{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T16:48:52Z","timestamp":1761324532106,"version":"3.37.3"},"reference-count":141,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Learning over the domain of 3D graphs has applications in a number of scientific and engineering disciplines, including molecular chemistry, high energy physics, and computer vision. We consider a specific problem in this domain, namely: given one such 3D graph, dubbed the base graph, our goal is to learn a conditional distribution over another such graph, dubbed the complement graph. Due to the three-dimensional nature of the graphs in question, there are certain natural invariances such a distribution should satisfy: it should be invariant to rigid body transformations that act jointly on the base graph and the complement graph, and it should also be invariant to permutations of the vertices of either graph. We propose a general method for learning the conditional probabilistic model, the central part of which is a continuous normalizing flow. We establish semi-equivariance conditions on the flow which guarantee the aforementioned invariance conditions on the conditional distribution. Additionally, we propose a graph neural network architecture which implements this flow, and which is designed to learn effectively despite the typical differences in size between the base graph and the complement graph. We demonstrate the utility of our technique in the molecular setting by training a conditional generative model which, given a receptor, can generate ligands which may successfully bind to that receptor. The resulting model, which has potential applications in drug design, displays high quality performance in the key \u0394Binding metric.<\/jats:p>","DOI":"10.1088\/2632-2153\/ace58c","type":"journal-article","created":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T22:40:25Z","timestamp":1688769625000},"page":"035037","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Semi-equivariant conditional normalizing flows, with applications to target-aware molecule generation"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6057-8117","authenticated-orcid":true,"given":"Eyal","family":"Rozenberg","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Freedman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2023,9,1]]},"reference":[{"key":"mlstace58cbib1","first-page":"p 17","article-title":"The correlated correspondence algorithm for unsupervised registration of nonrigid surfaces","author":"Anguelov","year":"2004"},{"key":"mlstace58cbib2","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1093\/bioinformatics\/btq112","article-title":"A machine learning approach to predicting protein\u2013ligand binding affinity with applications to molecular docking","volume":"26","author":"Ballester","year":"2010","journal-title":"Bioinformatics"},{"key":"mlstace58cbib3","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1111\/j.1476-5381.1976.tb07468.x","article-title":"Compounds designed to fit a site of known structure in human haemoglobin","volume":"57","author":"Beddell","year":"1976","journal-title":"Br. J. Pharmacol."},{"key":"mlstace58cbib4","doi-asserted-by":"publisher","first-page":"1729","DOI":"10.3390\/rs12111729","article-title":"Deep learning on 3d point clouds","volume":"12","author":"Bello","year":"2020","journal-title":"Remote Sens."},{"key":"mlstace58cbib5","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1038\/nsb1203-980","article-title":"Announcing the worldwide protein data bank","volume":"10","author":"Berman","year":"2003","journal-title":"Nat. Struct. Mol. Biol."},{"key":"mlstace58cbib6","first-page":"23","article-title":"Structure-based drug design","volume":"384","author":"Blundell","year":"1996","journal-title":"Nature"},{"article-title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges","year":"2021","author":"Bronstein","key":"mlstace58cbib7"},{"key":"mlstace58cbib8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0021-9991(87)90001-5","article-title":"Stiff ode solvers: a review of current and coming attractions","volume":"70","author":"Byrne","year":"1987","journal-title":"J. Comput. Phys."},{"key":"mlstace58cbib9","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1042\/cs0990255","article-title":"Science, art and drug discovery: a personal perspective","volume":"99","author":"Campbell","year":"2000","journal-title":"Clin. Sci."},{"key":"mlstace58cbib10","doi-asserted-by":"publisher","first-page":"5100","DOI":"10.1021\/jm990352k","article-title":"Consensus scoring: a method for obtaining improved hit rates from docking databases of three-dimensional structures into proteins","volume":"42","author":"Charifson","year":"1999","journal-title":"J. Med. Chem."