61–68 of 68 posts
Our startup (Chronomics) has built the most accurate epigenetic clock from Saliva (no needles..) which looks at 20 million positions (or features) https://www.chronomics.com/science
Really interesting area and we are starting to be able to define many more novel indicators of actionable health risks such as smoke exposure, alcohol consumption and metabolic status from DNA methylation.
When you post an article, please don't publish the code somewhere an account must be created in order to read it. In this case, I cannot check the full code because it is hosted at https://colab.research.google.com , a tarball attached to the article or a publicly accessible host like gitlab.com or github.com would have been fine.
You can now find the jupyter notebook code here: https://github.com/Ruborcalor/Age-Prediction-Via-Blood-Sampl...
Good to see other people interested in this! Our startup (Chronomics) has built the most accurate epigenetic clock from Saliva (no needles..) which looks at 20 million positions (or features) https://www.chronomics.com/science Really interesting area and we are starting to be able to define many more novel indicators of actionable health risks such as smoke exposure, alcohol consumption and metabolic status from DNA…
>Back to the computer science: 470,000+ features sounds nice at first, but is a recipe for overfitting when we only have 700 samples at our disposal. Proceeds to use (1024^2 * 2 + 1024) parameters in the neural network.
what a meme haha :) after many similar comments I plan on implementing a simpler model and seeing how it compares
Earlier quoted context omitted.
that's exactly the thing I'm seeing in my field (computational materials science). Basically a simple regression model (with very simple features) brings you 90% there, still people compete on publishing (on ONE shitty benchmark dataset) ever better results – the most-cited people are using KRR, e.g. each fit uses 2TB of RAM and "days" of CPU (features of length O(1000) and 100000 samples). The sample data is probabl…
I haven't thought as much about it as you have probably, but ok you get 90% of the way there, but now what? How do you get that last 10%? It would be a huge amount of work right?
Interesting write up. I'd be interested to see how it performs with k-folds validation as well as shuffling. Kind of worried its learning order or samples.
Thanks I really appreciate it. I'll try and get back to you with the performance of k-folds validation and shuffling. I don't think it can be learning the order or samples because the train and test data sets are separated very early on. If it were learning order or samples of the training set it would have to perform very poorly on the test set.
On a separate note, I think there may be a source file missing in your notebook. I kept getting an error when trying to load "GSE87571_series_matrix.csv". Might just be me.
[sklearn ref](https://scikit-learn.org/stable/modules/generated/sklearn.mo...)
[tf.keras](https://www.tensorflow.org/api_docs/python/tf/keras/Model#fi...)
For some context, the author is an undergraduate student.
Haha yes good point take everything with a grain of salt