How to classify a TE library of mixed species?

[CSU-KangHu]

Hello, I would like to classify a TE library that consists of a mixture of multiple species including animals, plants, and bacteria using DeepTE. I noticed that DeepTE requires specifying -m P or -m M or -m F or -m O. How should I classify a mixed-species TE library using DeepTE?

[songliVT]

We have not tried this before. I think the easy way is to run deepTE using different species separately and merge the predictions.

On Sun, Jul 9, 2023 at 10:23 PM Kang Hu @.***> wrote:

Hello, I would like to classify a TE library that consists of a mixture of multiple species including animals, plants, and bacteria using DeepTE. I noticed that DeepTE requires specifying -m P or -m M or -m F or -m O. How should I classify a mixed-species TE library using DeepTE?

— Reply to this email directly, view it on GitHub https://github.com/LiLabAtVT/DeepTE/issues/26, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACEEENQVMH4PLLT6664XJJTXPNRTDANCNFSM6AAAAAA2D4L4EA . You are receiving this because you are subscribed to this thread.Message ID: @.***>

-- Associate Professor in Plant Genomics and Bioinformatics School of Plant and Environmental Sciences Virginia Polytechnic Institute and State University

zoom https://virginiatech.zoom.us/j/8790572835

[CSU-KangHu]

Thank you for your prompt response. I would like to know the differences between models for different species. Since my mixed-species TE library contains hundreds of different species, it is challenging to determine whether each species belongs to Plants, Metazoans, Fungi, or Others. Can I use just one model, such as a Plant model, to predict this mixed-species TE library?

[songliVT]

I would just do the following:

1. make a prediction for all sequences using plant model first,
2. make a prediction for all sequences Metazoans model,
3. make a prediction for all sequences with fungi model.
4. put the model predictions side by side and compare.

Song

On Mon, Jul 10, 2023 at 8:36 PM Kang Hu @.***> wrote:

Thank you for your prompt response. I would like to know the differences between models for different species. Since my mixed-species TE library contains hundreds of different species, it is challenging to determine whether each species belongs to Plants, Metazoans, Fungi, or Others. Can I use just one model, such as a Plant model, to predict this mixed-species TE library?

— Reply to this email directly, view it on GitHub https://github.com/LiLabAtVT/DeepTE/issues/26#issuecomment-1629921466, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACEEENSZZYDFYRW7TL3UJY3XPSNZJANCNFSM6AAAAAA2D4L4EA . You are receiving this because you commented.Message ID: @.***>

-- Associate Professor in Plant Genomics and Bioinformatics School of Plant and Environmental Sciences Virginia Polytechnic Institute and State University

zoom https://virginiatech.zoom.us/j/8790572835