May 17, 2018 | BOSTON—Bio-IT World announced the winners of the 2018 Best Practices Awards this morning at the Bio-IT World Conference and Expo. Entries from Alexion Pharmaceuticals, Takeda Pharmaceuticals, AstraZeneca, Celgene, and Massachusetts General Hospital were honored.
Since 2003, the Bio-IT World Best Practices Awards has honored excellence in bioinformatics, basic and clinical research, and IT frameworks for biology and drug discovery. Winners were chosen in four categories, and one discretionary award was given.
“I continue to be inspired by the work done in our field,” said Bio-IT World Editorial Director Allison Proffitt. “The Bio-IT World Community is increasingly open, and the partnerships and projects showcased here prove our dedication to collaborative excellence.”
Bio-IT World debuted the Best Practices Awards at the second Bio-IT World Conference & Expo in 2003, hoping to not only elevate the critical role of information technology in modern biomedical research, but also to highlight platforms and strategies that could be widely shared across the industry to improve the quality, pace, and reach of science. In the years since, hundreds of projects have been entered in the annual competition, and over 80 prizes have been given out to the most outstanding entries.
This year, a panel of expert judges joined the Bio-IT World editors in reviewing detailed submissions from pharmaceutical companies, academic centers, government agencies, and technology providers.
The awards ceremony was held at the Seaport World Trade Center in Boston, where the winning teams received their prizes from Proffitt and Philips Kuhl, president of conference organizer Cambridge Healthtech Institute.
2018 Bio-IT World Best Practices Award Winners:
Clinical & Health-IT:
Takeda Pharmaceuticals nominated by Deloitte
Takeda has developed a Data and Analytics Hub platform conceived, designed, and built to address issues of data transparency, trust, and accessibility to support the efficient generation of data insights for functions across R&D. For this project, Takeda focused on a critical use case of this platform, clinical data review/medical monitoring: the Data Hub platform was configured to deliver a fit-for-purpose solution for medical reviewers to make the review process more efficient and incisive. The robust visualization tool and workflows allow for tool scalability and provide an efficient, intuitive interface for comprehensive data review and oversight across multiple disease indications. It will also reduce time constraints on internal staff and support various outsourcing strategies. The Data Hub architecture with support for standardized formats allows management and oversight of multiple vendors performing different functions and supplying different subsets of trial data e.g. lab data, PROs, adherence assessments.
Informatics & Knowledge Management:
AstraZeneca, Discovery Sciences, IMED Biotech Unit nominated by Genedata
Deep Learning for Automated Phenotypic Image Analysis
AstraZeneca’s project presents a new Deep Learning for Phenotypic Imaging software and corresponding workflows based on convolutional neural networks. It yields improvements in automated image analysis for high content screens (HCS) including the ability to: rapidly detect and define all cellular phenotypes in an HCS; efficiently generate training data and on these train Deep Learning networks for subsequent classification of HCS image sets in production assays; and precisely quantify the relevant pharmacology.
Celgene Laboratory Instrument Mobile Alert
The Celgene Lab Instrument Mobile Alert (LabAlert) system allows a user to get warning or error notifications generated from laboratory instruments delivered instantly to user’s mobile devices.
For the first time within the company's R&D organization, there is a system that combines digital technologies such as Amazon Web Services (AWS) Cloud-native application framework and corporate mobile application platform to deliver digital experience that empower the scientists to better plan and execute scientific experiments. In just six weeks the team built and delivered the first version of the system utilizing Agile methodology.
Personalized & Translational Medicine:
Center for Innovation and Bioinformatics, Neurological Clinical Research Institute, Massachusetts General Hospital
NeuroBANK Patient-Centric Platform for Clinical Research
Currently, there are no effective treatments in 95% of 7,000+ rare diseases. Establishing clinical trial readiness for rare neurological conditions by identifying patient populations, discovering and validating outcome measures and biomarkers, developing disease progression models and disease phenotypes is essential. Collaborations between multiple stakeholders in a clinical research continuum are vital.
NeuroBANK patient-centric platform allows researchers to capture and link patients’ data from multiple observational clinical research and natural history studies to medical images, genetic information. tissue repositories, and patient reported outcomes.
After data from a particular study are analyzed and the results are published, the entire study data set is de‐identified and released into a central pool of disease‐specific information available to anyone studying those conditions.
NeuroBANK platform helps to accelerate the discovery, development, and delivery of future treatments, providing new hope to patients and their families.
Alexion Pharmaceuticals nominated by EPAM Systems
SmartPanel: A Rare Genetic Disease Diagnosis Algorithm Competition Platform
Alexion in collaboration with EPAM has developed a software competition platform to allow the objective comparison of contributed algorithms for automated rare disease diagnosis. Each algorithm installed on the platform is given as input the same set of observations about real or simulated patients that have previously been positively diagnosed. The platform runs each algorithm and ranks it as to its ability to correctly diagnose the disease. It is an open platform wherein algorithms can be contributed to it by independent developers. The development team also developed and contributed a set of novel algorithms to increase the diversity of algorithms present on the platform.
Pfizer / SciBite
SciBite-Pfizer ClassifR: An Artificial Intelligence-driven tool for enabling pharmaceutical acquisitions and collaborations
For large pharma, knowledge transfer is crucial for the successful integration of an external research project or commercial acquisition into the organisation. Much of this knowledge is found in a myriad of free-text documents that must be catalogued and integrated with internal data management systems, often requiring extraction of key metadata and alignment to existing document categories. Carrying out this task manually is incredibly cumbersome and time consuming. To address this, Pfizer and SciBite collaborated on the development of ClassifR, a tool to automate this process. ClassifR combines SciBite’s named entity recognition (NER) platform with a novel machine learning approach to automatically align and store incoming documents against standards such as the FDAs Module 4 eCTD (Non-Clinical Study Reports) scheme. This work demonstrates how such technologies can address real-world business challenges in the pharma industry.
The Jackson Laboratory for Genomic Medicine
The Jackson Laboratory Clinical Knowledgebase (JAX-CKB)
Precision medicine has undeniably had an enormous impact on oncology, and while the understanding and treatment of cancer patients have improved, data interpretation still remains a significant bottleneck. The Jackson Laboratory (JAX) is offering its Clinical Knowledgebase (CKB) as a leading resource in the effort to provide evidence-based information to clinicians, researchers and ultimately patients. Initially developed to support its own in-house Clinical Genomics laboratory, JAX-CKB is an expertly curated and publicly accessible relational knowledgebase of gene variants, targeted therapies, efficacy evidence and clinical trials related to cancer. CKB has over 20,000 users to date, and continues to inform patient cancer care while contributing to technology and methodology development to advance the field of oncology precision medicine. Key commercial collaborators are aiding CKB sustainability by leveraging machine-learning capabilities and third-party software platforms have integrated CKB to enable easy and scalable accessibility for informing cancer patient care.