Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML Tools.
Ontology highlight
ABSTRACT:
SUBMITTER: Tran LM
PROVIDER: S-EPMC7384547 | biostudies-literature | 2020
REPOSITORIES: biostudies-literature
Publications
Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML Tools.
Tran Lina M LM Mocle Andrew J AJ Ramsaran Adam I AI Jacob Alexander D AD Frankland Paul W PW Josselyn Sheena A SA
Frontiers in neural circuits 20200715
<i>In vivo</i> 1-photon (1p) calcium imaging is an increasingly prevalent method in behavioral neuroscience. Numerous analysis pipelines have been developed to improve the reliability and scalability of pre-processing and ROI extraction for these large calcium imaging datasets. Despite these advancements in pre-processing methods, manual curation of the extracted spatial footprints and calcium traces of neurons remains important for quality control. Here, we propose an additional semi-automated ...[more]
Similar Datasets
Project description:Although there is increased interest in utilizing machine learning (ML) to support drug development, technical hurdles associated with complex algorithms have limited widespread adoption. In response, we have developed Pharm-AutoML, an open-source Python package that enables users to automate the construction of ML models and predict clinical outcomes, especially in the context of pharmacological interventions. In particular, our approach streamlines tedious steps within the ML workflow, including data preprocessing, model tuning, model selection, results analysis, and model interpretation. Moreover, our open-source package helps to identify the most predictive ML pipeline among defined search spaces by selecting the best data preprocessing strategy and tuning the ML model hyperparameters. The package currently supports multiclass classification tasks, and additional functions are being developed. Using a set of five publicly available biomedical datasets, we show that our Pharm-AutoML outperforms other ML frameworks, including H2O with default settings, by demonstrating improved predictive accuracy of classification. We further illustrate how model interpretation methods can be utilized to help explain the fine-tuned ML pipeline to end users. Pharm-AutoML provides both novice and expert users improved clinical predictions and scientific insights.
| S-EPMC8129712 | biostudies-literature
Project description:Background and objectiveEver since its discovery, calcium imaging has proven its worth in discovering new insights into the mechanisms of cellular communication. Yet, the analysis of the data generated by calcium imaging experiments demands a large amount of time from researchers. Tools enabling automated and semi-automated analysis are available, but often they allow automating only a part of the data analysis process. Therefore, we developed CALIMA (https://aethelraed.nl/calima), a free and open-source standalone software tool that provides an opportunity to quickly detect cells, to obtain the calcium spikes, and to determine the underlying network structure of neuronal cell cultures.MethodsOwing to the difference of Gaussians algorithm applied for the cell detection, CALIMA is able to detect regions of interest (ROIs) quickly. The z-scoring algorithm provides a means to set the requirements for spike detection, and the neuronal connections can be reconstructed by analyzing the cross-correlation between the cellular activity. We evaluated CALIMA's reliability, speed, and functionality with a special focus on neuronal cell detection and network reconstruction. The evaluation was performed by using real-life data such as a known example dataset (cultured primary rat cortical neurons, University of Pennsylvania) and by analyzing video graphic footage of in vitro brain cell samples (SH-SY5Y neuroblastoma cultures, one sample with synchronous neuron firing). The obtained results were compared to the corresponding outcomes observed on same datasets for other similar software solutions. Moreover, we compared the results of segmentation and peak detection analysis, the ones obtained using CALIMA and those acquired manually.ResultsCALIMA was able to detect the cells in the cultures within seconds. The average sensitivity was 82% across the datasets checked, comparing favorably with the alternative software solutions. Using the correct parameters, CALIMA's Ca-spikes detection sensitivity reached 96%. Lastly, neuronal networks were reconstructed by combining the data on the ROI's activity and the cell's positions, finding the most likely inter-cell connections.ConclusionsWe found that CALIMA proved to be a robust and fast tool to analyze the data of experiments for the digital reconstruction of the neuronal cellular network while being able to process the analysis steps with minimal user input required and in a time efficient manner.
| S-EPMC6718774 | biostudies-literature
Project description:How does the concerted activity of neuronal populations shape behavior? Impediments to address this question are primarily due to critical experimental barriers. An integrated perspective on large scale neural information processing requires an in vivo approach that can combine the advantages of exhaustively observing all neurons dedicated to a given type of stimulus, and simultaneously achieve a resolution that is precise enough to capture individual neuron activity. Current experimental data from in vivo observations are either restricted to a small fraction of the total number of neurons, or are based on larger brain volumes but at a low spatial and temporal resolution. Consequently, fundamental questions as to how sensory information is represented on a population scale remain unanswered. In Drosophila melanogaster, the mushroom body (MB) represents an excellent model to analyze sensory coding and memory plasticity. In this work, we present an experimental setup coupled with a dedicated computational method that provides in vivo measurements of the activity of hundreds of densely packed somata uniformly spread in the MB. We exploit spinning-disk confocal 3D imaging over time of the whole MB cell body layer in vivo while it is exposed to olfactory stimulation. Importantly, to derive individual signal from densely packed somata, we have developed a fully automated image analysis procedure that takes advantage of the specificities of our data. After anisotropy correction, our approach operates a dedicated spot detection and registration over the entire time sequence to transform trajectories to identifiable clusters. This enabled us to discard spurious detections and reconstruct missing ones in a robust way. We demonstrate that this approach outperformed existing methods in this specific context and made possible high-throughput analysis of approximately 500 single somata uniformly spread over the MB in various conditions. Applying this approach, we find that learned experiences change the population code of odor representations in the MB. After long-term memory (LTM) formation, we quantified an increase in responsive somata count and a stable single neuron signal. We predict that this method, which should further enable studying the population pattern of neuronal activity, has the potential to uncover fine details of sensory processing and memory plasticity.
