English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Nuclear magnetic resonance (NMR) spectroscopy plays an essential role acrossvarious scientific disciplines, providing valuable insights into moleculardynamics and interactions. Despite the promise of AI-enhanced NMR predictionmodels, challenges persist in the interpretation of spectra for tasks such asmolecular retrieval, isomer recognition, and peak assignment. In response, thispaper introduces Multi-Level Multimodal Alignment with Knowledge-GuidedInstance-Wise Discrimination (K-M3AID) to establish meaningful correspondencesbetween two heterogeneous modalities: molecular graphs (structures) and NMRspectra. In particular, K-M3AID employs a dual-coordinated contrastive learningarchitecture, and incorporates a graph-level alignment module, a node-levelalignment module, and a communication channel. Notably, the frameworkintroduces knowledge-guided instance-wise discrimination into contrastivelearning within the node-level alignment module, significantly enhancingaccuracy in cross-modal alignment. Additionally, K-M3AID showcases itscapability of meta-learning by demonstrating that skills acquired duringnode-level alignment positively impact graph-level alignment. Empiricalvalidation underscores K-M3AID's effectiveness in addressing multiple zero-shottasks, offering a promising solution to bridge the gap between structuralinformation and spectral data in complex NMR scenarios.

Molecular Identification and Peak Assignment: Leveraging Multi-Level Multimodal Alignment on NMR