Comments (3)
hi @ruicatxiao , sorry for the delay in the reply
I think it will be interesting to look at these other modifications. Technically, if this modification does not cause segmentation error during nanopolish eventalign step and it shows different signal profiles than normal Guanine like signal, this should be to some extent detectable by m6Anet model trained on good enough labels. One caveat here is perhaps if the modification does not alter the current that much, then the averaging done by Nanopolish eventalign might make it more difficult for us to detect the modification and in that case maybe we need to preprocess the raw squiggle differently / use the raw squiggle directly
from m6anet.
Thank you for taking your time to answer! I will extract sequence around predicted A modification and do a few motif enrichment. I do have deep RNA-seq to detect potential A to I editing from the same sample. Also planning to use TOMBO to check raw signal profile around those enriched motifs. Would be really nice if m6anet inference can identify more than m6A but inosine as well! My organism of interest completely lacks any type of m6A MTase. However it does have functional ADAR which does A to I editing.
from m6anet.
hi @ruicatxiao , I think TOMBO will be a good baseline for this problem. Currently you need to make edit to m6Anet preprocessing script in order to extract beyond the DRACH motifs (currently the preprocessing step will only extract DRACH step). You can extract other motifs by changing the M6A_KMERS variable in m6anet/scripts/constants.py (it is basically a python list that contains all allowed motifs). Afterwards you probably can re-train m6Anet to recognize this but I think current code will require some adjustment in order to do that, but let me know if it works for you
Regards
Christopher Hendra
from m6anet.
Related Issues (20)
- Identification of m6A with the SG-NEx samples HOT 4
- About the RNA04 dataset to train the model
- Arabidopsis m6anet model for RNA004 HOT 2
- Inference JSONDecoderError HOT 2
- m6Anet inference output missing probability_modified values HOT 8
- Question about the PCA in the paper
- Memory usage exploding HOT 3
- Empty Eventalign.txt for Negative Sense Viral RNA HOT 1
- dataprep and data.log HOT 8
- Questions about the m6A motif HOT 1
- Genome vs transcriptome alignment HOT 4
- m6anet, eventalign, galaxy HOT 3
- error with m6anet dataprep HOT 1
- yet another error with m6anet dataprep HOT 1
- running with test eventalign test file file form github produces another error HOT 8
- installation on linux failed HOT 3
- TypeError: argument should be integer or None, not 'numpy.float64' HOT 2
- Interpreting 'inference' results HOT 1
- m6anet dataprep fails to complete: cannot convert float NaN to integer HOT 3
- Issues with Read Selection HOT 2
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 m6anet.