Machine learning methods, in particular convolutional neural networks, have been applied to a variety of problems in cryo-EM and macromolecular crystallographic structure solution. With help of the CCP-EM mailing list and CCP4BB, we have made a survey of machine learning algorithms in crystallography and Cryo-EM, which culminated in the review "Artificial intelligence in the experimental determination and prediction of macromolecular structures"
Here is the corresponding poster and article list:
This overview lists scientific publications concerned with machine learning in macromolecular crystallography and single-particle electron cryomicroscopy. It was assembled 2021–2022 with help of members of the CCP4 Bulletin Board and is potentially incomplete; please contact us to add more!
First Author | Year | DOI | Paper Title | Topic | Method |
---|---|---|---|---|---|
Lata | 1995 | https://doi.org/10.1016/0304-3991(95)00002-i | Automatic particle picking from electron micrographs | cryo-EM particle picking | classification |
Berntson | 2003 | https://doi.org/10.1107/S0909049503020855 | Application of a neural network in high-throughput protein crystallography | diffraction quality estimation | classification via cascade correlation NNs |
Gopalakrishnan | 2004 | https://doi.org/10.1107/S090744490401683X | Machine-learning techniques for macromolecular crystallization data | crystallization optimization | heuristics system, HAMB |
Morris | 2004 | https://doi.org/10.1107/S090744490402061X | Statistical pattern recognition for macromolecular crystallographers | review | pattern recognition |
Pakric | 2004 | https://doi.org/10.1107/S0909049500012929 | Integration of macromolecular diffraction data using radial basis function networks | X-ray intensity calculation | regression via RBF NNs |
Rupp | 2004 | https://doi.org/10.1016/j.ymeth.2004.03.031 | Predictive models for protein crystallization | crystallization optimization | ANN, GA |
Wong | 2004 | https://doi.org/10.1016/j.jsb.2003.05.001 | Model-based particle picking for cryo-electron microscopy | cryo-EM particle picking | |
Liu | 2008 | https://doi.org/10.1107/S090744490802982X | Image-based crystal detection: a machine-learning approach | Crystal image recognition | boosting |
Arbelaez | 2011 | https://doi.org/10.1016/j.jsb.2011.05.017 | Experimental evaluation of support vector machine-based and correlation-based approaches to automatic particle selection | cryo-EM particle picking | SVM |
Ma | 2011 | https://doi.org/10.1109/TCBB.2011.52. | A Novel α-Helix Identification Approach for Intermediate Resolution Electron Density Maps | cryo-EM secondary structure recognition | classification via boosting |
Si | 2012 | https://doi.org/10.1002/bip.22063 | A Machine Learning Approach for the Identification of Protein Secondary Structure Elements from Electron Cryo-Microscopy Density Maps | cryo-EM secondary structure recognition | classification SVM |
Ng | 2014 | https://doi.org/10.1107/S1399004714017581 | Using textons to rank crystallization droplets by the likely presence of crystals | crystal image recognition | is it AI? |
Morshed | 2015 | https://doi.org/10.1107/S1399004715004241 | Using support vector machines to improve elemental ion identification in macromolecular crystal structures | crystallography model building & validation | classification via SVM |
Touw | 2015 | https://doi.org/10.1107/S1399004715008263 | Detection of trans-cis flips and peptide-plane flips in protein structures | crystallography model building & validation | Random Forest |
Cao | 2016 | https://doi.org/10.1186/s12859-016-1405-y | DeepQA: improving the estimation of single protein model quality with deep belief networks | ||
Li | 2016 | https://doi.org/10.1109/BIBM.2016.7822490 | Deep Convolutional Neural Networks for Detecting Secondary Structures in Protein Density Maps from Cryo-Electron Microscopy | cryo-EM secondary structure recognition | classification via CNN |
Sharma | 2016 | https://doi.org/10.1107/S2053273316018696 | Asymmetry in serial femtosecond crystallography data | serial crystallography peak analysis | is it AI? |
Wang | 2016 | https://doi.org/10.1016/j.jsb.2016.07.006 | DeepPicker: A deep learning approach for fully automated particle picking in cryo-EM | cryo-EM particle picking | CNN |
Uziela | 2017 | https://doi.org/10.1093/bioinformatics/btw819 | ProQ3D: improved model quality assessments using deep learning | ||
Xiao | 2017 | https://doi.org/10.1063/1.4982020 | A Fast Method for Particle Picking in Cryo-Electron Micrographs based on Fast R-CNN | cryo-EM particle picking | classification and object localization via CNN |
Xu | 2017 | https://doi.org/10.1093/bioinformatics/btx230 | Deep learning-based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms | cryo-EM tomography reconstruction | classification via CNN |
Zhu | 2017 | https://doi.org/10.1186/s12859-017-1757-y | A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy | cryo-EM particle picking | classification via CNN |
