# Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein Structures

arXiv: https://arxiv.org/abs/2007.06252 · HTML: https://mlsanity.com/paper/2007.06252/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2020.

## Built on by (most cited first, 2 of 2)

- [Learning Geometrically Disentangled Representations of Protein Folding Simulations](https://mlsanity.com/paper/2205.10423/) (2022)
- [Autoregressive Enzyme Function Prediction with Multi-scale Multi-modality Fusion](https://mlsanity.com/paper/2408.06391/) (2024)

## Abstract (arXiv)

Proteins perform a large variety of functions in living organisms, thus playing a key role in biology. As of now, available learning algorithms to process protein data do not consider several particularities of such data and/or do not scale well for large protein conformations. To fill this gap, we propose two new learning operations enabling deep 3D analysis of large-scale protein data. First, we introduce a novel convolution operator which considers both, the intrinsic (invariant under protein folding) as well as extrinsic (invariant under bonding) structure, by using n-D convolutions defined on both the Euclidean distance, as well as multiple geodesic distances between atoms in a multi-graph. Second, we enable a multi-scale protein analysis by introducing hierarchical pooling operators, exploiting the fact that proteins are a recombination of a finite set of amino acids, which can be pooled using shared pooling matrices. Lastly, we evaluate the accuracy of our algorithms on several large-scale data sets for common protein analysis tasks, where we outperform state-of-the-art methods.