Anne Condon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Anne Condon has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Holger H. Hoos
RWTH Aachen University
6 shared publications - Khanh Dao Duc
Department of Mathematics, University of British Columbia, Vancouver, Canada
6 shared publications - Chenwei Zhang
Department of Computer Science, University of British Columbia , ICICS/CS Building 201-2366 Main Mall, Vancouver BC V6T 1Z4
4 shared publications - Ján Maňuch
University of British Columbia
3 shared publications - Sohrab P. Shah
Memorial Sloan Kettering Cancer Center
3 shared publications - Baharak Rastegari
University of Southampton Southampton UK
2 shared publications
Latest Publications
- Open Access
- 2 July 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (4)
A comprehensive survey and benchmark of deep learning-based methods for atomic model building from cryo-electron microscopy density maps
Advancements in deep learning (DL) have recently led to new methods for automated construction of atomic models of proteins, from single-particle cryogenic electron microscopy (cryo-EM) density maps. We conduct a comprehensive survey of these methods, distinguishing between direct model building approaches that only use density maps, and indirect ones that integrate sequence-to-structure predictions from AlphaFold. To evaluate them with better precision, we refine standard existing metrics, and benchmark a subset of representative DL-methods against traditional physics-based approaches using 50 cryo-EM density maps at varying resolutions. Our findings demonstrate that overall, DL-based methods outperform traditional physics-based methods. Our benchmark also shows the benefit of integrating AlphaFold as it improved the completeness and accuracy of the model, although its dependency on available sequence information and limited training data may limit its usage.
- 2 July 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (4)
Open AccessA comprehensive survey and benchmark of deep learning-based methods for atomic model building from cryo-electron microscopy density maps
Advancements in deep learning (DL) have recently led to new methods for automated construction of atomic models of proteins, from single-particle cryogenic electron microscopy (cryo-EM) density maps. We conduct a comprehensive survey of these methods, distinguishing between direct model building approaches that only use density maps, and indirect ones that integrate sequence-to-structure predictions from AlphaFold. To evaluate them with better precision, we refine standard existing metrics, and benchmark a subset of representative DL-methods against traditional physics-based approaches using 50 cryo-EM density maps at varying resolutions. Our findings demonstrate that overall, DL-based methods outperform traditional physics-based methods. Our benchmark also shows the benefit of integrating AlphaFold as it improved the completeness and accuracy of the model, although its dependency on available sequence information and limited training data may limit its usage.
- Open Access
- 29 April 2025
- Published by American Physical Society (APS) in PRX Life
- Vol. 3 (2)
Alignment of Partially Overlapping Cryo-EM Maps Using Unbalanced Gromov-Wasserstein Divergence
Aligning EM density maps and fitting atomic models are essential steps in single-particle cryogenic electron microscopy (cryo-em), with recent methods leveraging various algorithms and machine learning tools. As aligning maps remains challenging in the presence of a map that only partially fits the other (e.g., one subunit), we here propose a procedure, em partial alignment with optimal transport (EMPOT), for partial alignment of three-dimensional (3D) maps. EMPOT finds a coupling between 3D point-cloud representations, which is associated with their so-called unbalanced Gromov Wasserstein divergence, and uses this coupling to find an optimal rigid body transformation. On running and benchmarking our method with experimental maps and structures, we show that EMPOT outperforms standard methods for aligning density maps and fitting atomic models to a density map, suggesting potential applications of partial optimal transport for improving cryo-em pipelines.
- 29 April 2025
- Published by American Physical Society (APS) in PRX Life
- Vol. 3 (2)
Open AccessAlignment of Partially Overlapping Cryo-EM Maps Using Unbalanced Gromov-Wasserstein Divergence
Aligning EM density maps and fitting atomic models are essential steps in single-particle cryogenic electron microscopy (cryo-em), with recent methods leveraging various algorithms and machine learning tools. As aligning maps remains challenging in the presence of a map that only partially fits the other (e.g., one subunit), we here propose a procedure, em partial alignment with optimal transport (EMPOT), for partial alignment of three-dimensional (3D) maps. EMPOT finds a coupling between 3D point-cloud representations, which is associated with their so-called unbalanced Gromov Wasserstein divergence, and uses this coupling to find an optimal rigid body transformation. On running and benchmarking our method with experimental maps and structures, we show that EMPOT outperforms standard methods for aligning density maps and fitting atomic models to a density map, suggesting potential applications of partial optimal transport for improving cryo-em pipelines.
