Open-source Python Toolbox Research Articles

Addressing Model Uncertainties in Finite Element Simulation of Electrically Stimulated Implants for Critical-Size Mandibular Defects.

Electrical stimulation is known to enhance bone healing. Novel electrostimulating devices are currently being developed for the treatment of critical-size bone defects in the mandible. Previous numerical models of these devices did not account for possible uncertainties in the input data. We present the numerical model of an electrically stimulated minipig mandible, including optimization and uncertainty quantification (UQ) methods that allow us to determine the most influential parameters. Uncertainties in the optimized finite element model are quantified using the polynomial chaos method that is implemented in the open-source Python toolbox Uncertainpy. The volumes of understimulated, beneficially stimulated, and overstimulated tissue are considered quantities of interest because they may significantly impact the expected healing success. Further, the current is a substantial quantity, limiting the lifetime of a battery-driven stimulation unit. With sensitivity analyses, the most critical parameters in the numerical model can be identified. Thus, we can learn which parameters are particularly relevant, for example, when conceptualizing the stimulation unit or planning the manufacturing process. The results of this study show that the parameters of the electrode-tissue interface (ETI), as well as the conductivity within the defect volume, have the most significant impact on the model results. The UQ results suggest that careful characterization of the ETI and the dielectric tissue properties is crucial to reduce these uncertainties. The numerical model regarding uncertainties yields important implications for reliable implant design and clinical translation.

An open-source toolbox for enhancing the assessment of muscle activation patterns during cyclical movements

Objective.The accurate temporal analysis of muscle activations is of great importance in several research areas spanning from the assessment of altered muscle activation patterns in orthopaedic and neurological patients to the monitoring of their motor rehabilitation. Several studies have highlighted the challenge of understanding and interpreting muscle activation patterns due to the high cycle-by-cycle variability of the sEMG data. This makes it difficult to interpret results and to use sEMG signals in clinical practice. To overcome this limitation, this study aims at presenting a toolbox to help scientists easily characterize and assess muscle activation patterns during cyclical movements.Approach.CIMAP(Clustering for the Identification of Muscle Activation Patterns) is an open-source Python toolbox based on agglomerative hierarchical clustering that aims at characterizing muscle activation patterns during cyclical movements by grouping movement cycles showing similar muscle activity.Main results.From muscle activation intervals to the graphical representation of the agglomerative hierarchical clustering dendrograms, the proposed toolbox offers a complete analysis framework for enabling the assessment of muscle activation patterns. The toolbox can be flexibly modified to comply with the necessities of the scientist.CIMAPis addressed to scientists of any programming skill level working in different research areas such as biomedical engineering, robotics, sports, clinics, biomechanics, and neuroscience. CIMAP is freely available on GitHub (https://github.com/Biolab-PoliTO/CIMAP).Significance.CIMAPtoolbox offers scientists a standardized method for analyzing muscle activation patterns during cyclical movements.

MotorNet, a Python toolbox for controlling differentiable biomechanical effectors with artificial neural networks.

Artificial neural networks (ANNs) are a powerful class of computational models for unravelling neural mechanisms of brain function. However, for neural control of movement, they currently must be integrated with software simulating biomechanical effectors, leading to limiting impracticalities: (1) researchers must rely on two different platforms and (2) biomechanical effectors are not generally differentiable, constraining researchers to reinforcement learning algorithms despite the existence and potential biological relevance of faster training methods. To address these limitations, we developed MotorNet, an open-source Python toolbox for creating arbitrarily complex, differentiable, and biomechanically realistic effectors that can be trained on user-defined motor tasks using ANNs. MotorNet is designed to meet several goals: ease of installation, ease of use, a high-level user-friendly application programming interface, and a modular architecture to allow for flexibility in model building. MotorNet requires no dependencies outside Python, making it easy to get started with. For instance, it allows training ANNs on typically used motor control models such as a two joint, six muscle, planar arm within minutes on a typical desktop computer. MotorNet is built on PyTorch and therefore can implement any network architecture that is possible using the PyTorch framework. Consequently, it will immediately benefit from advances in artificial intelligence through PyTorch updates. Finally, it is open source, enabling users to create and share their own improvements, such as new effector and network architectures or custom task designs. MotorNet's focus on higher-order model and task design will alleviate overhead cost to initiate computational projects for new researchers by providing a standalone, ready-to-go framework, and speed up efforts of established computational teams by enabling a focus on concepts and ideas over implementation.

