GitHub Repository Research Articles

Bridging the Coordination Chemistry of Small Compounds and Metalloproteins Using Machine Learning.

Metalloproteins require metal ions as cofactors to catalyze specific reactions with remarkable efficiency and specificity. In various electron transfer reactions, metals in the active sites change their oxidation states to facilitate the biochemical reactions. Cryogenic electron microscopy, X-ray, and X-ray free electron laser (XFEL) crystallography are used to image metalloproteins to understand the reaction mechanisms. However, radiation damage in cryoEM and X-ray crystallography, and the challenge of generating homogeneous crystals and keeping the appropriate experimental conditions for all the crystals in XFEL crystallography, may alter the oxidation states. Here, we build machine learning models trained on a large data set from the Cambridge Crystallographic Data Center to evaluate the metal oxidation states. The models yield high accuracy scores (from 82% to 94%) for all metals in the small molecules. Then, they were used to predict the oxidation states of more than 30 000 metal clusters in metalloproteins with Fe, Mn, Co, and Cu in their active sites. We found that most of the metals exist in the lower oxidation states (Fe2+ 77%, Mn2+ 85%, Co2+ 65%, and Cu+ 64%), and these populations correlate with the standard reduction potentials of the metal ions. Furthermore, we found no clear correlation between these populations and the resolution of the structures, which suggests no significant dependence of these predictions on the resolution. Our models represent a valuable tool for evaluating the oxidation states of the metals in metalloproteins imaged with different techniques. The data files and the machine learning code are available in a public GitHub repository: https://github.com/mamin03/OxitationStatesMetalloprotein.git.

Rarity: discovering rare cell populations from single-cell imaging data.

Cell type identification plays an important role in the analysis and interpretation of single-cell data and can be carried out via supervised or unsupervised clustering approaches. Supervised methods are best suited where we can list all cell types and their respective marker genes a priori, while unsupervised clustering algorithms look for groups of cells with similar expression properties. This property permits the identification of both known and unknown cell populations, making unsupervised methods suitable for discovery. Success is dependent on the relative strength of the expression signature of each group as well as the number of cells. Rare cell types therefore present a particular challenge that is magnified when they are defined by differentially expressing a small number of genes. Typical unsupervised approaches fail to identify such rare subpopulations, and these cells tend to be absorbed into more prevalent cell types. In order to balance these competing demands, we have developed a novel statistical framework for unsupervised clustering, named Rarity, that enables the discovery process for rare cell types to be more robust, consistent, and interpretable. We achieve this by devising a novel clustering method based on a Bayesian latent variable model in which we assign cells to inferred latent binary on/off expression profiles. This lets us achieve increased sensitivity to rare cell populations while also allowing us to control and interpret potential false positive discoveries. We systematically study the challenges associated with rare cell type identification and demonstrate the utility of Rarity on various IMC datasets. Implementation of Rarity together with examples is available from the Github repository (https://github.com/kasparmartens/rarity).

Scaling up single-cell RNA-seq data analysis with CellBridge workflow.

Single-cell RNA sequencing (scRNA-seq) has revolutionized the study of gene expression at the individual cell level, unraveling unprecedented insights into cellular heterogeneity. However, the analysis of scRNA-seq data remains a challenging and time-consuming task, often demanding advanced computational expertise, rendering it impractical for high-volume environments and applications. We present CellBridge, an automated workflow designed to simplify the standard procedures entailed in scRNA-seq data analysis, eliminating the need for specialized computational expertise. CellBridge utilizes state-of-the-art computational methods, integrating a range of advanced functionalities, covering the entire process from raw unaligned sequencing reads to cell type annotation. Hence, CellBridge accelerates the pace of discovery by seamlessly enabling insights into vast volumes of scRNA-seq data, without compromising workflow control and reproducibility. The source code, detailed documentation, and materials required to reproduce the results are available on GitHub and archived in Zenodo. For the CellBridge pre-processing step (v1.0.0), access the GitHub repository at https://github.com/Sanofi-Public/PMCB-ToBridge and the Zenodo archive at https://zenodo.org/records/10246161. For the CellBridge processing step (v1.0.0), visit the GitHub repository at https://github.com/Sanofi-Public/PMCB-CellBridge and the Zenodo archive at https://zenodo.org/records/10246046.

