Skip to main content
Premium Trial:

Request an Annual Quote

CollabRx Expands Treatment Guidance to Lung Cancer, Partners with CAP for Patient Outreach


By Molika Ashford

CollabRx has partnered with the College of American Pathologists to broaden patient access to its online cancer therapy guidance tools, which were recently expanded to encompass lung cancer in addition to melanoma.

As part of the partnership, patients can now access and download the CollabRx Targeted Therapy Finder applications for both lung cancer and melanoma through CAP's patient-centered website,

Meanwhile, CollabRx and its non-profit partner Cancer Commons published this week in PLoS One the full model of their scheme for lung cancer molecular subtyping and therapy matching. The new model represents the backbone of CollabRx's lung cancer TTF application, which became available on the company's website late last year. Like the company's previous Melanoma Molecular Disease Model, the Lung Cancer MDM will be updated by the partners in an online wiki-style document.

Stanley Robboy, president of CAP and pathology professor at Duke University, said in a statement that working with CollabRx will allow the association to put "valuable information into the hands of patients and hopefully lead to better patient outcomes.”

Last year CollabRx announced a similar partnership with the American Society of Clinical Oncology to provide a line to patients through ASCO's patient-oriented website. As part of that partnership, CollabRx gained enhanced and guided access to the society’s wide knowledge base and publications (PGx Reporter 4/27/2011).

Gavin Gordon, CollabRx's vice president of business development, told PGx Reporter this week that the new partnership with CAP is exciting because it offers the opportunity to connect with a different group of doctors and patients.

"We're addressing a different type of physician," he said. "CAP is pathologists. ASCO is oncology. So we're really expanding the breadth and scope of the types of users we are [hoping to reach.]"

"We don't expect most people to come to us by Google; we expect them to go where they usually go for information, so we are working on a number of [these] relationships to [facilitate] patients' use of the resource," he said.

That resource recently doubled its purview with CollabRx adding the lung cancer TTF application last November and publishing the full lung cancer MDM with Cancer Commons last week.

The model includes nine major subtypes for lung cancer that are considered "actionable" based on a number of criteria, including whether there are either approved targeted therapies or more experimental treatments available through current clinical trials, and whether there is an approved molecular diagnostic assay that defines the subtype.

Some of the nine types are further subdivided. For example, subtype one includes type 1.1, characterized by mutations in EGFR that make tumors responsive to EGFR inhibitors; type 1.2, defined as non-small cell lung cancer harboring a T790 mutation in exon 20 of the EGFR gene; and type 1.3, defined based on the VeriStrat proteomic signature.

The PLoS One paper outlines all subtypes along with their associated potential therapeutic approaches.

Based on this model, CollabRx's lung cancer TTF, like its melanoma cousin, allows patients to input information about their disease, including tumor stage, histology, metastasis status, and genomic testing information. The apps suggest molecular diagnostic tests, targeted therapies, and potential clinical trials based on which molecular subtype in the relevant MDM a patient falls into.

However, the lung cancer TTF, and the model that informs it, offer improvements over the initial melanoma project, CollabRx's Gordon said.

The creation of the model and its associated application followed the same process as in melanoma, he said, with the content curated and overseen by an expert advisory board. But, because lung cancer is more heterogeneous than melanoma, the model is broader. Additionally, the application incorporates information about patients' previous treatments, which was not a feature of the melanoma app.

"Like melanoma, it's a taxonomy — a standardized way to look at where targeted therapy has been and is going for lung cancer," he said. But because the disease has a higher incidence than melanoma, the developers also believe the new model will "allow many more researchers to interact in the way we envisioned."

The partners aim to eventually create a system for bringing real-world data back into the molecular disease models, using networking systems for experts involved in creating the MDMs as well as rapid learning communities that can provide data on outcomes and results from patients and doctors using the information in clinical practice.

The two partners are just now beginning to close this "information loop," according to Jay Bartels, vice president of operations at Cancer Commons, who said the team is in the process of incorporating information from users.

"After you launch the models it takes time for people to leverage the model and then give you feedback," he said. "We put together a campaign where people could provide data to us around the melanoma model last year [and] we're just beginning to see a little response on that."

He said the group is also building partnerships with a number of institutions to create the planned rapid learning communities that will add outcome and response data.

Marty Tenenbaum, chairman and co-founder of CollabRx, told PGx Reporter this week that the group is "gearing up" a first pilot learning community with lung cancer researchers at Oregon Health & Science University.

"If this works then we are planning to build these around all the models," he said.

Cancer Commons' role, aside from managing the development of the models, "is to find out what of the expert knowledge [actually] works and what needs to be refined based on interaction of experts … and most importantly based on clinical outcomes of patients treated according to the recommendations," Tenenbaum said.

"If data shows something unexpected, that's an opportunity to go back to the forum, discuss implications, and at some point revise the model," with the ultimate guidance and final say of expert advisory committees, he said.

From the technical side, Gordon said CollabRx is developing tools to better facilitate exchange between these experts tasked with creating and shepherding the molecular disease models.

"Those are probably not going to have a lot of public visibility because we are going to trial them internally first," he said.

"But you could imagine if doctor X says, 'I had a patient respond this way,' and someone else can comment on that, you get these really messy strings, so what Facebook did to social commentary we're trying to do with expert-based commentary."

Bartels said that there are additional cancers currently in the works for the organization. He declined to detail the lineup, but said the groups are planning to release details this year.

Have topics you'd like to see covered in Pharmacogenomics Reporter? Contact the editor at mashford [at] genomeweb [.] com.

The Scan

Genetic Tests Lead to Potential Prognostic Variants in Dutch Children With Dilated Cardiomyopathy

Researchers in Circulation: Genomic and Precision Medicine found that the presence of pathogenic or likely pathogenic variants was linked to increased risk of death and poorer outcomes in children with pediatric dilated cardiomyopathy.

Fragile X Syndrome Mutations Found With Comprehensive Testing Method

Researchers in Clinical Chemistry found fragile X syndrome expansions and other FMR1 mutations with ties to the intellectual disability condition using a long-range PCR and long-read sequencing approach.

Team Presents Strategy for Speedy Species Detection in Metagenomic Sequence Data

A computational approach presented in PLOS Computational Biology produced fewer false-positive species identifications in simulated and authentic metagenomic sequences.

Genetic Risk Factors for Hypertension Can Help Identify Those at Risk for Cardiovascular Disease

Genetically predicted high blood pressure risk is also associated with increased cardiovascular disease risk, a new JAMA Cardiology study says.