Abstract 3632: Adaptive operations and technology platform for nation-scale precision oncology
Bibliographic record
Abstract
Abstract Precision oncology requires predictive models for therapy selection using variety of biomarkers and clinical features as input. Building and validating these models requires analysis of large numbers of diverse cases in order to relate markers and treatments to positive outcomes. The -omics technologies provide a rich source of genetic and epigenetic markers but demand large compute and storage systems to process the data. Thus, there is an urgent need for scalable and reliable information systems to support nation-scale research and delivery of precision oncology. At Lockheed Martin, we deliver operational solutions to complex problems. Here, we present our vision for a precision oncology platform. This solution integrates best-in-class capabilities from multiple sources/vendors to support innovation, research and clinical care for a whole nation. We not only thought about the basic -omics based data collection, but also an infrastructure to collect and store data within a compliant privacy and security framework that also facilitates collaborative analytics and data sharing for deeper insight. Taking a systems engineering approach, we have examined some of the challenges to implement such a platform. For instance, running the basic genomic data processing pipelines to yield variant calls, which in turn will feed the variant store, should be a single scalable workflow. Accounting for multiple data sources, various use cases and selections of tools are at the core of an adaptable workflow. A variant store design that can scale and support a national cohort with an overlaying cohort selection tool are all part of this intricate design. It is our vision that a systems engineering and integration approach can deliver a unified solution for the national precision oncology roadmap. It is paramount that all the individual pieces should be well tuned to deliver scalability and reliability and simultaneously work in complete harmony. Only then we can process data at-scale needed for finding actionable mutations, designing effective treatments and implementing prevention strategies, affordably and reliably. Citation Format: Ogan Abaan, Amrita Basu, David Deal, Michael Hultner. Adaptive operations and technology platform for nation-scale precision oncology. [abstract]. In: Proceedings of the 107th Annual Meeting of the American Association for Cancer Research; 2016 Apr 16-20; New Orleans, LA. Philadelphia (PA): AACR; Cancer Res 2016;76(14 Suppl):Abstract nr 3632.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.003 | 0.007 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.020 | 0.009 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".