## Please note: Current v1.6.1 not compatible with Tensorflow >= 2.16.0, please downgrade to 2.15.1
`pip install tensorflow-cpu==2.15.1`
Please see issue [here](https://github.com/cytham/nanovar/issues/77)
We are actively working on this, thank you for your understanding.
## NanoVar - Structural variant caller using low-depth long-read sequencing
[](https://app.travis-ci.com/github/cytham/nanovar)
[](https://pypi.org/project/nanovar/)
[](https://pypi.org/project/nanovar/)
<!--[](https://anaconda.org/bioconda/nanovar)-->
[](../../releases)
[](./LICENSE.txt)
NanoVar is a genomic structural variant (SV) caller that utilizes low-depth long-read sequencing such as
Oxford Nanopore Technologies (ONT). It characterizes SVs with using only 4x depth
sequencing for homozygous SVs and 8x depth for heterozygous SVs.
### Basic capabilities
* Performs long-read mapping (Minimap2) and SV discovery in a single pipeline.
* Accurately characterizes SVs using long sequencing reads (High SV recall and precision in simulation datasets, overall F1
score >0.9)
* Characterizes six classes of SVs including novel-sequence insertion, deletion, inversion, tandem duplication, sequence
transposition (TPO) and translocation (TRA).
* Requires 4x and 8x sequencing depth for detecting homozygous and heterozygous SVs respectively.
* Rapid computational speed (Takes <3 hours to map and analyze 12 gigabases datasets (4x) using 24 CPU threads)
* Approximates SV genotype
* Identifies full-length LINE and SINE insertions (Marked by "TE=" in the INFO column of VCF file)
* Repeat element INS annotation using [NanoINSight](https://github.com/AsmaaSamyMohamedMahmoud/NanoINSight)
<!--
* Detect large chromosomal copy-number variation using [CytoCAD](https://github.com/cytham/cytocad)
| `--cnv` | hg38 | Perform large CNV detection using CytoCAD (Only works for hg38 genome)
-->
## Getting Started
### Quick run
```
nanovar [Options] -t 24 -f hg38 sample.fq/sample.bam ref.fa working_dir
```
| Parameter | Argument | Comment |
| :--- | :--- | :--- |
| `-t` | num_threads | Indicate number of CPU threads to use |
| `-f` (Optional) | gap_file (Optional) | Choose built-in gap BED file or specify own file to exclude gap regions in the reference genome. Built-in gap files include: hg19, hg38 and mm10 |
| - | sample.fq/sample.bam | Input long-read FASTA/FASTQ file or mapped BAM file |
| - | ref.fa | Input reference genome in FASTA format |
| - | working_dir | Specify working directory |
See [wiki](https://github.com/cytham/nanovar/wiki) for entire list of options.
### Output
| Output file | Comment |
| :--- | :--- |
| ${sample}.nanovar.pass.vcf | Final VCF filtered output file (1-based) |
| ${sample}.nanovar.pass.report.html | HTML report showing run summary and statistics |
For more information, see [wiki](https://github.com/cytham/nanovar/wiki).
### Full usage
```
usage: nanovar [options] [FASTQ/FASTA/BAM] [REFERENCE_GENOME] [WORK_DIRECTORY]
NanoVar is a neural network enhanced structural variant (SV) caller that handles low-depth long-read sequencing data.
positional arguments:
[FASTQ/FASTA/BAM] path to long reads or mapped BAM file.
Formats: fasta/fa/fa.gzip/fa.gz/fastq/fq/fq.gzip/fq.gz or .bam
[reference_genome] path to reference genome in FASTA. Genome indexes created
will overwrite indexes created by other aligners such as bwa.
[work_directory] path to work directory. Directory will be created
if it does not exist.
options:
-h, --help show this help message and exit
--cnv hg38 also detects large genomic copy-number variations
using CytoCAD (e.g. loss/gain of whole chromosomes).
