A similarity-based deep learning approach for determining the frequencies of drug side effects
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The side effects of drugs present growing concern attention in the healthcare system. Accurately identifying the side effects of drugs is very important for drug development and risk assessment. Some computational models have been developed to predict the potential side effects of drugs and provided satisfactory performance. However, most existing methods can only predict whether side effects will occur and cannot determine the frequency of side effects. Although a few existing methods can predict the frequency of drug side effects, they strongly depend on the known drug-side effect relationships. Therefore, they cannot be applied to new drugs without known side effect frequency information. In this paper, we develop a novel similarity-based deep learning method, named SDPred, for determining the frequencies of drug side effects. Compared with the existing state-of-the-art models, SDPred integrates rich features and can be applied to predict the side effect frequencies of new drugs without any known drug-side effect association or frequency information. To our knowledge, this is the first work that can predict the side effect frequencies of new drugs in the population. The comparison results indicate that SDPred is much superior to all previously reported models. In addition, some case studies also demonstrate the effectiveness of our proposed method in practical applications. The SDPred software and data are freely available at https://github.com/zhc940702/SDPred, https://zenodo.org/record/5112573 and https://hub.docker.com/r/zhc940702/sdpred.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| 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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it