{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T12:53:10Z","timestamp":1766407990793,"version":"3.37.3"},"reference-count":53,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T00:00:00Z","timestamp":1618358400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T00:00:00Z","timestamp":1618358400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Austrian Science Fund","award":["J4309"],"award-info":[{"award-number":["J4309"]}]},{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"crossref","award":["795206"],"award-info":[{"award-number":["795206"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Machine learning with application to questions in the physical sciences has become a widely used tool, successfully applied to classification, regression and optimization tasks in many areas. Research focus mostly lies in improving the accuracy of the machine learning models in numerical predictions, while scientific understanding is still almost exclusively generated by human researchers analysing numerical results and drawing conclusions. In this work, we shift the focus on the insights and the knowledge obtained by the machine learning models themselves. In particular, we study how it can be extracted and used to inspire human scientists to increase their intuitions and understanding of natural systems. We apply gradient boosting in decision trees to extract human-interpretable insights from big data sets from chemistry and physics. In chemistry, we not only rediscover widely know rules of thumb but also find new interesting motifs that tell us how to control solubility and energy levels of organic molecules. At the same time, in quantum physics, we gain new understanding on experiments for quantum entanglement. The ability to go beyond numerics and to enter the realm of scientific insight and hypothesis generation opens the door to use machine learning to accelerate the discovery of conceptual understanding in some of the most challenging domains of science.<\/jats:p>","DOI":"10.1088\/2632-2153\/abda08","type":"journal-article","created":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T16:48:35Z","timestamp":1610297315000},"page":"025027","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Scientific intuition inspired by machine learning-generated hypotheses"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4465-1465","authenticated-orcid":false,"given":"Pascal","family":"Friederich","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1620-9207","authenticated-orcid":false,"given":"Mario","family":"Krenn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8146-6667","authenticated-orcid":false,"given":"Isaac","family":"Tamblyn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8277-4434","authenticated-orcid":false,"given":"Al\u00e1n","family":"Aspuru-Guzik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2021,4,14]]},"reference":[{"key":"mlstabda08bib1","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.91.045002","article-title":"Machine learning and the physical sciences","volume":"91","author":"Carleo","year":"2019","journal-title":"Rev. Mod. Phys."},{"key":"mlstabda08bib2","doi-asserted-by":"publisher","first-page":"2087","DOI":"10.1021\/acs.jctc.5b00099","article-title":"Big data meets quantum chemistry approximations: the \u03b4-machine learning approach","volume":"11","author":"Ramakrishnan","year":"2015","journal-title":"J. Chem. Theory Comput."},{"key":"mlstabda08bib3","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1038\/s41557-020-0544-y","article-title":"Deep-neural-network solution of the electronic Schr\u00f6dinger equation","volume":"12","author":"Hermann","year":"2020","journal-title":"Nat. Chem."},{"key":"mlstabda08bib4","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.1021\/acscentsci.9b00576","article-title":"Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction","volume":"5","author":"Schwaller","year":"2019","journal-title":"ACS Cent. Sci."},{"key":"mlstabda08bib5","doi-asserted-by":"publisher","first-page":"5650","DOI":"10.1021\/acs.chemmater.0c01153","article-title":"Robot-accelerated perovskite investigation and discovery","volume":"32","author":"Li","year":"2020","journal-title":"Chem. Mater."},{"key":"mlstabda08bib6","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1038\/s41570-018-0066-y","article-title":"How to explore chemical space using algorithms and automation","volume":"3","author":"Gromski","year":"2019","journal-title":"Nat. Rev. Chem."},{"key":"mlstabda08bib7","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1126\/science.aat2663","article-title":"Inverse molecular design using machine learning: generative models for matter engineering","volume":"361","author":"Sanchez-Lengeling","year":"2018","journal-title":"Science"},{"key":"mlstabda08bib8","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1038\/nphys4035","article-title":"Machine learning phases of matter","volume":"13","author":"Carrasquilla","year":"2017","journal-title":"Nat. Phys."},{"key":"mlstabda08bib9","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/nature23463","article-title":"Fast automated analysis of strong gravitational lenses with convolutional neural networks","volume":"548","author":"Hezaveh","year":"2017","journal-title":"Nature"},{"key":"mlstabda08bib10","article-title":"Pattern recognition techniques for boson sampling validation","volume":"9","author":"Agresti","year":"2019","journal-title":"Phys. Rev. X"},{"key":"mlstabda08bib11","doi-asserted-by":"crossref","first-page":"706","DOI":"10.1038\/s41586-019-1923-7","article-title":"Improved protein structure prediction using potentials from deep learning","volume":"577","author":"Senior","year":"2020","journal-title":"Nature"},{"key":"mlstabda08bib12","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1038\/s41587-019-0224-x","article-title":"Deep learning enables rapid identification of potent DDR1 kinase inhibitors","volume":"37","author":"Zhavoronkov","year":"2019","journal-title":"Nat. Biotechnol."