Skip to content

Update benchmark.md #138

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ANRudrapatna wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update benchmark.md #138

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 14 additions & 10 deletions docs/readme/benchmark.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,21 +10,21 @@ maxatac benchmark --prediction GM12878_CTCF_chr1.bw --gold_standard GM12878_CTCF

## Required Arguments

### `--prediction`
### `-bed, --bed, -bw, --bw, --bigwig`
Copy link
Member

@FaizRizvi FaizRizvi Oct 2, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We do not have flags as listed here. The flags are usually --signal for a bw prediction track and different flags for bed files ("--bed", "--peaks", "--regions", "--roi", "-roi", and "--windows", "-w" for 1024 bp wide windowed BED file inputs. Please re-write, Thank you!

Copy link
Collaborator Author

@ANRudrapatna ANRudrapatna Oct 8, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hmmm, are you sure this is the case? I am currently running benchmark successfully with the --bw option, and the current version of parser.py accepts the listed arguments (as indicated in this screenshot).
parser_screenshot


The input bigwig file of transcription factor binding predictions. This file can also be any bigwig signal track that you want to compare against a gold standard.
The input file of transcription factor binding predictions (in either BED or bigWig format). This file can also be any BED/bigWig signal track that you want to compare against a gold standard.
Copy link
Member

@FaizRizvi FaizRizvi Oct 2, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How do you get a BED file at the end of prediction? You should only be getting a bw file. The input flag should --bw here

Copy link
Collaborator Author

@ANRudrapatna ANRudrapatna Oct 8, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I might totally be wrong, but this is what I was pointing out in the previous screenshot! Please let me know if I am wrong and I am happy to change what I have written.

Copy link
Collaborator

@XiaotingChen XiaotingChen Feb 11, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This seems to be from one of the Tariean's update here: e08be57#diff-2b28b3ee9d11c4502b4d3fa82584cd292b165b7ee3f43cfb7873d31005bbba87L673, in parser.py file and around line 670 in the updated version.

We might want to also update the *.md file to mention the mutually exclusive nature between bed input and bw input.


### `--gold_standard`

The input gold standard bigwig file. This file needs to be a binary signal track that has 1 corresponding to TFBS (e.g., from ChIP-seq) and 0 in positions with no TFBS.
The input gold standard bigWig file. This file needs to be a binary signal track that has 1 corresponding to TFBS (e.g., from ChIP-seq) and 0 in positions with no TFBS.

### `--prefix`
### `-n, --name, --prefix`

The output filename prefix to use. Default: `maxatac_benchmark`
The output filename prefix to use. Default: `maxatac_benchmark`.

## Optional Arguments

### `--chromosomes`
### `-c, --chroms, --chromosomes`

The chromosomes to benchmark the predictions for. Default: `chr1` is the held out test chromosome.

Expand All @@ -40,16 +40,20 @@ See the [pyBigWig documentation](https://github.com/deeptools/pyBigWig#compute-s

### `--round_predictions`

This flag will set the precision of the predictions signal track. Provide an integer that represents the number of floats before rounding. Currently, the predictions go from `0 - .0000000001`. Default: `9` is the limit of precision from TensorFlow.
This flag will set the precision of the prediction signal track. Provide an integer that represents the number of floats before rounding. Currently, the predictions go from `0 - .0000000001`. Default: `9` is the limit of precision from TensorFlow.

### `--output_directory`
### `-o, --output_directory`

The output directory to write the results to. Default: `./prediction_results`
The output directory to write the results to. Default: `./prediction_results`.

### `--blacklist_bw`

The path to the blacklist bigwig signal track of regions that should be excluded. Default: `hg38_maxatac_blacklist.bed` which contains regions that are specific to ATAC-seq.
The path to the blacklist bigWig signal track of regions that should be excluded. Default: `hg38_maxatac_blacklist.bed`, which contains regions that are specific to ATAC-seq.

### `--loglevel`

This argument is used to set the logging level. Currently, the only working logging level is `ERROR`.

### `-skip_plot`

If set, this argument prevents plotting of the associated precision-recall curve.