Skip to content

Update predict.md #166

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 predict.md #166

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
62 changes: 35 additions & 27 deletions docs/readme/predict.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,66 +22,74 @@ The user must provide either the TF name that they want to make predictions for

### `-s, --signal, -i`

The ATAC-seq signal bigwig track that will be used to make TF binding predictions.
The ATAC-seq signal bigWig track that will be used to make TF binding predictions.

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

Output filename prefix (without extension) to use. Default `maxatac_predict`.

## Optional Arguments

### `--sequence, --seq`
### `--batch_size`

This argument specifies the path to the 2bit DNA sequence for the genome of interest. maxATAC models are trained with hg38 so you will need the correct `.2bit` file.
The number of regions to predict on per batch. Default `10000`. Decrease this value if you are having memory issues.

### `"-ct", "-cutoff_type", "--cutoff_type"`
### `--bed, --peaks, --regions, , --roi, -roi`

The cutoff type (i.e. `Precision`, `Recall`, `F1`, `log2FC`). (F1 = F1-score, and log2FC = Log2( Precision : Random Precision)). Default: F1.
The path to a BED file containing genomic regions to focus TF predictions on. These peaks will be used to refine the prediction windows. Default: whole-chromosome predictions.

### `"-cv", "-cutoff_value", "--cutoff_value"`
### `-bl, --blacklist`

The cutoff value for the cutoff type provided. Note precision, recall, and F1-scores range 0-1, while better-than-random log2FC scores range from 0 to infinity. Example: 0.7.
The path to a bigWig file that has regions to exclude. Default: maxATAC-defined blacklist.

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

The chromosomes to make predictions on. Our models do not currently consider chromosomes X or Y. This means that most of the files will not contain this information. You should not predict in chrX or chrY unless you know your bigWig contains these chromosomes. Default: human autosomal chromosomes 1-22. Note: this argument MUST be specified in conjunction with `--genome`, `-sequence`, and `--chrom_sizes` if the input file was aligned to a genome build other than hg38.

### `-cs, --chrom_sizes, -chrom_sizes, --chromosome_sizes`

The path to the chromosome sizes file. This is used to generate the bigwig signal tracks. Note: this argument MUST be specified in conjunction with `--genome`, `-sequence`, and `--chromosomes` if the input file was aligned to a genome build other than hg38.

### `"-cf", -cutoff_file, --cutoff_file`

The cutoff file provided in /data/models that corresponds to the average validation performance metrics for the TF model.

### `-o, --output`
### `"-ct", "-cutoff_type", "--cutoff_type"`

Output directory path. Default: `./prediction_results`
The cutoff type (i.e. `Precision`, `Recall`, `F1`, `log2FC`). (F1 = F1-score, and log2FC = Log2( Precision : Random Precision)). Default: F1.

### `-bl, --blacklist`
### `"-cv", "-cutoff_value", "--cutoff_value"`

The path to a bigWig file that has regions to exclude. Default: maxATAC-defined blacklist.
The cutoff value for the cutoff type provided. Note: precision, recall, and F1-scores range from 0-1, while better-than-random log2FC scores range from 0 to infinity. Example: 0.7.

### `--bed, --peaks, --regions, , --roi, -roi`
### `--genome`

The path to a BED file containing genomic regions to focus TF predictions on. These peaks will be used to refine the prediction windows. Default: whole-chromosome predictions.
The genome build that was used for alignment of the ATAC-seq signal file. Default: hg38.

### `--batch_size`
### `--max_zooms`

The number of regions to predict on per batch. Default `10000`. Decrease this value if you are having memory issues.
The number of zoom levels that should be computed for the output bigWig file. Zoom levels are pre-computed summary statistics that enable fast zooming into/out of a genomic region in a bigWig file when a visualization tool (e.g., IGV, UCSC Genome Browser). Lower values of this parameter result in slower loading of bigWig files in visualization tools, while higher values of this parameter result in a large memory overhead. The range of potential parameter values is (0-10). Default: 5. Note: if this argument is set to 0, the resulting bigWig files are NOT compatible with other bigWig tools (e.g., deepTools) and cannot be visualized using tools like IGV and the UCSC Genome Browser. Please see: https://github.com/deeptools/pyBigWig/blob/master/README.md for additional details.

### `--step_size`
### `--loglevel`

The step size to use for building the prediction intervals. Overlapping prediction bins will be averaged together. Default: `INPUT_LENGTH/4`, where INPUT_LENGTH is the maxATAC model input size of 1,024 bp.
This argument is used to set the logging level. Currently, the only working logging level is `ERROR`.

### `-cs, --chrom_sizes, -chrom_sizes, --chromosome_sizes`
### `-o, --output`

The path to the chromosome sizes file. This is used to generate the bigwig signal tracks.
Output directory path. Default: `./prediction_results`

### `-c, -chroms, --chromosomes`
### `--sequence, --seq`

The chromosomes to make predictions on. Our models do not currently consider chromosomes X or Y. This means that most of the files will not contain this information. You should not predict in chrX or chrY unless you know your bigWig contains these chromosomes. Default: autosomal chromosomes 1-22.
This argument specifies the path to the 2bit DNA sequence for the genome of interest. maxATAC models are trained with hg38, so you will need the correct `.2bit` file. Note: this argument MUST be specified (with a valid 2bit file) in conjunction with `--genome`, `--chrom_sizes`, and `--chromosomes` if the input file was aligned to a genome build other than hg38.

### `--loglevel`
### `-skip_call_peaks, --skip_call_peaks`

This argument is used to set the logging level. Currently, the only working logging level is `ERROR`.
This will skip calling peaks on prediction tracks. Default: `False`

### `-w, --windows`
### `--step_size`

The windows to use for prediction. These windows must be 1,024 bp wide and have a consistent step size.
The step size to use for building the prediction intervals. Overlapping prediction bins will be averaged together. Default: `INPUT_LENGTH/4`, where INPUT_LENGTH is the maxATAC model input size of 1,024 bp.

### `-skip_call_peaks, --skip_call_peaks`
### `-w, --windows`

This will skip calling peaks on prediction tracks.
The windows to use for prediction. These windows must be 1,024 bp wide and have a consistent step size.