# Metalic: Meta-Learning In-Context with Protein Language Models

arXiv: https://arxiv.org/abs/2410.08355 · HTML: https://mlsanity.com/paper/2410.08355/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 22 of 22)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Axial Attention in Multidimensional Transformers](https://mlsanity.com/paper/1912.12180/) (2019)
- [Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples](https://mlsanity.com/paper/1903.03096/) (2019)
- [ProGen: Language Modeling for Protein Generation](https://mlsanity.com/paper/2004.03497/) (2020)
- [Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling](https://mlsanity.com/paper/2207.04179/) (2022)
- [Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs](https://mlsanity.com/paper/2110.05038/) (2021)
- [A Tutorial on Meta-Reinforcement Learning](https://mlsanity.com/paper/2301.08028/) (2023)
- [Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation](https://mlsanity.com/paper/1910.13616/) (2019)
- [A Survey of Deep Meta-Learning](https://mlsanity.com/paper/2010.03522/) (2020)
- [Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval](https://mlsanity.com/paper/2205.13760/) (2022)
- [PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding](https://mlsanity.com/paper/2206.02096/) (2022)
- [Meta-in-context learning in large language models](https://mlsanity.com/paper/2305.12907/) (2023)
- [PoET: A generative model of protein families as sequences-of-sequences](https://mlsanity.com/paper/2306.06156/) (2023)
- [Recurrent Hypernetworks are Surprisingly Strong in Meta-RL](https://mlsanity.com/paper/2309.14970/) (2023)
- [Modeling and Optimization Trade-off in Meta-learning](https://mlsanity.com/paper/2010.12916/) (2020)
- [On the Practical Consistency of Meta-Reinforcement Learning Algorithms](https://mlsanity.com/paper/2112.00478/) (2021)
- [An Investigation of the Bias-Variance Tradeoff in Meta-Gradients](https://mlsanity.com/paper/2209.11303/) (2022)
- [Contrastive losses as generalized models of global epistasis](https://mlsanity.com/paper/2305.03136/) (2023)
- [SplAgger: Split Aggregation for Meta-Reinforcement Learning](https://mlsanity.com/paper/2403.03020/) (2024)

## Built on by (most cited first, 3 of 3)

- [Few-shot Protein Fitness Prediction via In-context Learning and Test-time Training](https://mlsanity.com/paper/2512.02315/) (2025)
- [From Snapshots to Symphonies: The Evolution of Protein Prediction from Static Structures to Generative Dynamics and Multimodal Interactions](https://mlsanity.com/paper/2603.18505/) (2026)
- [AbICL: In-Context Learning for Antigen-Specific Antibody Affinity Ranking](https://mlsanity.com/paper/2607.05846/) (2026)

## Abstract (arXiv)

Predicting the biophysical and functional properties of proteins is essential for in silico protein design. Machine learning has emerged as a promising technique for such prediction tasks. However, the relative scarcity of in vitro annotations means that these models often have little, or no, specific data on the desired fitness prediction task. As a result of limited data, protein language models (PLMs) are typically trained on general protein sequence modeling tasks, and then fine-tuned, or applied zero-shot, to protein fitness prediction. When no task data is available, the models make strong assumptions about the correlation between the protein sequence likelihood and fitness scores. In contrast, we propose meta-learning over a distribution of standard fitness prediction tasks, and demonstrate positive transfer to unseen fitness prediction tasks. Our method, called Metalic (Meta-Learning In-Context), uses in-context learning and fine-tuning, when data is available, to adapt to new tasks. Crucially, fine-tuning enables considerable generalization, even though it is not accounted for during meta-training. Our fine-tuned models achieve strong results with 18 times fewer parameters than state-of-the-art models. Moreover, our method sets a new state-of-the-art in low-data settings on ProteinGym, an established fitness-prediction benchmark. Due to data scarcity, we believe meta-learning will play a pivotal role in advancing protein engineering.