{"entity": "researcher", "timestamp": "2026-08-20T20:51:28.260Z", "family": "Norinder", "given": "Ulf", "initials": "U", "orcid": "0000-0003-3107-331X", "affiliations": ["Department of Computer and Systems Sciences, Stockholm University, Box 7003, SE-164 07 Kista, Sweden.", "Department of Pharmaceutical Biosciences, Uppsala University, Box 591, SE-75124 Uppsala, Sweden.", "MTM Research Centre, School of Science and Technology, \u00d6rebro University, SE-70182 \u00d6rebro, Sweden."], "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/researcher/da36a1cdadab4126b4e2527721ac2710.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/researcher/da36a1cdadab4126b4e2527721ac2710"}}, "publications": [{"entity": "publication", "iuid": "827e1ae7e9be4cc6ad1f407a349a0fb6", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/827e1ae7e9be4cc6ad1f407a349a0fb6.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/827e1ae7e9be4cc6ad1f407a349a0fb6"}}, "title": "Safe-and-sustainable-by-design approach to polyesters from non-oestrogenic bisphenols", "authors": [{"family": "Margarita", "given": "Cristiana", "initials": "C", "orcid": "0000-0003-2897-4678", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/d51cf9cbdba24e45876a17c8fbc3e8cd.json"}}, {"family": "Pierozan", "given": "Paula", "initials": "P"}, {"family": "Subramaniyan", "given": "Sathiyaraj", "initials": "S", "orcid": "0000-0002-2477-6896", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/ee3e646506284d49a0d58b68b09f8719.json"}}, {"family": "Shatskiy", "given": "Andrey", "initials": "A", "orcid": "0000-0002-7249-7437", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/535bd09b27c04244b4a313c763eb6b0f.json"}}, {"family": "Pakarinen", "given": "Darius", "initials": "D", "orcid": "0009-0004-4003-7147", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/f2d3fb6804ce427686d083135a7915d6.json"}}, {"family": "Fritz", "given": "Annabelle", "initials": "A", "orcid": "0009-0004-3378-4494", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/ee17cf0db38f47779895b45271515317.json"}}, {"family": "Lundqvist", "given": "Emma", "initials": "E", "orcid": "0009-0000-0491-3649", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/024d9dde801c4edda4dcb3db2aa739ed.json"}}, {"family": "Chu", "given": "Victoria", "initials": "V"}, {"family": "Hagelin", "given": "Hampus", "initials": "H", "orcid": "0009-0009-0643-8285", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/aae97b84d8284f178651884af3677ef5.json"}}, {"family": "Norinder", "given": "Ulf", "initials": "U", "orcid": "0000-0003-3107-331X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/da36a1cdadab4126b4e2527721ac2710.json"}}, {"family": "Hakkarainen", "given": "Minna", "initials": "M", "orcid": "0000-0002-7790-8987", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/9d855814ea154871b096568c3e1d66a6.json"}}, {"family": "Karlsson", "given": "Oskar", "initials": "O", "orcid": "0000-0001-8009-0015", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/9e8bc211d3eb432a877e1f32671e6aa8.json"}}, {"family": "Lundberg", "given": "Helena", "initials": "H", "orcid": "0000-0002-4704-1892", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/8fd852b1231c40f094df0e5c9461efcc.json"}}], "type": "journal-article", "published": "2025-12-04", "journal": {"title": "Nat Sustain", "issn": "2398-9629", "volume": "9", "issue": "1", "pages": "86-95", "issn-l": null}, "abstract": null, "doi": "10.1038/s41893-025-01672-z", "pmid": null, "labels": [], "xrefs": [], "notes": [], "created": "2026-08-20T09:24:40.591Z", "modified": "2026-08-20T09:24:40.925Z"}, {"entity": "publication", "iuid": "8fa6d5080eed445db64b8858f99b66d8", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/8fa6d5080eed445db64b8858f99b66d8.