Self-Supervised Foundation Model for Calcium-imaging Population Dynamics

TL;DR

This paper introduces CalM, a self-supervised foundation model for calcium imaging data that improves neural population analysis and decoding across multiple tasks, using a novel tokenizer and transformer architecture.

Contribution

The paper presents a new self-supervised pretraining framework for calcium traces, enabling transfer across diverse neuroscience tasks with interpretable representations.

Findings

CalM outperforms specialized baselines in population dynamics forecasting.

CalM achieves superior behavior decoding with a task-specific head.

Linear analysis reveals interpretable neural structures in CalM representations.

Abstract

Recent work suggests that large-scale, multi-animal modeling can significantly improve neural recording analysis. However, for functional calcium traces, existing approaches remain task-specific, limiting transfer across common neuroscience objectives. To address this challenge, we propose \textbf{CalM}, a self-supervised neural foundation model trained solely on neuronal calcium traces and adaptable to multiple downstream tasks, including forecasting and decoding. Our key contribution is a pretraining framework, composed of a high-performance tokenizer mapping single-neuron traces into a shared discrete vocabulary, and a dual-axis autoregressive transformer modeling dependencies along both the neural and the temporal axis. We evaluate CalM on a large-scale, multi-animal, multi-session dataset. On the neural population dynamics forecasting task, CalM outperforms strong specialized baselines after pretraining. With a task-specific head, CalM further adapts to the behavior decoding task and achieves superior results compared with supervised decoding models. Moreover, linear analyses of CalM representations reveal interpretable functional structures beyond predictive accuracy. Taken together, we propose a novel and effective self-supervised pretraining paradigm for foundation models based on calcium traces, paving the way for scalable pretraining and broad applications in functional neural analysis. Code will be released soon.