},{"key":"mlstabda08bib13","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","article-title":"A deep learning approach to antibiotic discovery","volume":"180","author":"Stokes","year":"2020","journal-title":"Cell"},{"key":"mlstabda08bib14","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1126\/science.1165620","article-title":"The automation of science","volume":"324","author":"King","year":"2009","journal-title":"Science"},{"key":"mlstabda08bib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.124.010508","article-title":"Discovering physical concepts with neural networks","volume":"124","author":"Iten","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstabda08bib16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-018-07210-0","article-title":"Deep learning for universal linear embeddings of nonlinear dynamics","volume":"9","author":"Lusch","year":"2018","journal-title":"Nat. Commun."},{"key":"mlstabda08bib17","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevResearch.2.033499","article-title":"Discovering symmetry invariants and conserved quantities by interpreting Siamese neural networks","author":"Wetzel","year":"2020"},{"key":"mlstabda08bib18","doi-asserted-by":"publisher","first-page":"42200","DOI":"10.1109\/ACCESS.2020.2976199","article-title":"Explainable machine learning for scientific insights and discoveries","volume":"8","author":"Roscher","year":"2020","journal-title":"IEEE Access"},{"key":"mlstabda08bib19","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"mlstabda08bib20","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem. Inf. Mod."},{"key":"mlstabda08bib21","first-page":"pp 278","article-title":"Random decision forests","volume":"vol 1","author":"Ho","year":"1995"},{"key":"mlstabda08bib22","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"mlstabda08bib23","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1016\/j.joule.2017.10.006","article-title":"Design principles and top non-fullerene acceptor candidates for organic photovoltaics","volume":"1","author":"Lopez","year":"2017","journal-title":"Joule"},{"key":"mlstabda08bib24","first-page":"pp 2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","author":"Duvenaud","year":"2015"},{"key":"mlstabda08bib25","first-page":"pp 618","article-title":"Grad-cam: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"mlstabda08bib26","first-page":"pp 9244","article-title":"Gnnexplainer: generating explanations for graph neural networks","author":"Ying","year":"2019"},{"key":"mlstabda08bib27","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1038\/nmat4717","article-title":"Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach","volume":"15","author":"G\u00f3mez-Bombarelli","year":"2016","journal-title":"Nat. Mater."},{"key":"mlstabda08bib28","doi-asserted-by":"publisher","first-page":"2241","DOI":"10.1021\/jz200866s","article-title":"The Harvard clean energy project: large-scale computational screening and design of organic photovoltaics on the world community grid","volume":"2","author":"Hachmann","year":"2011","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstabda08bib29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.86","article-title":"The Harvard organic photovoltaic dataset","volume":"3","author":"Lopez","year":"2016","journal-title":"Sci. Data"},{"key":"mlstabda08bib30","doi-asserted-by":"publisher","first-page":"14808","DOI":"10.1039\/C8CP02162G","article-title":"The predictive power of aromaticity: quantitative correlation between aromaticity and ionization potentials and HOMO\u2013LUMO gaps in oligomers of benzene, pyrrole, furan and thiophene","volume":"20","author":"Gershoni-Poranne","year":"2018","journal-title":"Phys. Chem. Chem. Phys."},{"first-page":"pp 125","year":"2018","author":"Rasmussen","key":"mlstabda08bib31"},{"key":"mlstabda08bib32","doi-asserted-by":"publisher","first-page":"3808","DOI":"10.1063\/1.448868","article-title":"Relationship between band gap and bond length alternation in organic conjugated polymers","volume":"82","author":"Bredas","year":"1985","journal-title":"J. Chem. Phys."},{"key":"mlstabda08bib33","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1038\/s42254-018-0003-5","article-title":"Entanglement certification from theory to experiment","volume":"1","author":"Friis","year":"2019","journal-title":"Nat. Rev. Phys."},{"key":"mlstabda08bib34","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1038\/s42254-020-0193-5","article-title":"Advances in high-dimensional quantum entanglement","volume":"2","author":"Erhard","year":"2020","journal-title":"Nat. Rev. Phys."