The dotTHz Project: A Standard Data Format for Terahertz Time-Domain Data

From investigating molecular vibrations to observing galaxies, terahertz technology has found extensive applications in research and development over the past three decades. Terahertz time-domain spectroscopy and imaging have experienced significant growth and now dominate spectral observations ranging from 0.1 to 10 THz. However, the lack of standardised protocols for data processing, dissemination, and archiving poses challenges in collaborating and sharing terahertz data between research groups. To tackle these challenges, we present the dotTHz project, which introduces a standardised terahertz data format and the associated open-source tools for processing of dotTHz files. The dotTHz project aims to facilitate seamless data processing and analysis by providing a common framework. All software components are released under the MIT licence through GitHub repositories to encourage widespread adoption, modification, and collaboration. We invite the terahertz community to actively contribute to the dotTHz project, fostering the development of additional tools that encompass a greater breadth and depth of functionality. By working together, we can establish a comprehensive suite of resources that benefit the entire terahertz community.

A query-response causal analysis of reaction events in biochemical reaction networks

The stochastic kinetics of biochemical reaction networks is described by a chemical master equation (CME) and the underlying laws of mass action. Assuming network-free simulations of the rule-based models of biochemical reaction networks (BRNs), this paper departs from the usual analysis of network dynamics as the time-dependent distributions of chemical species counts, and instead considers statistically evaluating the sequences of reaction events generated from the stochastic simulations. The reaction event-time series can be used for reaction clustering, identifying rare events, and recognizing the periods of increased or steady-state activity. However, the main aim of this paper is to device an effective method for identifying causally and anti-causally related sub-sequences of reaction events using their empirical probabilities. This allows discovering some of the causal dynamics of BRNs as well as uncovering their short-term deterministic behaviors. In particular, it is proposed that the reaction sub-sequences that are conditionally nearly certain or nearly uncertain can be considered as being causally related. Moreover, since the time-ordering of reaction events is locally irrelevant, the reaction sub-sequences can be transformed into the reaction sets or multi-sets. The distance metrics can be then used to define the equivalences among the reaction events. The proposed method for identifying the causally related reaction sub-sequences has been implemented as a computationally efficient query-response mechanism. The method was evaluated for five models of genetic networks in seven defined numerical experiments. The models were simulated in BioNetGen using the open-source network-free simulator NFsim. This simulator had to be modified first to allow recording the traces of reaction events, and it is available in the Github repository, ploskot/nfsim_1.20. The generated event time-series were analyzed with Python and Matlab scripts. The whole process of data generation, analysis and visualization has been nearly fully automated using shell scripts. This demonstrates the opportunities for substantially increasing the research productivity by creating automated data generation and processing pipelines.

Eelbrain, a Python toolkit for time-continuous analysis with temporal response functions.

Even though human experience unfolds continuously in time, it is not strictly linear; instead, it entails cascading processes building hierarchical cognitive structures. For instance, during speech perception, humans transform a continuously varying acoustic signal into phonemes, words, and meaning, and these levels all have distinct but interdependent temporal structures. Time-lagged regression using temporal response functions (TRFs) has recently emerged as a promising tool for disentangling electrophysiological brain responses related to such complex models of perception. Here, we introduce the Eelbrain Python toolkit, which makes this kind of analysis easy and accessible. We demonstrate its use, using continuous speech as a sample paradigm, with a freely available EEG dataset of audiobook listening. A companion GitHub repository provides the complete source code for the analysis, from raw data to group-level statistics. More generally, we advocate a hypothesis-driven approach in which the experimenter specifies a hierarchy of time-continuous representations that are hypothesized to have contributed to brain responses, and uses those as predictor variables for the electrophysiological signal. This is analogous to a multiple regression problem, but with the addition of a time dimension. TRF analysis decomposes the brain signal into distinct responses associated with the different predictor variables by estimating a multivariate TRF (mTRF), quantifying the influence of each predictor on brain responses as a function of time(-lags). This allows asking two questions about the predictor variables: (1) Is there a significant neural representation corresponding to this predictor variable? And if so, (2) what are the temporal characteristics of the neural response associated with it? Thus, different predictor variables can be systematically combined and evaluated to jointly model neural processing at multiple hierarchical levels. We discuss applications of this approach, including the potential for linking algorithmic/representational theories at different cognitive levels to brain responses through computational models with appropriate linking hypotheses.

