Source

A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation

iScience 2026, 116522; PMC13444443 full-text XML · Peer-reviewed

DOI: 10.1016/j.isci.2026.116522

What this source contributed

Records in this release that cite this source. A record can cite several sources.

3 models
4 configurations
1 benchmark
4 protocols
4 datasets
16 evaluations
16 results

Results

Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.

Value	Metric	Model or configuration	Dataset	Evaluation
57.93% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	Boltz-2 (AlphaBind pairwise evaluation)	AlphaBind PEM antibody variants (held-out antigen)	Boltz-2 on AlphaBind PEM (pairwise accuracy)
55.52% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	Boltz-2 (AlphaBind pairwise evaluation)	AlphaBind PP489 antibody variants (held-out antigen)	Boltz-2 on AlphaBind PP489 (pairwise accuracy)
60.09% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	Boltz-2 (AlphaBind pairwise evaluation)	AlphaBind TRA antibody variants (held-out antigen)	Boltz-2 on AlphaBind TRA (pairwise accuracy)
57.90% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	Boltz-2 (AlphaBind pairwise evaluation)	AlphaBind VHH72 antibody variants (held-out antigen)	Boltz-2 on AlphaBind VHH72 (pairwise accuracy)
47.11% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	GeoDock (AlphaBind pairwise evaluation)	AlphaBind PEM antibody variants (held-out antigen)	GeoDock on AlphaBind PEM (pairwise accuracy)
50.17% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	GeoDock (AlphaBind pairwise evaluation)	AlphaBind PP489 antibody variants (held-out antigen)	GeoDock on AlphaBind PP489 (pairwise accuracy)
51.21% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	GeoDock (AlphaBind pairwise evaluation)	AlphaBind TRA antibody variants (held-out antigen)	GeoDock on AlphaBind TRA (pairwise accuracy)
49.58% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	GeoDock (AlphaBind pairwise evaluation)	AlphaBind VHH72 antibody variants (held-out antigen)	GeoDock on AlphaBind VHH72 (pairwise accuracy)
63.20% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	Graphinity (AlphaBind pairwise evaluation)	AlphaBind PEM antibody variants (held-out antigen)	Graphinity on AlphaBind PEM (pairwise accuracy)
67.01% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	Graphinity (AlphaBind pairwise evaluation)	AlphaBind PP489 antibody variants (held-out antigen)	Graphinity on AlphaBind PP489 (pairwise accuracy)
68.55% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	Graphinity (AlphaBind pairwise evaluation)	AlphaBind TRA antibody variants (held-out antigen)	Graphinity on AlphaBind TRA (pairwise accuracy)
58.63% percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	Graphinity (AlphaBind pairwise evaluation)	AlphaBind VHH72 antibody variants (held-out antigen)	Graphinity on AlphaBind VHH72 (pairwise accuracy)
72.35% (p < 0.0001) percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	MochiBind (AlphaBind pairwise evaluation)	AlphaBind PEM antibody variants (held-out antigen)	MochiBind on AlphaBind PEM (pairwise accuracy)
70.29% (p < 0.0001) percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	MochiBind (AlphaBind pairwise evaluation)	AlphaBind PP489 antibody variants (held-out antigen)	MochiBind on AlphaBind PP489 (pairwise accuracy)
74.27% (p < 0.0001) percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	MochiBind (AlphaBind pairwise evaluation)	AlphaBind TRA antibody variants (held-out antigen)	MochiBind on AlphaBind TRA (pairwise accuracy)
59.89% (p < 0.0001) percent	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)	MochiBind (AlphaBind pairwise evaluation)	AlphaBind VHH72 antibody variants (held-out antigen)	MochiBind on AlphaBind VHH72 (pairwise accuracy)

Models, benchmarks and other records

Models (3)

Configurations (4)

Benchmarks (1)

Universal antibody-antigen affinity evaluation on AlphaBind (MochiBind study)

Protocols (4)

Datasets (4)

Evaluations (16)

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.

