FDA has chosen to implement Ariana Pharma's KEM® (Knowledge Extraction Management) decision-support platform to facilitate data analysis for the validation of biomarker signatures. The technology will be used by FDA's reviewers to analyze pharmacogenomic and other data submitted through the agency's Voluntary Exploratory Data Submission (VXDS) program.
Ariana claims the collaboration will help FDA more systematically identify potential genomic fingerprints and develop recommendations relating to the analysis of genomic data prior to the submission of biomarker signatures. "We are looking forward to this collaboration to help the agency systematically analyze all equivalent signatures combining both genomic and phenotypic data, thus increasing chances of selecting the best biomarker signature," comments Federico Goodsaid, Ph.D., FDA's associate director for operations in genomics at the Center for Drug Evaluation and Research's Office of Clinical Pharmacology.
Ariana provides data-mining solutions and decision-support services for clinical and safety studies, drug discovery, diagnostics, and biomarker development. The firm's KEM platform is a rules-based method developed to mine data and systematically extract and manage all consistent hypotheses. Ariana claims the technology can be applied to biomarker discovery to identify the best subset of markers in order to maximize patient coverage, through the ability to evaluate heterogeneous information, including genomic, proteomic, polypharmacology, and clinical data. The firm also suggests that unlike existing numerical methods, KEM can generate and prioritize hypotheses, carry out more exhaustive analysis, and handle missing data.
Ariana offers access to the KEM platform through nonexclusive licensing and service partnerships. In February the firm signed a fee-for-service collaboration agreement with Fovea Pharmaceuticals, through which Ariana will use the KEM technology to carry out systematic analysis of Fovea's PrednisporinTM Phase II clinical data.
FDA's VXDS program (formerly Voluntary Genomic Data Submissions) is designed to encourage the submission of pharmacogenomic data that is currently not mandatory in terms of IND, NDA, or BLA submissions. The agency says it is particularly interested in gaining a greater insight into the types of genetic loci or gene-expression profiles being explored by the pharmaceutical industry for pharmacogenomic testing.
Most particularly, it says submitted data will help it understand factors such as: the test systems and techniques being employed; the problems encountered in applying pharmacogenomic tests to drug development; the ability to reproducibly transmit, store, and process large amounts of complex pharmacogenomic data streams; the scientific rationale for standardization of the naming and characterization of genes used on different genomic analysis platforms; and for developing bioinformatics software programs used to evaluate pharmacogenomic data.