Multi-label Deep Learning for Gene Function Annotation in Cancer Pathways
Bibliographic record
Abstract
The war on cancer is progressing globally but slowly as researchers around the world continue to seek and discover more innovative and effective ways of curing this catastrophic disease. Organizing biological information, representing it, and making it accessible, or biocuration, is an important aspect of biomedical research and discovery. However, because maintaining sophisticated biocuration is highly resource dependent, it continues to lag behind the continually being generated biomedical data. Another critical aspect of cancer research, pathway analysis, has proven to be an efficient method for gaining insight into the underlying biology associated with cancer. We propose a deep-learning-based model, Stacked Denoising Autoencoder Multi-Label Learning (SdaMLL), for facilitating gene multi-function discovery and pathway completion. SdaMLL can capture intermediate representations robust to partial corruption of the input pattern and generate low-dimensional codes superior to conditional dimension reduction tools. Experimental results indicate that SdaMLL outperforms existing classical multi-label algorithms. Moreover, we found some gene functions, such as Fused in Sarcoma (FUS, which may be part of transcriptional misregulation in cancer) and p27 (which we expect will become a member viral carcinogenesis), that can be used to complete the related pathways. We provide a visual tool ( https://www.keaml.cn/gpvisual ) to view the new gene functions in cancer pathways.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".