De novo design of potent inhibitors of Clostridioides difficile toxin B
Bibliographic record
Abstract
Abstract Clostridioides difficile is a major cause of secondary disease in hospitals. During infection, C. difficile toxin B drives disease pathology. Here we use deep learning and Rosetta-based approaches to de novo design small proteins that block the entry of TcdB into cells. These molecules have binding affinities and neutralization IC50’s in the pM range and are compelling candidates for further clinical development. By directly targeting the toxin rather than the pathogen, these molecules have the advantage of immediate cessation of disease and lower selective pressure for escape compared to conventional antibiotics. As C. difficile infects the colon, the protease and pH resistance of the designed proteins opens the door to oral delivery of engineered biologics. Significance statement C. difficile infection (CDI) is a major public health concern with over half a million cases in the United States annually resulting in 30,000 deaths. Current therapies are inadequate and frequently result in cycles of recurrent infection (rCDI). Progress has been made in the development of anti-toxin mAb therapies that can reduce the rate of rCDI, but these remain unaffordable and out of reach for many patients. Using de novo protein design, we developed small protein inhibitors targeting two independent receptor binding sites on the toxin that drives pathology during CDI. These molecules are high affinity, potently neutralizing and stable in simulated intestinal fluid, making them strong candidates for the clinical development of new CDI therapies.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| 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".