Deep Active Learning based Experimental Design to Uncover Synergistic Genetic Interactions for Host Targeted Therapeutics

2025-02-03

AI Summary

Identifying host gene pairs exhibiting synergistic antiviral effects against HIV remains challenging due to biological complexity and the prohibitive scale of combinatorial double-gene knockdown experiments (356 × 356). To address this, we propose a knowledge graph–enhanced deep active learning framework. We integrate the SPOKE knowledge graph with a graph neural network to generate task-specific gene embeddings and design a balanced exploration–exploitation sampling strategy coupled with ensemble-based uncertainty quantification. Pathway enrichment analysis is further incorporated to enhance biological interpretability. Our method significantly improves the efficiency of discovering potent synergistic anti-HIV gene pairs: it successfully identifies multiple experimentally validated high-synergy pairs and reveals their significant enrichment in immune regulation and viral replication pathways. This work establishes a novel paradigm for multi-gene-targeted therapeutic intervention strategies against HIV.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Combinatorial Optimization

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Recent technological advances have introduced new high-throughput methods for studying host-virus interactions, but testing synergistic interactions between host gene pairs during infection remains relatively slow and labor intensive. Identification of multiple gene knockdowns that effectively inhibit viral replication requires a search over the combinatorial space of all possible target gene pairs and is infeasible via brute-force experiments. Although active learning methods for sequential experimental design have shown promise, existing approaches have generally been restricted to single-gene knockdowns or small-scale double knockdown datasets. In this study, we present an integrated Deep Active Learning (DeepAL) framework that incorporates information from a biological knowledge graph (SPOKE, the Scalable Precision Medicine Open Knowledge Engine) to efficiently search the configuration space of a large dataset of all pairwise knockdowns of 356 human genes in HIV infection. Through graph representation learning, the framework is able to generate task-specific representations of genes while also balancing the exploration-exploitation trade-off to pinpoint highly effective double-knockdown pairs. We additionally present an ensemble method for uncertainty quantification and an interpretation of the gene pairs selected by our algorithm via pathway analysis. To our knowledge, this is the first work to show promising results on double-gene knockdown experimental data of appreciable scale (356 by 356 matrix).

Problem

• Gene Interaction
• HIV Therapy
• Cooperative Effects

Innovation

• DeepAL
• Gene Pair Screening
• Active Learning