},{"key":"mlstace58cbib11","first-page":"pp 824","article-title":"Continuous-time flows for efficient inference and density estimation","author":"Chen","year":"2018a"},{"key":"mlstace58cbib12","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1016\/j.drudis.2018.01.039","article-title":"The rise of deep learning in drug discovery","volume":"23","author":"Chen","year":"2018b","journal-title":"Drug Discovery Today"},{"key":"mlstace58cbib13","first-page":"p 31","article-title":"Neural ordinary differential equations","author":"Chen","year":"2018c"},{"key":"mlstace58cbib14","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1208\/s12248-012-9322-0","article-title":"Structure-based virtual screening for drug discovery: a problem-centric review","volume":"14","author":"Cheng","year":"2012","journal-title":"AAPS J."},{"key":"mlstace58cbib15","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1021\/ci9000053","article-title":"Comparative assessment of scoring functions on a diverse test set","volume":"49","author":"Cheng","year":"2009","journal-title":"J. Chem. Inf. Model."},{"key":"mlstace58cbib16","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1016\/S1359-6446(05)03484-7","article-title":"Keynote review: structural biology and drug discovery","volume":"10","author":"Congreve","year":"2005","journal-title":"Drug Discovery Today"},{"key":"mlstace58cbib17","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1073\/pnas.38.3.235","article-title":"Integration of stiff equations","volume":"38","author":"Curtiss","year":"1952","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstace58cbib18","first-page":"pp 5868","article-title":"Shape completion using 3d-encoder-predictor CNNS and shape synthesis","author":"Dai","year":"2017"},{"key":"mlstace58cbib19","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2022.103439","article-title":"Docking-based generative approaches in the search for new drug candidates","volume":"28","author":"Danel","year":"2023","journal-title":"Drug Discovery Today"},{"key":"mlstace58cbib20","doi-asserted-by":"publisher","first-page":"10363","DOI":"10.1021\/bi00107a001","article-title":"The coagulation cascade: initiation, maintenance and regulation","volume":"30","author":"Davie","year":"1991","journal-title":"Biochemistry"},{"article-title":"Scaling up machine learning for quantum field theory with equivariant continuous flows","year":"2021","author":"de Haan","key":"mlstace58cbib21"},{"key":"mlstace58cbib22","doi-asserted-by":"publisher","first-page":"11733","DOI":"10.1021\/ja960751u","article-title":"Smog: de novo design method based on simple, fast and accurate free energy estimates. 1. Methodology and supporting evidence","volume":"118","author":"DeWitte","year":"1996","journal-title":"J. Am. Chem. Soc."},{"article-title":"Nice: non-linear independent components estimation","year":"2014","author":"Dinh","key":"mlstace58cbib23"},{"article-title":"Density estimation using Real NVP","year":"2016","author":"Dinh","key":"mlstace58cbib24"},{"article-title":"Structure-aware generation of drug-like molecules","year":"2021","author":"Drot\u00e1r","key":"mlstace58cbib25"},{"key":"mlstace58cbib26","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1142\/9789811234033_0012","article-title":"Graph neural networks for particle tracking and reconstruction","author":"Duarte","year":"2022"},{"key":"mlstace58cbib27","first-page":"p 32","article-title":"Augmented neural odes","author":"Dupont","year":"2019"},{"key":"mlstace58cbib28","doi-asserted-by":"publisher","first-page":"2897","DOI":"10.1021\/ci2003889","article-title":"Nnscore 2.0: a neural-network receptor\u2013ligand scoring function","volume":"51","author":"Durrant","year":"2011","journal-title":"J. Chem. Inf. Model."},{"key":"mlstace58cbib29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1758-2946-1-8","article-title":"Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions","volume":"1","author":"Ertl","year":"2009","journal-title":"J. Cheminformatics"},{"article-title":"Labeled graph generative adversarial networks","year":"2019","author":"Fan","key":"mlstace58cbib30"},{"article-title":"Generative diffusion models on graphs: methods and applications","year":"2023","author":"Fan","key":"mlstace58cbib31"},{"key":"mlstace58cbib32","doi-asserted-by":"publisher","first-page":"2046","DOI":"10.1021\/acs.jcim.1c00469","article-title":"Libinvent: reaction-based generative scaffold decoration for in silico library design","volume":"62","author":"Fialkov\u00e1","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"mlstace58cbib33","first-page":"pp 3154","article-title":"How to train your neural ODE: the world of Jacobian and kinetic regularization","author":"Finlay","year":"2020"},{"key":"mlstace58cbib34","first-page":"pp 3165","article-title":"Generalizing convolutional neural networks for equivariance to Lie groups on arbitrary continuous data","author":"Finzi","year":"2020"},{"key":"mlstace58cbib35","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abf5b8","article-title":"Neural message passing on high order paths","volume":"2","author":"Flam-Shepherd","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstace58cbib36","doi-asserted-by":"publisher","first-page":"4200","DOI":"10.1021\/acs.jcim.0c00411","article-title":"Three-dimensional convolutional neural networks and a cross-docked data set for structure-based drug design","volume":"60","author":"Francoeur","year":"2020","journal-title":"J. Chem. Inf. Model."