Article

Fitness Landscape for Antibodies 2: Benchmarking Reveals That Protein AI Models Cannot Yet Consistently Predict Developability Properties

2025-12-27

Abstract excerpt

1 A prominent application of machine learning in therapeutic antibody design is the development of models that can generate or screen antibody candidates with a high probability of success in manufacturing and clinical trials. These models must accurately represent sequence-structure-function relationships, also known as the fitness landscape. Previous protein function benchmarks examine fitness landscapes across...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 5634b2c8-ca49-57c6-bd6c-c26cec1d57f2
DOI: 10.64898/2025.12.27.696706

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Fitness Landscape for Antibodies 2: Benchmarking Reveals That Protein AI Models Cannot Yet Consistently Predict Developability PropertiesDOI 10.64898/2025.12.27.696706Read

Biophysical cartography of the native and human-engineered antibody landscapes quantifies the plasticity of antibody developabilitySemantic proximity Read

Efficient evolution of human antibodies from general protein language models and sequence information aloneSemantic proximity Read

Benchmarking Inverse Folding Models for Antibody CDR Sequence DesignSemantic proximity Read

A synergistic generative-ranking framework for tailored design of therapeutic single-domain antibodiesSemantic proximity Read

Better antibodies engineered with a GLIMPSE of human dataSemantic proximity Read

AbNatiV: VQ-VAE-based assessment of antibody and nanobody nativeness for hit selection, humanisation, and engineeringSemantic proximity Read

A high-throughput platform for biophysical antibody developability assessment to enable AI/ML model trainingSemantic proximity Read

Efficient evolution of human antibodies from general protein language models.Semantic proximity Read

Sequence-Only Prediction of Antibody Fab Thermostability Using Protein Language Model EmbeddingsSemantic proximity Read

Deep learning-based design and experimental validation of a medicine-like human antibody librarySemantic proximity Read

Antibody immunogenicity prediction and optimization with ImmunoSeqSemantic proximity Read

Computational design of therapeutic antibodies with improved developability: efficient traversal of binder landscapes and rescue of escape mutations.Semantic proximity Read