EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

De Novo Reconstruction of 3D Human Facial Images from DNA Sequence

Mingqi Jiao iD, Jiarui Li, Bingxu Zhong, Siyuan Du, Shuning Li, Manfei Zhang, Qibin Zhang, Zhongming Liang, Fan Liu, Chunman Zuo, Sijia Wang, Luonan Chen iD

Advanced Science · 2025-08 · 12 (29)

DOI: 10.1002/advs.202414507 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 07.05.2025. Verfasst von Mingqi Jiao und 11 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Systems Health Science of Zhejiang Province, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Chin…. Hauptthemen laut MEDLINE: Forensic Imaging, Imaging, Three-Dimensional, Face, Imaging Genomics. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Zhejiang Province Vanguard Goose-Leading Initiative, Science and Technology Commission of Shanghai Municipality.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Facial morphology is a distinctive biometric marker, offering invaluable insights into personal identity, especially in forensic science. In the context of high‐throughput sequencing, the reconstruction of 3D human facial images from DNA is becoming a revolutionary approach for identifying individuals based on unknown biological specimens. Inspired by artificial intelligence techniques in text‐to‐image synthesis, it proposes Difface, a multi‐modality model designed to reconstruct 3D facial images only from DNA. Specifically, Difface first utilizes a transformer and a spiral convolution network to map high‐dimensional Single Nucleotide Polymorphisms and 3D facial images to the same low‐dimensional features, respectively, while establishing the association between both modalities in the latent features in a contrastive manner; and then incorporates a diffusion model to reconstruct facial structures from the characteristics of SNPs. Applying Difface to the Han Chinese database with 9,674 paired SNP phenotypes and 3D facial images demonstrates excellent performance in DNA‐to‐3D image alignment and reconstruction and characterizes the individual genomics. Also, including phenotype information in Difface further improves the quality of 3D reconstruction, i.e. Difface can generate 3D facial images of individuals solely from their DNA data, projecting their appearance at various future ages. This work represents pioneer research in de novo generating human facial images from individual genomics information.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Forensic ImagingImaging, Three-DimensionalFaceImaging GenomicsDNAHigh-Throughput Nucleotide SequencingPolymorphism, Single NucleotideSequence Analysis, DNAHumans

Stichwörter der Autor:innen

DNA‐guided 3D face generationartificial Intelligence in geneticsdeep multimodal integrationgenetic phenotypingrepresentational learning

Substanzen

DNA

Autor:innen und Institutionen

  • Key Laboratory of Systems Health Science of Zhejiang Province, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Hangzhou, 310024, China.
  • CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, 200031, China.
  • Bio-X Institutes, Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders, Ministry of Education, Shanghai Jiao Tong University, Shanghai, 200030, China.
  • Naif Arab University for Security Sciences, Riyadh, 11433, Saudi Arabia.
  • School of Life Sciences, Sun Yat-sen University, Guangzhou, 510275, China.
  • Taizhou Institute of Health Sciences, Fudan University, Taizhou, Jiangsu, 200433, China.

ORCID-Profile: Mingqi Jiao, Luonan Chen

Förderung

  • National Natural Science Foundation of China
  • Zhejiang Province Vanguard Goose-Leading Initiative
  • Science and Technology Commission of Shanghai Municipality
  • JST Moonshot R&D
  • Hangzhou Institute for advanced study of UCAS
  • National Key R&D Program of China
  • CAS Young Team Program for Stable Support of Basic Research
  • Strategic Priority Research Program of the Chinese Academy of Sciences

Zitieren

APA

Jiao, M., Li, J., Zhong, B., Du, S., Li, S., Zhang, M., Zhang, Q., Liang, Z., Liu, F., Zuo, C., Wang, S., & Chen, L. (2025). De Novo Reconstruction of 3D Human Facial Images from DNA Sequence. Advanced Science, 12(29). https://doi.org/10.1002/advs.202414507

Vancouver

Jiao M, Li J, Zhong B, Du S, Li S, Zhang M, et al. De Novo Reconstruction of 3D Human Facial Images from DNA Sequence. Advanced Science. 2025;12(29). doi:10.1002/advs.202414507

BibTeX
@article{Jiao2025,
  author = {Jiao, Mingqi and Li, Jiarui and Zhong, Bingxu and Du, Siyuan and Li, Shuning and Zhang, Manfei and Zhang, Qibin and Liang, Zhongming and Liu, Fan and Zuo, Chunman and Wang, Sijia and Chen, Luonan},
  title = {De Novo Reconstruction of 3D Human Facial Images from DNA Sequence},
  journal = {Advanced Science},
  year = {2025},
  volume = {12},
  number = {29},
  doi = {10.1002/advs.202414507}
}
Kostenlos starten →