- Open Access
A comprehensive survey and benchmark of deep learning-based methods for atomic model building from cryo-EM density maps
Advancements in deep learning (DL) have recently led to new methods for automated construction of atomic models of proteins, from single-particle cryogenic electron microscopy (cryo-EM) density maps. We conduct a comprehensive survey of these methods, distinguishing between direct model building approaches that only use density maps, and indirect ones that integrate sequence-to-structure predictions from AlphaFold. To evaluate them with better precision, we refine standard existing metrics, and benchmark a subset of representative DLmethods against traditional physics-based approaches using 50 cryo-EM density maps at varying resolutions. Our findings demonstrate that overall, DL-based methods outperform traditional physics-based methods. Our benchmark also shows the benefit of integrating AlphaFold as it improved the completeness and accuracy of the model, although its dependency on available sequence information and limited training data may limit its usage.
Open AccessA comprehensive survey and benchmark of deep learning-based methods for atomic model building from cryo-EM density maps
Advancements in deep learning (DL) have recently led to new methods for automated construction of atomic models of proteins, from single-particle cryogenic electron microscopy (cryo-EM) density maps. We conduct a comprehensive survey of these methods, distinguishing between direct model building approaches that only use density maps, and indirect ones that integrate sequence-to-structure predictions from AlphaFold. To evaluate them with better precision, we refine standard existing metrics, and benchmark a subset of representative DLmethods against traditional physics-based approaches using 50 cryo-EM density maps at varying resolutions. Our findings demonstrate that overall, DL-based methods outperform traditional physics-based methods. Our benchmark also shows the benefit of integrating AlphaFold as it improved the completeness and accuracy of the model, although its dependency on available sequence information and limited training data may limit its usage.
- Open Access
- 26 December 2024
- Published by Oxford University Press (OUP) in Bioinformatics Advances
- Vol. 5 (1)
Struc2mapGAN: improving synthetic cryogenic electron microscopy density maps with generative adversarial networks
Motivation: Generating synthetic cryogenic electron microscopy 3D density maps from molecular structures has potential important applications in structural biology. Yet existing simulation-based methods cannot mimic all the complex features present in experimental maps, such as secondary structure elements. As an alternative, we propose struc2mapGAN. Results: Struc2mapGAN is a novel data-driven method that employs a generative adversarial network to produce improved experimental-like density maps from molecular structures. More specifically, struc2mapGAN uses a nested U-Net architecture as the generator, with an additional L1 loss term and further processing of raw training experimental maps to enhance learning efficiency. While struc2mapGAN can promptly generate maps after training, we demonstrate that it outperforms existing simulation-based methods for a wide array of tested maps and across various evaluation metrics. Availability and implementation: The struc2mapGAN is publicly accessible via https://github.com/chenwei-zhang/struc2mapGAN.
- 26 December 2024
- Published by Oxford University Press (OUP) in Bioinformatics Advances
- Vol. 5 (1)
Open AccessStruc2mapGAN: improving synthetic cryogenic electron microscopy density maps with generative adversarial networks
Motivation: Generating synthetic cryogenic electron microscopy 3D density maps from molecular structures has potential important applications in structural biology. Yet existing simulation-based methods cannot mimic all the complex features present in experimental maps, such as secondary structure elements. As an alternative, we propose struc2mapGAN. Results: Struc2mapGAN is a novel data-driven method that employs a generative adversarial network to produce improved experimental-like density maps from molecular structures. More specifically, struc2mapGAN uses a nested U-Net architecture as the generator, with an additional L1 loss term and further processing of raw training experimental maps to enhance learning efficiency. While struc2mapGAN can promptly generate maps after training, we demonstrate that it outperforms existing simulation-based methods for a wide array of tested maps and across various evaluation metrics. Availability and implementation: The struc2mapGAN is publicly accessible via https://github.com/chenwei-zhang/struc2mapGAN.