A dynamic and collaborative database for morphogeometric information of trilobites

Modern morphometric-based approaches provide valuable metrics to quantify and understand macroevolutionary and macroecological patterns and processes. Here we describe TriloMorph, an openly accessible database for morpho-geometric information of trilobites, together with a landmark acquisition protocol. In addition to morphological traits, the database contains contextual data on chronostratigraphic age, geographic location, taxonomic information and lithology of landmarked specimens. In this first version, the dataset has broad taxonomic and temporal coverage and comprises more than 55% of all trilobite genera and 85% of families recorded in the Paleobiology Database through the Devonian. We provide a release of geometric morphometric data of 277 specimens linked to published references. Additionally, we established a Github repository for constant input of morphometric data by multiple contributors and present R functions that help with data retrieval and analysis. This is the first attempt of an online, dynamic and collaborative morphometric repository. By bringing this information into a single open database we enhance the possibility of performing global palaeobiological research, providing a major complement to current occurrence-based databases.

The two-point correlation function covariance with fewer mocks

ABSTRACT We present fitcov an approach for accurate estimation of the covariance of two-point correlation functions that requires fewer mocks than the standard mock-based covariance. This can be achieved by dividing a set of mocks into jackknife regions and fitting the correction term first introduced in Mohammad & Percival (2022), such that the mean of the jackknife covariances corresponds to the one from the mocks. This extends the model beyond the shot-noise limited regime, allowing it to be used for denser samples of galaxies. We test the performance of our fitted jackknife approach, both in terms of accuracy and precision, using lognormal mocks with varying densities and approximate EZmocks mimicking the Dark Energy Spectroscopic Instrument LRG and ELG samples in the redshift range of z = [0.8, 1.1]. We find that the Mohammad–Percival correction produces a bias in the two-point correlation function covariance matrix that grows with number density and that our fitted jackknife approach does not. We also study the effect of the covariance on the uncertainty of cosmological parameters by performing a full-shape analysis. We demonstrate that our fitted jackknife approach based on 25 mocks can recover unbiased and as precise cosmological parameters as the ones obtained from a covariance matrix based on 1000 or 1500 mocks, while the Mohammad–Percival correction produces uncertainties that are twice as large. The number of mocks required to obtain an accurate estimation of the covariance for the two-point correlation function is therefore reduced by a factor of 40–60. The fitcov code that accompanies this paper is available at this GitHub repository.

DeepFPlearn +: enhancing toxicity prediction across the chemical universe using graph neural networks.

Sophisticated approaches for the in silico prediction of toxicity are required to support the risk assessment of chemicals. The number of chemicals on the global chemical market and the speed of chemical innovation stand in massive contrast to the capacity for regularizing chemical use. We recently proved our ready-to-use application deepFPlearn as a suitable approach for this task. Here, we present its extension deepFPlearn+ incorporating (i) a graph neural network to feed our AI with a more sophisticated molecular structure representation and (ii) alternative train-test splitting strategies that involve scaffold structures and the molecular weights of chemicals. We show that the GNNs outperform the previous model substantially and that our models can generalize on unseen data even with a more robust and challenging test set. Therefore, we highly recommend the application of deepFPlearn+ on the chemical inventory to prioritize chemicals for experimental testing or any chemical subset of interest in monitoring studies. The software is compatible with python 3.6 or higher, and the source code can be found on our GitHub repository: https://github.com/yigbt/deepFPlearn. The data underlying this article are available in Zenodo, and can be accessed with the link below: https://zenodo.org/record/8146252. Detailed installation guides via Docker, Singularity, and Conda are provided within the repository for operability across all operating systems.

SilenceREIN: seeking silencers on anchors of chromatin loops by deep graph neural networks.

