{
  "abstract": "Activity cliffs are pairs of closely related compounds whose potencies differ far more than their structures suggest, and the compounds involved in them remain a leading cause of local failure in ligand-based potency prediction. The MoleculeACE benchmark established that models predict these compounds poorly and that the gap differs between datasets. What has been missing is a panel built on one activity endpoint, a per-target account of how large the gap is, and a measurement of how far it depends on the way the model is chosen. We curated inhibition constant (Ki) data for 33 human protein targets from ChEMBL release 37 and BindingDB and annotated activity cliffs using the MoleculeACE criteria. Sixteen descriptor and algorithm combinations per target were trained to predict potency and scored separately on cliff compounds, with the winner chosen by five-fold cross-validation inside the training set. Cliff frequency ranged from 3.95% to 61.34%. Error on cliff compounds exceeded global error for 26 of 33 targets, by 12.8% on average (Wilcoxon p = 3.4 × 10−5), with a range from an 8.0% reduction to a 122.0% increase. Choosing the model on the test set instead inflated apparent cliff accuracy by 0.119 pKi units and the number of targets that showed lower cliff-specific error than global error fell from 14 to seven once selection was corrected. Cliff-specific error has to be measured per target and quoted with the size of the subset it rests on.",
  "abstract_shown": true,
  "affiliations": [
    "SilicoScientia Private Limited (Registered Office), Nagananda Commercial Complex, No. 07/3, 15/1, 18th Main Road, Jayanagar 9th Block, Bengaluru 560 041, India",
    "SilicoScientia Private Limited (Corporate Office), Centre for Cellular and Molecular Platforms (C-CAMP), GKVK Campus, Bellary Road, Bengaluru 560 065, India",
    "School of Pharmacy and Research, Dnyaan Prasad Global University, Pune 411 018, India",
    "Dr. D. Y. Patil Institute of Pharmaceutical Sciences and Research, Pune 411 018, India",
    "Department of Pharmaceutical and Biological Chemistry, School of Pharmacy, University College London, London WC1N 1AX, UK",
    "SR University, Warangal, Telangana 506 371, India"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0,
        1,
        2,
        3
      ],
      "name": "Mohammed Musallam Mohammed Alamri",
      "orcid": "0009-0004-7433-270X"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Shovonlal Bhowmick"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Ritesh P. Bhole",
      "orcid": "0000-0003-4088-7470"
    },
    {
      "affs": [
        4
      ],
      "name": "Rupesh Chikhale",
      "orcid": "0000-0001-5622-3981"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Payal R. Kute"
    },
    {
      "affs": [
        0,
        1,
        5
      ],
      "name": "Md Ataul Islam"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6jth9wckn5xqy.bib",
  "cited_by": 0,
  "doi": "10.3390/ijms272210230",
  "fulltext_url": null,
  "id": "6jth9wckn5xqy",
  "issns": [
    "1422-0067"
  ],
  "landing_url": "https://www.mdpi.com/1422-0067/27/22/10230",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-14",
  "publisher": "MDPI AG",
  "ris": "https://research.draconitic.com/paper/6jth9wckn5xqy.ris",
  "sources": [
    {
      "first_seen": "2026-11-16T12:24:18Z",
      "native_id": "10.3390/ijms272210230",
      "source": "crossref",
      "url": "https://www.mdpi.com/1422-0067/27/22/10230"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "issn:1422-0067",
      "subfield": "general"
    }
  ],
  "title": "Target-Specific Benchmarking of Potency Prediction on Activity-Cliff Compounds Across 33 Human Protein Targets Using Inhibition Constants",
  "title_text": "Target-Specific Benchmarking of Potency Prediction on Activity-Cliff Compounds Across 33 Human Protein Targets Using Inhibition Constants",
  "type": "peer-reviewed",
  "updated_at": "2026-11-16T12:24:18Z",
  "url": "https://research.draconitic.com/paper/6jth9wckn5xqy",
  "venue": "International Journal of Molecular Sciences",
  "versions": []
}