Bruno | 2018 | https://doi.org/10.1371/journal.pone.0198883 | Classification of crystallization outcomes using deep convolutional neural networks | crystal image recognition | classification via CNN |
Elbasir | 2018 | https://doi.org/10.1093/bioinformatics/bty953 | DeepCrystal: a deep learning framework for sequence-based protein crystallization prediction | sequence-based protein crystallization prediction | classification via CNN |
Heimowitz | 2018 | https://doi.org/10.1016/j.jsb.2018.08.012 | APPLE picker: Automatic particle picking, a low-effort cryo-EM framework | cryo-EM particle picking | SVM |
Ke | 2018 | https://doi.org/10.1107/S1600577518004873 | A convolutional neural network-based screening tool for X-ray serial crystallography | spot finding in serial crystallography | classification via CNN |
Kowiel | 2018 | https://doi.org/10.1093/bioinformatics/bty626 | Automatic recognition of ligands in electron density by machine learning | ligand detection in electron density | k-nearest neighbors, random forest, gradient boosting machine |
Rozanov | 2018 | n/a | AAnchor: CNN guided detection of anchor amino acids in high resolution cryo-EM density maps | automatic model building in cryo-EM | classification via CNN |
Sanchez-Garcia | 2018 | https://doi.org/10.1107/S2052252518014392 | Deep Consensus, a deep learning-based approach for particle pruning in cryo-electron microscopy | cryo-EM particle elimination | classification via CNN |
Thomas | 2018 | n/a | Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds | method | TFN |
Zeng | 2018 | https://doi.org/10.1016/j.jsb.2017.12.015 | A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation | cryo-EM tomography reconstruction | convolutional autoencoder |
Aguiar | 2019 | https://doi.org/10.1126/sciadv.aaw1949 | Decoding crystallography from high-resolution electron imaging and diffraction datasets with deep learning | space group assigment in small molecule ED | classification via CNN |
Al-Azzawi | 2019 | https://doi.org/10.1186/s12859-019-2926-y | AutoCryoPicker: an unsupervised learning approach for fully automated single particle picking in Cryo-EM images | cryo-EM particle picking | clustering |
Alnabati | 2019 | https://doi.org/10.3390/molecules25010082 | Advances in Structure Modeling Methods for Cryo-Electron Microscopy Maps | review | various ML methods |
Avramov | 2019 | https://doi.org/10.3390/molecules24061181 | Deep Learning for Validating and Estimating Resolution of Cryo-Electron Microscopy Density Maps | resolution evaluation in CryoEM | classification via CNN |
Bepler | 2019 | https://doi.org/10.1038/s41592-019-0575-8 | Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs | cryo-EM particle picking | classification via CNN |
Chojnowski | 2019 | https://doi.org/10.1107/S2059798319009392 | Sequence assignment for low-resolution modelling of protein crystal structures | sequence alignment in modelling | classification via SVM |
Conover | 2019 | https://doi.org/10.1515/cmb-2019-0001 | AngularQA: protein model quality assessment with LSTM networks | ||
Gagner | 2019 | https://doi.org/10.1038/s41598-019-55777-5 | Clustering of atomic displacement parameters in bovine trypsin reveals a distributed lattice of atoms with shared chemical properties | ADP similarity | Clustering |
Garcia-Bonete | 2019 | https://doi.org/10.1107/S2053273319011446 | Bayesian machine learning improves single-wavelength anomalous diffraction phasing | anomalous phasing in MX | Bayesian machine learning model |
Ito | 2019 | https://doi.org/10.1107/S160057751900434X | DeepCentering: fully automated crystal centering using deep learning for macromolecular crystallography | crystal centering | object localization via CNN |
Ramirez-Aportela | 2019 | https://doi.org/10.1107/S2052252519011692 | DeepRes: a new deep-learning- and aspect-based local resolution method for electron-microscopy maps | resolution evaluation in CryoEM | regression via CNN |
Schurmann | 2019 | https://doi.org/10.1109/IEEECONF44664.2019.9048793 | Crystal centering using deep learning in X-ray crystallography | crystal centering | object localization via CNN |
Subramaniya | 2019 | https://doi.org/10.1038/s41592-019-0500-1 | Protein secondary structure detection in intermediate-resolution cryo-EM maps using deep learning | cryo-EM secondary structure recognition | classification via CNN |
Sullivan | 2019 | https://doi.org/10.1107/S1600576719008665 | BraggNet: integrating Bragg peaks using neural networks | neutron diffraction improvement | classification via CNN |
Tegunov | 2019 | https://doi.org/10.1038/s41592-019-0580-y | Real-time cryo-electron microscopy data preprocessing with Warp | micrograph preprocessing | CNN |
Vollmar | 2019 | https://doi.org/10.1107/S2052252520000895 | The predictive power of data-processing statistics | MX data quality | classification via random forest and SVM |
Wagner | 2019 | https://doi.org/10.1038/s42003-019-0437-z | SPHIRE-crYOLO is a fast and accurate fully automated particle picker for cryo-EM | cryo-EM particle picking | classification and object localization via CNN |
