Exploiting Pre-trained Models For Drug Target Affinity Prediction With Nearest Neighbors

Abstract

Drug-Target binding Affinity (DTA) prediction is essential for drug discovery. Despite the application of deep learning methods to DTA prediction, the achieved accuracy remain suboptimal. In this work, inspired by the recent success of retrieval methods, we propose \(k\)NN-DTA, a non-parametric embedding-based retrieval method adopted on a pre-trained DTA prediction model, which can extend the power of the DTA model with no or negligible cost. Different from existing methods, we introduce two neighbor aggregation ways from both embedding space and label space that are integrated into a unified framework. Specifically, we propose a *label aggregation* with *pair-wise retrieval* and a *representation aggregation* with *point-wise retrieval* of the nearest neighbors. This method executes in the inference phase and can efficiently boost the DTA prediction performance with no training cost. In addition, we propose an extension, Ada-\(k\)NN-DTA, an instance-wise and adaptive aggregation with

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keypei2024exploiting

Related papers

• NUDGE: Lightweight Non-parametric Fine-tuning Of Embeddings For Retrieval (2024)0.00
• Training-time Attacks Against K-nearest Neighbors (2022)2.26
• Efficient Data-aware Distance Comparison Operations For High-dimensional Approximate Nearest Neighbor Search (2024)5.24
• Utilizing Low-dimensional Molecular Embeddings For Rapid Chemical Similarity Search (2024)4.52
• Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees (2017)0.00
• Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings (2022)11.85
• Fast And Bayes-consistent Nearest Neighbors (2019)0.00
• Why Do Nearest Neighbor Language Models Work? (2023)3.56