Inverse statistical problems: from the inverse Ising problem to data science

Inverse problems in statistical physics are motivated by the challenges of ‘big data’ in different fields, in particular high-throughput experiments in biology. In inverse problems, the usual procedure of statistical physics needs to be reversed: Instead of calculating observables on the basis of model parameters, we seek to infer parameters of a model based on observations. In this review, we focus on the inverse Ising problem and closely related problems, namely how to infer the coupling strengths between spins given observed spin correlations, magnetizations, or other data. We review applications of the inverse Ising problem, including the reconstruction of neural connections, protein structure determination, and the inference of gene regulatory networks. For the inverse Ising problem in equilibrium, a number of controlled and uncontrolled approximate solutions have been developed in the statistical mechanics community. A particularly strong method, pseudolikelihood, stems from statistics. We also review the inverse Ising problem in the non-equilibrium case, where the model parameters must be reconstructed based on non-equilibrium statistics.

• Publication year

  2017

• Venue

  Advances in Physics

• Publication date

  2017-02-06

• Fields of study

  Biology, Physics, Computer Science

• Identifiers
  DOI 10.1080/00018732.2017.1341604arXiv 1702.01522
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Thermodynamics from Information

  2018cited by this paper
• A statistical physics approach to learning curves for the inverse Ising problem

  2017cited by this paper
• Inverse statistical physics of protein sequences: a key issues review

  2017cited by this paper
• Protein structure determination using metagenome sequence data

  2017cited by this paper
• Deep Learning

  2016cited by this paper
• Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model

  2016cited by this paper
• The Maximum Entropy Fallacy Redux?

  2016cited by this paper
• Inferring Contacting Residues within and between Proteins: What Do the Probabilities Mean?

  2016cited by this paper
• Sparse model selection in the highly under-sampled regime

  2016influential reference
• Network inference in the nonequilibrium steady state.

  2016cited by this paper
• Emergence of plasmid-mediated colistin resistance mechanism MCR-1 in animals and human beings in China: a microbiological and molecular biological study.

  2016cited by this paper
• Antimicrobial resistance: a major threat to public health

  2016cited by this paper
• Optimal structure and parameter learning of Ising models

  2016cited by this paper
• Interaction Screening: Efficient and Sample-Optimal Learning of Ising Models

  2016cited by this paper
• Machine learning phases of matter

  2016influential reference
• PSEUDOLIKELIHOOD ESTIMATION : SOME EXAMPLES

  2016cited by this paper
• Statistical mechanics of the inverse Ising problem and the optimal objective function

  2016cited by this paper
• Inverse problem in classical statistical mechanics

  2016cited by this paper
• Growth against entropy in bacterial metabolism: the phenotypic trade-off behind empirical growth rate distributions in E. coli

  2016cited by this paper
• ACE: adaptive cluster expansion for maximum entropy graphical model inference

  2016cited by this paper
• Learning maximum entropy models from finite-size data sets: A fast data-driven algorithm allows sampling from the posterior distribution.

  2016cited by this paper
• Approximated Newton Algorithm for the Ising Model Inference Speeds Up Convergence, Performs Optimally and Avoids Over-fitting

  2015cited by this paper
• Learning with hidden variables

  2015cited by this paper
• Electrophysiological, transcriptomic and morphologic profiling of single neurons using Patch-seq

  2015cited by this paper
• Resummed mean-field inference for strongly coupled data.

  2015cited by this paper
• Measuring entanglement entropy in a quantum many-body system

  2015cited by this paper
• Cell types in the mouse cortex and hippocampus revealed by single-cell RNA-seq

  2015cited by this paper
• Quantification of the effect of mutations using a global probability model of natural sequence variation

  2015cited by this paper
• Revealing neuronal function through microelectrode array recordings

  2015cited by this paper
• Highly Parallel Genome-wide Expression Profiling of Individual Cells Using Nanoliter Droplets.