Silencers are repressive cis-regulatory elements that play crucial roles in transcriptional regulation. Experimental methods for identifying silencers are always costly and time-consuming. Computational methods, which relies on genomic sequence features, have been introduced as alternative approaches. However, silencers do not have significant epigenomic signature. Therefore, we explore a new way to computationally identify silencers, by incorporating chromatin structural information. We propose the SilenceREIN method, which focuses on finding silencers on anchors of chromatin loops. By using graph neural networks, we extracted chromatin structural information from a regulatory element interaction network. SilenceREIN integrated the chromatin structural information with linear genomic signatures to find silencers. The predictive performance of SilenceREIN is comparable or better than other states-of-the-art methods. We performed a genome-wide scanning to systematically find silencers in human genome. Results suggest that silencers are widespread on anchors of chromatin loops. In addition, enrichment analysis of transcription factor binding motif support our prediction results. As far as we can tell, this is the first attempt to incorporate chromatin structural information in finding silencers. All datasets and source codes of SilenceREIN have been deposited in a GitHub repository (https://github.com/JianHPan/SilenceREIN).

Directional intensified feature description using tertiary filtering for augmented reality tracking

Augmented Reality (AR) is applied in almost every field, and a few, but not limited, are engineering, medical, gaming and internet of things. The application of image tracking is inclusive in all these mentioned fields. AR uses image tracking to localize and register the position of the user/AR device for superimposing the virtual image into the real-world. In general terms, tracking the image enhance the users’ experience. However, in the image tracking application, establishing the interface between virtual realm and the physical world has many shortcomings. Many tracking systems are available, but it lacks in robustness and efficiency. The robustness of the tracking algorithm, is the challenging task of implementation. This study aims to enhance the users’ experience in AR by describing an image using Directional Intensified Features with Tertiary Filtering. This way of describing the features improve the robustness, which is desired in the image tracking. A feature descriptor is robust, in the sense that it does not compromise, when the image undergoes various transformations. This article, describes the features based on the Directional Intensification using Tertiary Filtering (DITF). The robustness of the algorithm is improved, because of the inherent design of Tri-ocular, Bi-ocular and Dia-ocular filters that can intensify the features in all required directions. The algorithm’s robustness is verified with respect to various image transformations. The oxford dataset is used for performance analysis and validation. DITF model is designed to achieve the repeatability score of illumination-variation , blur changes and view-point variation, as 100%, 100% and 99% respectively. The comparative analysis has been performed in terms of precision and re-call. DITF outperforms the state-of-the-art descriptors, namely, BEBLID, BOOST, HOG, LBP, BRISK and AKAZE. An Implementation of DITF source code is available in the following GitHub repository: github.com/Johnchristopherclement/Directional-Intensified-Feature-Descriptor.

Photos and rendered images of LEGO bricks

The paper describes a collection of datasets containing both LEGO brick renders and real photos. The datasets contain around 155,000 photos and nearly 1,500,000 renders. The renders aim to simulate real-life photos of LEGO bricks allowing faster creation of extensive datasets. The datasets are publicly available via the Gdansk University of Technology “Most Wiedzy” institutional repository. The source files of all tools used during the creation of the dataset were made publicly available via GitHub repositories. The images, both photos and the renders were annotated with the unique brick ID and category from the official LEGO catalog. The proposed datasets are stored in easy-to-read formats and are labeled via directory structure allowing easy manipulation and conversion of metadata to other formats.

CardioRVAR: A New R Package and Shiny Application for the Evaluation of Closed-Loop Cardiovascular Interactions.

CardioRVAR is a new R package designed for the complete evaluation of closed-loop cardiovascular interactions and baroreflex sensitivity estimated from continuous non-invasive heart rate and blood pressure recordings. In this work, we highlight the importance of this software tool in the context of human cardiovascular and autonomic neurophysiology. A summary of the main algorithms that CardioRVAR uses are reviewed, and the workflow of this package is also discussed. We present the results obtained from this tool after its application in three clinical settings. These results support the potential clinical and scientific applications of this tool. The open-source tool can be downloaded from a public GitHub repository, as well as its specific Shiny application, CardioRVARapp. The open-source nature of the tool may benefit the future continuation of this work.

