ProDCARL: Reinforcement Learning-Aligned Diffusion Models for De Novo Antimicrobial Peptide Design

• URL: http://arxiv.org/abs/2602.00157v2
• Date: Wed, 04 Feb 2026 05:28:09 GMT
• Title: ProDCARL: Reinforcement Learning-Aligned Diffusion Models for De Novo Antimicrobial Peptide Design
• Authors: Fang Sheng, Mohammad Noaeen, Zahra Shakeri,
• Abstract summary: Antimicrobial resistance threatens healthcare sustainability and motivates low-cost computational discovery of antimicrobial peptides (AMPs)<n>We introduce ProDCARL, a reinforcement-learning framework that couples a diffusion-based protein generator with sequence property predictors for AMP activity and peptide toxicity.<n>In silico experiments show ProDCARL increases the mean predicted AMP score from 0.081 after fine-tuning to 0.178.
• Score: 0.5361389213879222
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Antimicrobial resistance threatens healthcare sustainability and motivates low-cost computational discovery of antimicrobial peptides (AMPs). De novo peptide generation must optimize antimicrobial activity and safety through low predicted toxicity, but likelihood-trained generators do not enforce these goals explicitly. We introduce ProDCARL, a reinforcement-learning alignment framework that couples a diffusion-based protein generator (EvoDiff OA-DM 38M) with sequence property predictors for AMP activity and peptide toxicity. We fine-tune the diffusion prior on AMP sequences to obtain a domain-aware generator. Top-k policy-gradient updates use classifier-derived rewards plus entropy regularization and early stopping to preserve diversity and reduce reward hacking. In silico experiments show ProDCARL increases the mean predicted AMP score from 0.081 after fine-tuning to 0.178. The joint high-quality hit rate reaches 6.3\% with pAMP $>$0.7 and pTox $<$0.3. ProDCARL maintains high diversity, with $1-$mean pairwise identity equal to 0.929. Qualitative analyses with AlphaFold3 and ProtBERT embeddings suggest candidates show plausible AMP-like structural and semantic characteristics. ProDCARL serves as a candidate generator that narrows experimental search space, and experimental validation remains future work.

Related papers

• Fine-Tuning ChemBERTa for Predicting Inhibitory Activity Against TDP1 Using Deep Learning [0.0]
  Predicting the potency of small molecules against Tyrosyl-DNA Phosphodiesterase 1 (TDP1) is a critical challenge in early drug discovery.<n>We present a deep learning framework for the quantitative regression of pIC50 values using fine-tuned variants of ChemBERTa.<n>Our approach outperforms classical baselines Random Predictor in both regression accuracy and virtual screening utility.
  arXiv  Detail & Related papers  (2025-12-03T20:42:22Z)
• A deep reinforcement learning platform for antibiotic discovery [101.30486136547285]
  Antimicrobial resistance (AMR) is projected to cause up to 10 million deaths annually by 2050.<n>We present ApexAmphion, a deep-learning framework for de novo design of antibiotics.
  arXiv  Detail & Related papers  (2025-09-16T18:21:42Z)
• OmegAMP: Targeted AMP Discovery through Biologically Informed Generation [37.08970479806285]
  Deep learning-based antimicrobial peptide (AMP) discovery faces critical challenges such as limited controllability.<n>We introduce OmegAMP, a framework designed for reliable AMP generation with increased controllability.<n>Our in silico experiments demonstrate that OmegAMP delivers state-of-the-art performance across key stages of the AMP discovery pipeline.
  arXiv  Detail & Related papers  (2025-04-24T04:53:04Z)
• REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy [93.8400683020273]
  Decoding methods for large language models (LLMs) usually struggle with the tradeoff between ensuring factuality and maintaining diversity. We propose REAL sampling, a decoding method that improved factuality and diversity over nucleus sampling.
  arXiv  Detail & Related papers  (2024-06-11T21:44:49Z)
• Regressor-free Molecule Generation to Support Drug Response Prediction [83.25894107956735]
  Conditional generation based on the target IC50 score can obtain a more effective sampling space. Regressor-free guidance combines a diffusion model's score estimation with a regression controller model's gradient based on number labels.
  arXiv  Detail & Related papers  (2024-05-23T13:22:17Z)
• Artificial intelligence-driven antimicrobial peptide discovery [0.0]
  Antimicrobial peptides (AMPs) emerge as promising agents against antimicrobial resistance. AMPs provide an alternative to conventional antibiotics. Artificial intelligence (AI) revolutionized AMP discovery through both discrimination and generation approaches.
  arXiv  Detail & Related papers  (2023-08-21T14:02:14Z)
• Target specific peptide design using latent space approximate trajectory collector [1.7289819674602296]
  We propose a novel machine based machine learning design, called Approximate Space Tray Collector (LSATC) It consists of a series of samplers that approximates peptides with desired binding properties in a space $284%$. We latent by the design of peptide extensions targeting Beta-catenin, a key effector protein involved in canonical Wnt signalling. All the four binding peptides extended by LSATC show improved Beta-catenin binding by at least $2%$, two of the peptides show a $3$ fold increase in affinity as compared to the base peptide.
  arXiv  Detail & Related papers  (2023-02-02T21:56:52Z)
• xTrimoABFold: De novo Antibody Structure Prediction without MSA [77.47606749555686]
  We develop a novel model named xTrimoABFold to predict antibody structure from antibody sequence. The model was trained end-to-end on the antibody structures in PDB by minimizing the ensemble loss of domain-specific focal loss on CDR and the frame-aligned point loss.
  arXiv  Detail & Related papers  (2022-11-30T09:26:08Z)
• Accelerating Antimicrobial Peptide Discovery with Latent Structure [33.288514128470425]
  We propose a latent sequence-structure model for designing AMPs (LSSAMP) LSSAMP exploits multi-scale vector quantization in the latent space to represent secondary structures. Experimental results show that the peptides generated by LSSAMP have a high probability of antimicrobial activity.
  arXiv  Detail & Related papers  (2022-11-28T06:43:32Z)
• Graph-Based Active Machine Learning Method for Diverse and Novel Antimicrobial Peptides Generation and Selection [57.131117785001194]
  Large-scale screening of new AMP candidates is expensive, time-consuming, and now affordable in developing countries. We propose a novel active machine learning-based framework that statistically minimizes the number of wet-lab experiments needed to design new AMPs.
  arXiv  Detail & Related papers  (2022-09-18T14:30:48Z)
• Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics [109.70543391923344]
  CLaSS (Controlled Latent attribute Space Sampling) is an efficient computational method for attribute-controlled generation of molecules. We screen the generated molecules for additional key attributes by using deep learning classifiers in conjunction with novel features derived from atomistic simulations. The proposed approach is demonstrated for designing non-toxic antimicrobial peptides (AMPs) with strong broad-spectrum potency.
  arXiv  Detail & Related papers  (2020-05-22T15:57:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.