{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T04:12:47Z","timestamp":1782274367503,"version":"3.54.5"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1011504","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T00:00:00Z","timestamp":1715299200000}}],"reference-count":26,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T00:00:00Z","timestamp":1714348800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012728","name":"Frederick National Laboratory for Cancer Research","doi-asserted-by":"publisher","award":["75N91019D00024"],"award-info":[{"award-number":["75N91019D00024"]}],"id":[{"id":"10.13039\/100012728","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>The use of deep learning (DL) is steadily gaining traction in scientific challenges such as cancer research. Advances in enhanced data generation, machine learning algorithms, and compute infrastructure have led to an acceleration in the use of deep learning in various domains of cancer research such as drug response problems. In our study, we explored tree-based models to improve the accuracy of a single drug response model and demonstrate that tree-based models such as XGBoost (eXtreme Gradient Boosting) have advantages over deep learning models, such as a convolutional neural network (CNN), for single drug response problems. However, comparing models is not a trivial task. To make training and comparing CNNs and XGBoost more accessible to users, we developed an open-source library called UNNT (A novel Utility for comparing Neural Net and Tree-based models). The case studies, in this manuscript, focus on cancer drug response datasets however the application can be used on datasets from other domains, such as chemistry.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1011504","type":"journal-article","created":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T13:43:06Z","timestamp":1714398186000},"page":"e1011504","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["UNNT: A novel Utility for comparing Neural Net and Tree-based models"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1382-8128","authenticated-orcid":true,"given":"Vineeth","family":"Gutta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2534-7548","authenticated-orcid":true,"given":"Satish Ranganathan","family":"Ganakammal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Jones","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9324-6429","authenticated-orcid":true,"given":"Matthew","family":"Beyers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3560-9428","authenticated-orcid":true,"given":"Sunita","family":"Chandrasekaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,4,29]]},"reference":[{"key":"pcbi.1011504.ref001","doi-asserted-by":"crossref","DOI":"10.3389\/fonc.2019.00984","article-title":"AI Meets Exascale Computing: Advancing Cancer Research With Large-Scale High Performance Computing","volume":"9","author":"T Bhattacharya","year":"2019","journal-title":"Frontiers in Oncology"},{"key":"pcbi.1011504.ref002","unstructured":"ECP-Candle-Benchmarks;. Available from: https:\/\/github.com\/ECP-CANDLE\/Benchmarks."},{"issue":"18","key":"pcbi.1011504.ref003","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1186\/s12859-018-2508-4","article-title":"CANDLE\/Supervisor: a workflow framework for machine learning applied to cancer research","volume":"19","author":"JM Wozniak","year":"2018","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"pcbi.1011504.ref004","doi-asserted-by":"crossref","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of Deep Learning: Concepts, CNN Architectures, challenges, applications, Future Directions","volume":"8","author":"L Alzubaidi","year":"2021","journal-title":"Journal of Big Data"},{"key":"pcbi.1011504.ref005","doi-asserted-by":"crossref","unstructured":"Shwartz-Ziv R, Armon A. Tabular Data: Deep Learning is Not All You Need. CoRR. 2021;abs\/2106.03253.","DOI":"10.1016\/j.inffus.2021.11.011"},{"key":"pcbi.1011504.ref006","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD\u201916. New York, NY, USA: ACM; 2016. p. 785\u2013794. Available from: http:\/\/doi.acm.org\/10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"key":"pcbi.1011504.ref007","unstructured":"Grinsztajn L, Oyallon E, Varoquaux G. Why do tree-based models still outperform deep learning on typical tabular data? In: Koyejo S, Mohamed S, Agarwal A, Belgrave D, Cho K, Oh A, editors. Advances in Neural Information Processing Systems. vol. 35. Curran Associates, Inc.; 2022. p. 507\u2013520. Available from: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/0378c7692da36807bdec87ab043cdadc-Paper-Datasets_and_Benchmarks.pdf."},{"key":"pcbi.1011504.ref008","first-page":"1","article-title":"Deep Neural Networks and Tabular Data: A Survey","author":"V Borisov","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"pcbi.1011504.ref009","unstructured":"McElfresh DC, Khandagale S, Valverde J, VishakPrasad C, Feuer B, Hegde C, et al. When Do Neural Nets Outperform Boosted Trees on Tabular Data? ArXiv. 