A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood?

• URL: http://arxiv.org/abs/2605.24045v1
• Date: Thu, 21 May 2026 20:50:03 GMT
• Title: A Large-Scale Dataset and Benchmark: Do Protein-Ligand Models Learn Binding Sites or Just Binding Likelihood?
• Abstract summary: We introduce InteractBind, a large-scale protein-ligand dataset comprising approximately 100k protein-ligand pairs.<n>The core fine-grained task is that of binding-site localization.<n>We evaluate eight existing sequence-based and interaction-aware models, assessing binary binding prediction and binding-site localization.
• Score: 29.589714550752348
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Protein-ligand modeling underpins computational drug discovery and molecular design. Existing protein-ligand benchmarks typically evaluate whether a protein and ligand interact and how strongly they bind, through tasks such as binary binding prediction and affinity regression. However, these evaluations provide limited evidence of whether models can localize binding sites or identify the non-covalent interactions underlying molecular recognition. To address this gap, we introduce InteractBind, a large-scale protein-ligand dataset comprising approximately 100k protein-ligand pairs, together with a benchmark for fine-grained evaluation. The core fine-grained task is that of binding-site localization, which uses protein-residue and ligand-atom interaction maps spanning six major types of non-covalent interactions to assess whether model-derived interaction maps localize binding sites. InteractBind further includes binding affinity and protein similarity-controlled splits to support realistic generalization assessment. Using InteractBind, we evaluate eight existing sequence-based and interaction-aware models, assessing binary binding prediction and binding-site localization. Results reveal limited binding-site localization despite strong binary binding prediction, with marked variation across non-covalent interaction types. Overall, InteractBind establishes a benchmark paradigm that encourages the development of more interpretable and physically grounded protein-ligand models.

Related papers

• K-Models: a Flexible and Interpretable Method for Ordinal Clustering with Application to Antigen-Antibody Interaction Profiles [65.21921642886367]
  K-Models is a novel framework that integrates ordinal constraints and estimates key underlying elements of the random process generating the observed functional profiles.<n>The proposed method is evaluated through simulations and real-world applications.
  arXiv  Detail & Related papers  (2026-05-14T13:35:44Z)
• An Interpretable Framework Applying Protein Words to Predict Protein-Small Molecule Complementary Pairing Rules [1.0775419935941009]
  We develop a framework to improve interpretability of protein-small molecule binding predictions.<n> PWRules applies binding affinity data to identify privileged small molecule fragments.<n>It then defines complementary pairing rules between these fragments and protein words.<n>The resulting word-fragment rules are ranked by the PWScore function to prioritize active compounds.
  arXiv  Detail & Related papers  (2026-04-17T06:56:00Z)
• PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs [88.98041407783502]
  PRING is the first benchmark that evaluates protein-protein interaction prediction from a graph-level perspective.<n> PRING curates a high-quality, multi-species PPI network dataset comprising 21,484 proteins and 186,818 interactions.
  arXiv  Detail & Related papers  (2025-07-07T15:21:05Z)
• 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)
• CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction [23.1499716310298]
  We build the largest protein-RNA binding affinity dataset PRA310 for performance evaluation.<n>We provide extensive analyses and verify that CoPRA can (1) accurately predict the protein-RNA binding affinity; (2) understand the binding affinity change caused by mutations; and (3) benefit from scaling data and model size.
  arXiv  Detail & Related papers  (2024-08-21T09:48:22Z)
• Protein-ligand binding representation learning from fine-grained interactions [29.965890962846093]
  We propose to learn protein-ligand binding representation in a self-supervised learning manner. This self-supervised learning problem is formulated as a prediction of the conclusive binding complex structure. Experiments have demonstrated the superiority of our method across various binding tasks.
  arXiv  Detail & Related papers  (2023-11-09T01:33:09Z)
• State-specific protein-ligand complex structure prediction with a multi-scale deep generative model [68.28309982199902]
  We present NeuralPLexer, a computational approach that can directly predict protein-ligand complex structures. Our study suggests that a data-driven approach can capture the structural cooperativity between proteins and small molecules, showing promise in accelerating the design of enzymes, drug molecules, and beyond.
  arXiv  Detail & Related papers  (2022-09-30T01:46:38Z)
• Predicting Protein-Ligand Binding Affinity via Joint Global-Local Interaction Modeling [34.18714126231236]
  We propose a novel global-local interaction framework to predict protein-ligand binding affinity. Our framework embeds the long-range interactions globally and aggregates local short-range interactions, respectively. Experiments demonstrate that our GLI framework outperforms state-of-the-art methods with simple neural network architectures and moderate computational costs.
  arXiv  Detail & Related papers  (2022-09-18T10:17:05Z)
• Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity [52.67037774136973]
  Drug discovery often relies on the successful prediction of protein-ligand binding affinity. Recent advances have shown great promise in applying graph neural networks (GNNs) for better affinity prediction by learning the representations of protein-ligand complexes. We propose a structure-aware interactive graph neural network (SIGN) which consists of two components: polar-inspired graph attention layers (PGAL) and pairwise interactive pooling (PiPool)
  arXiv  Detail & Related papers  (2021-07-21T03:34:09Z)
• InteractionNet: Modeling and Explaining of Noncovalent Protein-Ligand Interactions with Noncovalent Graph Neural Network and Layer-Wise Relevance Propagation [0.0]
  We propose a graph neural network architecture to learn noncovalent protein-ligand interactions. We show that our model successfully predicted the noncovalent interactions in both performance and relevance in chemical interpretation.
  arXiv  Detail & Related papers  (2020-05-12T12:46:44Z)
• 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.