Skip to content

Clair3 Version 2.0.0 #1590

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
RaheelSyedAhmed wants to merge 5 commits into
base: master
Choose a base branch
from
Open

Clair3 Version 2.0.0 #1590

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
8bda2ce
Generated dockerfile and README.md file for clair3_v2. Models and bui…
RaheelSyedAhmed Mar 11, 2026
4b4e664
Updated main README.md to include updated version link.
RaheelSyedAhmed Mar 11, 2026
6d08baf
Added prior maintainers.
RaheelSyedAhmed Mar 12, 2026
0c707c8
Edited app stage to reinstall essential micromamba packages only and …
RaheelSyedAhmed Mar 13, 2026
82502c3
Updated micromamba list / dependencies.
RaheelSyedAhmed Mar 13, 2026
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
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,7 +148,7 @@ To learn more about the docker pull rate limits and the open source software pro
| [Circlator](https://hub.docker.com/r/staphb/circlator) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/circlator)](https://hub.docker.com/r/staphb/circlator) | <details><summary>Click to see all versions</summary> <ul><li>[1.5.6](./build-files/circlator/1.5.6/)</li><li>[1.5.5](./build-files/circlator/1.5.5/)</li></ul> </details> | https://github.com/sanger-pathogens/circlator |
| [Circos](https://hub.docker.com/r/staphb/circos) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/circos)](https://hub.docker.com/r/staphb/circos) | <details><summary>Click to see all versions</summary> <ul><li>[0.69-9](./build-files/circos/0.69.9/)</li></ul> </details> | https://circos.ca/ |
| [CirculoCov](https://hub.docker.com/r/staphb/circulocov) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/circulocov)](https://hub.docker.com/r/staphb/circulocov) | <details><summary>Click to see all versions</summary> <ul><li>[0.1.20240104](./build-files/circulocov/0.1.20240104/)</li></ul> </details> | https://github.com/erinyoung/CirculoCov |
| [Clair3](https://hub.docker.com/r/staphb/clair3) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/clair3)](https://hub.docker.com/r/staphb/clair3) | <details><summary>Click to see all versions</summary><ul><li>[1.0.9](./build-files/clair3/1.0.9/)</li><li>[1.0.10](./build-files/clair3/1.0.10/)</li><li>[1.1.0](./build-files/clair3/1.1.0/)</li><li>[1.2.0](./build-files/clair3/1.2.0/)</li></ul></details> | https://github.com/HKU-BAL/Clair3 |
| [Clair3](https://hub.docker.com/r/staphb/clair3) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/clair3)](https://hub.docker.com/r/staphb/clair3) | <details><summary>Click to see all versions</summary><ul><li>[1.0.9](./build-files/clair3/1.0.9/)</li><li>[1.0.10](./build-files/clair3/1.0.10/)</li><li>[1.1.0](./build-files/clair3/1.1.0/)</li><li>[1.2.0](./build-files/clair3/1.2.0/)</li><li>[2.0.0](./build-files/clair3/2.0.0/)</li></ul></details> | https://github.com/HKU-BAL/Clair3 |
| [Clustalo](https://hub.docker.com/r/staphb/clustalo) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/clustalo)](https://hub.docker.com/r/staphb/clustalo) | <details><summary>Click to see all versions</summary> <ul><li>[1.2.4](./build-files/clustalo/1.2.4/)</li><li>[1.2.4-2025](./build-files/clustalo/1.2.4-2025/)</li></ul> </details> | http://www.clustal.org/omega/ |
| [colorid](https://hub.docker.com/r/staphb/colorid) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/colorid)](https://hub.docker.com/r/staphb/colorid) | <details><summary>Click to see all versions</summary> <ul><li>[0.1.4.3](./build-files/colorid/0.1.4.3/)</li><li>[0.1.4.3](./build-files/colorid/0.1.4.3-jammy/)</li></ul> </details> | https://github.com/hcdenbakker/colorid |
| [Core-SNP-filter](https://hub.docker.com/r/staphb/core-snp-filter) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/core-snp-filter)](https://hub.docker.com/r/staphb/core-snp-filter) | <details><summary>Click to see all versions</summary> <ul><li>[0.2.0](./build-files/core-snp-filter/0.2.0/)</li></ul> </details> | https://github.com/rrwick/Core-SNP-filter |
Expand Down
183 changes: 183 additions & 0 deletions build-files/clair3/2.0.0/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,183 @@
# Builder Stage
# Credit to https://github.com/HKU-BAL/Clair3/blob/main/Dockerfile for reference code
FROM mambaorg/micromamba:2.5.0-ubuntu24.04 AS builder
ARG CLAIR3_VER="2.0.0"
USER root
WORKDIR /opt/bin

# