Abstract B1-12: RNA Architect: High performance tools to exhaustively detect cancer-specific structural events in RNA sequencing data
Bibliographic record
Abstract
Abstract The transcriptomes of cancer cells differ structurally and numerically from normal tissue and between different types of cancer. However, a comprehensive large-scale analysis of structural transcriptomic events has been intractable so far due to computational limitations and the lack of an integrative software tool to detect a complete list of events. We developed an optimized computation pipeline, named RNA Architect, which enables the detection of such events from RNA sequencing data for thousands of cancer samples. RNA Architect detects events by discordant read pair and split-read analysis down to the resolution of individual breakpoints. Beside different kinds of fusion events (as in-frame, out of frame, fusions to intergenic regions), it reports a comprehensive overview of other transcriptional events including specific and novel splice-forms, inversions, cryptic and alternative splice sites, exon skips, exon re-usages, and early polyadenylation sites. In this poster, we describe the individual steps of the algorithm as well as our latest benchmarking results on a compilation of literature curated gene fusions: the approach shows a high sensitivity and recovers 92% of known fusion events. We also describe the post-processing of the data, which enables us to delineate relevant events from non-cancer specific ones and noise. We especially discuss optimizations implemented to run the software efficiently on a state of the art compute cluster. These optimizations enable the computation of a large amount of samples in a reasonable time frame (~ 8h on a 100 CPU system for the core split-read algorithm and ~3 hours for the discordant pair analysis on a 50 CPU system per sample). The high performance of the pipeline allows generating a comprehensive catalogue of all transcriptional events from large sets of cancer samples. RNA Architect is also fast enough to be used in time critical clinical settings as a potential diagnostic tool. Citation Format: Roland Chrisitian Arnold, Andrej Rosic, Reid JP Hayes, Adam Shlien. RNA Architect: High performance tools to exhaustively detect cancer-specific structural events in RNA sequencing data. [abstract]. In: Proceedings of the AACR Special Conference on Computational and Systems Biology of Cancer; Feb 8-11 2015; San Francisco, CA. Philadelphia (PA): AACR; Cancer Res 2015;75(22 Suppl 2):Abstract nr B1-12.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.027 | 0.016 |
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".