Machine Learning for Molecular dynamics — Why bother?
Simon Olsson
Chalmers University of Technology
20 October 2021
Online
With faster compute-infrastructures, molecular simulations play an increasingly important role in the basic sciences and application areas such as drug and materials design. Simultaneously, machine learning and artificial intelligence are receiving increased attention due to increasing volumes of data generated both inside and outside of science. In this talk, I will talk about a few applications of these technologies in molecular simulation, focusing on biomolecular simulations [1,2]
[1] Olsson & Noé ”Dynamic Graphical Models of Molecular Kinetics” Proc. Natl. Acad. Sci. U.S.A. (2019) doi: 10.1073/pnas.1901692116.
[2] Noe†, Olsson, Köhler, Wu ”Boltzmann Generators: Sampling Equilibrium States of Many-Body Systems with Deep Learning” Science (2019). 365, eaaw1147. doi:10.1126/science.aaw1147.
Video microscopy has a long history of providing insights and breakthroughs for a broad range of disciplines, from physics to biology. Image analysis to extract quantitative information from video microscopy data has traditionally relied on algorithmic approaches, which are often difficult to implement, time consuming, and computationally expensive. Recently, alternative data-driven approaches using deep learning have greatly improved quantitative digital microscopy, potentially offering automatized, accurate, and fast image analysis. However, the combination of deep learning and video microscopy remains underutilized primarily due to the steep learning curve involved in developing custom deep-learning solutions. To overcome this issue, we introduce a software, DeepTrack 2.0, to design, train and validate deep-learning solutions for digital microscopy. We use it to exemplify how deep learning can be employed for a broad range of applications, from particle localization, tracking and characterization to cell counting and classification. Thanks to its user-friendly graphical interface, DeepTrack 2.0 can be easily customized for user-specific applications, and, thanks to its open-source object-oriented programming, it can be easily expanded to add features and functionalities, potentially introducing deep-learning-enhanced video microscopy to a far wider audience.
After a brief overview of artificial intelligence, machine learning and deep learning, I will present a series of recent works in which we have employed deep learning for applications in photonics and active matter. In particular, I will explain how we employed deep learning to enhance digital video microscopy, to estimate the properties of anomalous diffusion, to characterize microscopic force fields, to improve the calculation of optical forces, and to characterize nanoparticles. Finally, I will provide an outlook for the application of deep learning in photonics and active matter.
Countless systems in biology, physics, and finance undergo diffusive dynamics. Many of these systems, including biomolecules inside cells, active matter systems and foraging animals, exhibit anomalous dynamics where the growth of the mean squared displacement with time follows a power law with an exponent that deviates from 1. When studying time series recording the evolution of these systems, it is crucial to precisely measure the anomalous exponent and confidently identify the mechanisms responsible for anomalous diffusion. These tasks can be overwhelmingly difficult when only few short trajectories are available, a situation that is common in the study of non-equilibrium and living systems. Here, we present a data-driven method to analyze single anomalous diffusion trajectories employing recurrent neural networks, which we name RANDI. We show that our method can successfully infer the anomalous exponent, identify the type of anomalous diffusion process, and segment the trajectories of systems switching between different behaviors. We benchmark our performance against the state-of-the art techniques for the study of single short trajectories that participated in the Anomalous Diffusion (AnDi) challenge. Our method proved to be the most versatile method, being the only one to consistently rank in the top 3 for all tasks proposed in the AnDi challenge.
DeepTrack 2.0 Logo. (Image from DeepTrack 2.0 Project)Quantitative Digital Microscopy with Deep Learning Giovanni Volpe
Invited Talk at the Virtual school “Machine Learning and Automated Experiment in Scanning Probe Microscopy”
Online
October 4-7, 2021
11:20 AM
Video microscopy has a long history of providing insights and breakthroughs for a broad range of disciplines, from physics to biology. Image analysis to extract quantitative information from video microscopy data has traditionally relied on algorithmic approaches, which are often difficult to implement, time consuming, and computationally expensive. Recently, alternative data-driven approaches using deep learning have greatly improved quantitative digital microscopy, potentially offering automatized, accurate, and fast image analysis. However, the combination of deep learning and video microscopy remains underutilized primarily due to the steep learning curve involved in developing custom deep-learning solutions. To overcome this issue, we introduce a software, DeepTrack 2.0, to design, train and validate deep- learning solutions for digital microscopy. We use it to exemplify how deep learning can be employed for a broad range of applications, from particle localization, tracking and characterization to cell counting and classification. Thanks to its user- friendly graphical interface, DeepTrack 2.0 can be easily customized for user-specific applications, and, thanks to its open-source object-oriented programming, it can be easily expanded to add features and functionalities, potentially introducing deep-learning-enhanced video microscopy to a far wider audience.
Neural net with input layer (left), dense internal layers, and output layer (right). (Image from the article Machine Learning for Active Matter)Machine Learning for Active Matter: Opportunities and Challenges
Giovanni Volpe
Invited Talk
(online at) ICTP, Trieste, Italy
8 September 2021, 11:30 CEST
Machine-learning methods are starting to shape active-matter research. Which new trends will this start? Which new groundbreaking insight and applications can we expect? More fundamentally, what can this contribute to our understanding of active matter? Can this help us to identify unifying principles and systematise active matter? This presentation addresses some of these questions with some concrete examples, exploring how machine learning is steering active matter towards new directions, offering unprecedented opportunities and posing practical and fundamental challenges. I will illustrate some most successful recent applications of machine learning to active matter with a slight bias towards work done in my research group: enhancing data acquisition and analysis; providing new data-driven models; improving navigation and search strategies; offering insight into the emergent dynamics of active matter in crowded and complex environments. I will discuss the opportunities and challenges that are emerging: implementing feedback control; uncovering underlying principles to systematise active matter; understanding the behaviour, organisation and evolution of biological active matter; realising active matter with embodied intelligence. Finally, I will highlight how active matter and machine learning can work together for mutual benefit.
