AI Science Tracker

Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning

ETH Zurich · 15 Apr 2021 · medicine

Discovery

ETH Zurich

Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning

Source check: Needs source check. Not independent scientific confirmation.

Finding: Neural networks trained on about 10^4 trastuzumab variants screened for HER2 specificity were used to screen about 10^8 computational variants and identify optimised HER2-specific variants.

Technology: Deep neural networks trained on antibody-library deep-sequencing/screening data

Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
Predicted antigen specificity from sequence to select optimised variants.
Test and result
Abstract reports prediction-led identification of variants; downstream validation details not assessed.
Limitation / still unknown
Developability and clinical relevance not assessed.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://europepmc.org/search?query=DOI:10.1038/s41551-021-00699-9

Needs source check · editorial details

The source has not been fully checked or contains conflicting information. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 17 Nov 2026. Review scope: Europe PMC metadata and abstract only; Methods not read..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.

Related catalog entries

Links use documented relationships where available, plus shared catalog context. A shared topic or model family does not establish a scientific dependency.