# A Systematic Comparison of In-Context Learning Strategies for Peptide Property Prediction in Low-Data Regimes

DevFeed: [A Systematic Comparison of In-Context Learning Strategies for Peptide Property Prediction in Low-Data Regimes](<https://devfeed.tech/articles/a-systematic-comparison-of-in-context-learning-strategies-for-peptide-property-prediction-in-low-data-regimes-125117.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09994>)

Author: Jiantao Zhao, Andrei Voinea, Mathijs F. J. Mabesoone

Published: 2026-11-10T05:00:00Z

Content type: comparison

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [generalization in machine learning](<https://devfeed.tech/topics/generalization-in-machine-learning.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Language models](<https://devfeed.tech/topics/language-models.md>)

Tags: [architectures](<https://devfeed.tech/tags/architectures.md>), [assembly](<https://devfeed.tech/tags/assembly.md>), [bias](<https://devfeed.tech/tags/bias.md>), [cancer](<https://devfeed.tech/tags/cancer.md>), [classification](<https://devfeed.tech/tags/classification.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decision](<https://devfeed.tech/tags/decision.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [design](<https://devfeed.tech/tags/design.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [examples](<https://devfeed.tech/tags/examples.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [learning](<https://devfeed.tech/tags/learning.md>), [physics-chem-ph](<https://devfeed.tech/tags/physics-chem-ph.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [property](<https://devfeed.tech/tags/property.md>), [strategies](<https://devfeed.tech/tags/strategies.md>)

## AI overview

The study compares in-context learning by large language models, tabular foundation models, and typed decision models with an XGBoost baseline for peptide property classification. Across binary and multiclass tasks involving pH-dependent surface activity, IR spectral signatures, self-assembly, and anti-cancer activity, in-context learning is competitive but does not significantly outperform classical baselines; performance varies by model and task. The authors suggest language models draw on both examples provided in context and pretraining knowledge, which may let them use existing literature but may also bias predictions toward established sequence-property relationships.

## Source excerpt

arXiv:2611.09994v1 Announce Type: cross Abstract: Peptide sequence-property relationships are often highly non-linear, but can be learned with machine learning models and exploited for the design of new materials and bioactive compounds. Various methods based on transformer architectures have become available for molecular property predictions. These foundation models promise straightforward inference and prediction of properties of new materials through in-context learning. Benchmarks of individual model architectures exist, but a systematic comparison of various foundation models against classical baselines on similar datasets is lacking. Here, we provide a systematic evaluation of the predictive performance of various in-context learning strategies. We compare several large language models, tabular foundation models, and typed decision models against an XGBoost baseline. We evaluate predictive performance on binary and multiclass classification tasks on pH-dependent surface activ-ity, IR spectral signatures, self-assembly, and anti-cancer activities. Our results show that ICL is competitive, yet does not significantly outperform classical baselines, and performance varies between models and tasks. Our findings further suggest that language models use both in context examples and knowledge acquired during pretraining to infer properties of unseen samples. This finding indicates that pretrained models can leverage the existing literature for predictions, but may also bias their predictions towards established sequence-property relationships.