Skip to main content
Premium Trial:

Request an Annual Quote

X-Mine Builds Flexible System for Multivariate Data Analysis

Premium

As more and more bioinformatics companies join the data-mining gold rush, newcomer X-Mine is determined to set itself apart from the rest of the crowd.

“We all have tools for clustering-based analysis,” said CEO and co-founder Sandip Ray. But in comparison to competitors such as GeneData, Molecular Mining, and BioWolf, “nobody else has supervised tools, nobody else has tools for discovery, and nobody else has tools for prediction,” he claimed.

X-Mine, based in Hayward, Calif., was founded in April 2000 with the aim of combining “different kinds of pattern recognition, machine learning, and data mining models into one system,” said Ray. It has moved rapidly, launching its first product, X-Miner, in August and announcing its first licensing collaboration — with BioCardia, a company trying to improve cardiac care — in November.

Ray said he wanted to move beyond the hierarchical clustering and self-organizing maps that were the state of the art in the industry at the time he launched the company. He said data-mining programs developed by NASA’s Jet Propulsion Laboratory to analyze red-shift data and to quantify chlorophyll in plants on earth by satellite inspired him to ask, “What kind of data-mining programs similar to this can we create so that the user will have sufficient flexibility?” He soon convinced Robert Tibshirani and Trevor Hastie, statisticians from Stanford University, to come on board with their expertise in data mining.

Ray describes X-Mine’s data mining approach as a three-tier system: exploratory analysis, which determines how many clusters there may be; discovery-based analysis, which seeks new information in the data; and predictive modeling. The company has developed around 24 data-mining engines to address gene expression data, protein chip data, mass spectrometry data, and “basically any situation where you have thousands of variables and hundreds of classes,” said Ray.

So far, X-Mine — which currently has 17 employees — has raised $1.5 million in venture capital and an additional $2 million in angel financing.

In contrast to many new bioinformatics companies, that just sell software, X-Mine collaborates with its clients, both licensing its software and providing expertise on how to use it. It is hoping to sign on more biotechnology, pharmaceutical, and clinical diagnostics companies.

But X-Mine doesn’t intend to limit itself to the biopharmaceutical sector. “We tried to create a system that was flexible … so that it would not only address needs in the biology sector but it might also have a bigger reach through the financial market industry,” said Ray.

— Julia Karow

 

Filed under

The Scan

UCLA Team Reports Cost-Effective Liquid Biopsy Approach for Cancer Detection

The researchers report in Nature Communications that their liquid biopsy approach has high specificity in detecting all- and early-stage cancers.

Machine Learning Improves Diagnostic Accuracy of Breast Cancer MRI, Study Shows

Combining machine learning with radiologists' interpretations further increased the diagnostic accuracy of MRIs for breast cancer, a Science Translational Medicine paper finds.

Genome Damage in Neurons Triggers Alzheimer's-Linked Inflammation

Neurons harboring increased DNA double-strand breaks activate microglia to lead to neuroinflammation like that seen in Alzheimer's disease, a new Science Advances study finds.

Long COVID-19 Susceptibility Clues Contained in Blood Plasma Proteome

A longitudinal study in eBioMedicine found weeks-long blood plasma proteome shifts after SARS-CoV-2 infection, along with proteomic signatures that appeared to coincide with long Covid risk.