kennthshang / phatyp Goto Github PK
View Code? Open in Web Editor NEWPhaTYP: Predicting lifestyle for bacteriophages using BERT
License: GNU General Public License v3.0
PhaTYP: Predicting lifestyle for bacteriophages using BERT
License: GNU General Public License v3.0
hi, I just want to know if the higher prediction score in the result table means more accurate? Can it be considered that reliable results require a score greater than 0.9? or 0.8? Is there an empirical value for this?
HI,
I get the following error when running PhaTYP:
Opening the database file... No such file or directory
[0.004s]
Error: Error calling stat on file database/database.fa
Running prodigal-gv...
---------------------------------Diamond BLASTp---------------------------------
Creating Diamond database and running Diamond...
Creating Diamond database...
create database failed
Traceback (most recent call last):
File "/data/umcg-llnext/python_venvs/PhaTYP_venv/PhaTYP/PhaTYP.py", line 37, in <module>
id2contig = pkl.load(open(f'{transformer_fn}/sentence_id2contig.dict', 'rb'))
FileNotFoundError: [Errno 2] No such file or directory: 'phatyp//sentence_id2contig.dict'
Do I need to add the location of the database to the path? Or is there any options/flags to add the database path when running thepreprocessing.py
script?
Hi,
Thanks for developing the tool! Is the pre-trained model (without any fine-tuning, but the same that was used for fine-tuning later) available? Could you maybe also share it?
Thank you!
Dear PhaTYPer,
Hope this mail find you well.
It seems the phatyp.yaml file has a formatting error at line 28, the log showed ruamel.yaml.scanner.ScannerError when I run conda create.
ruamel.yaml.scanner.ScannerError: mapping values are not allowed here
in "<unicode string>", line 28, column 66:
... le" content="{"groups": [], "environmentKey" ...
^ (line: 28)
Best,
Panpan
Hi!
Thanks for the great tool! I was wondering whether you are planning to update the current version of prodigal used by PhaTYP to prodigal-gv to improve gene calling for viruses with alternative genetic codes.
Best,
Asier
Hello,
Thanks for the excellent tool. Is it possible that the life styles of some viral contigs are undetermined (absence in the output csv file)?
Hello, thank you for the excellent tool. I used Phatyp to compare my metagenomic data with BACPHLIP. To be more stringent I used the following criteria:
Here, are the results:
classifier | No. of temperate | No. of virulent | contrasting predictions with respect to BACPHLIP | Not assigned |
---|---|---|---|---|
PhaTYP | 92 | 181 | 157 as virulent, 11 as temperate | 59 |
BACPHLIP | 284 | 48 | ย | 0 |
It seems like there is a significant difference between the output of the two classifiers.
When testing the tool with the test_contigs.fa file, I get the following error when it tries to build the DIAMOND database:
---------------------------------Diamond BLASTp---------------------------------
Creating Diamond database and running Diamond...
Creating Diamond database...
create database failed
I have tried installing different versions of DIAMOND (2.0.13, 4.0.515) but I get the same error. Which is the version you recommend?
Thanks!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.