Filters








19,167 Hits in 4.2 sec

Learning chemical reaction networks from trajectory data [article]

Wei Zhang, Stefan Klus, Tim Conrad, Christof Schütte
2019 arXiv   pre-print
We develop a data-driven method to learn chemical reaction networks from trajectory data.  ...  maximizing the likelihood function of the trajectory data under l^1 sparse regularization.  ...  Learning chemical reaction networks: inverse problem In this section, we study the problem of learning chemical reaction networks from trajectory data.  ... 
arXiv:1902.04920v2 fatcat:kt5iarbwo5bcbgrhlwyveqkgcm

Sparse Regression Based Structure Learning of Stochastic Reaction Networks from Single Cell Snapshot Time Series

Anna Klimovskaia, Stefan Ganscha, Manfred Claassen, Daniel A Beard
2016 PLoS Computational Biology  
We have assessed the structure learning capabilities of the reactionet lasso on synthetic data for the complete TRAIL induced apoptosis signaling cascade comprising 70 reactions.  ...  Stochastic chemical reaction networks constitute a model class to quantitatively describe dynamics and cell-to-cell variability in biological systems.  ...  Two main computational tasks arise when learning any of these models from data: parameter inference, and structure learning.  ... 
doi:10.1371/journal.pcbi.1005234 pmid:27923064 pmcid:PMC5140059 fatcat:mmsid5eoo5fb3js5aeh7yglrru

Value-Added Chemical Discovery Using Reinforcement Learning [article]

Peihong Jiang, Hieu Doan, Sandeep Madireddy, Rajeev Surendran Assary, Prasanna Balaprakash
2019 arXiv   pre-print
Finding viable and short pathways from sugar molecules to value-added chemicals can be modeled as a retrosynthesis planning problem with a catalyst allowed.  ...  While some effort has been made to adapt machine learning techniques to the retrosynthesis planning problem, value-added chemical discovery presents unique challenges.  ...  A trajectory is defined as an attempted path from the initial state to a goal state. Rewards are received only once in each trajectory.  ... 
arXiv:1911.07630v1 fatcat:y5crvdqba5ht5o7nq72ukbusoe

Using an Autoencoder for Dimensionality Reduction in Quantum Dynamics [chapter]

Sebastian Reiter, Thomas Schnappinger, Regina de Vivie-Riedle
2019 Lecture Notes in Computer Science  
After generating a meaningful data set from trajectory calculations, we train an autoencoder to find a lowdimensional set of non-linear coordinates for use in molecular quantum dynamics.  ...  Here, we introduce a machine learning approach for the (semi)automatic construction of reactive coordinates.  ...  The trajectories are started from the intrinsic reaction coordinate (IRC) or in general from any minimum energy path (MEP).  ... 
doi:10.1007/978-3-030-30493-5_73 fatcat:2lqnldg4tfe4nglk7qp7ir6d7m

Deep Abstractions of Chemical Reaction Networks [chapter]

Luca Bortolussi, Luca Palmieri
2018 Lecture Notes in Computer Science  
A more viable strategy is to learn them from single cell simulation data.  ...  In this paper, we explore this direction, constructing abstract models of chemical reaction networks in terms of Discrete Time Markov Chains on a continuous space, and learning transition kernels using  ...  Background Chemical reaction networks Chemical Reaction Networks (CRNs) are the standard formalism to describe dynamical models of biological systems.  ... 
doi:10.1007/978-3-319-99429-1_2 fatcat:2zqorwdqjnhkrlg6dxbwf5v6eu

Automated Deep Abstractions for Stochastic Chemical Reaction Networks

Denis Repin, Tatjana Petrov
2021 Information and Computation  
(CRN) A Chemical Reaction Network is a pair (S, R), such that S = {S 1 , . 143 stochastic chemical kinetics used for modelling molecular interactions, the 144 existence of reaction rates is justified  ...  Each agent 77 is a chemical reaction network (CRN) itself, and agents communicate 78 tion of a collective motion emerging from the mechanistic description 81 of individual dynamics, which would otherwise  ... 
doi:10.1016/j.ic.2021.104788 fatcat:q6kyscgdfzhd7blzh5m7uanxja

When Machine Learning Meets Multiscale Modeling in Chemical Reactions [article]

Wuyue Yang, Liangrong Peng, Yi Zhu, Liu Hong
2020 arXiv   pre-print
Due to the intrinsic complexity and nonlinearity of chemical reactions, direct applications of traditional machine learning algorithms may face with many difficulties.  ...  Our study highlights the necessity and effectiveness of an integration of machine learning algorithms and multiscale modeling during the study of chemical reactions.  ...  However, a direct application of ODENet to learn the time evolution of p(n A , n B ) (or the chemical master equations) from the training data generated by stochastic simulations is prohibited due to heavy  ... 
arXiv:2006.00700v1 fatcat:r7ccjwjdzfc6xlhtnczggf5wri

Automated Deep Abstractions for Stochastic Chemical Reaction Networks [article]

Tatjana Petrov, Denis Repin
2020 arXiv   pre-print
Predicting stochastic cellular dynamics as emerging from the mechanistic models of molecular interactions is a long-standing challenge in systems biology: low-level chemical reaction network (CRN) models  ...  time intervals (which can obtained either by simulating a given CRN or as time-series data from experiment).  ...  Low-level mechanisms of molecular interactions are usually hypothesised in form of chemical reaction networks. Each reaction fires with a corresponding rate.  ... 
arXiv:2002.01889v1 fatcat:623bkhtxgfbdzhoe77ochltoma

