2MO Personalised therapy in CUP: A feasibility study of Bayesian AI digital twins using ctDNA
Bibliographic record
Abstract
Background: Cancer cachexia impairs patient survival, marked by muscle wasting and metabolic disruption.Conventional muscle biopsies make continuous assessment and large-scale screening impractical.Blood DNA methylation profiles offer a promising non-invasive alternative, reflecting tissue-specific gene regulation patterns and enabling cross-tissue transcriptome prediction for cachexia risk assessment in cancer patients.Methods: We developed a Transformer-based deep learning framework to predict muscle tissue transcriptome expression from blood methylation data.Using multicentre database (15,606 samples), we trained a model integrating CpG site chromosomal position information and functional annotations.We employed GTEx database to develop a cross-tissue transcriptome prediction model using transfer and reinforcement learning strategies.The framework was applied to glioma patients' blood methylation data to predict virtual muscle transcriptome profiles.We analyzed similarity between predicted profiles and known cachexia transcriptomes using cosine similarity, Pearson correlation coefficient, and Manhattan distance metrics.Additionally, we integrated IDH mutation status data to assess its relationship with cachexia risk.Results: Our Transformer model achieved high accuracy in predicting gene expression from methylation data (Pearson correlation coefficient = 0.89).The cross-tissue prediction model maintained robust performance when transferring to muscle tissue prediction (Pearson correlation coefficient = 0.87).Importantly, IDH-wildtype gliomas showed significantly stronger association with abnormal expression of cachexia-related genes in predicted muscle transcriptomes compared to IDH-mutant tumors.Our CNN model for predicting the relationship between IDH mutation status and muscle gene expression patterns achieved 0.9733 accuracy. Conclusions:This study enables non-invasive monitoring of molecular changes in muscle tissue without requiring biopsies.This novel strategy offers a valuable tool for early prediction of cancer cachexia in glioma patients, with potential applications across multiple cancer types.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".