},{"article-title":"Reinforced genetic algorithm for structure-based drug design","year":"2022","author":"Fu","key":"mlstace58cbib37"},{"key":"mlstace58cbib38","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1038\/s41592-019-0666-6","article-title":"Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning","volume":"17","author":"Gainza","year":"2020","journal-title":"Nat. Methods"},{"article-title":"Independent SE(3)-equivariant models for end-to-end rigid protein docking","year":"2021","author":"Ganea","key":"mlstace58cbib39"},{"key":"mlstace58cbib40","first-page":"p 32","article-title":"Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules","author":"Gebauer","year":"2019"},{"key":"mlstace58cbib41","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1021\/cc9800071","article-title":"A knowledge-based approach in designing combinatorial or medicinal chemistry libraries for drug discovery. 1. A qualitative and quantitative characterization of known drug databases","volume":"1","author":"Ghose","year":"1999","journal-title":"J. Comb. Chem."},{"key":"mlstace58cbib42","first-page":"pp 14831","article-title":"STEER: simple temporal regularization for neural ODE","volume":"vol 33","author":"Ghosh","year":"2020"},{"key":"mlstace58cbib43","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1146\/annurev.pa.14.040174.001415","article-title":"Biochemical mechanisms of drug toxicity","volume":"14","author":"Gillette","year":"1974","journal-title":"Annu. Rev. Pharmacol."},{"key":"mlstace58cbib44","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1006\/jmbi.1999.3371","article-title":"Knowledge-based scoring function to predict protein-ligand interactions","volume":"295","author":"Gohlke","year":"2000","journal-title":"J. Mol. Biol."},{"article-title":"FFJORD: free-form continuous dynamics for scalable reversible generative models","year":"2018","author":"Grathwohl","key":"mlstace58cbib45"},{"key":"mlstace58cbib46","first-page":"p 32","article-title":"Hamiltonian neural networks","author":"Greydanus","year":"2019"},{"key":"mlstace58cbib47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2022.3144670","article-title":"Deep graph translation","author":"Guo","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"mlstace58cbib48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2022.3214832","article-title":"A systematic survey on deep generative models for graph generation","volume":"45","author":"Guo","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstace58cbib49","doi-asserted-by":"publisher","first-page":"4338","DOI":"10.1109\/TPAMI.2020.3005434","article-title":"Deep learning for 3d point clouds: a survey","volume":"43","author":"Guo","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstace58cbib50","first-page":"15","article-title":"The impact of structure-guided drug design on clinical agents","volume":"3","author":"Hardy","year":"2003","journal-title":"Curr. Drug Discov."},{"key":"mlstace58cbib51","doi-asserted-by":"crossref","DOI":"10.26434\/chemrxiv.6159143.v1","article-title":"DLSCORE: a deep learning model for predicting protein-ligand binding affinities","author":"Hassan","year":"2018"},{"key":"mlstace58cbib52","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":"mlstace58cbib53","first-page":"pp 2722","article-title":"Flow++: improving flow-based generative models with variational dequantization and architecture design","author":"Ho","year":"2019"},{"key":"mlstace58cbib54","first-page":"pp 12454","article-title":"Argmax flows and multinomial diffusion: learning categorical distributions","volume":"vol 34","author":"Hoogeboom","year":"2021"},{"key":"mlstace58cbib55","first-page":"pp 8867","article-title":"Equivariant diffusion for molecule generation in 3d","author":"Hoogeboom","year":"2022"},{"key":"mlstace58cbib56","doi-asserted-by":"publisher","first-page":"2097","DOI":"10.1021\/ci2000727","article-title":"Scoring and lessons learned with the CSAR benchmark using an improved iterative knowledge-based scoring function","volume":"51","author":"Huang","year":"2011","journal-title":"J. Chem. Inf. Model."