  2015cited by this paper
• Thermodynamics and signatures of criticality in a network of neurons

  2015influential reference
• Learning of couplings for random asymmetric kinetic Ising models revisited: random correlation matrices and learning curves

  2015cited by this paper
• Do-calculus when the True Graph Is Unknown

  2015cited by this paper
• Topology, structures, and energy landscapes of human chromosomes

  2015cited by this paper
• A General Approximation for the Dynamics of Quantitative Traits

  2015cited by this paper
• Inferring Pairwise Interactions from Biological Data Using Maximum-Entropy Probability Models

  2015cited by this paper
• Density-matrix based determination of low-energy model Hamiltonians from ab initio wavefunctions.

  2015cited by this paper
• On the Sufficiency of Pairwise Interactions in Maximum Entropy Models of Networks

  2015cited by this paper
• U.S. stock market interaction network as learned by the Boltzmann machine

  2015cited by this paper
• Causal analysis, Correlation-Response, and Dynamic cavity

  2015cited by this paper
• Statistical physics of inference: thresholds and algorithms

  2015cited by this paper
• Belief propagation and replicas for inference and learning in a kinetic Ising model with hidden spins

  2014cited by this paper
• Large pseudocounts and L2-norm penalties are necessary for the mean-field inference of Ising and Potts models.

  2014cited by this paper
• The Fitness Landscape of HIV-1 Gag: Advanced Modeling Approaches and Validation of Model Predictions by In Vitro Testing

  2014cited by this paper
• Bayesian approach to inverse statistical mechanics.

  2014cited by this paper
• Dynamical criticality in the collective activity of a population of retinal neurons.

  2014cited by this paper
• Illuminating cell signalling with optogenetic tools

  2014cited by this paper
• Parameter Estimation for Spatio-Temporal Maximum Entropy Distributions: Application to Neural Spike Trains

  2014cited by this paper
• MetaPSICOV: combining coevolution methods for accurate prediction of contacts and long range hydrogen bonding in proteins

  2014cited by this paper
• Consistent inference of a general model using the pseudolikelihood method.

  2014cited by this paper
• The value of monitoring to control evolving populations

  2014cited by this paper
• Chronic, Wireless Recordings of Large Scale Brain Activity in Freely Moving Rhesus Monkeys

  2014cited by this paper
• Pseudolikelihood decimation algorithm improving the inference of the interaction network in a general class of Ising models.

  2013cited by this paper
• A General Pairwise Interaction Model Provides an Accurate Description of In Vivo Transcription Factor Binding Sites

  2013cited by this paper
• Single-cell gene expression analysis reveals genetic associations masked in whole-tissue experiments

  2013cited by this paper
• Perturbation Biology: Inferring Signaling Networks in Cellular Systems

  2013cited by this paper
• Spin models inferred from patient-derived viral sequence data faithfully describe HIV fitness landscapes.

  2013cited by this paper
• Zipf's law and criticality in multivariate data without fine-tuning.

  2013cited by this paper
• A complete mass-spectrometric map of the yeast proteome applied to quantitative trait analysis

  2013cited by this paper
• Learning and inference in a nonequilibrium Ising model with hidden nodes.

  2013cited by this paper
• Translating HIV sequences into quantitative fitness landscapes predicts viral vulnerabilities for rational immunogen design.

  2013cited by this paper
• Dynamical maximum entropy approach to flocking.

  2013cited by this paper
• Social interactions dominate speed control in poising natural flocks near criticality

  2013cited by this paper
• Principles of maximum entropy and maximum caliber in statistical physics

  2013cited by this paper
• A statistical physics perspective on criticality in financial markets

  2013cited by this paper
• Inference of Hopfield-Potts patterns from covariation in protein families: calculation and statistical error bars

  2013cited by this paper
• Trend and fluctuations: analysis and design of population dynamics measurements in replicate ecosystems.

  2013cited by this paper
• Probing the limitations of isotropic pair potentials to produce ground-state structural extremes via inverse statistical mechanics.

