agingclock's Introduction

AgingClock BiT age

The repository contains the code to predict the biological age based on gene expression data of C. elegans.

The predict function in src/biological_age_prediction.py takes 2 files as input

a CSV file with count-per-million normalized RNA-seq counts with genes as rows, and samples as columns (e.g. Data/GSE65765_CPM.csv)
the CSV file Data/Predictor_Genes.csv with the predictor genes and corresponding regression coefficients

The function will return a Pandas DataFrame with the sample names in the first and the predicted biological age in the second column.

To calculate the second biological age correction described in the paper run the calculate_Bio_Age_correction function in src/biological_age_correction.py.
It takes a Pandas DataFrame as input with samples as rows and at least one column with the biological age of the samples.

For more details see:

A transcriptome based aging clock near the theoretical limit of accuracy
https://www.biorxiv.org/content/10.1101/2020.05.29.123430v1

The example data is downloaded from: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=gse65765
Sen, P. et al. H3K36 methylation promotes longevity by enhancing transcriptional fidelity. Genes Dev. 29, 1362–1376 (2015).

agingclock's People

Contributors

Stargazers

Watchers

agingclock's Issues

Transferring from wormID to human homolog

Very interesting application!!!
Could you please share how you transfer the wormID to human homolog or human homolog symbol to wormIDs to make the predictions? The biomart doesn't work recently.
Thanks!!!

AgingClock for Human Fibroblasts

Hi,
Very interesting approach!
I would like to test your clock on human fibroblast transcriptomic data, however I cannot find the intercept of the Human Clock.
Could you please include it.
Thanks,
Avital

Published Results Clarification

I am modifying the program to use the polars data frame and to have it seamlessly handle input files where the data uses gene symbols instead of ids, or even a mix. I want to verify that I get the same results as your program for the data you provided : GSE65765_CPM.csv

When I run your biological_age_prediction.py on this input file it does not give the values that you provide in bio_age_example.csv

I.e the published results file is

Run,Bio_Age
SRR1793991,26.5714285714
SRR1793992,26.5714285714
SRR1793993,212.5714285714
SRR1793994,318.8571428571

But the results of your program on the data you provide is

        Predicted_Biological_Age

Sample
SRR1793991 14.950266
SRR1793992 32.134522
SRR1793993 182.353657
SRR1793994 251.269911

These numbers are quite different. Can you publish an input data file, the expected output on that data from the predictor and then also the expected output from the corrector when using your published predicted result.

Recommend Projects