TM-score calculation for DeepBlast about deepblast HOT 4 CLOSED

from deepblast.

from deepblast.

Hi, a couple of clarifications. DeepBLAST cant compute TMscore, it computes alignment score, which measures the probability of alignment. The issue with these alignment scores is that they are sensitive to sequence length, and it is slower to compute (one of the motivations to creating TMvec). That being said, the code to compute alignment scores can be found here : https://github.com/flatironinstitute/deepblast/blob/master/scripts/deepblast-search#L38
…
On Mon, Mar 25, 2024 at 9:49 PM Qifan @.> wrote: Hi, Thank you so much for this excellent work! I am a newer in protein alignment and may test this method in my project. I only have protein sequence data and I would like to check their similarity using the TM-score given by DeepBlast. I note that Section 3.2 in your paper mentions we can calculate the TM-score for DeepBlast only through the linear alignment sequence but I can not find its corresponding function in your repo. Could you please tell me which is the demo script for calculating the TM-score for DeepBlast method? Thank you! — Reply to this email directly, view it on GitHub <#156>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA75VXITZCGIGMT5ZCRQAKLY2DH25AVCNFSM6AAAAABFIBNJXSVHI2DSMVQWIX3LMV43ASLTON2WKOZSGIYDOMBWHEZDONA . You are receiving this because you are subscribed to this thread.Message ID: @.>

Thank you for your reply! The score function in the script does work. However, I also note that the image in your README.md file also show a "Predicted TM-score" for DeepBlast and the scale of this score does not align with the alignment score calculated using the score provided in the script. Could you clarify a bit more about this?

Thanks again! :)

from deepblast.

ahh yes. So that TM score can only be computed using structures, that code is in the zenodo link. https://zenodo.org/records/4117030 Briefly, when you have the structures, the alignment can define a rotation of the structure, which can then be used to compute a TM-score.
…
On Tue, Mar 26, 2024 at 9:33 AM Qifan @.> wrote: Hi, a couple of clarifications. DeepBLAST cant compute TMscore, it computes alignment score, which measures the probability of alignment. The issue with these alignment scores is that they are sensitive to sequence length, and it is slower to compute (one of the motivations to creating TMvec). That being said, the code to compute alignment scores can be found here : https://github.com/flatironinstitute/deepblast/blob/master/scripts/deepblast-search#L38 … <#m_-6864755246795738568_> On Mon, Mar 25, 2024 at 9:49 PM Qifan @.> wrote: Hi, Thank you so much for this excellent work! I am a newer in protein alignment and may test this method in my project. I only have protein sequence data and I would like to check their similarity using the TM-score given by DeepBlast. I note that Section 3.2 in your paper mentions we can calculate the TM-score for DeepBlast only through the linear alignment sequence but I can not find its corresponding function in your repo. Could you please tell me which is the demo script for calculating the TM-score for DeepBlast method? Thank you! — Reply to this email directly, view it on GitHub <#156 <#156>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA75VXITZCGIGMT5ZCRQAKLY2DH25AVCNFSM6AAAAABFIBNJXSVHI2DSMVQWIX3LMV43ASLTON2WKOZSGIYDOMBWHEZDONA https://github.com/notifications/unsubscribe-auth/AA75VXITZCGIGMT5ZCRQAKLY2DH25AVCNFSM6AAAAABFIBNJXSVHI2DSMVQWIX3LMV43ASLTON2WKOZSGIYDOMBWHEZDONA . You are receiving this because you are subscribed to this thread.Message ID: @.> Thank you for your reply! The score function in the script does work. However, I also note that the image in your README.md file also show a "Predicted TM-score" for DeepBlast and the scale of this score does not align with the alignment score calculated using the score provided in the script. Could you clarify a bit more about this? Thanks again! :) — Reply to this email directly, view it on GitHub <#156 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA75VXNQUPEV3COJ45HMZRLY2F2KJAVCNFSM6AAAAABFIBNJXSVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAMRQGQ2DGNZRGM . You are receiving this because you commented.Message ID: @.**>

I see. Thank you!

from deepblast.