AI Paper Atlas

Research map / Point clouds / Point cloud classification

ProteinShake: Building datasets and benchmarks for deep learning on protein structures

Tim Kucera, Carlos Oliver, Dexiong Chen, Karsten Borgwardt

NeurIPS 2023 · Point clouds › Point cloud classification · approach: Equivariant point cloud networks · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use point cloud instead of graph representationPointNet++ vs GIN · Protein-Protein Interfacetask metric: 0.883 ± 0.050 -> 0.974 ± 0.003Improved
use voxel instead of graph representation3D CNN vs GIN · Structural Similaritytask metric: 0.598 ± 0.018 -> 0.645 ± 0.020Improved
use voxel instead of graph representation3D CNN vs GIN · Ligand Affinitytask metric: 0.670 ± 0.019 -> 0.689 ± 0.013Improved
use point cloud instead of graph representationPointNet++ vs GIN · Enzyme Classtask metric: 0.790 ± 0.007 -> 0.712 ± 0.016Hurt
use voxel instead of graph representation3D CNN vs GIN · Structural Classtask metric: 0.495 ± 0.012 -> 0.337 ± 0.011Hurt
use point cloud instead of graph representationPointNet++ vs GIN · Binding Sitetask metric: 0.721 ± 0.010 -> 0.609 ± 0.006Hurt
move from random to sequence to structure splitall models · all taskstask metricHurt
pre-train on AlphaFoldDB with residue masking (ablation)graph, point, voxel models · all tasksrelative improvementMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy