong 2024 dataset; source Table 1 carries cohort counts.; caveats: Source prose has inconsistent dataset sizes; exact cohort counts left unresolved, not inferred.; Feature-selection and evaluation leakage cannot be excluded by this table alone.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-clathrin-plm-2025-Tab3-657b713876; title: Clathrin independent test: selected-embedding classifiers · Table 3; protocol id: paper-protocol-bbffa94da73852557b; dataset id: paper-dataset-a1836de18515f3ab55; metric: MCC; unit: dimensionless; direction: higher; result ids: paper-result-a4a56a5352e1f4b25f; paper-result-655c72140d737d23c3; paper-result-1482c92aa694d2f027; paper-result-250b4aaac43175427d; paper-result-ddc5d5b4d806f5d683; paper-result-92d64dfea940c8e704; paper-result-1671d2e2b268f272a5; paper-result-b30374085233a5ee59; paper-result-40e463b7ca62e3c241; paper-result-6644f2850c0d5eb339; paper-result-c9dfd2f1b60d02b3df; paper-result-930a9b4bcf61fbe236; paper-result-12c7518a23c15c58d6; source ids: part2-clathrin-plm-2025; source locator: Table 3: MCC, Clathrin independent test: selected-embedding classifiers; context: Conventional classifiers and PLM-CLA compared using paper-selected features. CLA-IND 0.6 independent test from Shoombuatong 2024 dataset; source Table 1 carries cohort counts.; caveats: Source prose has inconsistent dataset sizes; exact cohort counts left unresolved, not inferred.; Feature-selection and evaluation leakage cannot be excluded by this table alone.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-clathrin-plm-2025-Tab3-a89d53b495; title: Clathrin independent test: selected-embedding classifiers · Table 3; protocol id: paper-protocol-bbffa94da73852557b; dataset id: paper-dataset-a1836de18515f3ab55; metric: F1; unit: fraction; direction: higher; result ids: paper-result-f92d473cd400e9e621; paper-result-96f846d80898fae95b; paper-result-9b9e600ad2446e697f; paper-result-af17b84609852bd79e; paper-result-5a6bc1834630e501e8; paper-result-2d7b6ae84bb35ea892; paper-result-a5bbea217db4b4a850; paper-result-d35402f96201b16bf8; paper-result-b30dbb80fd831aad99; paper-result-798a21dedf23053ac0; paper-result-3e7012cff605fa9f7f; paper-result-3431e8053e5b0bad25; paper-result-2b3a797967cdef7a15; source ids: part2-clathrin-plm-2025; source locator: Table 3: F1, Clathrin independent test: selected-embedding classifiers; context: Conventional classifiers and PLM-CLA compared using paper-selected features. CLA-IND 0.6 independent test from Shoombuatong 2024 dataset; source Table 1 carries cohort counts.; caveats: Source prose has inconsistent dataset sizes; exact cohort counts left unresolved, not inferred.; Feature-selection and evaluation leakage cannot be excluded by this table alone.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-clathrin-plm-2025-Tab3-b6e9f189ae; title: Clathrin independent test: selected-embedding classifiers · Table 3; protocol id: paper-protocol-bbffa94da73852557b; dataset id: paper-dataset-a1836de18515f3ab55; metric: AUC; unit: fraction; direction: higher; result ids: paper-result-2eaf94777fc7f857fc; paper-result-47d350f89848982a43; paper-result-f1a86ea15cd7479d5b; paper-result-e274031e8e17dc0933; paper-result-ad1e11f4f3b25e62ed; paper-result-3741a0c6925f2947e2; paper-result-ca68d167787e314805; paper-result-7ef5e7bcd2b4a87ef9; paper-result-9565fcdb350e8db673; paper-result-5250d6a1217d2812cf; paper-result-e0a382c956e9add325; paper-result-9c2aeff72feeb82f45; paper-result-ab057b14f1c421f3ca; source ids: part2-clathrin-plm-2025; source locator: Table 3: AUC, Clathrin independent test: selected-embedding classifiers; context: Conventional classifiers and PLM-CLA compared using paper-selected features. CLA-IND 0.6 independent test from Shoombuatong 2024 dataset; source Table 1 carries cohort counts.; caveats: Source prose has inconsistent dataset sizes; exact cohort counts left unresolved, not inferred.; Feature-selection and evaluation leakage cannot be excluded by this table alone.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17
benchmark research: review date: 2026-09-17; status: complete_comparison_tables_extracted_pending_publication_review; primary sources: part2-clathrin-plm-2025; inspected locators: Tables2–5; independent-test and dataset-construction sections; searched queries: Advancing the accuracy of clathrin protein prediction through multi-source protein language models primary paper benchmark results; gaps: Independent batch review before import; preserve existing observation identities.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
historical missing metadata: protocol version: not_reported_in_legacy_extract
metadata review scope: historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
legacy kinds: benchmark
entity classification: review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: clathrin-plm-2025; source locator: Methods: Dataset construction; Performance evaluation; Results: independent test datasets; cached text lines 9–10, 24–25, 54; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.

Related records

dataset: CLA-IND0.6
benchmark: ESM-2 embedding + paper classifier: clathrin protein classification
evaluates task: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)

Suggest a correction