Only works with hg38 genome assembly. Please state 'hg38' [None]
-x str, --data_type str
type of long-read data [ont]
ont - Oxford Nanopore Technologies
pacbio-clr - Pacific Biosciences CLR
pacbio-ccs - Pacific Biosciences CCS
-f file, --filter_bed file
BED file with genomic regions to be excluded [None]
(e.g. telomeres and centromeres) Either specify name of in-built
reference genome filter (i.e. hg38, hg19, mm10) or provide full
path to own BED file.
--annotate_ins str enable annotation of INS with NanoINSight,
please specify species of sample [None]
Currently supported species are:
'human', 'mouse', and 'rattus'.
-c int, --mincov int minimum number of reads required to call a breakend [2]
-l int, --minlen int minimum length of SV to be detected [25]
-p float, --splitpct float
minimum percentage of unmapped bases within a long read
to be considered as a split-read. 0.05<=p<=0.50 [0.05]
-a int, --minalign int
minimum alignment length for single alignment reads [200]
-b int, --buffer int nucleotide length buffer for SV breakend clustering [50]
-s float, --score float
score threshold for defining PASS/FAIL SVs in VCF [1.0]
Default score 1.0 was estimated from simulated analysis.
--homo float lower limit of a breakend read ratio to classify a homozygous state [0.75]
(i.e. Any breakend with homo<=ratio<=1.00 is classified as homozygous)
--hetero float lower limit of a breakend read ratio to classify a heterozygous state [0.35]
(i.e. Any breakend with hetero<=ratio<homo is classified as heterozygous)
--debug run in debug mode
-v, --version show version and exit
-q, --quiet hide verbose
-t int, --threads int
number of available threads for use [1]
--model path specify path to custom-built model
--mm path specify path to 'minimap2' executable
--st path specify path to 'samtools' executable
--ma path specify path to 'mafft' executable for NanoINSight
--rm path specify path to 'RepeatMasker' executable for NanoINSight
```
### Operating system
* Linux (x86_64 architecture, tested in Ubuntu 14.04, 16.04, 18.04)
### Installation
There are three ways to install NanoVar:
#### Option 1: Conda environment (Recommended)
```
conda create -n myenv -c bioconda python=3.11 samtools bedtools minimap2 -y
conda activate myenv
pip install nanovar
```
#### Option 2: PyPI (See dependencies below)
```
# Installing from PyPI requires own installation of dependencies, see below
pip install nanovar
```
#### Option 3: GitHub (See dependencies below)
```
# Installing from GitHub requires own installation of dependencies, see below
git clone https://github.com/cytham/nanovar.git
cd nanovar
pip install .
```
#### Installation of dependencies
* bedtools >=2.26.0
* samtools >=1.3.0
* minimap2 >=2.17
<!--
* makeblastdb and windowmasker
* hs-blastn ==0.0.5
-->
Please make sure each executable binary is in PATH.
##### 1. _bedtools_
Please visit [here](https://bedtools.readthedocs.io/en/latest/content/installation.html) for instructions to install.
##### 2. _samtools_
Please visit [here](http://www.htslib.org/download/) for instructions to install.
##### 3. _minimap2_
Please visit [here](https://github.com/lh3/minimap2) for instructions to install.
<!--
##### 4. _makeblastdb_ and _windowmasker_
```
# Download NCBI-BLAST v2.3.0+ from NCBI FTP server
wget ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/2.3.0/ncbi-blast-2.3.0+-x64-linux.tar.gz
# Extract tar.gz
tar zxf ncbi-blast-2.3.0+-x64-linux.tar.gz
# Copy makeblastdb and windowmasker binaries to PATH (e.g. ~/bin)
cp ncbi-blast-2.3.0+/bin/makeblastdb ~/bin && cp ncbi-blast-2.3.0+/bin/windowmasker ~/bin
```
##### 5. _hs-blastn_
```
# Download and compile the 0.0.5 version
git clone https://github.com/chenying2016/queries.git
cd queries/hs-blastn-src/v0.0.5
make
# Copy hs-blastn binary to path (e.g. ~/bin)
cp hs-blastn ~/bin
```
If you encounter "isnan" error during compilation, please refer to [this](https://github.com/cytham/nanovar/issues/7#issuecomment-644546378).