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/8fa6d5080eed445db64b8858f99b66d8"}}, "title": "CPSign - Conformal Prediction for Cheminformatics Modeling", "authors": [{"family": "McShane", "given": "Staffan Arvidsson", "initials": "SA", "orcid": "0000-0001-6709-7116", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/1529ee0acadb4f76bff770775ebd633b.json"}}, {"family": "Norinder", "given": "Ulf", "initials": "U", "orcid": "0000-0003-3107-331X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/da36a1cdadab4126b4e2527721ac2710.json"}}, {"family": "Alvarsson", "given": "Jonathan", "initials": "J", "orcid": "0000-0002-8682-7206", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/9415021fa24f47cf88a63d0cf805940c.json"}}, {"family": "Ahlberg", "given": "Ernst", "initials": "E", "orcid": "0000-0003-2050-9069", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a1f7735d80084774801a46b57aad5228.json"}}, {"family": "Carlsson", "given": "Lars", "initials": "L"}, {"family": "Spjuth", "given": "Ola", "initials": "O", "orcid": "0000-0002-8083-2864", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/2c192389f99d4801b91f3350e07dfb9e.json"}}], "type": "posted-content", "published": "2023-11-22", "journal": {"issn-l": null}, "abstract": null, "doi": "10.1101/2023.11.21.568108", "pmid": null, "labels": [], "xrefs": [], "notes": [], "created": "2026-08-20T10:50:29.137Z", "modified": "2026-08-20T10:50:29.223Z"}, {"entity": "publication", "iuid": "f92c4c8ab14c4be38124377c6a4f8305", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/f92c4c8ab14c4be38124377c6a4f8305.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/f92c4c8ab14c4be38124377c6a4f8305"}}, "title": "Synergy conformal prediction applied to large-scale bioactivity datasets and in federated learning.", "authors": [{"family": "Norinder", "given": "Ulf", "initials": "U", "orcid": "0000-0003-3107-331X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/da36a1cdadab4126b4e2527721ac2710.json"}}, {"family": "Spjuth", "given": "Ola", "initials": "O", "orcid": "0000-0002-8083-2864", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/2c192389f99d4801b91f3350e07dfb9e.json"}}, {"family": "Svensson", "given": "Fredrik", "initials": "F", "orcid": "0000-0002-5556-8133", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/10109223892d4924bbf4986bf71a7846.json"}}], "type": "journal article", "published": "2021-10-02", "journal": {"title": "J Cheminform", "issn": "1758-2946", "volume": "13", "issue": "1", "pages": "77", "issn-l": "1758-2946"}, "abstract": "Confidence predictors can deliver predictions with the associated confidence required for decision making and can play an important role in drug discovery and toxicity predictions. In this work we investigate a recently introduced version of conformal prediction, synergy conformal prediction, focusing on the predictive performance when applied to bioactivity data. We compare the performance to other variants of conformal predictors for multiple partitioned datasets and demonstrate the utility of synergy conformal predictors for federated learning where data cannot be pooled in one location. Our results show that synergy conformal predictors based on training data randomly sampled with replacement can compete with other conformal setups, while using completely separate training sets often results in worse performance. However, in a federated setup where no method has access to all the data, synergy conformal prediction is shown to give promising results. Based on our study, we conclude that synergy conformal predictors are a valuable addition to the conformal prediction toolbox.", "doi": "10.1186/s13321-021-00555-7", "pmid": "34600569", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC8487527"}, {"db": "pii", "key": "10.1186/s13321-021-00555-7"}], "notes": [], "created": "2026-08-20T12:22:17.942Z", "modified": "2026-08-20T12:22:18.027Z"}, {"entity": "publication", "iuid": "a1fc2da7a42345749830afe15318d35f", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/a1fc2da7a42345749830afe15318d35f.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/a1fc2da7a42345749830afe15318d35f"}}, "title": "Assessing the calibration in toxicological in vitro models with conformal prediction.", "authors": [{"family": "Morger", "given": "Andrea", "initials": "A"}, {"family": "Svensson", "given": "Fredrik", "initials": "F", "orcid": "0000-0002-5556-8133", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/10109223892d4924bbf4986bf71a7846.json"}}, {"family": "Arvidsson McShane", "given": "Staffan", "initials": "S", "orcid": "0000-0001-6709-7116", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/1529ee0acadb4f76bff770775ebd633b.json"}}, {"family": "Gauraha", "given": "Niharika", "initials": "N"}, {"family": "Norinder", "given": "Ulf", "initials": "U", "orcid": "0000-0003-3107-331X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/da36a1cdadab4126b4e2527721ac2710.json"}}, {"family": "Spjuth", "given": "Ola", "initials": "O", "orcid": "0000-0002-8083-2864", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/2c192389f99d4801b91f3350e07dfb9e.json"}}, {"family": "Volkamer", "given": "Andrea", "initials": "A", "orcid": "0000-0002-3760-580X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/bf1623a6e5b048589ac7968ee1b50a13.json"}}], "type": "journal