MotorNet, a Python toolbox for controlling differentiable biomechanical effectors with artificial neural networks

Artificial neural networks (ANNs) are a powerful class of computational models for unravelling neural mechanisms of brain function. However, for neural control of movement, they currently must be integrated with software simulating biomechanical effectors, leading to limiting impracticalities: (1) researchers must rely on two different platforms and (2) biomechanical effectors are not generally differentiable, constraining researchers to reinforcement learning algorithms despite the existence and potential biological relevance of faster training methods. To address these limitations, we developed MotorNet, an open-source Python toolbox for creating arbitrarily complex, differentiable, and biomechanically realistic effectors that can be trained on user-defined motor tasks using ANNs. MotorNet is designed to meet several goals: ease of installation, ease of use, a high-level user-friendly application programming interface, and a modular architecture to allow for flexibility in model building. MotorNet requires no dependencies outside Python, making it easy to get started with. For instance, it allows training ANNs on typically used motor control models such as a two joint, six muscle, planar arm within minutes on a typical desktop computer. MotorNet is built on PyTorch and therefore can implement any network architecture that is possible using the PyTorch framework. Consequently, it will immediately benefit from advances in artificial intelligence through PyTorch updates. Finally, it is open source, enabling users to create and share their own improvements, such as new effector and network architectures or custom task designs. MotorNet’s focus on higher-order model and task design will alleviate overhead cost to initiate computational projects for new researchers by providing a standalone, ready-to-go framework, and speed up efforts of established computational teams by enabling a focus on concepts and ideas over implementation.

A Python Toolbox for Data-Driven Aerodynamic Modeling Using Sparse Gaussian Processes

In aerodynamics, characterizing the aerodynamic behavior of aircraft typically requires a large number of observation data points. Real experiments can generate thousands of data points with suitable accuracy, but they are time-consuming and resource-intensive. Consequently, conducting real experiments at new input configurations might be impractical. To address this challenge, data-driven surrogate models have emerged as a cost-effective and time-efficient alternative. They provide simplified mathematical representations that approximate the output of interest. Models based on Gaussian Processes (GPs) have gained popularity in aerodynamics due to their ability to provide accurate predictions and quantify uncertainty while maintaining tractable execution times. To handle large datasets, sparse approximations of GPs have been further investigated to reduce the computational complexity of exact inference. In this paper, we revisit and adapt two classic sparse methods for GPs to address the specific requirements frequently encountered in aerodynamic applications. We compare different strategies for choosing the inducing inputs, which significantly impact the complexity reduction. We formally integrate our implementations into the open-source Python toolbox SMT, enabling the use of sparse methods across the GP regression pipeline. We demonstrate the performance of our Sparse GP (SGP) developments in a comprehensive 1D analytic example as well as in a real wind tunnel application with thousands of training data points.

Connectome-based reservoir computing with the conn2res toolbox

The connection patterns of neural circuits form a complex network. How signaling in these circuits manifests as complex cognition and adaptive behaviour remains the central question in neuroscience. Concomitant advances in connectomics and artificial intelligence open fundamentally new opportunities to understand how connection patterns shape computational capacity in biological brain networks. Reservoir computing is a versatile paradigm that uses high-dimensional, nonlinear dynamical systems to perform computations and approximate cognitive functions. Here we present conn2res: an open-source Python toolbox for implementing biological neural networks as artificial neural networks. conn2res is modular, allowing arbitrary network architecture and dynamics to be imposed. The toolbox allows researchers to input connectomes reconstructed using multiple techniques, from tract tracing to noninvasive diffusion imaging, and to impose multiple dynamical systems, from spiking neurons to memristive dynamics. The versatility of the conn2res toolbox allows us to ask new questions at the confluence of neuroscience and artificial intelligence. By reconceptualizing function as computation, conn2res sets the stage for a more mechanistic understanding of structure-function relationships in brain networks.

