ProT-Diff: A Modularized and Efficient Approach to De Novo Generation of Antimicrobial Peptide Sequences through Integration of Protein Language Model and Diffusion Model
Bibliographic record
Abstract
Abstract Antimicrobial Peptides (AMPs) represent a promising class of antimicrobial agents crucial for combating antibiotic-resistant pathogens. Despite the emergence of deep learning approaches for AMP discovery, there remains a gap in efficiently generating novel AMPs across various amino acid lengths without prior knowledge of peptide structures or sequence alignments. Here we introduce ProT-Diff, a modularized and efficient deep generative approach that ingeniously combines a pre-trained protein language model with a diffusion model to de novo generate candidate AMP sequences. ProT-Diff enabled the rapid generation of thousands of AMPs with diverse lengths within hours. Following in silico screening based on physicochemical properties and predicted antimicrobial activities, we selected 35 peptides for experimental validation. Remarkably, 34 of these peptides demonstrated antimicrobial activity against Gram-positive or Gram-negative bacteria, with 6 exhibiting broad-spectrum efficacy. Of particular interest, AMP_2, one of the broad-spectrum peptides, displayed potent antimicrobial activity, low hemolysis, and minimal cytotoxicity. Further in vivo assessment revealed its high effectiveness against a clinically relevant drug-resistant E. coli strain in a mouse model of acute peritonitis. This study not only presents a viable generative strategy for novel AMP design but also underscores its potential for generating other functional peptides, thereby broadening the horizon for new drug development.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".