Bibliographic record
Abstract
Abstract Cancer is driven by genomic mutations that alter common pathways that regulate cell growth and interaction with the microenvironment. More than 20,000 cancer genomes have been sequenced over the past decade, revealing multiple insights into the causes, evolution and consequences of cancer. However, almost everything we know about the cancer genome has been obtained using exome sequencing, which surveys the 2% of the genome that encodes protein coding genes. The 98% of the genome that is ignored by exome sequencing is the "dark matter" of the cancer genome and was until recently largely unexplored. In this talk, I will discuss highlights from the recently-published Pan-Cancer of Whole Genomes project (https://www.nature.com/articles/s41586-020-1969-6), in which an international team of researchers performed a comprehensive analysis of over 2,600 whole cancer genomes and matched normals, revealing new insights into origins, mechanisms and evolution of tumours. I'll also talk about how machine-learning techniques contributed to the Pan-Cancer project, including the development of an "electronic pathologist" that uses deep learning to accurately identify the tissue origins of tumours based on whole genome sequencing data. Citation Format: Lincoln D. Stein. Plumbing the depths of the non-coding cancer genome [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr IA-17.
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 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.002 | 0.005 |
| Insufficient payload (model declined to judge) | 0.018 | 0.007 |
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".