On the variability of dynamic functional connectivity assessment methods.

Dynamic functional connectivity (dFC) has become an important measure for understanding brain function and as a potential biomarker. However, various methodologies have been developed for assessing dFC, and it is unclear how the choice of method affects the results. In this work, we aimed to study the results variability of commonly used dFC methods. We implemented 7 dFC assessment methods in Python and used them to analyze the functional magnetic resonance imaging data of 395 subjects from the Human Connectome Project. We measured the similarity of dFC results yielded by different methods using several metrics to quantify overall, temporal, spatial, and intersubject similarity. Our results showed a range of weak to strong similarity between the results of different methods, indicating considerable overall variability. Somewhat surprisingly, the observed variability in dFC estimates was found to be comparable to the expected functional connectivity variation over time, emphasizing the impact of methodological choices on the final results. Our findings revealed 3 distinct groups of methods with significant intergroup variability, each exhibiting distinct assumptions and advantages. Overall, our findings shed light on the impact of dFC assessment analytical flexibility and highlight the need for multianalysis approaches and careful method selection to capture the full range of dFC variation. They also emphasize the importance of distinguishing neural-driven dFC variations from physiological confounds and developing validation frameworks under a known ground truth. To facilitate such investigations, we provide an open-source Python toolbox, PydFC, which facilitates multianalysis dFC assessment, with the goal of enhancing the reliability and interpretability of dFC studies.

A unifying method to study Respiratory Sinus Arrhythmia dynamics implemented in a new toolbox.

Respiratory sinus arrhythmia (RSA), the natural variation in heart rate synchronized with respiration, has been extensively studied in emotional and cognitive contexts. Various time or frequency-based methods using the cardiac signal have been proposed to analyze RSA. In this study, we present a novel approach that combines respiratory phase and heart rate to enable a more detailed analysis of RSA and its dynamics throughout the respiratory cycle. To facilitate the application of this method, we have implemented it in an open-source Python toolbox called physio This toolbox includes essential functionalities for processing ECG and respiratory signals, while also introducing this new approach for RSA analysis. Inspired by previous research conducted by our group, this method enables a cycle-by-cycle analysis of RSA providing the possibility to correlate any respiratory feature to any RSA feature. By employing this approach, we aim to gain a more accurate understanding of the neural mechanisms associated with RSA.Significance StatementRespiratory sinus arrhythmia (RSA), the natural variation in heart rate synchronized with respiration, has been extensively studied in emotional and cognitive contexts. Various time or frequency-based methods using the cardiac signal have been proposed to analyze RSA. This work presents a novel approach that combines respiratory phase and heart rate to enable a more detailed analysis of RSA and its dynamics over time and throughout the respiratory cycle. It is implemented in an open-source toolbox that incorporates this framework in easily configurable functions and readable code.

DarSIA: An Open-Source Python Toolbox for Two-Scale Image Processing of Dynamics in Porous Media

Understanding porous media flow is inherently a multi-scale challenge, where at the core lies the aggregation of pore-level processes to a continuum, or Darcy-scale, description. This challenge is directly mirrored in image processing, where pore-scale grains and interfaces may be clearly visible in the image, yet continuous Darcy-scale parameters may be what are desirable to quantify. Classical image processing is poorly adapted to this setting, as most techniques do not explicitly utilize the fact that the image contains explicit physical processes. Here, we extend classical image processing concepts to what we define as “physical images” of porous materials and processes within them. This is realized through the development of a new open-source image analysis toolbox specifically adapted to time-series of images of porous materials.