Xu | 2019 | n/a | A2-Net: Molecular Structure Estimation from Cryo-EM Density Volumes. | amino acid recognition in modelling cryo-EM maps | CNN classification, then MCTS |
Yao | 2019 | https://doi.org/10.1093/bioinformatics/btz728 | Deep-learning with synthetic data enables automated picking of cryo-EM particle images of biological macromolecules. | cryo-EM particle picking | classification via FCN |
Zhang | 2019 | https://doi.org/10.1186/s12859-019-2614-y | PIXER: an automated particle-selection method based on segmentation using a deep neural network | cryo-EM particle picking | AE |
Bepler | 2020 | https://doi.org/10.1038/s41467-020-18952-1 | Topaz-Denoise: general deep denoising models for cryoEM and cryoET | micrograph preprocessing | CNN |
Dalton | 2020 | https://doi.org/10.1101/2021.01.05.425510 | Careless: A Variational Bayesian Model for Merging X-ray Diffraction Data | diffraction data processing | Bayesian machine learning model |
Kappel | 2020 | https://doi.org/10.1038/s41592-020-0878-9 | Accelerated cryo-EM-guided determination of three-dimensional RNA-only structures | ||
Li | 2020 | https://doi.org/10.1109/BIBE50027.2020.00028 | Sequence-guided protein structure determination using graph convolutional and recurrent networks. | GCN | |
Mostosi | 2020 | https://doi.org/10.1002/anie.202000421 | Haruspex: A Neural Network for the Automatic Identification of Oligonucleotides and Protein Secondary Structure in Cryo-Electron Microscopy Maps | cryo-EM secondary structure recognition | classification via CNN |
Sanchez-Garcia | 2020 | https://doi.org/10.1016/j.jsb.2020.107498 | MicrographCleaner: A python package for cryo-EM micrograph cleaning using deep learning | cryo-EM particle elimination | classification via CNN |
Smith | 2020 | https://doi.org/10.1504/IJCBDD.2020.105095 | TopQA: a topological representation for single-model protein quality assessment with machine learning | ||
van Schayck | 2020 | https://doi.org/10.1016/j.ultramic.2020.113091 | Sub-pixel electron detection using a convolutional neural network | detector image processing in EM | CNN |
Chojnowski | 2021 | https://doi.org/10.1101/2021.04.18.440303 | Identification of unknown proteins in X-ray crystallography and cryo-EM | model building in cryo-EM and crystallography | CNN |
Czyzewski | 2021 | https://doi.org/10.1016/j.eswa.2021.114740 | Detecting anomalies in X-ray diffraction images using convolutional neural networks | diffraction image analysis | CNN |
Gagner | 2021 | https://doi.org/10.1088/2632-2153/ac022d | Estimating the probability of coincidental similarity between atomic displacement parameters with machine learning | ADP similarity | Bayesian machine learning model |
George | 2021 | https://doi.org/10.1038/s42003-021-01721-1 | CASSPER is a semantic segmentation-based particle picking algorithm for single-particle cryo-electron microscopy | cryo-EM particle picking | semantic segmentation, CNN |
He | 2021 | https://doi.org/10.1093/bib/bbab156 | EMNUSS: a deep learning framework for secondary structure annotation in cryo-EM maps | cryo-EM secondary structure recognition | classification via CNN |
Kimanius | 2021 | https://doi.org/10.1107/S2052252520014384 | Exploiting prior knowledge about biological macromolecules in cryo-EM structure determination | cryo-EM map reconstruction | AE |
Matsumoto | 2021 | https://doi.org/10.1038/s42256-020-00290-y | Extraction of protein dynamics information from cryo-EM maps using deep learning | cryo-EM dynamics analysis | prediction of the logarithmic RMSF value via CNN |
Miyaguchi | 2021 | https://doi.org/10.21203/rs.3.rs-687363/v1 | QAEmap: A Novel Local Quality Assessment Method for Protein Crystal Structures Using Machine Learning | crystallography model building & validation | ??? via CNN |
Nguyen | 2021 | https://doi.org/10.1186/s12859-020-03948-x | DRPnet: automated particle picking in cryo‑electron micrographs using deep regression | cryo-EM particle picking | object localization and classification via CNN |
Pfab | 2021 | https://doi.org/10.1073/pnas.2017525118 | DeepTracer for fast de novo cryo-EM protein structure modeling and special studies on CoV-related complexes | automatic model building in cryo-EM | classification via CNN |
Sanchez-Garcia | 2021 | https://doi.org/10.1038/s42003-021-02399-1 | DeepEMhancer: a deep learning solution for cryo-EM volume post-processing | cryo-EM map improvement | data processing via CNN |
Si | 2021 | https://doi.org/10.1002/wcms.1542 | Artificial intelligence advances for de novo molecular structure modeling in cryo-electron microscopy | review | AI |
Tegunov | 2021 | https://doi.org/10.1038/s41592-020-01054-7 | Multi-particle cryo-EM refinement with M visualizes ribosome-antibiotic complex at 3.5 Å in cells | reference-free motion correction and CTF estimation | CNN and other |
Zhong | 2021 | https://doi.org/10.1038/s41592-020-01049-4 | CryoDRGN: reconstruction of heterogeneous cryo-EM structures using neural networks | cryo-EM dynamics analysis | VAE |