-->
## Annotating INS variants with NanoINSight
NanoVar allows the concurrent repeat element annotation of INS variants using [NanoINSight](https://github.com/AsmaaSamyMohamedMahmoud/NanoINSight).
To run NanoINSight, simply add "--annotate_ins [species]" when running NanoVar.
```
nanovar -t 24 -f hg38 --annotate_ins human sample.bam ref.fa working_dir
```
To understand NanoINSight output files, please visit its repository [here](https://github.com/AsmaaSamyMohamedMahmoud/NanoINSight).
### Installation of NanoINSight dependencies
NanoINSight requires the installation of MAFFT and RepeatMasker. Please refer to [here](https://github.com/AsmaaSamyMohamedMahmoud/NanoINSight) for instructions on how to install them, or install them through Conda as shown below:
```
conda install -c bioconda mafft repeatmasker -y
```
## Documentation
See [wiki](https://github.com/cytham/nanovar/wiki) for more information.
## Versioning
See [CHANGELOG](./CHANGELOG.txt)
## Citation
If you use NanoVar, please cite:
Tham, CY., Tirado-Magallanes, R., Goh, Y. et al. NanoVar: accurate characterization of patients’ genomic structural variants using low-depth nanopore sequencing. Genome Biol. 21, 56 (2020). https://doi.org/10.1186/s13059-020-01968-7
## Authors
* **Tham Cheng Yong** - [cytham](https://github.com/cytham)
* **Roberto Tirado Magallanes** - [rtmag](https://github.com/rtmag)
* **Asmaa Samy** - [AsmaaSamyMohamedMahmoud](https://github.com/AsmaaSamyMohamedMahmoud)
* **Touati Benoukraf** - [benoukraflab](https://github.com/benoukraflab)
## License
This project is licensed under GNU General Public License - see [LICENSE.txt](./LICENSE.txt) for details.
## Simulation datasets and scripts used in the manuscript
SV simulation datasets used in the manuscript can be downloaded [here](https://doi.org/10.5281/zenodo.3569479). Scripts used for simulation dataset generation and tool performance comparison are available [here](./scripts).
Although NanoVar is provided with a universal model and threshold score, instructions required for building a custom neural-network model is available [here](https://github.com/cytham/nanovar/wiki/Model-training).
## Limitations
* The inaccurate basecalling of large homopolymer or low complexity DNA regions may result in the false determination of deletion SVs. We advise the use of up-to-date ONT basecallers such as [Dorado](https://github.com/nanoporetech/dorado) to minimize this possibility.
* For BND SVs, NanoVar is unable to calculate the actual number of SV-opposing reads (normal reads) at the novel adjacency as
there are two breakends from distant locations. It is not clear whether the novel adjacency is derived from both or either
breakends in cases of balanced and unbalanced variants, and therefore it is not possible to know which breakend location(s) to
consider for counting normal reads. Currently, NanoVar approximates the normal read count by the minimum count from either
breakend location. Although this helps in capturing unbalanced BNDs, it might lead to some false positives.