Statistical inference on representational geometries.

Neuroscience has recently made much progress, expanding the complexity of both neural activity measurements and brain-computational models. However, we lack robust methods for connecting theory and experiment by evaluating our new big models with our new big data. Here, we introduce new inference methods enabling researchers to evaluate and compare models based on the accuracy of their predictions of representational geometries: A good model should accurately predict the distances among the neural population representations (e.g. of a set of stimuli). Our inference methods combine novel 2-factor extensions of crossvalidation (to prevent overfitting to either subjects or conditions from inflating our estimates of model accuracy) and bootstrapping (to enable inferential model comparison with simultaneous generalization to both new subjects and new conditions). We validate the inference methods on data where the ground-truth model is known, by simulating data with deep neural networks and by resampling of calcium-imaging and functional MRI data. Results demonstrate that the methods are valid and conclusions generalize correctly. These data analysis methods are available in an open-source Python toolbox (rsatoolbox.readthedocs.io).

Py-Feat: Python Facial Expression Analysis Toolbox

Studying facial expressions is a notoriously difficult endeavor. Recent advances in the field of affective computing have yielded impressive progress in automatically detecting facial expressions from pictures and videos. However, much of this work has yet to be widely disseminated in social science domains such as psychology. Current state-of-the-art models require considerable domain expertise that is not traditionally incorporated into social science training programs. Furthermore, there is a notable absence of user-friendly and open-source software that provides a comprehensive set of tools and functions that support facial expression research. In this paper, we introduce Py-Feat, an open-source Python toolbox that provides support for detecting, preprocessing, analyzing, and visualizing facial expression data. Py-Feat makes it easy for domain experts to disseminate and benchmark computer vision models and also for end users to quickly process, analyze, and visualize face expression data. We hope this platform will facilitate increased use of facial expression data in human behavior research.

Blockly earthquake transformer: A deep learning platform for custom phase picking

Deep-learning (DL) algorithms are increasingly used for routine seismic data processing tasks, including seismic event detection and phase arrival picking. Despite many examples of the remarkable performance of existing (i.e., pre-trained) deep-learning detector/picker models, there are still some cases where the direct applications of such models do not generalize well. In such cases, substantial effort is required to improve the performance by either developing a new model or fine-tuning an existing one. To address this challenge, we present Blockly Earthquake Transformer(BET), a deep-learning platform for efficient customization of deep-learning phase pickers. BET implements Earthquake Transformer as its baseline model, and offers transfer learning and fine-tuning extensions. BET provides an interactive dashboard to customize a model based on a particular dataset. Once the parameters are specified, BET executes the corresponding phase-picking task without direct user interaction with the base code. Within the transfer-learning module, BET extends the application of a deep-learning P and S phase picker to more specific phases (e.g., Pn, Pg, Sn and Sg phases). In the fine-tuning module, the model performance is enhanced by customizing the model architecture. This no-code platform is designed to quickly deploy reusable workflows, build customized models, visualize training processes, and produce publishable figures in a lightweight, interactive, and open-source Python toolbox.

Informative and adaptive distances and summary statistics in sequential approximate Bayesian computation.

Calibrating model parameters on heterogeneous data can be challenging and inefficient. This holds especially for likelihood-free methods such as approximate Bayesian computation (ABC), which rely on the comparison of relevant features in simulated and observed data and are popular for otherwise intractable problems. To address this problem, methods have been developed to scale-normalize data, and to derive informative low-dimensional summary statistics using inverse regression models of parameters on data. However, while approaches only correcting for scale can be inefficient on partly uninformative data, the use of summary statistics can lead to information loss and relies on the accuracy of employed methods. In this work, we first show that the combination of adaptive scale normalization with regression-based summary statistics is advantageous on heterogeneous parameter scales. Second, we present an approach employing regression models not to transform data, but to inform sensitivity weights quantifying data informativeness. Third, we discuss problems for regression models under non-identifiability, and present a solution using target augmentation. We demonstrate improved accuracy and efficiency of the presented approach on various problems, in particular robustness and wide applicability of the sensitivity weights. Our findings demonstrate the potential of the adaptive approach. The developed algorithms have been made available in the open-source Python toolbox pyABC.