  2013cited by this paper
• Designer spin systems via inverse statistical mechanics

  2013cited by this paper
• Searching for Collective Behavior in a Large Network of Sensory Neurons

  2013influential reference
• Designer spin systems via inverse statistical mechanics. II. Ground-state enumeration and classification

  2013cited by this paper
• Multi-electrode array technologies for neuroscience and cardiology.

  2013cited by this paper
• Emerging methods in protein co-evolution

  2013cited by this paper
• The effect of nonstationarity on models inferred from neural data

  2012cited by this paper
• Mechanism-independent method for predicting response to multidrug combinations in bacteria

  2012influential reference
• Three-dimensional structures of membrane proteins from genomic sequencing.

  2012cited by this paper
• Microbial Co-occurrence Relationships in the Human Microbiome

  2012cited by this paper
• Structural basis of histidine kinase autophosphorylation deduced by integrating genomics, molecular dynamics, and mutagenesis

  2012cited by this paper
• The simplest maximum entropy model for collective behavior in a neural network

  2012cited by this paper
• Mean-field theory for the inverse Ising problem at low temperatures.

  2012cited by this paper
• Improved contact prediction in proteins: using pseudolikelihoods to infer Potts models.

  2012cited by this paper
• Maximum likelihood reconstruction for Ising models with asynchronous updates.

  2012cited by this paper
• Genomics-aided structure prediction

  2012cited by this paper
• Stimulus-dependent Maximum Entropy Models of Neural Population Codes

  2012cited by this paper
• The Protein-Folding Problem, 50 Years On

  2012cited by this paper
• Market structure explained by pairwise interactions

  2012cited by this paper
• An Introduction to Restricted Boltzmann Machines

  2012cited by this paper
• Being Critical of Criticality in the Brain

  2012cited by this paper
• Statistical mechanics for natural flocks of birds

  2011cited by this paper
• Adaptive Cluster Expansion for the Inverse Ising Problem: Convergence, Algorithm and Tests

  2011cited by this paper
• Dynamical TAP equations for non-equilibrium Ising spin glasses

  2011influential reference
• Bethe–Peierls approximation and the inverse Ising problem

  2011cited by this paper
• Sparse low-order interaction network underlies a highly correlated and learnable neural population code

  2011cited by this paper
• The Nature of Computation

  2011cited by this paper
• Gaussian graphical modeling reconstructs pathway reactions from high-throughput metabolomics data

  2011cited by this paper
• Protein 3D Structure Computed from Evolutionary Sequence Variation

  2011cited by this paper
• Coordinate linkage of HIV evolution reveals regions of immunological vulnerability

  2011cited by this paper
• Direct-coupling analysis of residue coevolution captures native contacts across many protein families

  2011cited by this paper
• Inverse Ising inference using all the data.

  2011cited by this paper
• Adaptive Cluster Expansion for Inferring Boltzmann Machines with Noisy Data

  2011influential reference

• Classification of SARS-CoV-2 Variants through The Epistatical Circos Plots with Convolutional Neural Networks

  2026cites this paper
• Computationally sufficient statistics for Ising models

  2026cites this paper
• CoRMF: Criticality-ordered recurrent mean field Ising solver

  2026cites this paper
• Correspondence Between Ising Machines and Neural Networks

  2025cites this paper
• Functional Renormalization for Signal Detection: Dimensional Analysis and Dimensional Phase Transition for Nearly Continuous Spectra Effective Field Theory

  2025cites this paper
• Learning and Testing Inverse Statistical Problems For Interacting Systems Undergoing Phase Transition

  2025influential citation
• Simple low-dimensional computations explain variability in neuronal activity

  2025cites this paper
• Minimax entropy: The statistical physics of optimal models.

