Using The Protein Corona to Train Deep Neural Networks and Build Patient-specific Nanomaterials
Bibliographic record
Abstract
When nanoparticles are exposed to biological environments, proteins rapidly adsorb to the surface and form a structure known as the protein corona. The protein corona always forms irrespective of the material composition, surface chemistry, size and shape. This interfacial network of protein is one of the biggest banes to nanomedicine as it mediates how nanoparticles behave in the body despite our synthetic control. Investigations outside the body have shown that it is possible to predict protein corona adsorption based on nanoparticle size, shape and surface chemistry. At present, no insight and forecast exists of protein assembly patterns in vivo, nor has this interfacial chemistry been used toward building new applications in medicine. This thesis presents an original contribution to biomedical nanotechnology as it exploits the protein corona across two themes with a collective effort to improve translation of nanomaterials into the clinic. First I demonstrate that the protein corona can be deciphered and used as input data to train a neural network that is able to predict nanoparticle biodistribution in an animal model. Second, a new class of nanomaterial is created by isolation, separation and materials ligation of the protein corona from a nanoparticle template. The latter provides a solution to a major problem facing nanomaterial design; the engineering of size and shape tunable organic nanomaterials under 100 nm. They are biodegradable and do not activate innate or adaptive immunity following single and repeated administrations in vivo. Together, these findings provide insight and foundational materials design to create a patient-specific nanomaterial that can have predictable biodistribution inside of the body.
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) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".