| S-EPMC7188892 | biostudies-literature
Project description:The Phoenicians were the dominant traders in the Mediterranean Sea two thousand to three thousand years ago and expanded from their homeland in the Levant to establish colonies and trading posts throughout the Mediterranean, but then they disappeared from history. We wished to identify their male genetic traces in modern populations. Therefore, we chose Phoenician-influenced sites on the basis of well-documented historical records and collected new Y-chromosomal data from 1330 men from six such sites, as well as comparative data from the literature. We then developed an analytical strategy to distinguish between lineages specifically associated with the Phoenicians and those spread by geographically similar but historically distinct events, such as the Neolithic, Greek, and Jewish expansions. This involved comparing historically documented Phoenician sites with neighboring non-Phoenician sites for the identification of weak but systematic signatures shared by the Phoenician sites that could not readily be explained by chance or by other expansions. From these comparisons, we found that haplogroup J2, in general, and six Y-STR haplotypes, in particular, exhibited a Phoenician signature that contributed > 6% to the modern Phoenician-influenced populations examined. Our methodology can be applied to any historically documented expansion in which contact and noncontact sites can be identified.
| S-EPMC2668035 | biostudies-literature
Project description:BackgroundCurrently, there exists tens of different microbial and eukaryotic metabolic reconstructions (e.g., Escherichia coli, Saccharomyces cerevisiae, Bacillus subtilis) with many more under development. All of these reconstructions are inherently incomplete with some functionalities missing due to the lack of experimental and/or homology information. A key challenge in the automated generation of genome-scale reconstructions is the elucidation of these gaps and the subsequent generation of hypotheses to bridge them.ResultsIn this work, an optimization based procedure is proposed to identify and eliminate network gaps in these reconstructions. First we identify the metabolites in the metabolic network reconstruction which cannot be produced under any uptake conditions and subsequently we identify the reactions from a customized multi-organism database that restores the connectivity of these metabolites to the parent network using four mechanisms. This connectivity restoration is hypothesized to take place through four mechanisms: a) reversing the directionality of one or more reactions in the existing model, b) adding reaction from another organism to provide functionality absent in the existing model, c) adding external transport mechanisms to allow for importation of metabolites in the existing model and d) restore flow by adding intracellular transport reactions in multi-compartment models. We demonstrate this procedure for the genome- scale reconstruction of Escherichia coli and also Saccharomyces cerevisiae wherein compartmentalization of intra-cellular reactions results in a more complex topology of the metabolic network. We determine that about 10% of metabolites in E. coli and 30% of metabolites in S. cerevisiae cannot carry any flux. Interestingly, the dominant flow restoration mechanism is directionality reversals of existing reactions in the respective models.ConclusionWe have proposed systematic methods to identify and fill gaps in genome-scale metabolic reconstructions. The identified gaps can be filled both by making modifications in the existing model and by adding missing reactions by reconciling multi-organism databases of reactions with existing genome-scale models. Computational results provide a list of hypotheses to be queried further and tested experimentally.
| S-EPMC1933441 | biostudies-literature
Project description:Early postoperative mortality risk prediction is crucial for clinical management of gastric cancer. This study aims to predict 90-day mortality in gastric cancer patients undergoing gastrectomy using automated machine learning (AutoML), optimize models for preoperative prediction, and identify factors influential in prediction. National Cancer Database was used to identify stage I-III gastric cancer patients undergoing gastrectomy between 2004 and 2016. 26 features were used to train predictive models using H2O.ai AutoML. Performance on validation cohort was measured. In 39,108 patients, 90-day mortality rate was 8.8%. The highest performing model was an ensemble (AUC = 0.77); older age, nodal ratio, and length of inpatient stay (LOS) following surgery were most influential for prediction. Removing the latter two parameters decreased model performance (AUC 0.71). For optimizing models for preoperative use, models were developed to first predict node ratio or LOS, and these predicted values were inputted for 90-day mortality prediction (AUC of 0.73-0.74). AutoML performed well in predicting 90-day mortality in a larger cohort of gastric cancer patients that underwent gastrectomy. These models can be implemented preoperatively to inform prognostication and patient selection for surgery. Our study supports broader evaluation and application of AutoML to guide surgical oncologic care.
