Task

clathrin protein classification

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

Sources

14 evaluations · 79 metric rows

At a glance

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

How it works

How it worksComputational evaluation flow

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

Sources

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

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.

Comparison and metric

Clathrin independent test: selected-embedding classifiers · Table 3

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

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.

Evaluation protocol · Clathrin independent test: selected-embedding classifiers

DT · Configuration · Author-reported evaluation0.715
NB · Configuration · Author-reported evaluation0.827
PLS · Configuration · Author-reported evaluation0.849
ADA · Configuration · Author-reported evaluation0.877
LDA · Configuration · Author-reported evaluation0.866
RF · Configuration · Author-reported evaluation0.894
LR · Configuration · Author-reported evaluation0.877
KNN · Configuration · Author-reported evaluation0.916
ET · Configuration · Author-reported evaluation0.888
XGB · Configuration · Author-reported evaluation0.877
MLP · Configuration · Author-reported evaluation0.933
SVM · Configuration · Author-reported evaluation0.927
PLM-CLA · Configuration · Author-reported evaluation0.961

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.

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

Values, uncertainty and evidence

ACC: original source values
Tested entity	Printed value	Uncertainty	Evidence
DT · Configuration	0.715 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row DT, column ACC; XML row2 column2
NB · Configuration	0.827 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row NB, column ACC; XML row3 column2
PLS · Configuration	0.849 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row PLS, column ACC; XML row4 column2
ADA · Configuration	0.877 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row ADA, column ACC; XML row5 column2
LDA · Configuration	0.866 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row LDA, column ACC; XML row6 column2
RF · Configuration	0.894 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row RF, column ACC; XML row7 column2
LR · Configuration	0.877 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row LR, column ACC; XML row8 column2
KNN · Configuration	0.916 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row KNN, column ACC; XML row9 column2
ET · Configuration	0.888 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row ET, column ACC; XML row10 column2
XGB · Configuration	0.877 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row XGB, column ACC; XML row11 column2
MLP · Configuration	0.933 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row MLP, column ACC; XML row12 column2
SVM · Configuration	0.927 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row SVM, column ACC; XML row13 column2
PLM-CLA · Configuration	0.961 fraction	Not reported	Author-reported evaluation · source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row PLM-CLA, column ACC; XML row14 column2

Scope and limitations

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.

Source transcription and grouping reviewed by automated source review on 2026-09-17. These experiments were not independently reproduced by rewire.