},{"key":"mlstace58cbib57","doi-asserted-by":"publisher","first-page":"e00950","DOI":"10.1128\/mSphere.00950-20","article-title":"Novel immune modulators enhance caenorhabditis elegans resistance to multiple pathogens","volume":"6","author":"Hummell","year":"2021","journal-title":"Msphere"},{"key":"mlstace58cbib58","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1080\/03610919008812866","article-title":"A stochastic estimator of the trace of the influence matrix for Laplacian smoothing splines","volume":"19","author":"Hutchinson","year":"1990","journal-title":"Commun. Stat.-Simul. Comput."},{"article-title":"Graphein\u2014a Python library for geometric deep learning and network analysis on biomolecular structures and interaction networks","year":"2022","author":"Jamasb","key":"mlstace58cbib59"},{"key":"mlstace58cbib60","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-020-00479-8","article-title":"Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models","volume":"13","author":"Jiang","year":"2021","journal-title":"J. Cheminformatics"},{"article-title":"Learning from protein structure with geometric vector perceptrons","year":"2020","author":"Jing","key":"mlstace58cbib61"},{"key":"mlstace58cbib62","first-page":"pp 23858","article-title":"Particle cloud generation with message passing generative adversarial networks","volume":"vol 34","author":"Kansal","year":"2021"},{"key":"mlstace58cbib63","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","article-title":"Physics-informed machine learning","volume":"3","author":"Karniadakis","year":"2021","journal-title":"Nat. Rev. Phys."},{"key":"mlstace58cbib64","article-title":"Poisson surface reconstruction","volume":"vol 7","author":"Kazhdan","year":"2006"},{"key":"mlstace58cbib65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2487228.2487237","article-title":"Screened Poisson surface reconstruction","volume":"32","author":"Kazhdan","year":"2013","journal-title":"ACM Trans. Graph."},{"key":"mlstace58cbib66","first-page":"pp 4370","article-title":"Learning differential equations that are easy to solve","volume":"vol 33","author":"Kelly","year":"2020"},{"key":"mlstace58cbib67","first-page":"p 31","article-title":"Glow: generative flow with invertible 1\u00d71 convolutions","author":"Kingma","year":"2018"},{"key":"mlstace58cbib68","doi-asserted-by":"publisher","first-page":"935","DOI":"10.1038\/nrd1549","article-title":"Docking and scoring in virtual screening for drug discovery: methods and applications","volume":"3","author":"Kitchen","year":"2004","journal-title":"Nat. Rev. Drug Discovery"},{"key":"mlstace58cbib69","doi-asserted-by":"publisher","first-page":"1893","DOI":"10.1021\/ci300604z","article-title":"Lessons learned in empirical scoring with smina from the CSAR 2011 benchmarking exercise","volume":"53","author":"Koes","year":"2013","journal-title":"J. Chem. Inf. Model."},{"article-title":"Equivariant flows: sampling configurations for multi-body systems with symmetric energies","year":"2019","author":"K\u00f6hler","key":"mlstace58cbib70"},{"key":"mlstace58cbib71","first-page":"pp 5361","article-title":"Equivariant flows: exact likelihood generative learning for symmetric densities","author":"K\u00f6hler","year":"2020"},{"article-title":"RDKit: open-source cheminformatics software","year":"2016","author":"Landrum","key":"mlstace58cbib72"},{"key":"mlstace58cbib73","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1038\/342299a0","article-title":"x-ray analysis of HIV-1 proteinase at 2.7 \u00c5resolution confirms structural homology among retroviral enzymes","volume":"342","author":"Lapatto","year":"1989","journal-title":"Nature"},{"key":"mlstace58cbib74","doi-asserted-by":"publisher","first-page":"1809","DOI":"10.1109\/TVCG.2016.2553102","article-title":"Shape completion from a single RGBD image","volume":"23","author":"Li","year":"2016","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"mlstace58cbib75","doi-asserted-by":"publisher","first-page":"13664","DOI":"10.1039\/D1SC04444C","article-title":"Structure-based de novo drug design using 3d deep generative models","volume":"12","author":"Li","year":"2021","journal-title":"Chem. Sci."},{"article-title":"DiffBP: generative diffusion of 3d molecules for target protein binding","year":"2022","author":"Lin","key":"mlstace58cbib76"},{"key":"mlstace58cbib77","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0169-409X(96)00423-1","article-title":"Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings","volume":"23","author":"Lipinski","year":"1997","journal-title":"Adv. Drug. Deliv. Rev."},{"key":"mlstace58cbib78","article-title":"Graph normalizing flows","volume":"vol 32","author":"Liu","year":"2019a"},{"article-title":"Generating 3d molecules for target protein binding","year":"2022","author":"Liu","key":"mlstace58cbib79"},{"key":"mlstace58cbib80","doi-asserted-by":"publisher","first-page":"4188","DOI":"10.3390\/s19194188","article-title":"Deep learning on point clouds and its application: a survey","volume":"19","author":"Liu","year":"2019b","journal-title":"Sensors"},{"key":"mlstace58cbib81","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1021\/acs.accounts.6b00491","article-title":"Forging the basis for developing protein\u2013ligand interaction scoring functions","volume":"50","author":"Liu","year":"2017","journal-title":"Acc. Chem. Res."