Configuration

PredFull retrained on PROSPECT (PepSpecBench)

PredFull retrained by the PepSpecBench authors on the PROSPECT backbone-disjoint training split (500k spectra).

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

13 evaluations · 14 results. Different protocols are not a single leaderboard.

Sorted by Spectral angle (median over spectra, shared canonical fragment space) (lower is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Protocol and dataset	Spectral angle (median over spectra, shared canonical fragment space)	Spectral angle similarity (median over spectra, shared canonical fragment space)	Pearson (median over spectra, shared canonical fragment space)	Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14))
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench A. thaliana OOD subset, median SA, PepSpecBench A. thaliana OOD subset	0.163 (best in column)	Not reported	Not reported	Not reported
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench HeLa OOD subset, median SA, PepSpecBench HeLa OOD subset	0.196	Not reported	Not reported	Not reported
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench C. elegans OOD subset, median SA, PepSpecBench C. elegans OOD subset	0.199	Not reported	Not reported	Not reported
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench PROSPECT-Mini test split, median SA, PepSpecBench PROSPECT-Mini test split	0.204	Not reported	Not reported	0.203
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench E. coli OOD subsets (both sources aggregated), median SA, PepSpecBench E. coli OOD subsets (both sources aggregated)	0.236	Not reported	Not reported	Not reported
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench Yeast OOD subset, median SA, PepSpecBench Yeast OOD subset	0.236	Not reported	Not reported	Not reported
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench A. thaliana OOD subset, median SAS, PepSpecBench A. thaliana OOD subset	Not reported	0.837 (best in column)	Not reported	Not reported
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench C. elegans OOD subset, median SAS, PepSpecBench C. elegans OOD subset	Not reported	0.801	Not reported	Not reported
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench E. coli OOD subsets (both sources aggregated), median SAS, PepSpecBench E. coli OOD subsets (both sources aggregated)	Not reported	0.764	Not reported	Not reported
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench HeLa OOD subset, median SAS, PepSpecBench HeLa OOD subset	Not reported	0.804	Not reported	Not reported
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench PROSPECT-Mini test split, median PCC, PepSpecBench PROSPECT-Mini test split	Not reported	Not reported	0.749	Not reported
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench PROSPECT-Mini test split, median SAS, PepSpecBench PROSPECT-Mini test split	Not reported	0.797	Not reported	Not reported
PredFull retrained on PROSPECT (PepSpecBench)Evaluation	PepSpecBench Yeast OOD subset, median SAS, PepSpecBench Yeast OOD subset	Not reported	0.764	Not reported	Not reported