Tested entities and results

Release 2026-09-17-d277315f7d76 · 14 evaluations · 79 metric rows. Different protocols are not a single leaderboard.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
ESM-2 embedding + paper classifier: clathrin protein classification Pipeline: ESM-2 embedding + paper classifierTask: clathrin protein classificationDataset: CLA-IND0.6 single-feature ESM-2 embedding comparison Independent external evaluation · Evaluation metadata: needs review
0.916 accuracy Unit: fraction · Direction: unknown	Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 2, Independent test / ESM-2 row, ACC column Source checking is not independent reproduction.
DT: Clathrin independent test: selected-embedding classifiers Configuration: DTProtocol: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)Dataset: Clathrin independent test: selected-embedding classifiers 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. Author-reported evaluation · Evaluation metadata: needs review
0.715 ACC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row DT, column ACC; XML row2 column2 Source checking is not independent reproduction.
0.551 SP Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row DT, column SP; XML row2 column4 Source checking is not independent reproduction.
0.726 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row DT, column AUC; XML row2 column7 Source checking is not independent reproduction.
RF: Clathrin independent test: selected-embedding classifiers Configuration: RFProtocol: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)Dataset: Clathrin independent test: selected-embedding classifiers 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. Author-reported evaluation · Evaluation metadata: needs review
0.884 SP Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row RF, column SP; XML row7 column4 Source checking is not independent reproduction.
0.912 F1 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row RF, column F1; XML row7 column6 Source checking is not independent reproduction.
0.894 ACC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row RF, column ACC; XML row7 column2 Source checking is not independent reproduction.
0.959 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row RF, column AUC; XML row7 column7 Source checking is not independent reproduction.
PLM-CLA: Clathrin independent test: selected-embedding classifiers Configuration: PLM-CLAProtocol: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)Dataset: Clathrin independent test: selected-embedding classifiers 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. Author-reported evaluation · Evaluation metadata: needs review
0.917 MCC Unit: dimensionless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row PLM-CLA, column MCC; XML row14 column5 Source checking is not independent reproduction.
0.949 F1 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row PLM-CLA, column F1; XML row14 column6 Source checking is not independent reproduction.
0.961 ACC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row PLM-CLA, column ACC; XML row14 column2 Source checking is not independent reproduction.
PLS: Clathrin independent test: selected-embedding classifiers Configuration: PLSProtocol: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)Dataset: Clathrin independent test: selected-embedding classifiers 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. Author-reported evaluation · Evaluation metadata: needs review
0.690 MCC Unit: dimensionless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row PLS, column MCC; XML row4 column5 Source checking is not independent reproduction.
0.845 SN Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row PLS, column SN; XML row4 column3 Source checking is not independent reproduction.
LR: Clathrin independent test: selected-embedding classifiers Configuration: LRProtocol: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)Dataset: Clathrin independent test: selected-embedding classifiers 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. Author-reported evaluation · Evaluation metadata: needs review
0.747 MCC Unit: dimensionless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row LR, column MCC; XML row8 column5 Source checking is not independent reproduction.
0.884 SP Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row LR, column SP; XML row8 column4 Source checking is not independent reproduction.
ADA: Clathrin independent test: selected-embedding classifiers Configuration: ADAProtocol: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)Dataset: Clathrin independent test: selected-embedding classifiers 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. Author-reported evaluation · Evaluation metadata: needs review
0.877 ACC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row ADA, column ACC; XML row5 column2 Source checking is not independent reproduction.
0.739 MCC Unit: dimensionless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row ADA, column MCC; XML row5 column5 Source checking is not independent reproduction.
0.918 SN Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row ADA, column SN; XML row5 column3 Source checking is not independent reproduction.
NB: Clathrin independent test: selected-embedding classifiers Configuration: NBProtocol: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)Dataset: Clathrin independent test: selected-embedding classifiers 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. Author-reported evaluation · Evaluation metadata: needs review
0.773 SN Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row NB, column SN; XML row3 column3 Source checking is not independent reproduction.
0.868 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row NB, column AUC; XML row3 column7 Source checking is not independent reproduction.
SVM: Clathrin independent test: selected-embedding classifiers Configuration: SVMProtocol: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)Dataset: Clathrin independent test: selected-embedding classifiers 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. Author-reported evaluation · Evaluation metadata: needs review
0.942 F1 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row SVM, column F1; XML row13 column6 Source checking is not independent reproduction.
0.964 SN Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row SVM, column SN; XML row13 column3 Source checking is not independent reproduction.
MLP: Clathrin independent test: selected-embedding classifiers Configuration: MLPProtocol: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)Dataset: Clathrin independent test: selected-embedding classifiers 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. Author-reported evaluation · Evaluation metadata: needs review
0.946 F1 Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row MLP, column F1; XML row12 column6 Source checking is not independent reproduction.
ET: Clathrin independent test: selected-embedding classifiers Configuration: ETProtocol: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)Dataset: Clathrin independent test: selected-embedding classifiers 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. Author-reported evaluation · Evaluation metadata: needs review
0.764 MCC Unit: dimensionless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row ET, column MCC; XML row10 column5 Source checking is not independent reproduction.
XGB: Clathrin independent test: selected-embedding classifiers Configuration: XGBProtocol: Clathrin independent test: selected-embedding classifiers (clathrin protein classification)Dataset: Clathrin independent test: selected-embedding classifiers 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. Author-reported evaluation · Evaluation metadata: needs review
0.877 ACC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedAdvancing the accuracy of clathrin protein prediction through multi-source protein language models · Table 3, row XGB, column ACC; XML row11 column2 Source checking is not 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

What is still missing

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

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

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 2026-09-17-d277315f7d76
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

Release 2026-09-17-d277315f7d76 · 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