---
title: "UnibindMD: AI-plus-MD Platform for De Novo Peptide Binder Design"
id: "biorxiv-16-unibindmd-an-integrated-ai-and-molecular-dynamics-platform-for-de-novo-peptide"
canonical_url: "https://medichelpline.com/clinical-feed/biorxiv-16-unibindmd-an-integrated-ai-and-molecular-dynamics-platform-for-de-novo-peptide"
content_type: "clinical_feed_article"
specialty: "Pharmacology"
source_name: "bioRxiv (Biomedical Preprints)"
source_url: "https://www.biorxiv.org/content/10.64898/2026.10.20.760329v1?rss=1"
published_at: "2026-10-23T12:00:00.000Z"
evidence_level: "Verified Feed"
license: "CC-BY-NC-4.0 / Informational Use"
---
# UnibindMD: AI-plus-MD Platform for De Novo Peptide Binder Design
## Provenance & Clinical Metadata
- **Canonical URL:** https://medichelpline.com/clinical-feed/biorxiv-16-unibindmd-an-integrated-ai-and-molecular-dynamics-platform-for-de-novo-peptide
- **Specialty:** [Pharmacology](https://medichelpline.com/clinical-feed/pharmacology.md)
- **Primary Source:** bioRxiv (Biomedical Preprints)
- **Source URL:** [Original Journal Publication](https://www.biorxiv.org/content/10.64898/2026.10.20.760329v1?rss=1)
- **Published At:** 2026-10-23T12:00:00.000Z
- **Evidence Rating:** Verified Feed
## Executive GIST (TL;DR)
- The authors presented **UnibindMD**, an integrated computational pipeline that converts a protein target into de novo peptide-binder leads by chaining five orthogonal stages. - The five stages are deep-learning design (BindCraft), independent structure prediction and confidence assessment (AlphaFold3-class / Boltz-2), binding-affinity estimation (PRODIGY), developability profiling (ADMET-AI), and all-atom molecular-dynamics validation (GROMACS/CHARMM36m). - Investigators applied the platform to three Andes virus (ANDV) intervention points: the **Gn-Gc** glycoprotein complex (entry), the L-protein endonuclease domain (cap-snatching; PDB 6Q99), and host **VEGFR2** kinase (vascular permeability; PDB 2XIR). - Across nine BindCraft campaigns yielding 4,475 trajectories, the platform produced 464 accepted binders with campaign acceptance rates ranging from 2.3% to 67.6%. - Top candidates reached ipTM = 0.94 and pLDDT = 0.94 in structure-prediction confidence metrics. - PRODIGY predicted binding free energies (ΔG) for three selected leads of −9.1 to −11.1 kcal·mol−1, corresponding to Kd values reported in the source of 8 nM to 0.2 μM. - All three selected leads remained stably bound during 100 ns of unrestrained MD: receptor Cα RMSD ≤ 2.6 Å, peptides retained fold, ≥99.5% frames preserved >50% initial interface contacts, and 75–82% helical content. - ADMET-AI flagged expected poor oral bioavailability for large polar peptides but reported no PAINS alerts. - The authors argued that chaining independent methods addresses the problem that single-method confidence metrics (ipTM, pLDDT) can be self-consistent yet not independently predictive of physical stability. - The preprint reported no competing interests and provides a generalizable, rapid workflow from protein target to dynamics-tested peptide-binder candidates.
## Clinical Analysis & Structured Key Points
UnibindMD: An Integrated AI and Molecular Dynamics Platform for De Novo Peptide Binder Design | bioRxiv Skip to main content New Results UnibindMD: An Integrated AI and Molecular Dynamics Platform for De Novo Peptide Binder Design Xu Wu , Aihong Huang , Congmei Fu , Zhujun Wang , View ORCID Profile Wei Fu doi: https://doi.org/10.64898/2026.10.20.760329 Xu Wu 1 ShenZhen UnibindMD Computation Biotech Co., Ltd.; Find this author on Google Scholar Find this author on PubMed Search for this author on this site Aihong Huang 1 ShenZhen UnibindMD Computation Biotech Co., Ltd.; Find this author on Google Scholar Find this author on PubMed Search for this author on this site Congmei Fu 2 Shenzhen UnibindMD Computation Biotech Co., Ltd. Find this author on Google Scholar Find this author on PubMed Search for this author on this site Zhujun Wang 2 Shenzhen UnibindMD Computation Biotech Co., Ltd. Find this author on Google Scholar Find this author on PubMed Search for this author on this site Wei Fu 1 ShenZhen UnibindMD Computation Biotech Co., Ltd.; Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Wei Fu For correspondence: fuwei{at}unibindmd.tech Abstract Info/History Metrics Supplementary material Preview PDF Abstract UnibindMD is an integrated computational platform that turns a protein target into validated de novo peptide-binder leads by chaining five orthogonal stages: deep-learning binder design (BindCraft), independent structure prediction and confidence assessment (AlphaFold3-class / Boltz-2), binding-affinity prediction (PRODIGY), developability profiling (ADMET-AI), and all-atom molecular-dynamics validation (GROMACS/CHARMM36m). The platform targets a persistent weakness of single-method design, namely that confidence metrics such as ipTM and pLDDT are self-consistent but not independent, so a design predicted to be confident may still be physically unstable. We demonstrate UnibindMD on three Andes virus (ANDV) intervention points, a setting of urgent need given a case fatality rate approaching 40%, a 2026 MV Hondius cruise-ship outbreak (13 cases, 3 deaths), and no approved therapeutic: the Gn-Gc glycoprotein complex (viral entry), the L-protein endonuclease domain (cap-snatching; PDB 6Q99), and the host VEGFR2 kinase (vascular permeability; PDB 2XIR). Across nine BindCraft campaigns (4,475 trajectories) the platform produced 464 accepted binders (acceptance 2.3-67.6%), with top candidates reaching ipTM = 0.94 and pLDDT = 0.94. The three selected leads were predicted by PRODIGY to bind with G = -9.1 to -11.1 kcal mol-1 (Kd 8 nM-0.2 μM), and all three remained stably bound over 100 ns of unrestrained molecular dynamics (receptor CαRMSD ≤ 2.6 Å, retained peptide fold, ≥ 99.5% of frames preserving more than half of the initial interface contacts, and 75-82% helical content). ADMET-AI flagged the expected poor oral bioavailability of large polar peptides and no PAINS alerts. By converting single-prediction design into a cross-validated, dynamics-tested workflow, UnibindMD provides a rapid, scalable, and generalizable path from any protein target to validated peptide-binder candidates. Competing Interest Statement The authors have declared no competing interest. Copyright The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-NC-ND 4.0 International license . Back to top Previous Next Posted October 23, 2026. Download PDF Supplementary Material Email Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following UnibindMD: An Integrated AI and Molecular Dynamics Platform for De Novo Peptide Binder Design Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share UnibindMD: An Integrated AI and Molecular Dynamics Platform for De Novo Peptide Binder Design Xu Wu , Aihong Huang , Congmei Fu , Zhujun Wang , Wei Fu bioRxiv 2026.10.20.760329; doi: https://doi.org/10.64898/2026.10.20.760329 Share This Article: Copy Citation Tools UnibindMD: An Integrated AI and Molecular Dynamics Platform for De Novo Peptide Binder Design Xu Wu , Aihong Huang , Congmei Fu , Zhujun Wang , Wei Fu bioRxiv 2026.10.20.760329; doi: https://doi.org/10.64898/2026.10.20.760329 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Areas All Articles Animal Behavior and Cognition (8164) Biochemistry (19027) Bioengineering (15171) Bioinformatics (45329) Biophysics (22958) Cancer Biology (20111) Cell Biology (27298) Clinical Trials (138) Developmental Biology (14143) Ecology (21395) Epidemiology (2067) Evolutionary Biology (25783) Genetics (16342) Genomics (23828) Immunology (19018) Microbiology (43184) Molecular Biology (18339) Neuroscience (95055) Paleontology (712) Pathology (3032) Pharmacology and Toxicology (5198) Physiology (8280) Plant Biology (16270) Scientific Communication and Education (2115) Synthetic Biology (4644) Systems Biology (10384) Zoology (2426)
## Related Clinical Research