},{"key":"mlstabda08bib35","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.95.042123","article-title":"Mermin inequalities for perfect correlations in many-qutrit systems","volume":"95","author":"Lawrence","year":"2017","journal-title":"Phys. Rev. A"},{"key":"mlstabda08bib36","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.97.032312","article-title":"Layered quantum key distribution","volume":"97","author":"Pivoluska","year":"2018","journal-title":"Phys. Rev. A"},{"key":"mlstabda08bib37","doi-asserted-by":"crossref","DOI":"10.1038\/s41534-020-00318-6","article-title":"Experimental creation of multi-photon high-dimensional layered quantum states","author":"Hu","year":"2020"},{"key":"mlstabda08bib38","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1103\/RevModPhys.84.777","article-title":"Multiphoton entanglement and interferometry","volume":"84","author":"Pan","year":"2012","journal-title":"Rev. Mod. Phys."},{"key":"mlstabda08bib39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.116.090405","article-title":"Automated search for new quantum experiments","volume":"116","author":"Krenn","year":"2016","journal-title":"Phys. Rev. Lett."},{"key":"mlstabda08bib40","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/18\/7\/073033","article-title":"A search algorithm for quantum state engineering and metrology","volume":"18","author":"Knott","year":"2016","journal-title":"New J. Phys."},{"key":"mlstabda08bib41","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.1.010301","article-title":"Machine learning for long-distance quantum communication","volume":"1","author":"Walln\u00f6fer","year":"2020","journal-title":"PRX Quantum"},{"key":"mlstabda08bib42","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.101.010302","article-title":"Experimental quantum cloning in a pseudo-unitary system","volume":"101","author":"Zhan","year":"2020","journal-title":"Phys. Rev. A"},{"key":"mlstabda08bib43","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1038\/s42254-020-0230-4","article-title":"Computer-inspired quantum experiments","volume":"2","author":"Krenn","year":"2020","journal-title":"Nature Rev. Phys."},{"article-title":"Conceptual understanding through efficient inverse-design of quantum optical experiments","year":"2020","author":"Krenn","key":"mlstabda08bib44"},{"key":"mlstabda08bib45","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.110.030501","article-title":"Structure of multidimensional entanglement in multipartite systems","volume":"110","author":"Huber","year":"2013","journal-title":"Phys. Rev. Lett."},{"key":"mlstabda08bib46","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.88.042328","article-title":"Entropy vector formalism and the structure of multidimensional entanglement in multipartite systems","volume":"88","author":"Huber","year":"2013","journal-title":"Phys. Rev. A"},{"key":"mlstabda08bib47","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1038\/nphoton.2016.12","article-title":"Multi-photon entanglement in high dimensions","volume":"10","author":"Malik","year":"2016","journal-title":"Nat. Photon."},{"key":"mlstabda08bib48","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1038\/s41566-018-0257-6","article-title":"Experimental Greenberger\u2013Horne\u2013Zeilinger entanglement beyond qubits","volume":"12","author":"Erhard","year":"2018","journal-title":"Nat. Photon."},{"key":"mlstabda08bib49","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1070\/PU1988v031n01ABEH002537","article-title":"A simple method of preparing pure states of an optical field, of implementing the Einstein\u2013Podolsky\u2013Rosen experiment and of demonstrating the complementarity principle","volume":"31","author":"Klyshko","year":"1988","journal-title":"Sov. Phys. Usp."},{"key":"mlstabda08bib50","doi-asserted-by":"publisher","first-page":"1446","DOI":"10.1126\/science.aaa5372","article-title":"Dynamic DNA devices and assemblies formed by shape-complementary, non-base pairing 3D components","volume":"347","author":"Gerling","year":"2015","journal-title":"Science"},{"key":"mlstabda08bib51","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1038\/nature24650","article-title":"Biotechnological mass production of DNA origami","volume":"552","author":"Praetorius","year":"2017","journal-title":"Nature"},{"year":"1996","author":"Temkin","key":"mlstabda08bib52"},{"key":"mlstabda08bib53","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1021\/ct401004r","article-title":"Complex chemical reaction networks from heuristics-aided quantum chemistry","volume":"10","author":"Rappoport","year":"2014","journal-title":"J. Chem. Theory Comput."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abda08","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abda08\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abda08","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abda08\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abda08\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abda08\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abda08\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abda08\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,21]],"date-time":"2022-01-21T01:27:10Z","timestamp":1642728430000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abda08"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,14]]},"references-count":53,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,4,14]]},"published-print":{"date-parts":[[2021,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abda08","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2021,4,14]]},"assertion":[{"value":"Scientific intuition inspired by machine learning-generated hypotheses","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-11-07","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-01-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-04-14","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}