Prediction of pathogenic mutations in human transmembrane proteins and their associated diseases via utilizing pre-trained Bio-LLMs
Bibliographic record
Abstract
Missense mutations can disrupt the structure and function of membrane proteins, potentially impairing key biological processes and leading to various human diseases. However, existing computational methods primarily focus on binary pathogenicity classification for general proteins, with limited approaches specifically designed for membrane proteins, and even fewer methods capable of fine-grained, multi-label classification for specific disease categories. To address this gap, we proposed MutDPAL, a deep learning method specifically designed to identify pathogenic mutations in membrane proteins and further classify such pathogenic mutations into potential diseases categories. MutDPAL utilizes two pre-trained biological large language models (Bio-LLMs), one for raw sequence features and the other for encoding transmembrane environment features. By employing a cross-attention-based disease-protein association learning approach in the context of membrane proteins, MutDPAL captures the intricate relationships between mutations and diseases, enabling accurate pathogenicity prediction and classification into 15 distinct disease categories. Experimental results demonstrate that MutDPAL outperforms existing methods in predicting membrane protein mutation pathogenicity and excels in multi-label disease classification tasks, achieving high predictive accuracy across all 15 disease categories. MutDPAL is the first to combine transmembrane environment with disease encoding features for fine-grained disease classification, offering valuable insights into the pathogenicity of missense mutations in membrane protein.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".