| S-EPMC10329647 | biostudies-literature
Project description:MotivationMetabolomics generates complex data necessitating advanced computational methods for generating biological insight. While machine learning (ML) is promising, the challenges of selecting the best algorithms and tuning hyperparameters, particularly for non-experts, remain. Automated machine learning (AutoML) can streamline this process; however, the issue of interpretability could persist. This research introduces a unified pipeline that combines AutoML with explainable AI (XAI) techniques to optimize metabolomics analysis.ResultsWe tested our approach on two datasets: renal cell carcinoma (RCC) urine metabolomics and ovarian cancer (OC) serum metabolomics. AutoML, using auto-sklearn, surpassed standalone ML algorithms such as SVM and random forest in differentiating between RCC and healthy controls, as well as OC patients and those with other gynecological cancers (Non-OC). Auto-sklearn employed a mix of algorithms and ensemble techniques, yielding a superior performance (AUC of 0.97 for RCC and 0.85 for OC). Shapley Additive Explanations (SHAP) provided a global ranking of feature importance, identifying dibutylamine and ganglioside GM(d34:1) as the top discriminative metabolites for RCC and OC, respectively. Waterfall plots offered local explanations by illustrating the influence of each metabolite on individual predictions. Dependence plots spotlighted metabolite interactions, such as the connection between hippuric acid and one of its derivatives in RCC, and between GM3(d34:1) and GM3(18:1_16:0) in OC, hinting at potential mechanistic relationships. Through decision plots, a detailed error analysis was conducted, contrasting feature importance for correctly versus incorrectly classified samples. In essence, our pipeline emphasizes the importance of harmonizing AutoML and XAI, facilitating both simplified ML application and improved interpretability in metabolomics data science.Availabilityhttps://github.com/obifarin/automl-xai-metabolomics.
| S-EPMC10634896 | biostudies-literature
Project description:BackgroundThe ChEMBL database is one of a number of public databases that contain bioactivity data on small molecule compounds curated from diverse sources. Incoming compounds are typically not standardised according to consistent rules. In order to maintain the quality of the final database and to easily compare and integrate data on the same compound from different sources it is necessary for the chemical structures in the database to be appropriately standardised.ResultsA chemical curation pipeline has been developed using the open source toolkit RDKit. It comprises three components: a Checker to test the validity of chemical structures and flag any serious errors; a Standardizer which formats compounds according to defined rules and conventions and a GetParent component that removes any salts and solvents from the compound to create its parent. This pipeline has been applied to the latest version of the ChEMBL database as well as uncurated datasets from other sources to test the robustness of the process and to identify common issues in database molecular structures.ConclusionAll the components of the structure pipeline have been made freely available for other researchers to use and adapt for their own use. The code is available in a GitHub repository and it can also be accessed via the ChEMBL Beaker webservices. It has been used successfully to standardise the nearly 2 million compounds in the ChEMBL database and the compound validity checker has been used to identify compounds with the most serious issues so that they can be prioritised for manual curation.
| S-EPMC7458899 | biostudies-literature
Project description:Although the scientific community increasingly recognizes that its communication with the public may shape civic engagement with science, few studies have characterized how this communication occurs online. Social media plays a growing role in this engagement, yet it is not known if or how different platforms support different types of engagement. This study sets out to explore how users engage with science communication items on different platforms of social media, and what are the characteristics of the items that tend to attract large numbers of user interactions. Here, user interactions with almost identical items on five of CERN's social media platforms were quantitatively compared over an eight-week period, including likes, comments, shares, click-throughs, and time spent on CERN's site. The most popular items were qualitatively analyzed for content features. Findings indicate that as audience size of a social media platform grows, the total rate of engagement with content tends to grow as well. However, per user, engagement tends to decline with audience size. Across all platforms, similar topics tend to consistently receive high engagement. In particular, awe-inspiring imagery tends to frequently attract high engagement across platforms, independent of newsworthiness. To our knowledge, this study provides the first cross-platform characterization of public engagement with science on social media. Findings, although focused on particle physics, have a multidisciplinary nature; they may serve to benchmark social media analytics for assessing science communication activities in various domains. Evidence-based suggestions for practitioners are also offered.
| S-EPMC4883777 | biostudies-literature
Project description:The development of automated software and the device for determination of wicking of textile materials, using open-source ImageJ libraries for image processing, and newly designed additional algorithm for the determination of threshold, is presented in this paper. The description of the device, design of the open-source software "Kapilarko", as well as an explanation of the steps: image processing, threshold determination and reading of wicking height, are provided. We have also investigated the possibility of using the artificial neural networks for automatic recognition of the wicking height. The results showed that the recognition of the wet area of the sample, based on the application of artificial neural networks was in a very good agreement with the experimental data. The device's utility for the measurement of wicking ability of textile materials was proved by testing various knitted fabrics. The constructed device has the advantages of providing automated measurement and minimization of the subjective errors of the operators; extremely fast or long-term measurements; digital recording of results; consistency of experimental conditions; possibility of using water instead of colors and, last but not least, low cost of the device. Considering the importance and frequent measurements of wicking ability of textile materials, the advantages of the presented device, as well as the fact that commercial software without publishing the source-code, are used for most of the available devices, we believe that our idea to design the automated software and device by applying the "open-source" approach, will be of benefit to scientists and engineers in using or improving wicking experiments.
| S-EPMC7668598 | biostudies-literature