Deep learning analysis of defect and phase evolution during electron beam-induced transformations in WS2

Artem Maksov, Ondrej Dyck, Kai Wang, Kai Xiao, David B. Geohegan, Bobby G. Sumpter, Rama K. Vasudevan, Stephen Jesse, Sergei V. Kalinin, Maxim Ziatdinov
2019 npj Computational Materials  
This approach is universal and its application to beam induced reactions allows mapping chemical transformation pathways in solids at the atomic level.  ...  This framework allows extracting thousands of lattice defects from raw STEM data (single images and movies) in a matter of seconds, which are then classified into different categories using unsupervised  ...  INTRODUCTION Chemical reactions and phase transformations underpin phenomena ranging from cosmological processes, to the emergence of life on Earth, to modern technologies and are therefore of tremendous  ... 
doi:10.1038/s41524-019-0152-9 fatcat:5krtkavwajekdpyodbj4n3eugq

Estimating information in time-varying signals [article]

Sarah A Cepeda-Humerez and Jakob Ruess and Gašper Tkačik
2018 arXiv   pre-print
For biological reaction networks governed by the chemical Master equation, we derive model-based information approximations and analytical upper bounds, against which we benchmark our proposed model-free  ...  A pressing data-analysis challenge has thus been to efficiently estimate the amount of information that these dynamics convey from experimental data.  ...  core, cellular processes consist of networks of chemical reactions. A chemical reaction network consists of a set of m molecular species {X 1 ,X 2 , . . .  ... 
arXiv:1812.11884v1 fatcat:oa4hklp6gzgvjpnfuyjnvjufmq

DeepCME: A deep learning framework for computing solution statistics of the chemical master equation

Ankit Gupta, Christoph Schwab, Mustafa Khammash, James R. Faeder
2021 PLoS Computational Biology  
Stochastic models of biomolecular reaction networks are commonly employed in systems and synthetic biology to study the effects of stochastic fluctuations emanating from reactions involving species with  ...  This allows not just the numerical approximation of various expectations for the CME solution but also of its sensitivities with respect to all the reaction network parameters (e.g. rate constants).  ...  The central object of interest in stochastic reaction network models is a high-dimensional system of linear ODEs, called the Chemical Master Equation (CME).  ... 
doi:10.1371/journal.pcbi.1009623 pmid:34879062 pmcid:PMC8687598 fatcat:i3z4rewtsfhjtk2bjhd5zth57m

Learning reduced kinetic Monte Carlo models of complex chemistry from molecular dynamics

Qian Yang, Carlos A. Sing-Long, Evan J. Reed
2017 Chemical Science  
We propose a novel statistical learning framework for automatically and efficiently building reduced kinetic Monte Carlo (KMC) models of large-scale elementary reaction networks from data generated by  ...  We show that the resulting models are able to extrapolate in time to new regions of molecular concentration space, which suggests that KMC models learned from molecular dynamics data can be used to meaningfully  ...  We dene a chemical reaction network to be a set of elementary reactions and their corresponding rates of reaction.  ... 
doi:10.1039/c7sc01052d pmid:28989618 pmcid:PMC5625287 fatcat:mhu7poof75g2rjuj3bvuw57u34

Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learning [article]

Julien Horwood, Emmanuel Noutahi
2020 arXiv   pre-print
This becomes possible by defining transitions in our Markov Decision Process as chemical reactions, and allows us to leverage synthetic routes as an inductive bias.  ...  We instead propose a novel Reinforcement Learning framework for molecular design in which an agent learns to directly optimize through a space of synthetically-accessible drug-like molecules.  ...  These approaches generally ensure validity of the generated compounds and avoid the need to learn a latent space mapping from the data.  ... 
arXiv:2004.14308v2 fatcat:dbmnzvy3mfdl5np7hlnwsz3ama

Machine Learning for the Dynamic Scanning Transmission Electron Microscopy Experiment on Solid State Transformations

Maxim Ziatdinov, Artem Maksov, Ondrej Dyck, Stephen Jesse, Sergei V. Kalinin
2018 Microscopy and Microanalysis  
Here we developed a deep-learning-based approach for elucidating the solid-state transformations and reaction pathways from dynamic STEM data on 2dimensional Mo-doped WS 2 .  ...  Yet despite large volumes of data generated in STEM experiments, the available to date analytical tools do not allow to learn much from the collected data.  ...  Here we developed a deep-learning-based approach for elucidating the solid-state transformations and reaction pathways from dynamic STEM data on 2dimensional Mo-doped WS 2 .  ... 
doi:10.1017/s1431927618008486 fatcat:e7sd43vbz5bsxix66gspjnasoy

Estimating information in time-varying signals

Sarah Anhala Cepeda-Humerez, Jakob Ruess, Gašper Tkačik, Alexandre V. Morozov
2019 PLoS Computational Biology  
For biological reaction networks governed by the chemical Master equation, we derive model-based information approximations and analytical upper bounds, against which we benchmark our proposed model-free  ...  A pressing data-analysis challenge has thus been to efficiently estimate the amount of information that these dynamics convey from experimental data.  ...  Models and methods Biochemical reaction networks At their core, cellular processes consist of networks of chemical reactions.  ... 
doi:10.1371/journal.pcbi.1007290 pmid:31479447 pmcid:PMC6743786 fatcat:xd42ac4wzvdx5ocs63szasj2qu
« Previous Showing results 1 — 15 out of 19,167 results