Metadata-Version: 2.1
Name: helen
Version: 0.0.23
Summary: RNN based assembly HELEN. It works paired with MarginPolish.
Home-page: https://github.com/kishwarshafin/helen
Author: Kishwar Shafin
Author-email: kishwar.shafin@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Requires-Python: >=3.5.*
Description-Content-Type: text/markdown
Requires-Dist: h5py
Requires-Dist: tqdm
Requires-Dist: numpy
Requires-Dist: wget
Requires-Dist: torch
Requires-Dist: torchvision
Requires-Dist: torchnet
Requires-Dist: pyyaml
Requires-Dist: onnx
Requires-Dist: onnxruntime
Requires-Dist: hyperopt
Requires-Dist: matplotlib

# H.E.L.E.N.
H.E.L.E.N. (Homopolymer Encoded Long-read Error-corrector for Nanopore)


[![Build Status](https://travis-ci.com/kishwarshafin/helen.svg?branch=master)](https://travis-ci.com/kishwarshafin/helen)
___________________________________________________________
Pre-print of a paper describing the methods and overview of a suggested `de novo assembly` pipeline is now available:
#### [Efficient de novo assembly of eleven human genomes using PromethION sequencing and a novel nanopore toolkit](https://www.biorxiv.org/content/10.1101/715722v1)
__________________________________________________________

## Overview
`HELEN` uses a Recurrent-Neural-Network (RNN) based Multi-Task Learning (MTL) model that can predict a base and a run-length for each genomic position using the weights generated by `MarginPolish`.

© 2020 Kishwar Shafin, Trevor Pesout, Benedict Paten. <br/>
Computational Genomics Lab (CGL), University of California, Santa Cruz.

## Why MarginPolish-HELEN ?
* `MarginPolish-HELEN` outperforms other graph-based and Neural-Network based polishing pipelines.
* Simple installation steps.
* `HELEN` can use multiple GPUs at the same time.
* Highly optimized pipeline that is faster than any other available polishing tool.
* We have <b>sequenced-assembled-polished 11 samples</b> to ensure robustness, runtime-consistency and cost-efficiency.
* We tested GPU usage on `Amazon Web Services (AWS)` and `Google Cloud Platform (GCP)` to ensure scalability.
* Open source [(MIT License)](LICENSE).

## Walkthrough
* [Docker based installation walkthrough](./docs/walkthrough_docker.md).
* [Local installation walkthrough](./docs/walkthrough_local.md).

## Installation
`MarginPolish-HELEN` is supported on  <b>`Ubuntu 16.10/18.04`</b> or any other Linux-based system.
Â
#### Install prerequisites
Before you follow any of the methods, make sure you install all the dependencies:
```bash
sudo apt-get -y install git cmake make gcc g++ autoconf bzip2 lzma-dev zlib1g-dev \
libcurl4-openssl-dev libpthread-stubs0-dev libbz2-dev liblzma-dev libhdf5-dev \
python3-pip python3-virtualenv virtualenv
```

#### Method 1: Install MarginPolish-HELEN from GitHub
You can install from the `GitHub` repository:
```bash
git clone https://github.com/kishwarshafin/helen.git
cd helen
make install
. ./venv/bin/activate

helen --help
marginpolish --help
```
Each time you want to use it, activate the virtualenv:
```bash
. <path/to/helen/venv/bin/activate>
```

#### Method 2: Install using PyPi
Install  prerequisites and the install `MarginPolish-HELEN` using pip:
```bash
python3 -m pip install helen --user

python3 -m helen.helen --help
python3 -m helen.marginpolish --help
```

Update the installed version:
```bash
python3 -m pip install update pip
python3 -m pip install helen --upgrade
```

You can also add module locations to path:
```bash
echo 'export PATH="$(python3 -m site --user-base)/bin":$PATH' >> ~/.bashrc
source ~/.bashrc

marginpolish --help
helen --help
```

#### Method 3: Use docker image

##### CPU based docker:
```bash
# SEE CONFIGURATION
docker run --rm -it --ipc=host kishwars/helen:latest helen --help
docker run --rm -it --ipc=host kishwars/helen:latest marginpolish --help

docker run -it --ipc=host --user=`id -u`:`id -g` --cpus="16" \
-v </directory/with/inputs_outputs>:/data kishwars/helen:latest \
helen --help
```

