Multi-Scale Representation Learning on Proteins

By Vignesh Ram Somnath, Charlotte Bunne, Andreas Krause. 2022

122 citations recorded by the source corpus.

Proteins are fundamental biological entities mediating key roles in cellular function and disease. This paper introduces a multi-scale graph construction of a protein -- HoloProt -- connecting surface to structure and sequence. The surface captures coarser details of the protein, while sequence as primary component and structure -- comprising secondary and tertiary components -- capture finer details. Our graph encoder then learns a multi-scale representation by allowing each level to integrate the encoding from level(s) below with the graph at that level. We test the learned representation on different tasks, (i.) ligand binding affinity (regression), and (ii.) protein function prediction (classification). On the regression task, contrary to previous methods, our model performs consistently and reliably across different dataset splits, outperforming all baselines on most splits. On the classification task, it achieves a performance close to the top-performing model while using 10x fewer parameters. To improve the memory efficiency of our construction, we segment the multiplex protein surface manifold into molecular superpixels and substitute the surface with these superpixels at little to no performance loss.

Subfields: Materials Chemistry, Molecular Biology, Representation & Self-Supervised Learning, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

In Molecular Biology

In Representation & Self-Supervised Learning

In Computational Biology & Bioinformatics

Citations in the corpus

TANKBind: Trigonometry-Aware Neural NetworKs for Drug-Protein Binding Structure Prediction (2022, methodology): “Similar to previous methods [23, 44], we predict negative log-transformed binding affinity.”
DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking (2022, background): “Then, the representations of the different [33], HOLOPTOT [34], STAMPDPI [35] and TANKBind [4].”
EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction (2022, background): “Somnath et al. (2021) create a hierarchical representation of proteins and prove its utility in binding and function prediction.”
Protein Representation Learning by Geometric Structure Pretraining (2022, methodology): “Somnath et al. (2021) combined the advantages of both worlds and proposed a parameter-efﬁcient multi-scale model.”
Masked Inverse Folding with Sequence Transfer for Protein Representation Learning (2023, background): “…the structure in addition to the sequence (Mansoor et al., 2021; Chen et al., 2022), encoding surface features (Townshend et al., 2019), contrastive learning (Zhang et al., 2022; Cao et al., 2021), or a graph encoder without sequence decoding (Somnath et al., 2021; Fuchs et al., 2020).”
3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction (2023, methodology): “…our model, and compare it with two state-of-the-art sequence-based models TransCPI (Chen et al., 2020) and MONN (Li et al., 2020), one complex model IGN (Jiang et al., 2021), two structure-based model HOLOPROT (Somnath et al., 2021) and STAMP-DPI (Wang et al., 2022) and ﬁnally the base EGNN model.”