24 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
attributes.artifact_sha256 0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d Source metadata	A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation Original source ↗ No field-specific location recorded Version: iScience 2026, 116522; PMC13444443 full-text XML Retrieved: 2026-10-11T21:26:34Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.artifact_sha256` Source artifact SHA-256: `0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Artifact url https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13444443/fullTextXML Source metadata	A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation Original source ↗ No field-specific location recorded Version: iScience 2026, 116522; PMC13444443 full-text XML Retrieved: 2026-10-11T21:26:34Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.artifact_url` Source artifact SHA-256: `0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Doi 10.1016/j.isci.2026.116522 Source metadata	A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation Original source ↗ No field-specific location recorded Version: iScience 2026, 116522; PMC13444443 full-text XML Retrieved: 2026-10-11T21:26:34Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.doi` Source artifact SHA-256: `0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Evidence concerns 1 values source id lit-interactions-20261011-mochibind-source-isci2026 message The Table 2 footnote says "Values denote chi-squared statistics, with significance levels in parentheses", which contradicts the column headers ("Pairwise accuracy (%)", "Graphinity (%)" and so on), the cell contents (percentages between 47.11 and 74.27) and the body text, which places the chi-squared statistics in Table S1. The records read the cells as accuracies with a p-value, which the headers and body support; the footnote is wrong as printed. source locator Table 2 footnote artifact sha256 0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d reviewed at 2026-10-11T00:00:00Z review method ai-assisted-source-review Source metadata	A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation Original source ↗ No field-specific location recorded Version: iScience 2026, 116522; PMC13444443 full-text XML Retrieved: 2026-10-11T21:26:34Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.evidence_concerns` Source artifact SHA-256: `0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Licence CC-BY-NC-ND-4.0 Source metadata	A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation Original source ↗ No field-specific location recorded Version: iScience 2026, 116522; PMC13444443 full-text XML Retrieved: 2026-10-11T21:26:34Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.licence` Source artifact SHA-256: `0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Limitations 3 values Retrieval results (Precision@K and retrieval accuracy) are in figures only and were not read. Supplementary Tables S1 (McNemar statistics) and S2 (Graphinity before and after fine-tuning) were not retrieved. Licence CC BY-NC-ND: the XML is not archived in the repository. Source metadata	A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation Original source ↗ No field-specific location recorded Version: iScience 2026, 116522; PMC13444443 full-text XML Retrieved: 2026-10-11T21:26:34Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.limitations` Source artifact SHA-256: `0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Media type application/xml Source metadata	A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation Original source ↗ No field-specific location recorded Version: iScience 2026, 116522; PMC13444443 full-text XML Retrieved: 2026-10-11T21:26:34Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.media_type` Source artifact SHA-256: `0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Publication status peer_reviewed Source metadata	A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation Original source ↗ No field-specific location recorded Version: iScience 2026, 116522; PMC13444443 full-text XML Retrieved: 2026-10-11T21:26:34Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.publication_status` Source artifact SHA-256: `0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Retrieved at 2026-10-11T21:26:34Z Source metadata	A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation Original source ↗ No field-specific location recorded Version: iScience 2026, 116522; PMC13444443 full-text XML Retrieved: 2026-10-11T21:26:34Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.retrieved_at` Source artifact SHA-256: `0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Review: date 2026-10-11 Source metadata	A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation Original source ↗ No field-specific location recorded Version: iScience 2026, 116522; PMC13444443 full-text XML Retrieved: 2026-10-11T21:26:34Z	catalogued No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit details Field: `attributes.review.date` Source artifact SHA-256: `0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

Primary source retrieved and hashed for the 2026-10-11 microbial and interactions literature pass.

Release history

No supporting source is linked yet.

Read original source

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-interactions-20261011-mochibind-source-isci2026

areas: molecular-interactions; proteins-complexes
contexts: research
url: https://doi.org/10.1016/j.isci.2026.116522
artifact url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13444443/fullTextXML
version: iScience 2026, 116522; PMC13444443 full-text XML
retrieved at: 2026-10-11T21:26:34Z
artifact sha256: 0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d
doi: 10.1016/j.isci.2026.116522
publication status: peer_reviewed
licence: CC-BY-NC-ND-4.0
media type: application/xml
limitations: Retrieval results (Precision@K and retrieval accuracy) are in figures only and were not read.; Supplementary Tables S1 (McNemar statistics) and S2 (Graphinity before and after fine-tuning) were not retrieved.; Licence CC BY-NC-ND: the XML is not archived in the repository.
evidence concerns: source id: lit-interactions-20261011-mochibind-source-isci2026; message: The Table 2 footnote says "Values denote chi-squared statistics, with significance levels in parentheses", which contradicts the column headers ("Pairwise accuracy (%)", "Graphinity (%)" and so on), the cell contents (percentages between 47.11 and 74.27) and the body text, which places the chi-squared statistics in Table S1. The records read the cells as accuracies with a p-value, which the headers and body support; the footnote is wrong as printed.; source locator: Table 2 footnote; artifact sha256: 0f57b9b13bae7460d3789fdcd7f3aaa062ec8cfe8e8d1ef9242d480ea444368d; reviewed at: 2026-10-11T00:00:00Z; review method: ai-assisted-source-review
review: method: source-hash-verification; method note: Full-text XML re-downloaded from the recorded Europe PMC URL and its SHA-256 matched.; reviewer: claude; reviewer note: Claude review agent reviewer-mi-1, independent of the extractor lit-microbial-interactions; no human review claimed; date: 2026-10-11

Related records

Suggest a correction