Machine Learning Based Virtual Screening for Biodegradable Polyesters
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
Current biodegradation timelines show that polyesters take over 200 years to break down. A crucial component of several industries, polyesters are relied upon for materials development and thus require sustainable alternatives. Recent works in generative modeling have made it possible to produce large sets of chemical structures, but current molecular screening methods are expensive, not scalable, and are oversimplified. This work evaluates whether a molecule’s biodegradability potential can be accurately predicted by training a model on recent experimental data. Additionally, three chemical descriptors were evaluated on the final molecules for their effects on biodegradability: molecular structure, bond types, and solubility. A Gradient Boosted Machine was trained on a dataset of 600 molecules and their binary labels on biodegradability. The classification model effectively captured the biodegradability property, yielding an Area Under the Receiver Operating Characteristics, AUROC, of 84% and an Area Under the Precision Recall Curve, or AUPRC, of 87%. Additionally, an existing amortized synthetic tree generation model, SynNet, validated each molecule by showing chemical synthesizability and producing simple and interpretable synthesis pathways. This approach of filtering by prediction and chemical rule interpretation is inexpensive, highly scalable and can capture the necessary complexity. Using this method, novel polyester candidates can be polymerized and produced into sustainable fabrics, reducing environmental stress from textile-reliant industries.
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 | 0.000 | 0.000 |
| 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 | 0.000 | 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