DeepNeo-CLv4.2

Benchmark methodology

How the head-to-head against NetMHCpan-4.2c was constructed, and how we decontaminated the test data.

Primary benchmark: multi-study mono-allelic HLA-I EL

Union of three post-cutoff, publicly-available PRIDE proteomics studies. 601,565 unique 8–14mer positives across 13 HLA-A and HLA-B alleles. Scored subset: 496,240 candidates (cap 500 positives per sample; 19:1 source-protein-matched decoys).

PRIDE accessioncell line(s)allelespositives
PXD082505721.221 mono-allelic (Kim et al., FDA CBERS)3 HLA-B2,051
PXD070374C1R-B*57:01 (ExCID FragPipe)1 HLA-B9,118
PXD07320710 mono-allelic FDA01 lines (timsTOF-SCP DDA-PASEF, Nilsson lab)10 HLA-A/B590,396

Benchmark protocol

1. Temporal gate

Every benchmark row has first-public date ≥ 2025-08-08 — the day after NetMHCpan-4.2's release. This guarantees that both models' training data was frozen strictly before the test observations.

2. Overlap audit vs the reference model's public training data

Every benchmark's positives are audited against a 17.6 M-row union catalogue assembled from the reference predictor's public training partitions, keyed on the exact (peptide, HLA) pair and any contiguous 8-mer sub-string overlap (via an MD5-hashed 8-mer index of 12 M unique hashes). Two locked analysis sets result: exact-disjoint and strict-sequence-disjoint.

3. Multi-study mono-allelic EL (primary result)

Three post-cutoff PRIDE studies (see table above). 601,565 unique positives across 13 alleles; 86.06 % exact-disjoint from the training corpus (517,679 novel peptide–HLA pairs).

4. Source-protein-matched decoys

For every positive, decoys are drawn from k-mers of the same source proteins observed in that sample's positive set. This removes the "protein-was-expressed" trivial signal that length-matched random-proteome decoys leave in — a stricter test than most published benchmarks.

5. Reference predictor

Version-pinned NetMHCpan-4.2c executable, unmodified from the DTU distribution, invoked with -BA for IC50 output. HLA-B*07:01 is unsupported by NetMHCpan-4.2 and is excluded from paired comparisons.

6. Statistics

Bootstrap CIs: 1,000 iterations at seed 42, study-clustered where possible. Paired-delta CIs on the intersection of covered rows.

Decontamination audit — all 4 benchmarks

Percent of positives that are novel relative to the reference model's public training data.

Benchmarknexact pep-HLA leakexact-disjointstrict-seq-disjoint
BA temporal (IEDB post-2025-08-08)5920.00%100.00%98.82%
IEDB auto_bench pooled (post-2025-08-08)5942.53%97.47%42.42%
Mono-allelic EL v1 (superseded)2,05173.67%26.33%0.49%
Mono-allelic EL v2 (primary)601,56513.94%86.06%8.01%

Head-to-head result — mono-allelic EL v2

PredictorPooled AUROC95% CIPer-allele macro AUROCAlleles won
DeepNeo-CL v4.2 (EL)0.8100[0.8068, 0.8132]0.843612 / 12
NetMHCpan-4.2c0.7762[0.7728, 0.7801]0.8157

Paired Δ AUROC (BA head, common-support subset) = +0.0113 [+0.0094, +0.0134], bootstrap p ≈ 0. Full per-allele + interactive Plotly charts on the Benchmarks page.

Live service