Accelerating breakthroughs: Platforms for life sciences R&D
Gene editing
One of the hot topics in biotechnology today is gene editing, which allows correction or disruption of some genes without interfering with others. A computational pipeline or data pipeline in the Catalytic platform is used to copy, move, and combine data from different sources and analyze it with sequential processing steps outside the originating computer environment. The data flows to a storage container such as a data lake from which other analytic tools call on.
When an organization implements the Catalytic platform, it already has more than 30 million open access documents in its content repository, including every drug patent since 1984. “Users can search the repository, retrieve the documents most relevant to their projects, and put them in a shared, secure folder,” explained Sacane, adding that they can also contribute data such as verified gene interactions and push a list of that data to an analytics engine. “For example, a gene function prediction map can be generated from the literature. This kind of workflow is common among users of our platform.”
The platform helps get smaller companies on an equal footing with larger ones because they do not need to make big investments in hardware, software, or IT infrastructure to support their R&D efforts. “Many small research organizations are focused on advanced areas such as therapeutic development, gene editing and gene therapies, including anti-cancer drugs,” noted Sacane. “The pace of innovation in R&D today is unlike anything I have seen before. Research projects produce tremendous amounts of data, but data alone is not productive unless there is a way to manage and understand it.” The Catalytic platform provides a single environment in which researchers can explore information, test products and analyze data, collaborate with others, and arrive at conclusions based on an efficient and informed research process.
Clinical trial data management
Missing, inaccurate, or inconsistent data is one of the most common problems in clinical trials. In a study commissioned by Oracle and conducted by Pharma Intelligence, more than half the respondents identified data completeness as a top operational challenge, and nearly half identified data quality as a challenge.
Large clinical trials can involve hundreds of doctors and thousands of patients from all over the world, and the studies can go on for several years. “Given that some data used in clinical trials is coming from electronic health records (EHR), labs, wearable devices, and online surveys,” noted Jim Streeter, global VP of life sciences for health sciences at Oracle, “it is important to be able to verify and cross-check.” A lab sample collection date in an electronic data capture system, for example, may not agree with the one recorded in lab results. The sooner these inconsistencies are detected, the less delay there is in obtaining test results.
Oracle has developed a set of applications that address needs along the value chain of pharmaceutical R&D, and the Oracle Life Sciences Data Hub for integrating them. Oracle’s InForm is an integrated electronic clinical data capture and management cloud platform that is used to capture patient data during a clinical trial. It allows all the doctors who are participating in the clinical trial to input patient data into a single system that the pharmaceutical company which is sponsoring the investigational new drug can access. InForm also applies edit checks, such as verifying that a date is in the proper format, to ensure data cleanliness. With InForm, the pharmaceutical company does not have to spend time aggregating data from several different systems or cleaning data that may be in different formats from different doctors.
To manage the volumes of data from these other sources, clinical teams need a way to aggregate, clean, and organize it. Oracle’s Data Management Workbench (DMW) is fed from the Oracle cloud and provides these and other capabilities such as traceability. “FDA regulations require that clinical trial data be tracked in an uninterrupted path from the doctor’s office or other collection location to the repository from which the analysis is conducted,” Streeter stated. “It’s therefore essential to know that no one has modified this data.” The DMW also provides an environment for managing discrepancies and transforming data.
Improving workflow
Oracle has several other solutions to support the clinical development lifecycle; it recently announced that it has entered into an agreement to acquire goBalto, which offers a workflow system for on-boarding physicians and their staff at research sites for clinical trials. Before sites can begin enrolling patients in a clinical trial, they need to complete several activation steps. The software provides insight into which steps have been completed and which are missing. “Activation has been an area that can significantly slow a clinical trial, so solutions that can help prevent these bottlenecks are very valuable,” Streeter commented.
n addition, Oracle’s Argus Safety Case Management software allows researchers to collect adverse event information for patients participating in clinical trials. Such data is collected both during clinical trials and after the drug is approved by the FDA and is on the market. Safety data normally comes in the form of unstructured notes, and Argus provides advanced analytics that are effective at detecting adverse events, despite the use of varying terminology.
Software products that help expedite the R&D process are playing an important role in speeding the development of new drugs. By providing workflow tailored to the scientific process, improved data management, and collaboration environments, these solutions have the potential to reduce costs and time to market and bring new medications to populations that are in need.