Laura Pérez presented the work “FORMA and BEFORE: expanding applications of optical tweezers” at the ELS conference (online) on the 13th of July.
The main objective of the Electromagnetic and Light Scattering Conference (ELS) is to bring together scientists and engineers studying various aspects of light scattering and to provide a relaxed academic atmosphere for in-depth discussions of theoretical advances, measurements, and applications.
FORMA allows to identify and characterize all the equilibrium points in a force field generated by a speckle pattern.FORMA and BEFORE: Expanding Applications of Optical Tweezers. Laura Pérez Garcia, Martin Selin, Alejandro V. Arzola, Giovanni Volpe, Alessandro Magazzù, Isaac Pérez Castillo.
ELS 2021 Date: 13 July 2021 Time: 15:45 (CEST)
Abstract:
FORMA (force reconstruction via maximum-likelihood-estimator analysis) addresses the need to measure the force fields acting on microscopic particles. Compared to alternative established methods, FORMA is faster, simpler, more accurate, and more precise. Furthermore, FORMA can also measure non-conservative and out-of-equilibrium force fields. Here, after a brief introduction to FORMA, I will present its use, advantages, and limitations. I will conclude with the most recent work where we exploit Bayesian inference to expand FORMA’s scope of application.
Deep learning for particle tracking. (Image by Aykut Argun)Deep learning for microscopy, optical trapping, and active matter
Giovanni Volpe
Colloquium
(online at) TU-Darmstadt, Germany
18 June 2021, 14:00 CEST
After a brief overview of artificial intelligence, machine learning and deep learning, I will present a series of recent works in which we have employed deep learning for applications in photonics and active matter.
In particular, I will explain how we employed deep learning to enhance digital video microscopy, to estimate the properties of anomalous diffusion, to characterize microscopic force fields, to improve the calculation of optical forces, and to characterize nanoparticles.
Finally, I will provide an outlook for the application of deep learning in photonics and active matter.
Comparison of different evolution regimes of disease spreading: free evolution (bottom left half) vs network strategy (top right half). (Image by Laura Natali.)Improving epidemic testing and containment strategies using machine learning. Laura Natali, Saga Helgadottir, Onofrio M. Maragò, Giovanni Volpe. Submitted to SDS2020 Date: 11 June Time: 16:15 (CEST)
Abstract:
Containment of epidemic outbreaks entails great societal and economic costs. Cost-effective containment strategies rely on efficiently identifying infected individuals, making the best possible use of the available testing resources. Therefore, quickly identifying the optimal testing strategy is of critical importance. Here, we demonstrate that machine learning can be used to identify which individuals are most beneficial to test, automatically and dynamically adapting the testing strategy to the characteristics of the disease outbreak. Specifically, we simulate an outbreak using the archetypal susceptible-infectious-recovered (SIR) model and we use data about the first confirmed cases to train a neural network that learns to make predictions about the rest of the population. Using these prediction, we manage to contain the outbreak more effectively and more quickly than with standard approaches. Furthermore, we demonstrate how this method can be used also when there is a possibility of reinfection (SIRS model) to efficiently eradicate an endemic disease.
Deep learning for particle tracking. (Image by Aykut Argun.)Quantitative Digital Microscopy with Deep Learning Giovanni Volpe
Seminar Vi2 Seminar (Visual Information and Interaction)
University of Uppsala
17 May 2021, 14:15 CEST
Online
Video microscopy has a long history of providing insights and breakthroughs for a broad range of disciplines, from physics to biology. Image analysis to extract quantitative information from video microscopy data has traditionally relied on algorithmic approaches, which are often difficult to implement, time consuming, and computationally expensive. Recently, alternative data-driven approaches using deep learning have greatly improved quantitative digital microscopy, potentially offering automatized, accurate, and fast image analysis. However, the combination of deep learning and video microscopy remains underutilized primarily due to the steep learning curve involved in developing custom deep-learning solutions. To overcome this issue, we introduce a software, DeepTrack 2.0, to design, train and validate deep-learning solutions for digital microscopy. We use it to exemplify how deep learning can be employed for a broad range of applications, from particle localization, tracking and characterization to cell counting and classification. Thanks to its user-friendly graphical interface, DeepTrack 2.0 can be easily customized for user-specific applications, and, thanks to its open-source object-oriented programming, it can be easily expanded to add features and functionalities, potentially introducing deep-learning-enhanced video microscopy to a far wider audience.
Bio: Giovanni Volpe is Professor at the Physics Department at the University of Gothenburg (Gothenburg, Sweden), where he has been leading the Soft Matter Lab since 2016. He has established a strong research group of 18 people (3 postdocs, 12 PhD students, 3 Master students, http://www.softmatterlab.org ) with an externally-funded, ambitious and interdisciplinary research program that combines soft condensed matter, optical manipulation, nanotechnology, and machine learning. He has attracted external funding exceeding 6M €, including several national and European grants such as the ERC-StG ComplexSwimmers (2016-2021) and the ERC-CoG MAPEI (2021-2026). He is a co-funder of the startup companies Lucero Bio and IFLAI.
Link: Vi2 Seminars (zoom link included in the webpage)
