An Interpretable Deep Learning Framework with Dual-Modality Feature Fusion for Accurate Drug-Target Affinity Prediction

Deep cross-modal representation fusion learning for enhanced drug target affinity prediction.

Prediction of Drug Target Affinity (DTA) is essential for accelerating computational drug discovery and reducing experimental costs. However, traditional experimental approaches for DTA estimation are resource-intensive and are further challenged by the structural flexibility of both drugs and target proteins. In this work, we propose the PCBERT-GAT-DFFNN-DTA model, a three-stage deep cross-modal representation fusion framework for accurate DTA prediction. In the first stage, variable-length protein sequences are transformed into contextual representations using ProtBERT to obtain fixed-size protein embeddings. Drug molecules are represented using two modalities: sequence-based embeddings generated from ChemBERT and structure-based embeddings learned from molecular graphs using a Graph Attention Network (GAT). In the second stage, each modality is processed through dedicated subnetworks to refine features and reduce dimensionality while preserving modality-specific information. In the final stage, the refined representations are fused and passed to a Deep Feed-Forward Neural Network (DFFNN) to predict drug target binding affinity. The proposed model consistently outperformed most baseline methods under the S1-S3 evaluation settings across the benchmark datasets. Under the more challenging S4 blind setting, the model achieved strong performance on the KIBA dataset and competitive results on the Davis and Metz datasets. Compared with LLMDTA, the proposed approach achieves significant improvements in R2 scores across all datasets, demonstrating its effectiveness in learning complex drug protein interactions for reliable DTA prediction.

DeepGCL: Multi-View Graph Contrastive Learning for Enhanced Drug-Target Binding Affinity Prediction Through Protein Pocket-Drug Interaction Modeling.

DeepGCL is presented, a novel multi-modal framework that leverages multi-view graph contrastive learning to capture latent representations of pocket-drug interactions and their underlying molecular determinants and underscores the effectiveness of multi-view learning paradigms in capturing the multifaceted nature of drug-target interactions.

A linear interpretable model for drug target prediction

Abstract Motivation Identifying drug targets is fundamental in drug development, both for discovering new therapies and for ensuring effective and safe treatments. Drug-target interactions (DTIs) have been predicted using machine learning approaches that integrate heterogeneous data; however, often these models are complex and lack interpretability. Results We investigate whether a simple, fully interpretable linear model can achieve competitive performance for DTI prediction. We propose Linear Interpretable Drug-Target Interaction (LI-DTI), a prediction model inspired by recommender systems. LI-DTI learns from different drug-drug and target-target similarity matrices and provides interpretable predictions as a linear combination of these similarity measures. We show that LI-DTI can recover DTIs even when drugs or targets have no previously known interactions, across multiple cross-validation settings. We further evaluate performance while mitigating potential bias arising from high chemical similarity between drugs or sequence similarity between targets. Finally, we assess LI-DTI in a prospective evaluation, training on DTIs present in DrugBank from 2011 and testing on interactions added through 2022. Across all evaluations, LI-DTI achieves state-of-the-art performance while producing interpretable predictions. For practical use, we provide a web-based tool that enables users to visualize individual LI-DTI predictions for DrugBank (2025) and inspect the biological evidence underlying them. Our results indicate that simple linear models with well-curated similarity features can deliver robust and interpretable DTI predictions, facilitating hypothesis generation and downstream experimental prioritization. Availability and implementation Code and data available at https://github.com/paccanarolab/LI-DTI. Web tool available at https://paccanarolab.org/lidtiweb/.

Multimodal deep learning with a joint uncertainty quantification scheme for drug-target interaction prediction.

Recent Advances in Deep Learning-Based Drug-Target Binding Affinity Prediction

It is indicated that although many methods report strong performance on standard benchmarks, their effectiveness is often influenced by dataset bias and limited evaluation settings, and most methods exhibit reduced performance in cold-start scenarios, highlighting challenges in generalization.

Prediction of Drug Target Interactions Based on Artificial Intelligence

Drug-target interaction (DTI) prediction is an efficient pre-screening method that uses algorithmic models to assess the binding potential of drug molecules to protein targets. Current research is accelerating towards the integration of heterogeneous graph neural networks, protein language models, and generative artificial intelligence. This review systematically summarizes the latest developments in these technologies, pointing out the problems currently being addressed in research such as data sparsity and cold start, as well as the manifestations of general machine learning challenges such as recommendation systems and noise learning in the biomedical field; Interpret representative models such as Dual Heterogeneous Graph Transformer for Drug-Target Interaction (DHGT-DTI) and Graph Positional encoding and Sequence features for Drug-Target Interaction (GPS-DTI). The combination of dual perspective learning, equivariant graph convolution, and attention mechanism enhances the understanding and reasoning ability of these models in complex biological networks. The generative artificial intelligence diffusion model has opened up a path for developing new drugs through structured and data enhanced approaches. Research has shown that important issues related to computational performance, interpretability, and data compatibility still need to be addressed in existing models. Building a high-performance, multifunctional pre trained model for large-scale biomolecules should be a key direction for development.