Learning to Align Molecules and Proteins: A Geometry-Aware Approach to Binding Affinity

• URL: http://arxiv.org/abs/2509.20693v1
• Date: Thu, 25 Sep 2025 02:55:24 GMT
• Title: Learning to Align Molecules and Proteins: A Geometry-Aware Approach to Binding Affinity
• Authors: Mohammadsaleh Refahi, Bahrad A. Sokhansanj, James R. Brown, Gail Rosen,
• Abstract summary: FIRM-DTI is a lightweight framework that conditions molecular embeddings on protein embeddings through a feature-wise linear modulation layer.<n>An RBF regression head operating on embedding distances yields smooth, interpretable affinity predictions.<n>Our results underscore the value of conditioning and metric learning for robust drug-target affinity prediction.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate prediction of drug-target binding affinity can accelerate drug discovery by prioritizing promising compounds before costly wet-lab screening. While deep learning has advanced this task, most models fuse ligand and protein representations via simple concatenation and lack explicit geometric regularization, resulting in poor generalization across chemical space and time. We introduce FIRM-DTI, a lightweight framework that conditions molecular embeddings on protein embeddings through a feature-wise linear modulation (FiLM) layer and enforces metric structure with a triplet loss. An RBF regression head operating on embedding distances yields smooth, interpretable affinity predictions. Despite its modest size, FIRM-DTI achieves state-of-the-art performance on the Therapeutics Data Commons DTI-DG benchmark, as demonstrated by an extensive ablation study and out-of-domain evaluation. Our results underscore the value of conditioning and metric learning for robust drug-target affinity prediction.

Related papers

• S$^2$Drug: Bridging Protein Sequence and 3D Structure in Contrastive Representation Learning for Virtual Screening [72.89086338778098]
  We propose a two-stage framework for protein-ligand contrastive representation learning.<n>In the first stage, we perform protein sequence pretraining on ChemBL using an ESM2-based backbone.<n>In the second stage, we fine-tune on PDBBind by fusing sequence and structure information through a residue-level gating module.<n>This auxiliary task guides the model to accurately localize binding residues within the protein sequence and capture their 3D spatial arrangement.
  arXiv  Detail & Related papers  (2025-11-10T11:57:47Z)
• Structure-Aware Contrastive Learning with Fine-Grained Binding Representations for Drug Discovery [3.1716746406651457]
  This work introduces a sequence-based drug-target interaction framework that integrates structural priors into protein representations.<n>The model achieves state-of-the-art performance on Human and BioSNAP datasets and remains competitive on BindingDB.
  arXiv  Detail & Related papers  (2025-09-18T09:38:46Z)
• A Geometric Graph-Based Deep Learning Model for Drug-Target Affinity Prediction [0.0]
  We introduce DeepGGL, a deep convolutional neural network that integrates residual connections and an attention mechanism within a geometric graph learning framework.<n>By leveraging multiscale weighted colored bipartite subgraphs, DeepGGL effectively captures fine-grained atom-level interactions in protein-ligand complexes across multiple scales.<n>DeepGGL consistently maintained high predictive accuracy, highlighting its adaptability and reliability for binding affinity prediction in structure-based drug discovery.
  arXiv  Detail & Related papers  (2025-09-15T14:06:39Z)
• KEPLA: A Knowledge-Enhanced Deep Learning Framework for Accurate Protein-Ligand Binding Affinity Prediction [60.23701115249195]
  KEPLA is a novel deep learning framework that integrates prior knowledge from Gene Ontology and ligand properties to enhance prediction performance.<n> Experiments on two benchmark datasets demonstrate that KEPLA consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-06-16T08:02:42Z)
• SE(3)-Equivariant Ternary Complex Prediction Towards Target Protein Degradation [28.648225112411637]
  Targeted protein degradation (TPD) induced by small molecules has emerged as a rapidly evolving modality in drug discovery.<n>DeepTernary is a novel deep learning-based approach that directly predicts ternary structures in an end-to-end manner.
  arXiv  Detail & Related papers  (2025-02-26T06:33:24Z)
• MIN: Multi-channel Interaction Network for Drug-Target Interaction with Protein Distillation [64.4838301776267]
  Multi-channel Interaction Network (MIN) is a novel framework designed to predict drug-target interaction (DTI)<n>MIN incorporates a representation learning module and a multi-channel interaction module.<n>MIN is not only a potent tool for DTI prediction but also offers fresh insights into the prediction of protein binding sites.
  arXiv  Detail & Related papers  (2024-11-23T05:38:36Z)
• Binding Affinity Prediction: From Conventional to Machine Learning-Based Approaches [48.66541987908136]
  Much work has been devoted to predicting binding affinity over the past decades.<n>We note growing use of both traditional machine learning and deep learning models for predicting binding affinity.<n>With improved predictive performance and the FDA's phasing out of animal testing, AI-driven in silico models, such as AI virtual cells (AIVCs), are poised to advance binding affinity prediction.
  arXiv  Detail & Related papers  (2024-09-30T03:40:49Z)
• ResDTA: Predicting Drug-Target Binding Affinity Using Residual Skip Connections [0.0]
  We present a deep learning-based methodology for predicting DT binding affinities using just sequencing information from both targets and drugs. The proposed model achieves the best Concordance Index (CI) performance in one of the largest benchmark datasets.
  arXiv  Detail & Related papers  (2023-03-20T20:27:11Z)
• From Static to Dynamic Structures: Improving Binding Affinity Prediction with Graph-Based Deep Learning [40.83037811977803]
  Dynaformer is a graph-based deep learning model developed to predict protein-ligand binding affinities. It exhibits state-of-the-art scoring and ranking power on the CASF-2016 benchmark dataset. In a virtual screening on heat shock protein 90 (HSP90), 20 candidates are identified and their binding affinities are experimentally validated.
  arXiv  Detail & Related papers  (2022-08-19T14:55:12Z)
• SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity Prediction [127.43571146741984]
  Drug-Target Affinity (DTA) is of vital importance in early-stage drug discovery. wet experiments remain the most reliable method, but they are time-consuming and resource-intensive. Existing methods have primarily focused on developing techniques based on the available DTA data, without adequately addressing the data scarcity issue. We present the SSM-DTA framework, which incorporates three simple yet highly effective strategies.
  arXiv  Detail & Related papers  (2022-06-20T14:53:25Z)
• Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts [80.69440684790925]
  DeepRelations is a physics-inspired deep relational network with intrinsically explainable architecture. It shows superior interpretability to the state-of-the-art. It boosts the AUPRC of contact prediction 9.5, 16.9, 19.3 and 5.7-fold for the test, compound-unique, protein-unique, and both-unique sets.
  arXiv  Detail & Related papers  (2019-12-29T00:14:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.