Raw data
{
"_id": null,
"home_page": "https://github.com/cytham/nanovar",
"name": "nanovar",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "nanovar, structural variant caller, sv, nanopore, long read, low coverage, low depth",
"author": "Tham Cheng Yong",
"author_email": "chengyong.tham@u.nus.edu",
"download_url": "https://files.pythonhosted.org/packages/15/db/6eaaad1cbf15657197bf0275ff8e83af3f8fa1b22eaf8f341b435d879d66/nanovar-1.6.1.tar.gz",
"platform": null,
"description": "## Please note: Current v1.6.1 not compatible with Tensorflow >= 2.16.0, please downgrade to 2.15.1\n\n`pip install tensorflow-cpu==2.15.1`\n\nPlease see issue [here](https://github.com/cytham/nanovar/issues/77)\n\nWe are actively working on this, thank you for your understanding.\n\n## NanoVar - Structural variant caller using low-depth long-read sequencing\n[](https://app.travis-ci.com/github/cytham/nanovar)\n[](https://pypi.org/project/nanovar/)\n[](https://pypi.org/project/nanovar/)\n<!--[](https://anaconda.org/bioconda/nanovar)-->\n[](../../releases)\n[](./LICENSE.txt)\n \nNanoVar is a genomic structural variant (SV) caller that utilizes low-depth long-read sequencing such as\n Oxford Nanopore Technologies (ONT). It characterizes SVs with using only 4x depth\n sequencing for homozygous SVs and 8x depth for heterozygous SVs.\n\n### Basic capabilities\n* Performs long-read mapping (Minimap2) and SV discovery in a single pipeline.\n* Accurately characterizes SVs using long sequencing reads (High SV recall and precision in simulation datasets, overall F1\n score >0.9) \n* Characterizes six classes of SVs including novel-sequence insertion, deletion, inversion, tandem duplication, sequence\n transposition (TPO) and translocation (TRA). \n* Requires 4x and 8x sequencing depth for detecting homozygous and heterozygous SVs respectively. \n* Rapid computational speed (Takes <3 hours to map and analyze 12 gigabases datasets (4x) using 24 CPU threads) \n* Approximates SV genotype\n* Identifies full-length LINE and SINE insertions (Marked by \"TE=\" in the INFO column of VCF file)\n* Repeat element INS annotation using [NanoINSight](https://github.com/AsmaaSamyMohamedMahmoud/NanoINSight)\n<!--\n* Detect large chromosomal copy-number variation using [CytoCAD](https://github.com/cytham/cytocad)\n| `--cnv` | hg38 | Perform large CNV detection using CytoCAD (Only works for hg38 genome)\n-->\n\n## Getting Started\n\n### Quick run\n\n```\nnanovar [Options] -t 24 -f hg38 sample.fq/sample.bam ref.fa working_dir \n```\n\n| Parameter | Argument | Comment |\n| :--- | :--- | :--- |\n| `-t` | num_threads | Indicate number of CPU threads to use |\n| `-f` (Optional) | gap_file (Optional) | Choose built-in gap BED file or specify own file to exclude gap regions in the reference genome. Built-in gap files include: hg19, hg38 and mm10 |\n| - | sample.fq/sample.bam | Input long-read FASTA/FASTQ file or mapped BAM file |\n| - | ref.fa | Input reference genome in FASTA format |\n| - | working_dir | Specify working directory |\n\nSee [wiki](https://github.com/cytham/nanovar/wiki) for entire list of options.\n\n### Output\n| Output file | Comment |\n| :--- | :--- |\n| ${sample}.nanovar.pass.vcf | Final VCF filtered output file (1-based) |\n| ${sample}.nanovar.pass.report.html | HTML report showing run summary and statistics |\n\nFor more information, see [wiki](https://github.com/cytham/nanovar/wiki).