Interaction Concordance Index: Performance Evaluation for Interaction Prediction Methods

• URL: http://arxiv.org/abs/2510.14419v1
• Date: Thu, 16 Oct 2025 08:24:16 GMT
• Title: Interaction Concordance Index: Performance Evaluation for Interaction Prediction Methods
• Authors: Tapio Pahikkala, Riikka Numminen, Parisa Movahedi, Napsu Karmitsa, Antti Airola,
• Abstract summary: We introduce interaction directions' prediction performance estimator (IC-index) for both fixed predictors and machine learning algorithms.<n>IC-index complements the popularly used DTA prediction performance estimators by evaluating the ratio of correctly predicted directions of interaction effects in data.<n>We make a comprehensive empirical evaluation over several biomedical interaction data sets with various state-of-the-art machine learning algorithms.
• Score: 0.7176906280023595
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Consider two sets of entities and their members' mutual affinity values, say drug-target affinities (DTA). Drugs and targets are said to interact in their effects on DTAs if drug's effect on it depends on the target. Presence of interaction implies that assigning a drug to a target and another drug to another target does not provide the same aggregate DTA as the reversed assignment would provide. Accordingly, correctly capturing interactions enables better decision-making, for example, in allocation of limited numbers of drug doses to their best matching targets. Learning to predict DTAs is popularly done from either solely from known DTAs or together with side information on the entities, such as chemical structures of drugs and targets. In this paper, we introduce interaction directions' prediction performance estimator we call interaction concordance index (IC-index), for both fixed predictors and machine learning algorithms aimed for inferring them. IC-index complements the popularly used DTA prediction performance estimators by evaluating the ratio of correctly predicted directions of interaction effects in data. First, we show the invariance of IC-index on predictors unable to capture interactions. Secondly, we show that learning algorithm's permutation equivariance regarding drug and target identities implies its inability to capture interactions when either drug, target or both are unseen during training. In practical applications, this equivariance is remedied via incorporation of appropriate side information on drugs and targets. We make a comprehensive empirical evaluation over several biomedical interaction data sets with various state-of-the-art machine learning algorithms. The experiments demonstrate how different types of affinity strength prediction methods perform in terms of IC-index complementing existing prediction performance estimators.

Related papers

• Constructing Confidence Intervals for Average Treatment Effects from Multiple Datasets [51.2467404472005]
  We propose a new method that estimates the ATE from multiple observational datasets and provides valid CIs.<n>Our method makes little assumptions about the observational datasets and is thus widely applicable in medical practice.
  arXiv  Detail & Related papers  (2024-12-16T07:39:46Z)
• A Cross-Field Fusion Strategy for Drug-Target Interaction Prediction [85.2792480737546]
  Existing methods fail to utilize global protein information during DTI prediction. Cross-field information fusion strategy is employed to acquire local and global protein information. Siamese drug-target interaction SiamDTI prediction method achieves higher accuracy levels than other state-of-the-art (SOTA) methods on novel drugs and targets.
  arXiv  Detail & Related papers  (2024-05-23T13:25:20Z)
• Learning to Denoise Biomedical Knowledge Graph for Robust Molecular Interaction Prediction [50.7901190642594]
  We propose BioKDN (Biomedical Knowledge Graph Denoising Network) for robust molecular interaction prediction. BioKDN refines the reliable structure of local subgraphs by denoising noisy links in a learnable manner. It maintains consistent and robust semantics by smoothing relations around the target interaction.
  arXiv  Detail & Related papers  (2023-12-09T07:08:00Z)
• Zero-shot causal learning [64.9368337542558]
  CaML is a causal meta-learning framework which formulates the personalized prediction of each intervention's effect as a task. We show that CaML is able to predict the personalized effects of novel interventions that do not exist at the time of training.
  arXiv  Detail & Related papers  (2023-01-28T20:14:11Z)
• Parallel Reasoning Network for Human-Object Interaction Detection [53.422076419484945]
  We propose a new transformer-based method named Parallel Reasoning Network(PR-Net) PR-Net constructs two independent predictors for instance-level localization and relation-level understanding. Our PR-Net has achieved competitive results on HICO-DET and V-COCO benchmarks.
  arXiv  Detail & Related papers  (2023-01-09T17:00:34Z)
• Interpretable bilinear attention network with domain adaptation improves drug-target prediction [4.15790071124993]
  DrugBAN is a deep bilinear attention network framework with domain adaptation to learn pair-wise local interactions between drugs and targets. DrugBAN works on drug molecular graphs and target protein sequences to perform prediction. Experiments on three benchmark datasets show that DrugBAN achieves the best overall performance against five state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-08-03T16:27:29Z)
• 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)
• An Interpretable Framework for Drug-Target Interaction with Gated Cross Attention [4.746451824931381]
  In this study, we propose a novel interpretable framework that can provide reasonable cues for the interaction sites. We elaborately design a gated cross-attention mechanism that crossly attends drug and target features by constructing explicit interactions between these features. The experimental results show the efficacy of the proposed method in two DTI datasets.
  arXiv  Detail & Related papers  (2021-09-17T05:53:40Z)
• Optimizing Area Under the Curve Measures via Matrix Factorization for Drug-Target Interaction Prediction [7.385579678137434]
  This paper proposes two matrix factorization methods that optimize the area under the precision-recall curve (AUPR) and the receiver operating characteristic curve (AUC) Experimental results over four updated benchmark datasets show the superiority of the proposed methods in terms of the corresponding evaluation metric they optimize.
  arXiv  Detail & Related papers  (2021-05-01T14:48:32Z)
• Drug-Target Interaction Prediction via an Ensemble of Weighted Nearest Neighbors with Interaction Recovery [5.8683934849211745]
  Drug-target interactions are predicted via structure-based drug similarities and sequence-based target protein similarities. Most existing similarity-based methods follow the transductive setting. A large amount of missing interactions in current DTI datasets hinders most DTI prediction methods. We propose a new method denoted as Weighted k Nearest Neighbor with Interaction Recovery (WkNNIR)
  arXiv  Detail & Related papers  (2020-12-22T19:54:18Z)
• DTI-SNNFRA: Drug-Target interaction prediction by shared nearest neighbors and fuzzy-rough approximation [0.0]
  We have proposed DTI-SNNFRA, a framework for predicting drug-target interaction (DTI) based on shared nearest neighbour (SNN) and fuzzy-rough approximation (FRA) The model performs exceptionally well with a high prediction score of 0.95 for ROC-AUC.
  arXiv  Detail & Related papers  (2020-09-22T19:10:10Z)

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.