VAMP-Net: An Interpretable Multi-Path Framework of Genomic Permutation-Invariant Set Attention and Quality-Aware 1D-CNN for MTB Drug Resistance

TL;DR

The paper tackles MTB drug resistance prediction by addressing two core challenges: complex epistatic interactions among genomic variants and variable sequencing data quality. It introduces VAMP-Net, a dual-path architecture that combines a permutation-invariant Set Attention Transformer pathway for variant-level interactions with a quality-aware 1D-CNN pathway that learns data-quality-driven confidence, fused in a late-stage fusion module. The model delivers state-of-the-art predictive performance (accuracy >95%, AUC ~0.97 for RIF and RFB) while providing auditable interpretability at both genetic (variant importance and epistasis) and technical (VCF quality metrics) levels. Moreover, the framework demonstrates robustness and generalizability, offering a new paradigm for clinically actionable, interpretable genotype–phenotype prediction beyond MTB drug resistance.

Abstract

Genomic prediction of drug resistance in Mycobacterium tuberculosis remains challenging due to complex epistatic interactions and highly variable sequencing data quality. We present a novel Interpretable Variant-Aware Multi-Path Network (VAMP-Net) that addresses both challenges through complementary machine learning pathways. Path-1 employs a Set Attention Transformer processing permutation-invariant variant sets to capture epistatic interactions between genomic loci. Path-2 utilizes a 1D Convolutional Neural Network that analyzes Variant Call Format quality metrics to learn adaptive confidence scores. A fusion module combines both pathways for final resistance classification. We conduct comparative evaluations of unmasked versus padding-masked Set Attention Blocks, and demonstrate that our multi-path architecture achieves superior performance over baseline CNN and MLP models, with accuracy exceeding 95% and AUC around 97% for Rifampicin (RIF) and Rifabutin (RFB) resistance prediction. The framework provides dual-layer interpretability: Attention Weight Analysis reveals Epistatic networks, and Integrated Gradients (IG) was applied for critical resistance loci (notably rpoB), while gradient-based feature importance from the CNN pathway uncovers drug-specific dependencies on data quality metrics. This architecture advances clinical genomics by delivering state-of-the-art predictive performance alongside auditable interpretability at two distinct levels, genetic causality of mutation sets and technical confidence of sequencing evidence, establishing a new paradigm for robust, clinically-actionable resistance prediction.

Figures (13)

• Figure 1: Overview of the Variant-Aware Multi-Path Network (VAMP-Net) Architecture
• Figure 2: Path-1 Architecture: Set Attention Transformer Block (SAB) for Symbolic Variant Processing
• Figure 3: Path-2 Architecture: Quality-Aware 1D Convolutional Neural Network (1D-CNN) for VCF Feature Processing
• Figure 4: Distribution of classes for the selected drugs.
• Figure 5: Comparison of Static Encoding vs BERT Tokeniser metrics over epochs