article", "published": "2021-04-29", "journal": {"title": "J Cheminform", "issn": "1758-2946", "volume": "13", "issue": "1", "pages": "35", "issn-l": "1758-2946"}, "abstract": "Machine learning methods are widely used in drug discovery and toxicity prediction. While showing overall good performance in cross-validation studies, their predictive power (often) drops in cases where the query samples have drifted from the training data's descriptor space. Thus, the assumption for applying machine learning algorithms, that training and test data stem from the same distribution, might not always be fulfilled. In this work, conformal prediction is used to assess the calibration of the models. Deviations from the expected error may indicate that training and test data originate from different distributions. Exemplified on the Tox21 datasets, composed of chronologically released Tox21Train, Tox21Test and Tox21Score subsets, we observed that while internally valid models could be trained using cross-validation on Tox21Train, predictions on the external Tox21Score data resulted in higher error rates than expected. To improve the prediction on the external sets, a strategy exchanging the calibration set with more recent data, such as Tox21Test, has successfully been introduced. We conclude that conformal prediction can be used to diagnose data drifts and other issues related to model calibration. The proposed improvement strategy-exchanging the calibration data only-is convenient as it does not require retraining of the underlying model.", "doi": "10.1186/s13321-021-00511-5", "pmid": "33926567", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC8082859"}, {"db": "pii", "key": "10.1186/s13321-021-00511-5"}], "notes": [], "created": "2026-08-20T12:22:16.174Z", "modified": "2026-08-20T12:23:44.448Z"}, {"entity": "publication", "iuid": "ce71a0f88896406883baaaa8ed534c6d", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/ce71a0f88896406883baaaa8ed534c6d.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/ce71a0f88896406883baaaa8ed534c6d"}}, "title": "Using Predicted Bioactivity Profiles to Improve Predictive Modeling.", "authors": [{"family": "Norinder", "given": "Ulf", "initials": "U", "orcid": "0000-0003-3107-331X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/da36a1cdadab4126b4e2527721ac2710.json"}}, {"family": "Spjuth", "given": "Ola", "initials": "O", "orcid": "0000-0002-8083-2864", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/2c192389f99d4801b91f3350e07dfb9e.json"}}, {"family": "Svensson", "given": "Fredrik", "initials": "F", "orcid": "0000-0002-5556-8133", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/10109223892d4924bbf4986bf71a7846.json"}}], "type": "journal article", "published": "2020-06-22", "journal": {"title": "J Chem Inf Model", "issn": "1549-960X", "volume": "60", "issue": "6", "pages": "2830-2837", "issn-l": "1549-9596"}, "abstract": "Predictive modeling is a cornerstone in early drug development. Using information for multiple domains or across prediction tasks has the potential to improve the performance of predictive modeling. However, aggregating data often leads to incomplete data matrices that might be limiting for modeling. In line with previous studies, we show that by generating predicted bioactivity profiles, and using these as additional features, prediction accuracy of biological endpoints can be improved. Using conformal prediction, a type of confidence predictor, we present a robust framework for the calculation of these profiles and the evaluation of their impact. We report on the outcomes from several approaches to generate the predicted profiles on 16 datasets in cytotoxicity and bioactivity and show that efficiency is improved the most when including the p-values from conformal prediction as bioactivity profiles.", "doi": "10.1021/acs.jcim.0c00250", "pmid": "32374618", "labels": [], "xrefs": [], "notes": [], "created": "2026-08-20T08:10:19.854Z", "modified": "2026-08-20T08:10:19.988Z"}]}