  2025influential citation
• Assortment optimization given basket shopping behavior using the Ising model

  2025cites this paper
• Uncertainty quantification and posterior sampling for network reconstruction

  2025cites this paper
• Stability Analysis and Local Influence Diagnostics for an Extreme-Value Regression Model of Anomalous Wind Gusts

  2025cites this paper
• Inferring entropy production in many-body systems using nonequilibrium MaxEnt

  2025cites this paper
• Statistical methods for the inversion of the source term and initial values of the diffusion equation

  2025cites this paper
• Finite-size effects in molecular simulations: a physico-mathematical view

  2025cites this paper
• Dilemmas and trade-offs in the diffusion of conventions

  2025cites this paper
• Data augmentation using diffusion models to enhance inverse Ising inference

  2025cites this paper
• Quantifying the compressibility of the human brain

  2025cites this paper
• Hybrid Quantum-Classical Framework for Anomaly Detection in Time Series with QUBO formulation and QAOA

  2025cites this paper
• Solving the Ising Problem by Noisy Quantum Genetic Algorithms

  2025cites this paper
• Mereological approach to higher-order structure in complex systems: From macro to micro with Möbius

  2025cites this paper
• Inferring Higher-Order Couplings with Neural Networks.

  2025cites this paper
• Two-dimensional membranes with precisely controlled graphitic nanoconduits for ultrafast water vapour transport

  2025cites this paper
• Belief propagation for finite networks using a symmetry-breaking source node

  2025cites this paper
• Pseudo-likelihood produces associative memories able to generalize, even for asymmetric couplings

  2025cites this paper
• Quantitative Assessment of Randomized DNA Base Sequences Using Multi‐Model Physical Analysis for High‐Fidelity Data Storage

  2025cites this paper
• Inferring Entropy Production in Many-Body Systems Using Nonequilibrium Maximum Entropy.

  2025cites this paper
• Maximum entropy models of neuronal populations at and off criticality

  2025influential citation
• Advancing the inverse problem in statistical mechanics: A five-body interaction perspective

  2025cites this paper
• A guide to D-SPIN: constructing regulatory network models from single-cell RNA-seq perturbation data

  2025influential citation
• Non-equilibrium dynamics in complex networks via asymmetric Glauber models

  2025influential citation
• A theoretical framework for overfitting in energy-based modeling

  2025cites this paper
• Geometric Theory of Ising Machines

  2025cites this paper
• Enhanced network inference from sparse incomplete time series through automatically adapted L1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-

  2024cites this paper
• Thermodynamic analog of integrate-and-fire neuronal networks by maximum entropy modelling

  2024cites this paper
• Unveiling Gene Perturbation Effects through Gene Regulatory Networks Inference from single-cell transcriptomic data

  2024cites this paper
• The quality and complexity of pairwise maximum entropy models for large cortical populations

  2024cites this paper
• New spin models in ecology: Super multi-stationarity and chaos

  2024cites this paper
• A Mereological Approach to Higher-Order Structure in Complex Systems: from Macro to Micro with M\"obius

  2024cites this paper
• Simplicity science

  2024cites this paper
• Long‐range Ising model for regional‐scale seismic risk analysis

  2024cites this paper
• Solving Boltzmann optimization problems with deep learning

  2024cites this paper
• Network reconstruction via the minimum description length principle

  2024cites this paper
• Lattice physics approaches for neural networks

  2024cites this paper
• Unsupervised learning of effective quantum impurity models

  2024cites this paper
• Software cost estimation predication using a convolutional neural network and particle swarm optimization algorithm

  2024cites this paper
• Entropy, concentration, and learning: a statistical mechanics primer

  2024cites this paper
• LoopSage: An Energy-Based Monte Carlo approach for the Loop Extrusion Modelling of Chromatin

  2024cites this paper
• Machine learning and optimization-based approaches to duality in statistical physics

  2024cites this paper
• Self-attention as an attractor network: transient memories without backpropagation

  2024cites this paper
• Discrete distributions are learnable from metastable samples

  2024cites this paper
• Synergistic Signatures of Group Mechanisms in Higher-Order Systems.

