Comments (4)
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.
Related Issues (20)
- Consistent usage of 'cuda' or 'gpu'
- Pass the device in load_model to Neural aligner HOT 1
- cannot import name 'LightningAligner' from 'deepblast.trainer' HOT 2
- DeepBLAST issue with model load HOT 3
- mat1 and mat2 must have the same dtype HOT 1
- Encountering an Issue While Building a Queryable Protein Sequence Database HOT 2
- Running time for searching query
- Running time for large query sequences HOT 1
- Smith-waterman test broken HOT 1
- ImportError: cannot import name 'LightningAligner' from 'deepblast.trainer' for deepblast and AttributeError: 'tuple' object has no attribute 'strip' for tm-vec HOT 12
- Deepblast model confusion
- Where is the structure alignment output? HOT 2
- RuntimeError: The NVIDIA driver on your system is too old HOT 3
- After entering the command line, the program keeps running without any result. HOT 10
- Questions about evaluation metrics for sequence alignment HOT 4
- Unexpected keys in state_dict when I run this code on cpu HOT 3
- SW_cuda modual HOT 8
- Feasible approach to build a large database HOT 1
- Pretraind model download HOT 7
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deepblast.