},{"key":"mlstace58cbib82","first-page":"pp 6229","article-title":"A 3d generative model for structure-based drug design","volume":"vol 34","author":"Luo","year":"2021"},{"article-title":"GraphNVP: an invertible flow model for generating molecular graphs","year":"2019","author":"Madhawa","key":"mlstace58cbib83"},{"key":"mlstace58cbib84","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1016\/j.cbpa.2007.08.033","article-title":"Virtual screening strategies in drug discovery","volume":"11","author":"McInnes","year":"2007","journal-title":"Curr. Opin. Chem. Biol."},{"key":"mlstace58cbib85","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-021-00522-2","article-title":"GNINA 1.0: molecular docking with deep learning","volume":"13","author":"McNutt","year":"2021","journal-title":"J. Cheminformatics"},{"key":"mlstace58cbib86","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1007\/s008940100038","article-title":"Generation and evaluation of dimension-reduced amino acid parameter representations by artificial neural networks","volume":"7","author":"Meiler","year":"2001","journal-title":"Mol. Model. Annu."},{"key":"mlstace58cbib87","doi-asserted-by":"publisher","first-page":"1149","DOI":"10.1126\/science.2686029","article-title":"Structure of complex of synthetic HIV-1 protease with a substrate-based inhibitor at 2.3 \u00c5 resolution","volume":"246","author":"Miller","year":"1989","journal-title":"Science"},{"key":"mlstace58cbib88","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1023\/A:1008729005958","article-title":"A knowledge-based scoring function for protein-ligand interactions: probing the reference state","volume":"20","author":"Muegge","year":"2000","journal-title":"Perspect. Drug Discov. Des."},{"key":"mlstace58cbib89","doi-asserted-by":"publisher","first-page":"eaaw1147","DOI":"10.1126\/science.aaw1147","article-title":"Boltzmann generators: sampling equilibrium states of many-body systems with deep learning","volume":"365","author":"No\u00e9","year":"2019","journal-title":"Science"},{"key":"mlstace58cbib90","doi-asserted-by":"publisher","first-page":"pp 9223","DOI":"10.1609\/aaai.v35i10.17113","article-title":"OT-Flow: fast and accurate continuous normalizing flows via optimal transport","volume":"vol 35","author":"Onken","year":"2021"},{"key":"mlstace58cbib91","first-page":"2617","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"mlstace58cbib92","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1140\/epjc\/s10052-021-09158-w","article-title":"MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks","volume":"81","author":"Pata","year":"2021","journal-title":"Eur. Phys. J. C"},{"key":"mlstace58cbib93","first-page":"pp 23","article-title":"Example-based 3d scan completion","author":"Pauly","year":"2005"},{"article-title":"Pocket2Mol: efficient molecular sampling based on 3d protein pockets","year":"2022","author":"Peng","key":"mlstace58cbib94"},{"key":"mlstace58cbib95","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2020.565644","article-title":"Molecular sets (MOSES): a benchmarking platform for molecular generation models","volume":"11","author":"Polykovskiy","year":"2020","journal-title":"Front. Pharmacol."},{"key":"mlstace58cbib96","doi-asserted-by":"publisher","DOI":"10.1101\/2022.03.17.484653","article-title":"Fragment-based ligand generation guided by geometric deep learning on protein-ligand structure","author":"Powers","year":"2022"},{"key":"mlstace58cbib97","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.101.056019","article-title":"Jet tagging via particle clouds","volume":"101","author":"Qu","year":"2020","journal-title":"Phys. Rev. D"},{"article-title":"Particle transformer for jet tagging","year":"2022","author":"Qu","key":"mlstace58cbib98"},{"key":"mlstace58cbib99","doi-asserted-by":"publisher","first-page":"2701","DOI":"10.1039\/D1SC05976A","article-title":"Generating 3d molecules conditional on receptor binding sites with deep generative models","volume":"13","author":"Ragoza","year":"2022","journal-title":"Chem. Sci."},{"key":"mlstace58cbib100","doi-asserted-by":"publisher","first-page":"10024","DOI":"10.1021\/ja00051a040","article-title":"UFF, a full periodic table force field for molecular mechanics and molecular dynamics simulations","volume":"114","author":"Rapp\u00e9","year":"1992","journal-title":"J. Am. Chem. Soc."},{"article-title":"Equivariant Hamiltonian flows","year":"2019","author":"Rezende","key":"mlstace58cbib101"},{"key":"mlstace58cbib102","first-page":"pp 1530","article-title":"Variational inference with normalizing flows","author":"Rezende","year":"2015"},{"key":"mlstace58cbib103","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","article-title":"Quantifying the chemical beauty of drugs","volume":"4","author":"Richard Bickerton","year":"2012","journal-title":"Nat. Chem."