Rancho BioSciences: Organizing and Unifying Datasets for Streamlined Analysis

Julie Bryant, CEO
For efficient data mining and analysis, semantically aligned and streamlined data remains of utmost importance. The pharmaceutical industry imbibes a large amount of data that constrain companies with a tedious and time-consuming task of data classification. Headquartered in San Diego, CA, Rancho Biosciences is a scientific data consulting company that caters to the pharmaceutical industry. They not only subtract the data clutter out of their clients’ business domain, but also add on efficiency by organizing and harmonizing the data.

Spearheaded by Julie Bryant, Rancho Biosciences works towards data organization activity for life science companies, government and academia organizing their public and internal data sets from various sources and unifying the data for search and analysis. The company renders both on-site and off-site data curation services for all kinds of data including OMICs, assay and clinical data. Alongside, it builds customer-based ontologies, often using commonly accepted naming such as MeSH, MedDRA or CDISC, moving on to customizing and enriching them to fit the requirements of a specific project.“We clean and organize datasets using the client’s ontology or creating one for them, which makes it easy to find the information they are searching for,” asserts Julie Bryant, CEO, Rancho Biosciences. They encompass robust manual curation workflow in collaboration with an application of controlled vocabularies from scientific ontologies and dictionaries and in house automation tools.

Rancho Biosciences renders one of its efficient solutions, ‘tranSMART’—an open source platform hosted on a server accessible to its clients. It acts as a data warehouse where rationalized content can be stored and makes it adaptable to phenotypical, genomic, proteomic, metabolomics, and other data types. The firm also develops internal tools for its clients. For instance, they were given a huge project by one of their customers that they were required to complete in limited time. Rancho Biosciences developed an expertise in ‘Fuzzy Logic’ that allowed their scientists to initiate and harness the database cleanup in minimum timeframe. “Fuzzy Logic can also be used to maintain synonyms for internal platforms, but basically it works for cleaning up any kind of dirty datasets,” says Julie.
In addition, Rancho Biosciences recently announced its efficiency in manually organizing GEO public data sets for several customers across multiple therapeutic areas. “We have autoimmune data sets from GEO as well as neurological and metabolic diseases and cancers. By using ontologies and controlled dictionaries, it was much easier for the end-user to find and use everything they were looking for, resulting in a more comprehensive analysis product,” explains Julie.

The firm is dedicated to simplify and analyze the intricate data output from their customers. For instance, several customers have approached them to decipher the in-depth understanding of their clinical trial data. Partnering with a Pharma customer, Rancho Biosciences investigated possible new disease markets for their drugs and consolidated the entire information onto a spreadsheet for the biologists and a detailed report for management.

We love to clean and organize our client’s data using, public domain or de novo ontologies or dictionaries which makes it easier for the client to retrieve the information they need. Before we come in they often cannot find and leverage what they are looking for

“We are very passionate to help patients in any way possible. By helping support our clients, we believe that a small portion of our contribution goes to finding new cures and diagnostics for patients which is very fulfilling,” sighs Julie. For the years ahead, Rancho Biosciences envisions its growth in data curation, bioinformatics, and IT development space for better client assistance.

Rancho BioSciences

San Diego, CA

Julie Bryant, CEO

A scientific data consulting company focused onto data curation and organization of public and internal data sets.