1 - 12 of 12 results


An extension of the OMERO.web client that provides the ability to search for images by their content (e.g., subcellular patterns) rather than just by their annotations. It was developed by the Murphy group at Carnegie Mellon University. OMERO.searcher 1) finds images whose content, as reflected by subcellular location image features, is similar to one or more query images, 2) can use positive and/or negative examples 3) can be iterative, meaning it allows the user to refine the search results (a process referred to as relevance feedback).

PRECOG / PREsentation and Characterization Of Growth-data

Automates visualization, analysis and exploration of complex and highly resolved microbial growth data. PRECOG allows the user to quality control, interact with and evaluate microbial growth data with ease, speed and accuracy, also in cases of non-standard growth dynamics. It filters the raw optical densities in a three-step procedure to remove or reduce noise and bias. PREGOG’s data filtering has been tested by comparing its performance to a multi-layered neural networks noise reduction filter.

hctsa / Highly Comparative Time-Series Analysis

A software package for running highly comparative time-series analysis. hctsa automates the selection of quantitative phenotypes from time-series data by leveraging a large and interdisciplinary literature on time-series analysis. hctsa allows thousands of time-series analysis features to be extracted from time series (or a time-series dataset), as well as tools for normalizing and clustering the data, producing low-dimensional representations of the data, identifying discriminating features between different classes of time series, learning multivariate classification models using large sets of time-series features, finding nearest matches to a time series of interest, and a range of other visualization and analysis functionality.

Planform / Planarian formalization

A manually curated database and software tool for planarian regenerative experiments, based on a mathematical graph formalism. Planform contains more than a thousand experiments from the main publications in the planarian literature. The software tool provides the user with a graphical interface to easily interact with and mine the database. The presented system is a valuable resource for the regeneration community and, more importantly, will pave the way for the application of novel artificial intelligence tools to extract knowledge from this dataset.


Imputes missing values in large-scale high-dimensional phenome data. phenomeImpute contains four variations of K-nearest-neighbor (KNN) methods and was compared with two existing methods, multivariate imputation by chained equations and missForest. The four variations are imputation by variables (KNN-V), by subjects (KNN-S), their weighted hybrid (KNN-H) and an adaptively weighted hybrid (KNN-A). The results show that Imputation of missing values with low imputability measures increased imputation errors greatly and could potentially deteriorate downstream analyses.