SimpleNomo: A Python Package of Making Nomograms for Visualizable Calculation of Logistic Regression Models.

Logistic regression models are widely used in clinical prediction, but their application in resource-poor settings or areas without internet access can be challenging. Nomograms can serve as a useful visualization tool to speed up the calculation procedure, but existing nomogram generators often require the input of raw data, inhibiting the transformation of established logistic regression models that only provide coefficients. Developing a tool that can generate nomograms directly from logistic regression coefficients would greatly increase usability and facilitate the translation of research findings into patient care. We designed and developed simpleNomo, an open-source Python toolbox that enables the construction of nomograms for logistic regression models. Uniquely, simpleNomo allows for the creation of nomograms using only the coefficients of the model. Further, we also devoloped an online website for nomogram generation. simpleNomo properly maintains the predictive ability of the original logistic regression model and easy to follow. simpleNomo is compatible with Python 3 and can be installed through Python Package Index (PyPI) or https://github.com/Hhy096/nomogram. This paper presents simpleNomo, an open-source Python toolbox for generating nomograms for logistic regression models. It facilitates the process of transferring established logistic regression models to nomograms and can further convert more existing works into practical use.

Recovering Individual Emotional States from Sparse Ratings Using Collaborative Filtering

A fundamental challenge in emotion research is measuring feeling states with high granularity and temporal precision without disrupting the emotion generation process. Here we introduce and validate a new approach in which responses are sparsely sampled and the missing data are recovered using a computational technique known as collaborative filtering (CF). This approach leverages structured covariation across individual experiences and is available in Neighbors, an open-source Python toolbox. We validate our approach across three different experimental contexts by recovering dense individual ratings using only a small subset of the original data. In dataset 1, participants (n=316) separately rated 112 emotional images on 6 different discrete emotions. In dataset 2, participants (n=203) watched 8 short emotionally engaging autobiographical stories while simultaneously providing moment-by-moment ratings of the intensity of their affective experience. In dataset 3, participants (n=60) with distinct social preferences made 76 decisions about how much money to return in a hidden multiplier trust game. Across all experimental contexts, CF was able to accurately recover missing data and importantly outperformed mean and multivariate imputation, particularly in contexts with greater individual variability. This approach will enable new avenues for affective science research by allowing researchers to acquire high dimensional ratings from emotional experiences with minimal disruption to the emotion-generation process.

Integrating scientific knowledge into machine learning using interactive decision trees

Decision Trees (DT) describe a type of machine learning method that has been widely used in the geosciences to automatically extract patterns from complex and high dimensional data. However, like any data-based method, the application of DT is hindered by data limitations, such as significant biases, leading to potentially physically unrealistic results. We develop interactive DT (iDT) that put humans in the loop to integrate the power of experts' scientific knowledge with the power of the algorithms to automatically learn patterns from large datasets. We created an open-source Python toolbox that implements the iDT framework. Users can interactively create new composite variables, change the variable and threshold to split, prune and group variables based on their physical meaning. We demonstrate with three case studies how iDT overcomes problems with current DT thus achieving higher interpretability and robustness of the result.

A semi-automatic toolbox for markerless effective semantic feature extraction

VisionTool is an open-source python toolbox for semantic features extraction, capable to provide accurate features detectors for different applications, including motion analysis, markerless pose estimation, face recognition and biological cell tracking. VisionTool leverages transfer-learning with a large variety of deep neural networks allowing high-accuracy features detection with few training data. The toolbox offers a friendly graphical user interface, efficiently guiding the user through the entire process of features extraction. To facilitate broad usage and scientific community contribution, the code and a user guide are available at https://github.com/Malga-Vision/VisionTool.git.