\n\n### Full usage\n```\nusage: nanovar [options] [FASTQ/FASTA/BAM] [REFERENCE_GENOME] [WORK_DIRECTORY]\n\nNanoVar is a neural network enhanced structural variant (SV) caller that handles low-depth long-read sequencing data.\n\npositional arguments:\n [FASTQ/FASTA/BAM] path to long reads or mapped BAM file.\n Formats: fasta/fa/fa.gzip/fa.gz/fastq/fq/fq.gzip/fq.gz or .bam\n [reference_genome] path to reference genome in FASTA. Genome indexes created\n will overwrite indexes created by other aligners such as bwa.\n [work_directory] path to work directory. Directory will be created\n if it does not exist.\n\noptions:\n -h, --help show this help message and exit\n --cnv hg38 also detects large genomic copy-number variations\n using CytoCAD (e.g. loss/gain of whole chromosomes).\n Only works with hg38 genome assembly. Please state 'hg38' [None]\n -x str, --data_type str\n type of long-read data [ont]\n ont - Oxford Nanopore Technologies\n pacbio-clr - Pacific Biosciences CLR\n pacbio-ccs - Pacific Biosciences CCS\n -f file, --filter_bed file\n BED file with genomic regions to be excluded [None]\n (e.g. telomeres and centromeres) Either specify name of in-built\n reference genome filter (i.e. hg38, hg19, mm10) or provide full\n path to own BED file.\n --annotate_ins str enable annotation of INS with NanoINSight,\n please specify species of sample [None]\n Currently supported species are:\n 'human', 'mouse', and 'rattus'.\n -c int, --mincov int minimum number of reads required to call a breakend [2]\n -l int, --minlen int minimum length of SV to be detected [25]\n -p float, --splitpct float\n minimum percentage of unmapped bases within a long read\n to be considered as a split-read. 0.05<=p<=0.50 [0.05]\n -a int, --minalign int\n minimum alignment length for single alignment reads [200]\n -b int, --buffer int nucleotide length buffer for SV breakend clustering [50]\n -s float, --score float\n score threshold for defining PASS/FAIL SVs in VCF [1.0]\n Default score 1.0 was estimated from simulated analysis.\n --homo float lower limit of a breakend read ratio to classify a homozygous state [0.75]\n (i.e. Any breakend with homo<=ratio<=1.00 is classified as homozygous)\n --hetero float lower limit of a breakend read ratio to classify a heterozygous state [0.35]\n (i.e. Any breakend with hetero<=ratio<homo is classified as heterozygous)\n --debug run in debug mode\n -v, --version show version and exit\n -q, --quiet hide verbose\n -t int, --threads int\n number of available threads for use [1]\n --model path specify path to custom-built model\n --mm path specify path to 'minimap2' executable\n --st path specify path to 'samtools' executable\n --ma path specify path to 'mafft' executable for NanoINSight\n --rm path specify path to 'RepeatMasker' executable for NanoINSight\n```\n\n### Operating system\n* Linux (x86_64 architecture, tested in Ubuntu 14.04, 16.04, 18.04) \n\n### Installation\nThere are three ways to install NanoVar:\n#### Option 1: Conda environment (Recommended)\n```\nconda create -n myenv -c bioconda python=3.11 samtools bedtools minimap2 -y\nconda activate myenv\npip install nanovar\n```\n#### Option 2: PyPI (See dependencies below)\n```\n# Installing from PyPI requires own installation of dependencies, see below\npip install nanovar\n```\n#### Option 3: GitHub (See dependencies below)\n```\n# Installing from GitHub requires own installation of dependencies, see below\ngit clone https://github.com/cytham/nanovar.git \ncd nanovar \npip install .