Exploring the Integration of Machine Learning Models in Programming Languages on GitHub: Impact on Compatibility to Address Them

GitHub repositories are often used for collaborative development, allowing multiple developers to work on the same codebase and contribute their changes. Each repository is typically associated with a specific project, and it can contain everything from code files to documentation, bug reports, and feature requests. Depending on the context, it can contain files, directories, other resources related to a project, and it is often associated with a particular programming language. By default, GitHub automatically detects the primary programming language used in a repository based on the file extensions and content within the repository. However, this detection is not true all the time; there are some potential issues to consider. One of these problems is that the detected language may not accurately reflect the actual programming languages used in the project, especially if the project utilizes multiple programming languages or has undergone language migrations. In this study, we apply an alternative technology to resolve problems with classifying the programming language of a GitHub repository by analysing file extensions and identifying all programming languages used in the project. We also determine the appropriate primary programming language for the repository. This paper investigates how this technology can address the issues surrounding GitHub’s automatic detection of a repository’s primary programming language and how it can provide information on all the programming languages used in a project.

Fake news detection: Taxonomy and comparative study

The proliferation of social networks has presented a significant challenge in combating the pervasive issue of fake news within modern societies. Due to the large amount of information and news produced daily in text, audio, and video, the validation and verification of this information have become crucial tasks. Leveraging advancements in artificial intelligence, distinguishing between fake news and factual information through automatic fake news detection systems has become more feasible. Automatic fake news detection has been explored from diverse perspectives, employing various feature extraction and classification models. Nonetheless, empirical evaluations, categorization, and comparisons of existing techniques for handling this problem remain limited. In this paper, we revisit the definitions and perspectives of fake news and propose an updated taxonomy for the field based on multiple criteria: (1) Type of features used in fake news detection; (2) Fake news detection perspectives; (3) Feature representation methods; and (4) Classification approaches. Moreover, we conduct an extensive empirical study to evaluate several feature representation techniques and classification approaches based on accuracy and computational cost. Our experimental results demonstrate that the optimal feature extraction techniques vary depending on the characteristics of the dataset. Notably, context-dependent models based on transformer models consistently exhibit superior performance. Additionally, employing transformer models as feature extraction methods, rather than solely fine-tuning the network for the downstream task, improves overall performance. Through extensive error analysis, we identify that a combination of feature representation methods and classification algorithms, including classical ones, offer complementary aspects and should be considered for achieving better generalization performance while maintaining a relatively low computational cost. For further details, including source codes, figures, and datasets, please refer to our project’s GitHub repository: [https://github.com/FFarhangian/Fake-news-detection-Comparative-Study].

An effective and robust genetic algorithm with hybrid multi-strategy and mechanism for airport gate allocation

Gate allocation is a combinatorial scheduling problem with multi-constraint and multi-objective. It is challenging to solve this problem when the size of flights increases continuously. As an adaptive technology with a random search ability, the genetic algorithm (GA) has been widely used for resource scheduling and combinatorial optimization. However, it is prone to slow convergence and falling into local optimal solutions. Therefore, an effective and robust GA based on hybrid multi-strategy of reverse learning, interval probability mutation, and phagocytosis mechanism, called RPIP-GA, is proposed to implement a new airport gate-allocation method. In the RPIP-GA, the population is divided into several subpopulations based on the fitness values of all individuals to prevent population degradation and improve population quality. The reverse learning strategy with elite retention is designed to initialize the population, expand the global search space, improve the quality of the original solution, and increase the population diversity. The phagocytosis mechanism is employed to implement a crossover operation to enhance the convergence rate and local search ability. An interval probability mutation technique is designed to improve the local search ability in the early stage and prevent falling into the local optimum in the later stage. The effectiveness of the RPIP-GA is validated using 45 complex functions selected from the benchmark functions and CEC 2017, 22 real-world engineering problems selected from CEC 2011, and an actual gate allocation problem via comparisons with the GA, PSO, GSA, DNLGSA, WMSDE, PADE, HIRCGA, and other algorithms. The experimental results show that the RPIP-GA can obtain optimal results with improved stability in most cases. The maximum allocation rate of actual airport gates reaches 98%, and the average convergence accuracy increases by 19% compared with that of the GA. The data used in the study is publicly available from the GitHub repository (https://github.com/xiaocangjiu).