MicNet toolbox: Visualizing and unraveling a microbial network.

Applications of network theory to microbial ecology are an emerging and promising approach to understanding both global and local patterns in the structure and interplay of these microbial communities. In this paper, we present an open-source python toolbox which consists of two modules: on one hand, we introduce a visualization module that incorporates the use of UMAP, a dimensionality reduction technique that focuses on local patterns, and HDBSCAN, a clustering technique based on density; on the other hand, we have included a module that runs an enhanced version of the SparCC code, sustaining larger datasets than before, and we couple the resulting networks with network theory analyses to describe the resulting co-occurrence networks, including several novel analyses, such as structural balance metrics and a proposal to discover the underlying topology of a co-occurrence network. We validated the proposed toolbox on 1) a simple and well described biological network of kombucha, consisting of 48 ASVs, and 2) we validate the improvements of our new version of SparCC. Finally, we showcase the use of the MicNet toolbox on a large dataset from Archean Domes, consisting of more than 2,000 ASVs. Our toolbox is freely available as a github repository (https://github.com/Labevo/MicNetToolbox), and it is accompanied by a web dashboard (http://micnetapplb-1212130533.us-east-1.elb.amazonaws.com) that can be used in a simple and straightforward manner with relative abundance data. This easy-to-use implementation is aimed to microbial ecologists with little to no experience in programming, while the most experienced bioinformatics will also be able to manipulate the source code’s functions with ease.

Group-level inference of information-based measures for the analyses of cognitive brain networks from neurophysiological data

The reproducibility crisis in neuroimaging and in particular in the case of underpowered studies has introduced doubts on our ability to reproduce, replicate and generalize findings. As a response, we have seen the emergence of suggested guidelines and principles for neuroscientists known as Good Scientific Practice for conducting more reliable research. Still, every study remains almost unique in its combination of analytical and statistical approaches. While it is understandable considering the diversity of designs and brain data recording, it also represents a striking point against reproducibility. Here, we propose a non-parametric permutation-based statistical framework, primarily designed for neurophysiological data, in order to perform group-level inferences on non-negative measures of information encompassing metrics from information-theory, machine-learning or measures of distances. The framework supports both fixed- and random-effect models to adapt to inter-individuals and inter-sessions variability. Using numerical simulations, we compared the accuracy in ground-truth retrieving of both group models, such as test- and cluster-wise corrections for multiple comparisons. We then reproduced and extended existing results using both spatially uniform MEG and non-uniform intracranial neurophysiological data. We showed how the framework can be used to extract stereotypical task- and behavior-related effects across the population covering scales from the local level of brain regions, inter-areal functional connectivity to measures summarizing network properties. We also present an open-source Python toolbox called Frites1 that includes the proposed statistical pipeline using information-theoretic metrics such as single-trial functional connectivity estimations for the extraction of cognitive brain networks. Taken together, we believe that this framework deserves careful attention as its robustness and flexibility could be the starting point toward the uniformization of statistical approaches.

NNMT: Mean-Field Based Analysis Tools for Neuronal Network Models.

Mean-field theory of neuronal networks has led to numerous advances in our analytical and intuitive understanding of their dynamics during the past decades. In order to make mean-field based analysis tools more accessible, we implemented an extensible, easy-to-use open-source Python toolbox that collects a variety of mean-field methods for the leaky integrate-and-fire neuron model. The Neuronal Network Mean-field Toolbox (NNMT) in its current state allows for estimating properties of large neuronal networks, such as firing rates, power spectra, and dynamical stability in mean-field and linear response approximation, without running simulations. In this article, we describe how the toolbox is implemented, show how it is used to reproduce results of previous studies, and discuss different use-cases, such as parameter space explorations, or mapping different network models. Although the initial version of the toolbox focuses on methods for leaky integrate-and-fire neurons, its structure is designed to be open and extensible. It aims to provide a platform for collecting analytical methods for neuronal network model analysis, such that the neuroscientific community can take maximal advantage of them.