\n```\n#### Installation of dependencies\n* bedtools >=2.26.0\n* samtools >=1.3.0\n* minimap2 >=2.17\n<!--\n* makeblastdb and windowmasker\n* hs-blastn ==0.0.5\n-->\n\nPlease make sure each executable binary is in PATH.\n##### 1. _bedtools_\nPlease visit [here](https://bedtools.readthedocs.io/en/latest/content/installation.html) for instructions to install.\n\n##### 2. _samtools_\nPlease visit [here](http://www.htslib.org/download/) for instructions to install.\n\n##### 3. _minimap2_\nPlease visit [here](https://github.com/lh3/minimap2) for instructions to install.\n<!--\n##### 4. _makeblastdb_ and _windowmasker_\n```\n# Download NCBI-BLAST v2.3.0+ from NCBI FTP server\nwget ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/2.3.0/ncbi-blast-2.3.0+-x64-linux.tar.gz\n\n# Extract tar.gz\ntar zxf ncbi-blast-2.3.0+-x64-linux.tar.gz\n\n# Copy makeblastdb and windowmasker binaries to PATH (e.g. ~/bin)\ncp ncbi-blast-2.3.0+/bin/makeblastdb ~/bin && cp ncbi-blast-2.3.0+/bin/windowmasker ~/bin\n```\n##### 5. _hs-blastn_\n```\n# Download and compile the 0.0.5 version\ngit clone https://github.com/chenying2016/queries.git\ncd queries/hs-blastn-src/v0.0.5\nmake\n\n# Copy hs-blastn binary to path (e.g. ~/bin)\ncp hs-blastn ~/bin\n```\nIf you encounter \"isnan\" error during compilation, please refer to [this](https://github.com/cytham/nanovar/issues/7#issuecomment-644546378).\n-->\n\n## Annotating INS variants with NanoINSight\nNanoVar allows the concurrent repeat element annotation of INS variants using [NanoINSight](https://github.com/AsmaaSamyMohamedMahmoud/NanoINSight).\n\nTo run NanoINSight, simply add \"--annotate_ins [species]\" when running NanoVar.\n```\nnanovar -t 24 -f hg38 --annotate_ins human sample.bam ref.fa working_dir\n```\nTo understand NanoINSight output files, please visit its repository [here](https://github.com/AsmaaSamyMohamedMahmoud/NanoINSight).\n\n### Installation of NanoINSight dependencies\n\nNanoINSight requires the installation of MAFFT and RepeatMasker. Please refer to [here](https://github.com/AsmaaSamyMohamedMahmoud/NanoINSight) for instructions on how to install them, or install them through Conda as shown below:\n\n```\nconda install -c bioconda mafft repeatmasker -y\n```\n\n \n## Documentation\nSee [wiki](https://github.com/cytham/nanovar/wiki) for more information.\n\n## Versioning\nSee [CHANGELOG](./CHANGELOG.txt)\n\n## Citation\nIf you use NanoVar, please cite:\n\nTham, CY., Tirado-Magallanes, R., Goh, Y. et al. NanoVar: accurate characterization of patients\u2019 genomic structural variants using low-depth nanopore sequencing. Genome Biol. 21, 56 (2020). https://doi.org/10.1186/s13059-020-01968-7\n\n\n## Authors\n\n* **Tham Cheng Yong** - [cytham](https://github.com/cytham)\n* **Roberto Tirado Magallanes** - [rtmag](https://github.com/rtmag)\n* **Asmaa Samy** - [AsmaaSamyMohamedMahmoud](https://github.com/AsmaaSamyMohamedMahmoud)\n* **Touati Benoukraf** - [benoukraflab](https://github.com/benoukraflab)\n\n## License\n\nThis project is licensed under GNU General Public License - see [LICENSE.txt](./LICENSE.txt) for details.\n\n## Simulation datasets and scripts used in the manuscript\nSV simulation datasets used in the manuscript can be downloaded [here](https://doi.org/10.5281/zenodo.3569479). Scripts used for simulation dataset generation and tool performance comparison are available [here](./scripts).