- Open Access
Visualizing DNA reaction trajectories with deep graph embedding approaches
Synthetic biologists and molecular programmers design novel nucleic acid reactions, with many potential applications. Good visualization tools are needed to help domain experts make sense of the complex outputs of folding pathway simulations of such reactions. Here we present ViDa, a new approach for visualizing DNA reaction folding trajectories over the energy landscape of secondary structures. We integrate a deep graph embedding model with common dimensionality reduction approaches, to map high-dimensional data onto 2D Euclidean space. We assess ViDa on two well-studied and contrasting DNA hybridization reactions. Our preliminary results suggest that ViDa's visualization successfully separates trajectories with different folding mechanisms, thereby providing useful insight to users, and is a big improvement over the current state-of-the-art in DNA kinetics visualization.
Open AccessVisualizing DNA reaction trajectories with deep graph embedding approaches
Synthetic biologists and molecular programmers design novel nucleic acid reactions, with many potential applications. Good visualization tools are needed to help domain experts make sense of the complex outputs of folding pathway simulations of such reactions. Here we present ViDa, a new approach for visualizing DNA reaction folding trajectories over the energy landscape of secondary structures. We integrate a deep graph embedding model with common dimensionality reduction approaches, to map high-dimensional data onto 2D Euclidean space. We assess ViDa on two well-studied and contrasting DNA hybridization reactions. Our preliminary results suggest that ViDa's visualization successfully separates trajectories with different folding mechanisms, thereby providing useful insight to users, and is a big improvement over the current state-of-the-art in DNA kinetics visualization.
- 27 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 20 (6) , 3842-3850
AlignOT: An Optimal Transport Based Algorithm for Fast 3D Alignment With Applications to Cryogenic Electron Microscopy Density Maps
Aligning electron density maps from Cryogenic electron microscopy (cryo-EM) is a first key step for studying multiple conformations of a biomolecule. As this step remains costly and challenging, with standard alignment tools being potentially stuck in local minima, we propose here a new procedure, called AlignOT , which relies on the use of computational optimal transport (OT) to align EM maps in 3D space. By embedding a fast estimation of OT maps within a stochastic gradient descent algorithm, our method searches for a rotation that minimizes the Wasserstein distance between two maps, represented as point clouds. We quantify the impact of various parameters on the precision and accuracy of the alignment, and show that AlignOT can outperform the standard local alignment methods, with an increased range of rotation angles leading to proper alignment. We further benchmark AlignOT on various pairs of experimental maps, which account for different types of conformational heterogeneities and geometric properties. As our experiments show good performance, we anticipate that our method can be broadly applied to align 3D EM maps.
- 27 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 20 (6) , 3842-3850
AlignOT: An Optimal Transport Based Algorithm for Fast 3D Alignment With Applications to Cryogenic Electron Microscopy Density Maps
Aligning electron density maps from Cryogenic electron microscopy (cryo-EM) is a first key step for studying multiple conformations of a biomolecule. As this step remains costly and challenging, with standard alignment tools being potentially stuck in local minima, we propose here a new procedure, called AlignOT , which relies on the use of computational optimal transport (OT) to align EM maps in 3D space. By embedding a fast estimation of OT maps within a stochastic gradient descent algorithm, our method searches for a rotation that minimizes the Wasserstein distance between two maps, represented as point clouds. We quantify the impact of various parameters on the precision and accuracy of the alignment, and show that AlignOT can outperform the standard local alignment methods, with an increased range of rotation angles leading to proper alignment. We further benchmark AlignOT on various pairs of experimental maps, which account for different types of conformational heterogeneities and geometric properties. As our experiments show good performance, we anticipate that our method can be broadly applied to align 3D EM maps.