},{"article-title":"High-dimensional probability estimation with deep density models","year":"2013","author":"Rippel","key":"mlstace58cbib104"},{"year":"2023","author":"Rozenberg","key":"mlstace58cbib105"},{"article-title":"E(n) equivariant normalizing flows","year":"2021a","author":"Satorras","key":"mlstace58cbib106"},{"key":"mlstace58cbib107","first-page":"pp 9323","article-title":"E(n) equivariant graph neural networks","author":"Satorras","year":"2021b"},{"article-title":"Structure-based drug design with equivariant diffusion models","year":"2022","author":"Schneuing","key":"mlstace58cbib108"},{"article-title":"GraphAF: a flow-based autoregressive model for molecular graph generation","year":"2020","author":"Shi","key":"mlstace58cbib109"},{"key":"mlstace58cbib110","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abbf9a","article-title":"Graph neural networks in particle physics","volume":"2","author":"Shlomi","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstace58cbib111","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1007\/978-3-030-01418-6_41","article-title":"Graphvae: towards generation of small graphs using variational autoencoders","author":"Simonovsky","year":"2018"},{"key":"mlstace58cbib112","first-page":"pp 20503","article-title":"EquiBind: geometric deep learning for drug binding structure prediction","author":"St\u00e4rk","year":"2022"},{"key":"mlstace58cbib113","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1021\/acs.jcim.8b00545","article-title":"Comparative assessment of scoring functions: the CASF-2016 update","volume":"59","author":"Su","year":"2018","journal-title":"J. Chem. Inf. Model."},{"key":"mlstace58cbib114","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1093\/bib\/bbz042","article-title":"Graph convolutional networks for computational drug development and discovery","volume":"21","author":"Sun","year":"2020","journal-title":"Brief. Bioinformatics"},{"key":"mlstace58cbib115","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818094","article-title":"Data-driven structural priors for shape completion","volume":"34","author":"Sung","year":"2015","journal-title":"ACM Trans. Graph."},{"key":"mlstace58cbib116","first-page":"pp 15272","article-title":"Fast end-to-end learning on protein surfaces","author":"Sverrisson","year":"2021"},{"article-title":"Physics-informed deep neural network for rigid-body protein docking","year":"2022","author":"Sverrisson","key":"mlstace58cbib117"},{"key":"mlstace58cbib118","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1038\/nrd1500","article-title":"Biochemical mechanisms of drug action: what does it take for success?","volume":"3","author":"Swinney","year":"2004","journal-title":"Nat. Rev. Drug Discovery"},{"key":"mlstace58cbib119","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-021-00516-0","article-title":"Comparison of structure-and ligand-based scoring functions for deep generative models: a GPCR case study","volume":"13","author":"Thomas","year":"2021","journal-title":"J. Cheminformatics"},{"article-title":"Diffusion probabilistic modeling of protein backbones in 3d for the motif-scaffolding problem","year":"2022","author":"Trippe","key":"mlstace58cbib120"},{"key":"mlstace58cbib121","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1002\/jcc.21334","article-title":"AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization and multithreading","volume":"31","author":"Trott","year":"2010","journal-title":"J. Comput. Chem."},{"key":"mlstace58cbib122","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1002\/(SICI)1098-2299(199903\/04)46:3\/4<176::AID-DDR4>3.0.CO;2-6","article-title":"Development of neuraminidase inhibitors as anti-influenza virus drugs","volume":"46","author":"Varghese","year":"1999","journal-title":"Drug Dev. Res."},{"key":"mlstace58cbib123","doi-asserted-by":"publisher","first-page":"2615","DOI":"10.1021\/jm020017n","article-title":"Molecular properties that influence the oral bioavailability of drug candidates","volume":"45","author":"Veber","year":"2002","journal-title":"J. Med. Chem."},{"key":"mlstace58cbib124","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-022-19363-6","article-title":"A pocket-based 3d molecule generative model fueled by experimental electron density","volume":"12","author":"Wang","year":"2022a","journal-title":"Sci. Rep."},{"key":"mlstace58cbib125","doi-asserted-by":"publisher","first-page":"9478","DOI":"10.1021\/acs.jmedchem.2c00732","article-title":"Relation: a deep generative model for structure-based de novo drug design","volume":"65","author":"Wang","year":"2022b","journal-title":"J. Med. Chem."