- [Community pharmacy telephone counseling often leads to unnecessary oral emergency contraception re](https://medichelpline.com/clinical-feed/plos-one-20-do-community-pharmacies-unnecessarily-recommend-oral-emergency-contraception-a.md)
- [Biocatalytic production of Danshensu from L‑Tyrosine using engineered Escherichia coli](https://medichelpline.com/clinical-feed/plos-one-1-multienzyme-cascade-biotransformation-of-l-tyrosine-to-danshensu-by-engineered.md)
- [PINN-iPRC: Inferring infinitesimal phase response curves from finite-pulse circadian data](https://medichelpline.com/clinical-feed/biorxiv-3-a-physics-informed-neural-network-framework-for-inferring-infinitesimal-phase.md)
- [Agent K: Automated LLM-Orchestrated Pipeline for Mapping Genes to Biosynthetic Pathways](https://medichelpline.com/clinical-feed/biorxiv-4-agent-k-an-agent-orchestrated-pipeline-for-mapping-genes-to-biosynthetic.md)
- [Single‑port robotic vs conventional laparoscopy in gynecology: outcomes and hospital cost avoidance](https://medichelpline.com/clinical-feed/pubmed-42920014.md) (DOI: 10.1007/s11701-026-03977-3)

## Navigation
- [← Back to Pharmacology Feed](https://medichelpline.com/clinical-feed/pharmacology.md)
- [← All Clinical Specialties](https://medichelpline.com/clinical-feed.md)
## Medical & Regulatory Disclaimer

> [!CAUTION]
> MedicHelpline content is structured for research, educational, and professional discovery purposes. It does not constitute individual medical advice, clinical diagnosis, or treatment recommendations.
> Always verify dosing, contraindications, and regulatory alerts against official product labeling and primary regulatory sources before clinical decision-making.