- 24 February 2023
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 104, 107837
Predicting DNA kinetics with a truncated continuous-time Markov chain method
- 24 February 2023
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 104, 107837
Predicting DNA kinetics with a truncated continuous-time Markov chain method
- Open Access
The pathway elaboration method for mean first passage time estimation in large continuous-time Markov chains with applications to nucleic acid kinetics
For predicting the kinetics of nucleic acid reactions, continuous-time Markov chains (CTMCs) are widely used. The rate of a reaction can be obtained through the mean first passage time (MFPT) of its CTMC. However, a typical issue in CTMCs is that the number of states could be large, making MFPT estimation challenging, particularly for events that happen on a long time scale (rare events). We propose the pathway elaboration method, a time-efficient probabilistic truncation-based approach for detailed-balance CTMCs. It can be used for estimating the MFPT for rare events in addition to rapidly evaluating perturbed parameters without expensive recomputations. We demonstrate that pathway elaboration is suitable for predicting nucleic acid kinetics by conducting computational experiments on 267 measurements that cover a wide range of rates for different types of reactions. We utilize pathway elaboration to gain insight on the kinetics of two contrasting reactions, one being a rare event. We then compare the performance of pathway elaboration with the stochastic simulation algorithm (SSA) for MFPT estimation on 237 of the reactions for which SSA is feasible. We further build truncated CTMCs with SSA and transition path sampling (TPS) to compare with pathway elaboration. Finally, we use pathway elaboration to rapidly evaluate perturbed model parameters during optimization with respect to experimentally measured rates for these 237 reactions. The testing error on the remaining 30 reactions, which involved rare events and were not feasible to simulate with SSA, improved comparably with the training error. Our framework and dataset are available at https://github.com/ DNA-and-Natural-Algorithms-Group/PathwayElaboration.
Open AccessThe pathway elaboration method for mean first passage time estimation in large continuous-time Markov chains with applications to nucleic acid kinetics
For predicting the kinetics of nucleic acid reactions, continuous-time Markov chains (CTMCs) are widely used. The rate of a reaction can be obtained through the mean first passage time (MFPT) of its CTMC. However, a typical issue in CTMCs is that the number of states could be large, making MFPT estimation challenging, particularly for events that happen on a long time scale (rare events). We propose the pathway elaboration method, a time-efficient probabilistic truncation-based approach for detailed-balance CTMCs. It can be used for estimating the MFPT for rare events in addition to rapidly evaluating perturbed parameters without expensive recomputations. We demonstrate that pathway elaboration is suitable for predicting nucleic acid kinetics by conducting computational experiments on 267 measurements that cover a wide range of rates for different types of reactions. We utilize pathway elaboration to gain insight on the kinetics of two contrasting reactions, one being a rare event. We then compare the performance of pathway elaboration with the stochastic simulation algorithm (SSA) for MFPT estimation on 237 of the reactions for which SSA is feasible. We further build truncated CTMCs with SSA and transition path sampling (TPS) to compare with pathway elaboration. Finally, we use pathway elaboration to rapidly evaluate perturbed model parameters during optimization with respect to experimentally measured rates for these 237 reactions. The testing error on the remaining 30 reactions, which involved rare events and were not feasible to simulate with SSA, improved comparably with the training error. Our framework and dataset are available at https://github.com/ DNA-and-Natural-Algorithms-Group/PathwayElaboration.
- 8 August 2019
- Published by Springer Nature in Natural Computing
- Vol. 19 (1) , 249-270
Approximate majority analyses using tri-molecular chemical reaction networks
- 8 August 2019
- Published by Springer Nature in Natural Computing
- Vol. 19 (1) , 249-270
Approximate majority analyses using tri-molecular chemical reaction networks
- 29 June 2018
- Published by Springer Nature
- p. 1-3
On Design and Analysis of Chemical Reaction Network Algorithms
- 29 June 2018
- Published by Springer Nature
- p. 1-3
On Design and Analysis of Chemical Reaction Network Algorithms