Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CAPSUL: A Comprehensive Human Protein Benchmark for Subcellular Localization

Yicheng Hu, Xinyu Lin, Shulin Li, Wenjie Wang, Fengbin Zhu, Fuli Feng

Abstract

Subcellular localization is a crucial biological task for drug target identification and function annotation. Although it has been biologically realized that subcellular localization is closely associated with protein structure, no existing dataset offers comprehensive 3D structural information with detailed subcellular localization annotations, thus severely hindering the application of promising structure-based models on this task. To address this gap, we introduce a new benchmark called $\mathbf{CAPSUL}$, a $\mathbf{C}$omprehensive hum$\mathbf{A}$n $\mathbf{P}$rotein benchmark for $\mathbf{SU}$bcellular $\mathbf{L}$ocalization. It features a dataset that integrates diverse 3D structural representations with fine-grained subcellular localization annotations carefully curated by domain experts. We evaluate this benchmark using a variety of state-of-the-art sequence-based and structure-based models, showcasing the importance of involving structural features in this task. Furthermore, we explore reweighting and single-label classification strategies to facilitate future investigation on structure-based methods for this task. Lastly, we showcase the powerful interpretability of structure-based methods through a case study on the Golgi apparatus, where we discover a decisive localization pattern $α$-helix from attention mechanisms, demonstrating the potential for bridging the gap with intuitive biological interpretability and paving the way for data-driven discoveries in cell biology.

CAPSUL: A Comprehensive Human Protein Benchmark for Subcellular Localization

Abstract

Subcellular localization is a crucial biological task for drug target identification and function annotation. Although it has been biologically realized that subcellular localization is closely associated with protein structure, no existing dataset offers comprehensive 3D structural information with detailed subcellular localization annotations, thus severely hindering the application of promising structure-based models on this task. To address this gap, we introduce a new benchmark called , a omprehensive humn rotein benchmark for bcellular ocalization. It features a dataset that integrates diverse 3D structural representations with fine-grained subcellular localization annotations carefully curated by domain experts. We evaluate this benchmark using a variety of state-of-the-art sequence-based and structure-based models, showcasing the importance of involving structural features in this task. Furthermore, we explore reweighting and single-label classification strategies to facilitate future investigation on structure-based methods for this task. Lastly, we showcase the powerful interpretability of structure-based methods through a case study on the Golgi apparatus, where we discover a decisive localization pattern -helix from attention mechanisms, demonstrating the potential for bridging the gap with intuitive biological interpretability and paving the way for data-driven discoveries in cell biology.
Paper Structure (41 sections, 7 equations, 4 figures, 20 tables)

This paper contains 41 sections, 7 equations, 4 figures, 20 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. CAPSUL Dataset
  4. Processing of Protein Sequence and Structure Data
  5. Processing of Subcellular Localization Annotations
  6. Data Merging
  7. Dataset Analysis
  8. Experiments
  9. Baseline Models
  10. Benchmark Overall Results and Discussion
  11. In-depth Analysis
  12. Protein Imbalance Mitigation via Reweighting
  13. Single-label Classification
  14. Biological Interpretability
  15. Conclusion and Future Work
  16. ...and 26 more sections

Figures (4)

  • Figure 1: Procedures of CAPSUL dataset construction, including 3 key steps: Step 1 extracts and filters the sequence and structure data for each high-quality protein from AlphaFold2; Step 2 collects the annotations from UniProt and HPA for the resulting proteins in Step 1; Step 3 merges the structure data and the annotations for each protein, which consists of protein ID, localization annotations, amino acid sequence, sequence length, 3Di tokens, and C$\alpha$ coordinates, etc.
  • Figure 2: Visualization of the top 20 attention-scored residues of the three representative proteins.
  • Figure 3: Sample efficiency curve on CDConv.
  • Figure 4: Visualization of full attention scores and structures of proteins MFNG, B3GALT2, and GIMAP1, where the residues of known pattern $\alpha$-helix are highlighted.