# Towards AI-Driven Nanomedicine Discovery: A Benchmark and Multimodal Learning Framework for Nano Self-Assembly Prediction

arXiv: https://arxiv.org/abs/2609.04278 · HTML: https://mlsanity.com/paper/2609.04278/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 41 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [Learning Multi-view Molecular Representations with Structured and Unstructured Knowledge](https://mlsanity.com/paper/2406.09841/) (2024)
- [Advancing Molecular Graph-Text Pre-training via Fine-grained Alignment](https://mlsanity.com/paper/2409.14106/) (2024)
- [Towards Interpretable Drug-Drug Interaction Prediction: A Graph-Based Approach with Molecular and Network-Level Explanations](https://mlsanity.com/paper/2507.09173/) (2025)
- [MIN: Multi-channel Interaction Network for Drug-Target Interaction with Protein Distillation](https://mlsanity.com/paper/2412.07778/) (2024)

## Abstract (arXiv)

Nano self-assembly organizes molecular components into bioactive nanoscale structures. Self-assembled nanoparticles (NAPs) derived from Chinese herbal formulas and applications such as anti-lung-cancer therapy demonstrate the substantial potential of self-assembly for nanomedicine discovery. Yet discovery still relies on costly wet-lab screening, while existing machine learning approaches lack standardized tasks, effective pairwise compatibility modeling, and public benchmarks with unified evaluation. To address these limitations, we formalize NSA prediction as a binary classification task for predicting self-assembly between molecular pairs and then establish NSA-Bench, the first public benchmark with curated molecular combinations, experimental conditions, self-assembly labels, and standardized evaluation protocols. We further develop NSA-Net, an interaction-aware multimodal framework that integrates complementary molecular evidence from graph topology, sequence semantics, and physicochemical descriptors to learn molecular-pair representations for self-assembly prediction. Extensive experiments on NSA-Bench show that NSA-Net achieves a ROC-AUC of 0.9470±0.0112 (Small) and 0.9492±0.0062 (Large). On the Small track, it surpasses the strongest machine-learning and graph-based baselines by 3.9 and 17.1 percentage points, respectively. Representation analyses reveal interpretable molecular characteristics associated with self-assembly prediction captured by the learned representations. Moreover, an NSA-Agent case study further demonstrates how NSA-Net predictions can support formulation refinement through experimental-condition-aware reasoning. Our code is available at https://github.com/developer-hq/NSA-Net.