##### GPU based docker:
```bash
sudo apt-get install -y nvidia-docker2
# SEE CONFIGURATION
nvidia-docker run -it --ipc=host kishwars/helen:latest helen torch_stat
nvidia-docker run -it --ipc=host kishwars/helen:latest helen --help
nvidia-docker run -it --ipc=host kishwars/helen:latest marginpolish --help

# RUN HELEN
nvidia-docker run -it --ipc=host --user=`id -u`:`id -g` --cpus="16" \
-v </directory/with/inputs_outputs>:/data kishwars/helen:latest \
helen --help
```
## Usage
`MarginPolish` requires a draft assembly and a mapping of reads to the draft assembly. We commend using `Shasta` as the initial assembler and `MiniMap2` for the mapping.

#### Step 1: Generate an initial assembly
Generate an assembly using one of the ONT assemblers:
* [Shasta long read assembler](https://github.com/chanzuckerberg/shasta).
* [Flye assembler](https://github.com/fenderglass/Flye)
* [Canu assembler](https://github.com/marbl/canu)
* [WTDBG2 assembler](https://github.com/ruanjue/wtdbg2)

#### Step 2: Create an alignment between reads and shasta assembly
We recommend using `MiniMap2` to generate the mapping between the reads and the assembly. You don't have to follow these exact commands.
```bash
minimap2 -ax map-ont -t 32 shasta_assembly.fa reads.fq | samtools view -hb -q 60 -F 0x904 > unsorted.bam ; samtools sort -@ 32 unsorted.bam | samtools view > reads_2_assembly.0x904q60.bam
samtools index -@32 reads_2_assembly.0x904q60.bam
```
#### Step 3: Generate images using MarginPolish
##### Download Model
```bash
helen download_models \
--output_dir <path/to/mp_helen_models/>
```

##### Run MarginPolish
You can generate images using MarginPolish by running:
```bash
marginpolish reads_2_assembly.bam \
Assembly.fa \
</path/to/model_name.json> \
-t <number_of_threads> \
-o <path/to/marginpolish_images> \
-f
```

You can find the models by downloading them.

#### Step 4: Run HELEN
Next, run `HELEN` to polish using a RNN.
```bash
helen polish \
--image_dir </path/to/marginpolish_images/> \
--model_path </path/to/model.pkl> \
--batch_size 256 \
--num_workers 4 \
--threads <num_of_threads> \
--output_dir </path/to/output_dir> \
--output_prefix <output_filename.fa> \
--gpu_mode
```

If you are using `CPUs` then remove the `--gpu_mode` argument.

## Help
Please open a github issue if you face any difficulties.

## Acknowledgement
We are thankful to [Segey Koren](https://github.com/skoren) and [Karen Miga](https://github.com/khmiga) for their help with `CHM13` data and evaluation.

We downloaded our data from [Telomere-to-telomere consortium](https://github.com/nanopore-wgs-consortium/CHM13) to evaluate our pipeline against `CHM13`.

We acknowledge the work of the developers of these packages: </br>
* [Shasta](https://github.com/chanzuckerberg/shasta/commits?author=paoloczi)
* [pytorch](https://pytorch.org/)
* [ssw library](https://github.com/mengyao/Complete-Striped-Smith-Waterman-Library)
* [hdf5 python (h5py)](https://www.h5py.org/)
* [pybind](https://github.com/pybind/pybind11)
* [hyperband](https://github.com/zygmuntz/hyperband)

## Fun Fact
<img src="https://vignette.wikia.nocookie.net/marveldatabase/images/e/eb/Iron_Man_Armor_Model_45_from_Iron_Man_Vol_5_8_002.jpg/revision/latest?cb=20130420194800" alt="guppy235" width="240p"> <img src="https://vignette.wikia.nocookie.net/marveldatabase/images/c/c0/H.E.L.E.N._%28Earth-616%29_from_Iron_Man_Vol_5_19_002.jpg/revision/latest?cb=20140110025158" alt="guppy235" width="120p"> <br/>

The name "HELEN" is inspired from the A.I. created by Tony Stark in the  Marvel Comics (Earth-616). HELEN was created to control the city Tony was building named "Troy" making the A.I. "HELEN of Troy".

READ MORE: [HELEN](https://marvel.fandom.com/wiki/H.E.L.E.N._(Earth-616))



© 2020 Kishwar Shafin, Trevor Pesout, Benedict Paten.