  2024cites this paper
• CoRMF: Criticality-Ordered Recurrent Mean Field Ising Solver

  2024cites this paper
• Hybrid Geometry-Adaptive MCMC for Bayesian Inference in Higher-Order Ising Models

  2024cites this paper
• Ising-like model replicating time-averaged spiking behaviour of in vitro neuronal networks

  2024cites this paper
• Energy landscape analysis based on the Ising model: Tutorial review

  2024cites this paper
• Mapping inter-city trade networks to maximum entropy models using electronic invoice data

  2024cites this paper
• Hidden high-risky states identification from routine urban traffic

  2024cites this paper
• A simple intelligent adaptive network

  2024cites this paper
• AI meets physics: a comprehensive survey

  2024cites this paper
• Diffusion reconstruction for the diluted Ising model.

  2024cites this paper
• Statistical physics of large-scale neural activity with loops.

  2024cites this paper
• Dynamical phase transitions in the nonreciprocal Ising model.

  2024cites this paper
• Fast training and sampling of Restricted Boltzmann Machines

  2024cites this paper
• Monte Carlo, blocking, and inference: How to measure the renormalization group flow

  2024cites this paper
• Scalable network reconstruction in subquadratic time

  2024cites this paper
• Spatiotemporal organization of ant foraging from a complex systems perspective

  2024cites this paper
• A statistical mechanics approach to measure peer-to-peer effects in Pharma research and development investments

  2024cites this paper
• Nonlinear Dynamics for the Ising Model

  2023cites this paper
• Feature Programming for Multivariate Time Series Prediction

  2023cites this paper
• A Perspective on Lindblad's Non-Equilibrium Entropy

  2023cites this paper
• Scale-free correlations and potential criticality in weakly ordered populations of brain cancer cells

  2023cites this paper
• D-SPIN constructs gene regulatory network models from multiplexed scRNA-seq data revealing organizing principles of cellular perturbation response

  2023cites this paper
• Mapping of attention mechanisms to a generalized Potts model

  2023cites this paper
• Exact minimax entropy models of large-scale neuronal activity.

  2023influential citation
• Does the brain behave like a (complex) network? I. Dynamics.

  2023cites this paper
• The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems

  2023cites this paper
• Tailoring the overlap distribution in driven mean-field spin models

  2023cites this paper
• Quantifying heterogeneity to drug response in cancer–stroma kinetics

  2023cites this paper
• Biases in Inverse Ising Estimates of Near-Critical Behaviour

  2023influential citation
• Explaining the effects of non-convergent sampling in the training of energy-based models

  2023cites this paper
• Introduction to correlation networks: Interdisciplinary approaches beyond thresholding.

  2023cites this paper
• Accelerating convergence of inference in the inverse Ising problem

  2023cites this paper
• Exactly solvable statistical physics models for large neuronal populations

  2023influential citation
• Reconstruct Ising Model with Global Optimality via SLIDE*

  2023cites this paper
• Quantitative approaches for decoding the specificity of the human T cell repertoire

  2023cites this paper
• Inferring effective couplings with Restricted Boltzmann Machines

  2023cites this paper
• RNA contact prediction by data efficient deep learning

  2023cites this paper
• Inverse problem for the quartic mean-field Ising model

  2023cites this paper
• Financial price dynamics and phase transitions in the stock markets

  2023cites this paper
• Efficient Hi-C inversion facilitates chromatin folding mechanism discovery and structure prediction

  2023cites this paper
• Network science Ising states of matter

  2023cites this paper
• On Commutative Penalty Functions in Parent-Hamiltonian Constructions

  2023cites this paper
• Neural Activity in Quarks Language: Lattice Field Theory for a Network of Real Neurons

  2023cites this paper
• Total Empiricism: Learning from Data

  2023cites this paper
• Privacy-preserving machine learning with tensor networks

  2022cites this paper
• Statistical models of complex brain networks: a maximum entropy approach

  2022cites this paper
• A maximum entropy approach for the modelling of car-sharing parking dynamics

  2022cites this paper
• Inferring Cultural Landscapes with the Inverse Ising Model

  2022cites this paper
• Thermodynamics of the Ising Model Encoded in Restricted Boltzmann Machines

  2022cites this paper
• Inverse problem beyond two-body interaction: The cubic mean-field Ising model.

  2022cites this paper