FiLM-Enhanced Biologically Informed Neural Networks for Multiclass Omics Analysis and Biomarker Discovery

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not reported in abstract

• Primary Outcome: BINN-FiLM consistently outperformed conventional BINNs and standard machine learning models

• Nnt Or Sensitivity: Classification performance metrics not specified in abstract

• Confidence Interval: Not reported

Clinical Application

Requires high-throughput proteomics infrastructure and computational expertise Could support precision medicine initiatives and complement existing diagnostic pathways, but would require validation in Australian populations and integration with TGA-approved diagnostic platforms Patients requiring multiclass disease classification based on proteomic profiles

Abstract

High-throughput proteomics enables detailed molecular phenotyping but poses challenges for predictive modeling and interpretation due to high dimensionality, sparsity, and nonlinear interactions. Biologically informed neural networks (BINNs) address these challenges by embedding pathway knowledge into network architectures, providing interpretable models of complex omics data. We present BINN-FiLM, which extends conventional BINNs by integrating feature-wise linear modulation, enabling task-specific scaling and shifting of pathway-level activations while preserving a fixed Reactome-based hierarchy. Unlike BINNs that share all pathway parameters across classes, BINN-FiLM captures class-dependent biological rewiring, making it particularly effective for multiclass classification tasks. Multiclass problems are reformulated as multitask binary learning, allowing pathway activations to adapt to disease-specific contexts. We evaluated BINN-FiLM on three multiclass proteomic data sets, and BINN-FiLM consistently outperformed conventional BINNs and standard machine learning models. FiLM modulation parameters revealed task-specific pathway activity, and SHAP-based interpretation identified key proteins and pathways driving disease discrimination.

References

1. 1.Liu, W., Zheng, Z., Wang, X., & Ji, H. (2026). FiLM-Enhanced Biologically Informed Neural Networks for Multiclass Omics Analysis and Biomarker Discovery. Analytical Chemistry. https://doi.org/10.1021/acs.analchem.6c00372