2023;abs\/2305.02997."},{"issue":"11","key":"pcbi.1011504.ref010","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Y Lecun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"pcbi.1011504.ref011","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. ImageNet Classification with Deep Convolutional Neural Networks. In: Pereira F, Burges CJ, Bottou L, Weinberger KQ, editors. Advances in Neural Information Processing Systems. vol. 25. Curran Associates, Inc.; 2012. Available from: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2012\/file\/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf."},{"key":"pcbi.1011504.ref012","unstructured":"NVIDIA. cuDF;. Available from: https:\/\/github.com\/rapidsai\/cudf."},{"key":"pcbi.1011504.ref013","unstructured":"Dask;. Available from: https:\/\/github.com\/dask\/dask."},{"key":"pcbi.1011504.ref014","unstructured":"Institute NC. Predictive Oncology Model and Data Clearinghouse (MoDaC); 2023. Available from: https:\/\/modac.cancer.gov."},{"issue":"10","key":"pcbi.1011504.ref015","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1038\/nrc1951","article-title":"The NCI60 human tumour cell line Anticancer Drug Screen","volume":"6","author":"RH Shoemaker","year":"2006","journal-title":"Nature Reviews Cancer"},{"issue":"3","key":"pcbi.1011504.ref016","doi-asserted-by":"crossref","first-page":"lqaa078","DOI":"10.1093\/nargab\/lqaa078","article-title":"ComBat-seq: batch effect adjustment for RNA-seq count data","volume":"2","author":"Y Zhang","year":"2020","journal-title":"NAR Genomics and Bioinformatics"},{"issue":"D1","key":"pcbi.1011504.ref017","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkx911","article-title":"PharmacoDB: An integrative database for mining in vitro anticancer drug screening studies","volume":"46","author":"P Smirnov","year":"2017","journal-title":"Nucleic Acids Research"},{"key":"pcbi.1011504.ref018","unstructured":"CHEMOINFORMATICS K. Dragon (software for molecular descriptor calculation); 2017. Available from: https:\/\/chm.kode-solutions.net\/pf\/dragon-7-0\/."},{"key":"pcbi.1011504.ref019","unstructured":"Reinhold WC. NCI60 RNA-sequence gene expression value dataset;. Available from: https:\/\/discover.nci.nih.gov\/cellminer\/download\/processeddataset\/nci60_RNA__RNA_seq_composite_expression.zip."},{"key":"pcbi.1011504.ref020","unstructured":"NCI60 drug response dataset;. Available from: https:\/\/modac.cancer.gov\/api\/v2\/dataObject\/NCI_DOE_Archive\/JDACS4C\/JDACS4C_Pilot_1\/cancer_drug_response_prediction_dataset\/combined_single_response_agg."},{"key":"pcbi.1011504.ref021","unstructured":"NCI60 molecular drug descriptors dataset;. Available from: https:\/\/modac.cancer.gov\/api\/v2\/dataObject\/NCI_DOE_Archive\/JDACS4C\/JDACS4C_Pilot_1\/cancer_drug_response_prediction_dataset\/descriptors.2D-NSC.5dose.filtered.txt."},{"key":"pcbi.1011504.ref022","unstructured":"Subramanian A. Broad Institute Human L1000 epsilon;. Available from: https:\/\/www.ncbi.nlm.nih.gov\/geo\/query\/acc.cgi?acc=GPL20573."},{"issue":"11","key":"pcbi.1011504.ref023","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1038\/nchembio.1337","article-title":"Metrics other than potency reveal systematic variation in responses to cancer drugs","volume":"9","author":"M Fallahi-Sichani","year":"2013","journal-title":"Nature Chemical Biology"},{"key":"pcbi.1011504.ref024","unstructured":"DARWIN. Delaware Advanced Research Workforce and Innovation Network (DARWIN); 2021. Available from: https:\/\/dsi.udel.edu\/core\/computational-resources\/darwin\/."},{"key":"pcbi.1011504.ref025","unstructured":"NERSC. Perlmutter (National Energy Research Scientific Computing center (NERSC); 2022. Available from: https:\/\/docs.nersc.gov\/systems\/perlmutter\/architecture\/."},{"key":"pcbi.1011504.ref026","doi-asserted-by":"crossref","first-page":"e623","DOI":"10.7717\/peerj-cs.623","article-title":"The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation","volume":"7","author":"D Chicco","year":"2021","journal-title":"PeerJ Comput Sci"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1011504","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T00:00:00Z","timestamp":1715299200000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T13:47:23Z","timestamp":1715348843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011504"}},"subtitle":[],"editor":[{"given":"Samuel V.","family":"Scarpino","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,4,29]]},"references-count":26,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,4,29]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1011504","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.09.12.557300","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,29]]}}}