Re-defining wearable robots: a multidisciplinary approach towards a unified terminology

Effective communication is especially important in the wearable robots (WRs) community, which encloses a great variety of devices across different application domains, e.g., healthcare, occupational, and consumer. In this paper we present a vocabulary of terms with the aim to create a common understanding of terms and concepts among the different fields of expertise relevant in the WRs community. Our goal is to develop shared documentation that could serve as a reference to facilitate the use of accepted definitions in the field. The presented vocabulary is the result of different focus group discussions among experts in the field. The resulting document was then validated by presenting it to the WR community through an online survey. The results of the survey highlight a strong agreement in terms of acceptance of the vocabulary, its usefulness, and applicability of the proposed definitions as well as an overall appreciation for its purpose and target. This work represents a pilot study providing unique material for the WR community, encouraging the use of shared agreed definitions. The reported version of the vocabulary has been made available as a live document in a github repository, for public commenting and further improvements.

Uncertainty aware neural network from similarity and sensitivity

Recent uncertainty quantification approaches lack transparency. Algorithms often perform poorly in an input domain and the reason for poor performance remains unknown. Therefore, we present a neural network training method that considers similar samples with sensitivity awareness in this paper. In the proposed NN training method for UQ, first, we train a shallow NN for the point prediction. Then, we train another NN to predict absolute differences between targets and predictions. In the next step, we select each sample in the training set one by one and compute both prediction and error sensitivities. Then we select similar samples with sensitivity consideration and save indexes of similar samples. The ranges of an input parameter become narrower when the output is highly sensitive to that parameter. After that, we construct initial uncertainty bounds (UB) by considering the distribution of sensitivity-aware similar samples. Prediction intervals (PIs) from initial uncertainty bounds are larger and cover more samples than required. Therefore, we train bound correction NN. As following all the steps for finding UB for each sample requires a lot of computation and memory access, we train a UB computation NN. The UB computation NN takes an input sample and provides an uncertainty bound. The UB computation NN is the final product of the proposed approach. We have achieved superior performance in most situations through the proposed transparent method. Scripts of the proposed method are available in the following GitHub repository: https://github.com/dipuk0506/UQ

On moments of truncated multivariate normal/independent distributions

Multivariate normal/independent (MNI) distributions contain many renowned heavy-tailed distributions such as the multivariate t, multivariate slash, multivariate contaminated normal, multivariate variance-gamma, and multivariate double exponential distributions. A frequent problem encountered in statistical analysis is the occurrence of truncated observations and non-normality such that theoretical moments are required for the estimation of the truncated multivariate normal/independent (TMNI) distributions. This paper is dedicated to deriving explicit expressions for the moments of the TMNI distributions with supports confined within a hyper-rectangle. A Monte Carlo experiment is undertaken to validate to the correctness of the proposed formulae for five selected members of the TMNI distributions. R scripts and data to reproduce the results are available in the GitHub repository.

A community convention for ecological forecasting: Output files and metadata version 1.0

AbstractThis paper summarizes the open community conventions developed by the Ecological Forecasting Initiative (EFI) for the common formatting and archiving of ecological forecasts and the metadata associated with these forecasts. Such open standards are intended to promote interoperability and facilitate forecast communication, distribution, validation, and synthesis. For output files, we first describe the convention conceptually in terms of global attributes, forecast dimensions, forecasted variables, and ancillary indicator variables. We then illustrate the application of this convention to the two file formats that are currently preferred by the EFI, netCDF (network common data form), and comma‐separated values (CSV), but note that the convention is extensible to future formats. For metadata, EFI's convention identifies a subset of conventional metadata variables that are required (e.g., temporal resolution and output variables) but focuses on developing a framework for storing information about forecast uncertainty propagation, data assimilation, and model complexity, which aims to facilitate cross‐forecast synthesis. The initial application of this convention expands upon the Ecological Metadata Language (EML), a commonly used metadata standard in ecology. To facilitate community adoption, we also provide a Github repository containing a metadata validator tool and several vignettes in R and Python on how to both write and read in the EFI standard. Lastly, we provide guidance on forecast archiving, making an important distinction between short‐term dissemination and long‐term forecast archiving, while also touching on the archiving of code and workflows. Overall, the EFI convention is a living document that can continue to evolve over time through an open community process.