Age Prediction Based on Transcriptome


The prediction of biological age is important for identifying aging interventions and anti-aging and disease treatments. Currently common aging biomarkers used in the aging clock are DNA methylation, telomere length and omics features. As a leading solution provider for aging research, CD BioSciences can provide research services to accurately predict the biological age of organisms based on transcriptome-defined genomes.

Introduction to Transcriptional Aging Clock

Both DNA methylation and RNA transcription have been associated with biological age and age-related diseases, and a number of human age prediction models based on DNA levels and RNA levels have been developed. Transcriptome-based aging clocks have limitations of high data variability and low accuracy compared to DNA methylation aging clocks, but DNA methylation is absent in certain populations such as Cryptobacterium hidradenum, making transcriptome characterization important for aging studies in these species.

Biological age prediction is an important tool in aging research and treatment, and the combination of transcriptomic data and bioinformatics techniques can be used to develop diagnostic and therapeutic tools for aging and related diseases.

What We Provide

We can use data from different populations to construct cross-tissue or tissue-specific transcriptional age predictors, including options for different species and tissues.

Services Types Options

Species types
  • Mouse
  • Rats
  • Drosophila
  • Cryptobacterium hidradenum
  • Yeast
  • Zebrafish
  • Small fish

Tissue types
  • Blood
  • Saliva
  • Skin tissue
  • Brain tissue
  • Muscle tissue
  • Nerve tissue
  • Adipose tissue
  • Heart
  • Pancreas
  • Small intestine
  • Stomach
  • Testes
  • Thyroid gland
  • Uterus

Transcriptome dataset collection

We can generate a broad RNA-seq dataset from species-specific tissue sequencing or collect existing data, which will cover a wide range of ages of individuals, providing a powerful benchmark for age prediction.

Predictive model construction and evaluation

We construct a fitted model to predict the actual age of transcriptomic data of biological individuals using specific mathematical processing methods such as classification, regression algorithms, etc. The prediction model will be validated by data set training to evaluate the performance.

Age prediction from transcriptome

Our high-precision biological age prediction model can be used to correctly predict long and short-lived individuals, and can be applied to test the ability to predict the effects of multiple lifespan influences, such as drugs, external stressors, and genetic factors on lifespan.

Our Advantages

  • A wide range of species models can be constructed to accurately predict age and longevity impact effects in different populations.
  • Specific cross-tissue and tissue-specific transcriptome-based age prediction model development is available.
  • Widely used for genetic, nutritional, environmental and therapeutic interventions in the aging process.

CD BioSciences is a leading aging research technology company focused on providing unique aging clock technologies and aging-related research services for basic research and therapy development. Our advanced technology platform, dedicated technical team and experience in serving hundreds of clients worldwide are the foundation of our quality services.

The transcriptome-based age prediction services we target include, but are not limited to, the options listed above. If you are interested in any related direction, please contact us for a specific inquiry.


  1. Fleischer J G, et al. Predicting age from the transcriptome of human dermal fibroblasts. Genome biology, 2018, 19(1).

Our services are for research use only and not for any clinical use.

Online Inquiry

  • * Name:
  • Phone:
  • * Email:
  • * Services or Products of Interest:
  • Project Description:

We are a comprehensive technology platform company integrating aging DNA methylation, telomere, transcriptome, proteome, and metabolome research.

Learn More
Contact Us