},{"key":"mlstace58cbib126","doi-asserted-by":"publisher","first-page":"2287","DOI":"10.1021\/jm0203783","article-title":"Comparative evaluation of 11 scoring functions for molecular docking","volume":"46","author":"Wang","year":"2003","journal-title":"J. Med. Chem."},{"key":"mlstace58cbib127","doi-asserted-by":"publisher","first-page":"5912","DOI":"10.1021\/jm050362n","article-title":"A critical assessment of docking programs and scoring functions","volume":"49","author":"Warren","year":"2006","journal-title":"J. Med. Chem."},{"key":"mlstace58cbib128","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1021\/ci990307l","article-title":"Prediction of physicochemical parameters by atomic contributions","volume":"39","author":"Wildman","year":"1999","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"mlstace58cbib129","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1093\/bioinformatics\/bty757","article-title":"Development of a protein\u2013ligand extended connectivity (PLEC) fingerprint and its application for binding affinity predictions","volume":"35","author":"W\u00f3jcikowski","year":"2019","journal-title":"Bioinformatics"},{"key":"mlstace58cbib130","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"mlstace58cbib131","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"Moleculenet: a benchmark for molecular machine learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem. Sci."},{"key":"mlstace58cbib132","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing learned molecular representations for property prediction","volume":"59","author":"Yang","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"mlstace58cbib133","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1109\/TNNLS.2020.3028042","article-title":"Potential flow generator with L 2 optimal transport regularity for generative models","volume":"33","author":"Yang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"mlstace58cbib134","first-page":"pp 5708","article-title":"GraphRNN: generating realistic graphs with deep auto-regressive models","author":"You","year":"2018"},{"key":"mlstace58cbib135","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1021\/acs.jchemed.5b00404","article-title":"RCSB protein data bank: a resource for chemical, biochemical and structural explorations of large and small biomolecules","volume":"93","author":"Zardecki","year":"2016","journal-title":"J. Chem. Educ."},{"article-title":"PNODE: a memory-efficient neural ode framework based on high-level adjoint differentiation","year":"2022","author":"Zhang","key":"mlstace58cbib136"},{"key":"mlstace58cbib137","doi-asserted-by":"publisher","first-page":"3291","DOI":"10.1021\/acs.jcim.2c00177","article-title":"De novo molecule design using molecular generative models constrained by ligand\u2013protein interactions","volume":"62","author":"Zhang","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"mlstace58cbib138","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1007\/s00371-007-0167-y","article-title":"A robust hole-filling algorithm for triangular mesh","volume":"23","author":"Zhao","year":"2007","journal-title":"Vis. Comput."},{"key":"mlstace58cbib139","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: a review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"article-title":"A survey on deep graph generation: methods and applications","year":"2022","author":"Zhu","key":"mlstace58cbib140"},{"article-title":"MALI: a memory efficient and reverse accurate integrator for neural ODEs","year":"2021","author":"Zhuang","key":"mlstace58cbib141"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace58c","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace58c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace58c","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace58c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace58c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace58c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace58c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace58c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T11:24:47Z","timestamp":1693567487000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ace58c"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":141,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,9,1]]},"published-print":{"date-parts":[[2023,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ace58c","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2023,9,1]]},"assertion":[{"value":"Semi-equivariant conditional normalizing flows, with applications to target-aware molecule generation","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 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-01-11","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-07-07","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-09-01","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}