Enhancing the confidence of potential targets enriched by similarity-centric models: the crucial role of the similarity threshold

BackgroundComputational target fishing (TF) tools have made tremendous progress in narrowing down the set of potential targets, thereby expediting time- and resource-consuming wet-lab experiments. Among these tools, similarity-centric TF methods are particularly prominent and extensively employed to...

Full description

Saved in:
Bibliographic Details
Main Authors: Ling-Fei Tong, You-Jin Ge, Su-Qing Yang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Pharmacology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fphar.2025.1574540/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849391404615204864
author Ling-Fei Tong
You-Jin Ge
Su-Qing Yang
author_facet Ling-Fei Tong
You-Jin Ge
Su-Qing Yang
author_sort Ling-Fei Tong
collection DOAJ
description BackgroundComputational target fishing (TF) tools have made tremendous progress in narrowing down the set of potential targets, thereby expediting time- and resource-consuming wet-lab experiments. Among these tools, similarity-centric TF methods are particularly prominent and extensively employed to guide target identification in modern research. Despite substantial progress, similarity-centric models still have significant limitations, particularly regarding the confidence of enriched targets.MethodsWe constructed several baseline similarity-based TF models to explore supplementary aspects that could enhance the confidence of enriched targets. A high-quality library was first constructed. Multiple fingerprint representations and scoring schemes were applied to construct individual or ensemble models. The leave-one-out-like cross-validation and rigorous validation metrics were used to measure the performance. Based on the performance under different conditions, multiple influential factors, focusing on the similarity threshold, were investigated.ResultsEvidence showed that the similarity between the query molecule and the reference ligands that bind to the target could serve as a quantitative measure of the target reliability. The distribution of effective similarity scores for TF was fingerprint-dependent. To highlight the identification of true positives by filtering background noise and to maximize reliability by balancing precision and recall, the corresponding similarity thresholds for each fingerprint type were identified. Furthermore, additional influential factors, including the choice of different fingerprints, the integration of different models, the target-ligand interaction profile, and the promiscuity of the query molecule, were investigated.ConclusionCollectively, our findings provide novel insights into enhancing the confidence of enriched targets by applying the similarity threshold and other perspectives. These results also lay the groundwork for developing more robust and reliable target prediction models in the future.
format Article
id doaj-art-9b8c3f0c24ec4e859e796cf663f68d50
institution Kabale University
issn 1663-9812
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Pharmacology
spelling doaj-art-9b8c3f0c24ec4e859e796cf663f68d502025-08-20T03:41:05ZengFrontiers Media S.A.Frontiers in Pharmacology1663-98122025-08-011610.3389/fphar.2025.15745401574540Enhancing the confidence of potential targets enriched by similarity-centric models: the crucial role of the similarity thresholdLing-Fei Tong0You-Jin Ge1Su-Qing Yang2Department of Pharmacy, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, Jiangxi, ChinaOffice of Drug Clinical Trials Institution, Nanchang People’s Hospital (The Third Hospital of Nanchang), Nanchang, Jiangxi, ChinaDepartment of Pharmacy, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, Jiangxi, ChinaBackgroundComputational target fishing (TF) tools have made tremendous progress in narrowing down the set of potential targets, thereby expediting time- and resource-consuming wet-lab experiments. Among these tools, similarity-centric TF methods are particularly prominent and extensively employed to guide target identification in modern research. Despite substantial progress, similarity-centric models still have significant limitations, particularly regarding the confidence of enriched targets.MethodsWe constructed several baseline similarity-based TF models to explore supplementary aspects that could enhance the confidence of enriched targets. A high-quality library was first constructed. Multiple fingerprint representations and scoring schemes were applied to construct individual or ensemble models. The leave-one-out-like cross-validation and rigorous validation metrics were used to measure the performance. Based on the performance under different conditions, multiple influential factors, focusing on the similarity threshold, were investigated.ResultsEvidence showed that the similarity between the query molecule and the reference ligands that bind to the target could serve as a quantitative measure of the target reliability. The distribution of effective similarity scores for TF was fingerprint-dependent. To highlight the identification of true positives by filtering background noise and to maximize reliability by balancing precision and recall, the corresponding similarity thresholds for each fingerprint type were identified. Furthermore, additional influential factors, including the choice of different fingerprints, the integration of different models, the target-ligand interaction profile, and the promiscuity of the query molecule, were investigated.ConclusionCollectively, our findings provide novel insights into enhancing the confidence of enriched targets by applying the similarity threshold and other perspectives. These results also lay the groundwork for developing more robust and reliable target prediction models in the future.https://www.frontiersin.org/articles/10.3389/fphar.2025.1574540/fulltarget predictiondrug–target interactionspolypharmacologydrug repositioningadverse effectssimilarity threshold
spellingShingle Ling-Fei Tong
You-Jin Ge
Su-Qing Yang
Enhancing the confidence of potential targets enriched by similarity-centric models: the crucial role of the similarity threshold
Frontiers in Pharmacology
target prediction
drug–target interactions
polypharmacology
drug repositioning
adverse effects
similarity threshold
title Enhancing the confidence of potential targets enriched by similarity-centric models: the crucial role of the similarity threshold
title_full Enhancing the confidence of potential targets enriched by similarity-centric models: the crucial role of the similarity threshold
title_fullStr Enhancing the confidence of potential targets enriched by similarity-centric models: the crucial role of the similarity threshold
title_full_unstemmed Enhancing the confidence of potential targets enriched by similarity-centric models: the crucial role of the similarity threshold
title_short Enhancing the confidence of potential targets enriched by similarity-centric models: the crucial role of the similarity threshold
title_sort enhancing the confidence of potential targets enriched by similarity centric models the crucial role of the similarity threshold
topic target prediction
drug–target interactions
polypharmacology
drug repositioning
adverse effects
similarity threshold
url https://www.frontiersin.org/articles/10.3389/fphar.2025.1574540/full
work_keys_str_mv AT lingfeitong enhancingtheconfidenceofpotentialtargetsenrichedbysimilaritycentricmodelsthecrucialroleofthesimilaritythreshold
AT youjinge enhancingtheconfidenceofpotentialtargetsenrichedbysimilaritycentricmodelsthecrucialroleofthesimilaritythreshold
AT suqingyang enhancingtheconfidenceofpotentialtargetsenrichedbysimilaritycentricmodelsthecrucialroleofthesimilaritythreshold