\n\nAlthough NanoVar is provided with a universal model and threshold score, instructions required for building a custom neural-network model is available [here](https://github.com/cytham/nanovar/wiki/Model-training).\n\n## Limitations\n* The inaccurate basecalling of large homopolymer or low complexity DNA regions may result in the false determination of deletion SVs. We advise the use of up-to-date ONT basecallers such as [Dorado](https://github.com/nanoporetech/dorado) to minimize this possibility.\n\n* For BND SVs, NanoVar is unable to calculate the actual number of SV-opposing reads (normal reads) at the novel adjacency as\n there are two breakends from distant locations. It is not clear whether the novel adjacency is derived from both or either\n breakends in cases of balanced and unbalanced variants, and therefore it is not possible to know which breakend location(s) to\n consider for counting normal reads. Currently, NanoVar approximates the normal read count by the minimum count from either \n breakend location. Although this helps in capturing unbalanced BNDs, it might lead to some false positives.\n",
"bugtrack_url": null,
"license": "gpl-3.0",
"summary": "Structural variant caller using low-depth long reads",
"version": "1.6.1",
"project_urls": {
"Download": "https://github.com/cytham/nanovar/releases",
"Homepage": "https://github.com/cytham/nanovar"
},
"split_keywords": [
"nanovar",
" structural variant caller",
" sv",
" nanopore",
" long read",
" low coverage",
" low depth"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "15db6eaaad1cbf15657197bf0275ff8e83af3f8fa1b22eaf8f341b435d879d66",
"md5": "5b8d167cae93502bdb8823107ae3fa08",
"sha256": "a3efd20d809ecdbd7ff3f964814b2f9970e14ef1c15234d046ea1054a2a4d7c8"
},
"downloads": -1,
"filename": "nanovar-1.6.1.tar.gz",
"has_sig": false,
"md5_digest": "5b8d167cae93502bdb8823107ae3fa08",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 418020,
"upload_time": "2024-03-31T07:54:18",
"upload_time_iso_8601": "2024-03-31T07:54:18.603342Z",
"url": "https://files.pythonhosted.org/packages/15/db/6eaaad1cbf15657197bf0275ff8e83af3f8fa1b22eaf8f341b435d879d66/nanovar-1.6.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-03-31 07:54:18",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "cytham",
"github_project": "nanovar",
"travis_ci": true,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "absl-py",
"specs": [
[
"==",
"2.0.0"
]
]
},
{
"name": "astunparse",
"specs": [
[
"==",
"1.6.3"
]
]
},
{
"name": "beautifulsoup4",
"specs": [
[
"==",
"4.12.2"
]
]
},
{
"name": "biopython",
"specs": [
[
"==",
"1.83"
]
]
},
{
"name": "cached-property",
"specs": [
[
"==",
"1.5.2"
]
]
},
{
"name": "cachetools",
"specs": [
[
"==",
"5.3.2"
]
]
},
{
"name": "certifi",
"specs": [
[
"==",
"2023.11.17"
]
]
},
{
"name": "charset-normalizer",
"specs": [
[
"==",
"3.3.2"
]
]
},
{
"name": "click",
"specs": [
[
"==",
"8.1.7"
]
]
},
{
"name": "cloudpickle",
"specs": [
[
"==",
"3.0.0"
]
]
},
{
"name": "contourpy",
"specs": [
[
"==",
"1.2.0"
]
]
},
{
"name": "cycler",
"specs": [
[
"==",
"0.12.1"
]
]
},
{
"name": "dask",
"specs": [
[
"==",
"2024.1.0"
]
]
},
{
"name": "flatbuffers",
"specs": [
[
"==",
"23.5.26"
]
]
},
{
"name": "fonttools",
"specs": [
[
"==",
"4.47.2"
]
]
},
{
"name": "fsspec",
"specs": [
[
"==",
"2023.12.2"
]
]
},
{
"name": "gast",
"specs": [
[
"==",
"0.5.4"
]
]
},