All 14 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench A. thaliana OOD subset, median SA Dataset: PepSpecBench A. thaliana OOD subset	0.163 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on A. thaliana OOD subset, SA lit-otheromics-20261011-pepspecbench-protocol-a-thaliana-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 4, block 'PROSPECT Trained', row 'PredFull', column 'A. thaliana' (first value of SA / SAS)
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench A. thaliana OOD subset, median SAS Dataset: PepSpecBench A. thaliana OOD subset	0.837 Spectral angle similarity (median over spectra, shared canonical fragment space) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on A. thaliana OOD subset, SAS lit-otheromics-20261011-pepspecbench-protocol-a-thaliana-sas Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 4, block 'PROSPECT Trained', row 'PredFull', column 'A. thaliana' (second value of SA / SAS)
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench C. elegans OOD subset, median SA Dataset: PepSpecBench C. elegans OOD subset	0.199 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on C. elegans OOD subset, SA lit-otheromics-20261011-pepspecbench-protocol-c-elegans-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 4, block 'PROSPECT Trained', row 'PredFull', column 'C. elegans' (first value of SA / SAS)
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench C. elegans OOD subset, median SAS Dataset: PepSpecBench C. elegans OOD subset	0.801 Spectral angle similarity (median over spectra, shared canonical fragment space) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on C. elegans OOD subset, SAS lit-otheromics-20261011-pepspecbench-protocol-c-elegans-sas Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 4, block 'PROSPECT Trained', row 'PredFull', column 'C. elegans' (second value of SA / SAS)
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench E. coli OOD subsets (both sources aggregated), median SA Dataset: PepSpecBench E. coli OOD subsets (both sources aggregated)	0.236 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on E. coli OOD subsets (both sources aggregated), SA lit-otheromics-20261011-pepspecbench-protocol-e-coli-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 4, block 'PROSPECT Trained', row 'PredFull', column 'E. coli' (first value of SA / SAS)
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench E. coli OOD subsets (both sources aggregated), median SAS Dataset: PepSpecBench E. coli OOD subsets (both sources aggregated)	0.764 Spectral angle similarity (median over spectra, shared canonical fragment space) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on E. coli OOD subsets (both sources aggregated), SAS lit-otheromics-20261011-pepspecbench-protocol-e-coli-sas Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 4, block 'PROSPECT Trained', row 'PredFull', column 'E. coli' (second value of SA / SAS)
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench HeLa OOD subset, median SA Dataset: PepSpecBench HeLa OOD subset	0.196 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on HeLa OOD subset, SA lit-otheromics-20261011-pepspecbench-protocol-hela-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 4, block 'PROSPECT Trained', row 'PredFull', column 'HeLa' (first value of SA / SAS)
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench HeLa OOD subset, median SAS Dataset: PepSpecBench HeLa OOD subset	0.804 Spectral angle similarity (median over spectra, shared canonical fragment space) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on HeLa OOD subset, SAS lit-otheromics-20261011-pepspecbench-protocol-hela-sas Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 4, block 'PROSPECT Trained', row 'PredFull', column 'HeLa' (second value of SA / SAS)
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench PROSPECT-Mini test split, median PCC Dataset: PepSpecBench PROSPECT-Mini test split	0.749 Pearson (median over spectra, shared canonical fragment space) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on PROSPECT-Mini test split, PCC lit-otheromics-20261011-pepspecbench-protocol-prospect-pcc Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 2, row 'PredFull', column group 'PROSPECT', column 'PCC'
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench PROSPECT-Mini test split, median SA Dataset: PepSpecBench PROSPECT-Mini test split	0.203 Spectral angle (median over spectra, shared canonical fragment space; four-decimal value with 95% bootstrap CI (Table 14)) unitless · lower Uncertainty: 95% CI 0.2022 to 0.2049. Table 14 caption: 95% bootstrap CI, 1000 resamples over 50k test spectra. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on PROSPECT-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-prospect-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 14, source 'PROSPECT', row 'PredFull', column 'Med. SA'
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench PROSPECT-Mini test split, median SA Dataset: PepSpecBench PROSPECT-Mini test split	0.204 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on PROSPECT-Mini test split, SA lit-otheromics-20261011-pepspecbench-protocol-prospect-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 2, row 'PredFull', column group 'PROSPECT', column 'SA'
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench PROSPECT-Mini test split, median SAS Dataset: PepSpecBench PROSPECT-Mini test split	0.797 Spectral angle similarity (median over spectra, shared canonical fragment space) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on PROSPECT-Mini test split, SAS lit-otheromics-20261011-pepspecbench-protocol-prospect-sas Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 2, row 'PredFull', column group 'PROSPECT', column 'SAS'
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench Yeast OOD subset, median SA Dataset: PepSpecBench Yeast OOD subset	0.236 Spectral angle (median over spectra, shared canonical fragment space) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on Yeast OOD subset, SA lit-otheromics-20261011-pepspecbench-protocol-yeast-sa Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 4, block 'PROSPECT Trained', row 'PredFull', column 'Yeast' (first value of SA / SAS)
Configuration: PredFull retrained on PROSPECT (PepSpecBench)	Protocol: PepSpecBench Yeast OOD subset, median SAS Dataset: PepSpecBench Yeast OOD subset	0.764 Spectral angle similarity (median over spectra, shared canonical fragment space) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source PredFull (trained on PROSPECT) on Yeast OOD subset, SAS lit-otheromics-20261011-pepspecbench-protocol-yeast-sas Aggregation: Not reported PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Table 4, block 'PROSPECT Trained', row 'PredFull', column 'Yeast' (second value of SA / SAS)

Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

Evidence

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

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-23-5347695500ed
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-23-5347695500ed · Record review: source checked

1 source record and release history

PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction · Original source · arXiv:2605.01945v1 (submitted 2026-05-03), arXiv HTML rendering

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-otheromics-20261011-pepspecbench-config-predfull-trained-prospect

areas: proteins-complexes
contexts: research
method types: supervised_machine_learning
reported name: PredFull
foundation model eligible: false
parameters: Retrained on the PROSPECT-Mini backbone-disjoint training split (500k/50k/50k train/validation/test); outputs projected to the shared canonical b/y fragment space; hyperparameters in Appendix Table 12
training setting: Trained on PROSPECT
access reuse: Benchmark data at https://huggingface.co/datasets/Chris-young-2004/PepSpecBench; model code not stated
source locator: Section 3.2; Appendix E and Table 12
missing metadata: version: reason: unreported; note: No model or code version is printed

Related records

Suggest a correction