Work

VALANCE: a machine learning algorithm to predict antibody neutralization potency

Year: 2026

Type: dataset

Abstract: VALANCE is a machine learning pipeline that predicts HIV-1 broadly neutralizing antibody (bNAb) resistance from Env sequences. It embeds sequences with ESM2, performs feature down-selection, and classifies neutralization sensitivity/resistance with a fine-tuned TabPFN transformer at a chosen IC₅₀ threshold (0.2, 1, or 50 µg/mL). This site contains pretrained models for all 25 bNAbs across all three thresholds & training data file (.txt) which are available for download.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.21781829

Authors: Qiao, Yujie, Jiang, Raymond, Lu, Hong, Wu, Xueling, Sheng, Zizhang

Institutions: Yale University, Boston Medical Center, Columbia University Irving Medical Center

Language: English

Topic: HIV Research and Treatment

Subfield: Virology

Field: Immunology and Microbiology

Domain: Life Sciences

Open Access status: green

OpenAlex ID: W7172376668

Cites:

Cited by:

Related to: 10