{
"name": "google-auth",
"specs": [
[
"==",
"2.26.2"
]
]
},
{
"name": "google-auth-oauthlib",
"specs": [
[
"==",
"1.2.0"
]
]
},
{
"name": "google-pasta",
"specs": [
[
"==",
"0.2.0"
]
]
},
{
"name": "grpcio",
"specs": [
[
"==",
"1.60.0"
]
]
},
{
"name": "h5py",
"specs": [
[
"==",
"3.10.0"
]
]
},
{
"name": "HTMLArk",
"specs": [
[
"==",
"1.0.0"
]
]
},
{
"name": "idna",
"specs": [
[
"==",
"3.6"
]
]
},
{
"name": "importlib-metadata",
"specs": [
[
"==",
"7.0.1"
]
]
},
{
"name": "keras",
"specs": [
[
"==",
"2.15.0"
]
]
},
{
"name": "kiwisolver",
"specs": [
[
"==",
"1.4.5"
]
]
},
{
"name": "libclang",
"specs": [
[
"==",
"16.0.6"
]
]
},
{
"name": "locket",
"specs": [
[
"==",
"1.0.0"
]
]
},
{
"name": "Markdown",
"specs": [
[
"==",
"3.5.2"
]
]
},
{
"name": "MarkupSafe",
"specs": [
[
"==",
"2.1.3"
]
]
},
{
"name": "matplotlib",
"specs": [
[
"==",
"3.8.2"
]
]
},
{
"name": "ml-dtypes",
"specs": [
[
"==",
"0.2.0"
]
]
},
{
"name": "NanoINSight",
"specs": [
[
"==",
"0.0.1"
]
]
},
{
"name": "nanovar",
"specs": [
[
"==",
"1.6.0"
]
]
},
{
"name": "natsort",
"specs": [
[
"==",
"8.4.0"
]
]
},
{
"name": "numpy",
"specs": [
[
"==",
"1.26.3"
]
]
},
{
"name": "oauthlib",
"specs": [
[
"==",
"3.2.2"
]
]
},
{
"name": "opt-einsum",
"specs": [
[
"==",
"3.3.0"
]
]
},
{
"name": "packaging",
"specs": [
[
"==",
"23.2"
]
]
},
{
"name": "pandas",
"specs": [
[
"==",
"2.1.4"
]
]
},
{
"name": "partd",
"specs": [
[
"==",
"1.4.1"
]
]
},
{
"name": "pillow",
"specs": [
[
"==",
"10.2.0"
]
]
},
{
"name": "pip",
"specs": [
[
"==",
"23.3.2"
]
]
},
{
"name": "progress",
"specs": [
[
"==",
"1.6"
]
]
},
{
"name": "protobuf",
"specs": [
[
"==",
"4.23.4"
]
]
},
{
"name": "pyasn1",
"specs": [
[
"==",
"0.5.1"
]
]
},
{
"name": "pyasn1-modules",
"specs": [
[
"==",
"0.3.0"
]
]
},
{
"name": "pybedtools",
"specs": [
[
"==",
"0.9.1"
]
]
},
{
"name": "pyparsing",
"specs": [
[
"==",
"3.1.1"
]
]
},
{
"name": "pysam",
"specs": [
[
"==",
"0.22.0"
]
]
},
{
"name": "python-dateutil",
"specs": [
[
"==",
"2.8.2"
]
]
},
{
"name": "pytz",
"specs": [
[
"==",
"2023.3.post1"
]
]
},
{
"name": "PyYAML",
"specs": [
[
"==",
"6.0.1"
]
]
},
{
"name": "requests",
"specs": [
[
"==",
"2.31.0"
]
]
},
{
"name": "requests-oauthlib",
"specs": [
[
"==",
"1.3.1"
]
]
},
{
"name": "rsa",
"specs": [
[
"==",
"4.9"
]
]
},
{
"name": "scikit-allel",
"specs": [
[
"==",
"1.3.7"
]
]
},
{
"name": "scipy",
"specs": [
[
"==",
"1.11.4"
]
]
},
{
"name": "setuptools",
"specs": [
[
"==",
"69.0.3"
]
]
},
{
"name": "six",
"specs": [
[
"==",
"1.16.0"
]
]
},
{
"name": "soupsieve",
"specs": [
[
"==",
"2.5"
]
]
},
{
"name": "tensorboard",
"specs": [
[
"==",
"2.15.1"
]
]
},
{
"name": "tensorboard-data-server",
"specs": [
[
"==",
"0.7.2"
]
]
},
{
"name": "tensorflow-cpu",
"specs": [
[
"==",
"2.15.0.post1"
]
]
},
{
"name": "tensorflow-estimator",
"specs": [
[
"==",
"2.15.0"
]
]
},
{
"name": "tensorflow-io-gcs-filesystem",
"specs": [
[
"==",
"0.35.0"
]
]
},
{
"name": "termcolor",
"specs": [
[
"==",
"2.4.0"
]
]
},
{
"name": "toolz",
"specs": [
[
"==",
"0.12.0"
]
]
},
{
"name": "typing_extensions",
"specs": [
[
"==",
"4.9.0"
]
]
},
{
"name": "tzdata",
"specs": [
[
"==",
"2023.4"
]
]
},
{
"name": "urllib3",
"specs": [
[
"==",
"2.1.0"
]
]
},
{
"name": "Werkzeug",
"specs": [
[
"==",
"3.0.1"
]
]
},
{
"name": "wheel",
"specs": [
[
"==",
"0.42.0"
]
]
},
{
"name": "wrapt",
"specs": [
[
"==",
"1.14.1"
]
]
},
{
"name": "zipp",
"specs": [
[
"==",
"3.17.0"
]
]
}
],
"lcname": "nanovar"
}
