Signals Inventa

Edison Analysis is a next-generation scientific data-analysis agent built by Edison Scientific. It is the analytical engine underpinning their AI Scientist platform, Kosmos, and it’s available both on Edison’s platform and via API. Edison Analysis performs complex scientific data analysis by iteratively building and updating Jupyter notebooks in a dedicated environment; given a dataset plus a prompt, the agent explores, analyzes, and interprets the data to provide comprehensive insights, reports, and visualizations, very much like a human scientist. It supports execution of Python, R, and Bash code, and includes a full suite of common scientific-analysis packages in a Docker environment. Because all work is done within a notebook, the reasoning is fully transparent and auditable; users can inspect exactly how data was manipulated, which parameters were chosen, how conclusions were drawn, and can download the notebook and associated assets at any time.

With visual analytics powered by TIBCO Spotfire®, PerkinElmer Signals Translational provides all the necessary tools to harmonize, manage, search, aggregate and analyze data consistently across large datasets for use in translational research in a highly scalable manner. Powered by the industry-leading visual analytics platform TIBCO Spotfire®, Signals Translational enables precision medicine studies with the most advanced biomarker discovery and patient stratification solution available today. The Linear Mixed Effect App (LME) in Signals Translational allows scientists to rank the effect of multiple variables on a phenotype of interest, with the option to correct the effect of random variables in the analysis. The genes with the strongest impact on cancer stage progression can be identified independently of the origin of the patients. With the advantage of properly handling missing values and outliers, LME models are an effective tool to identify potential biomarkers.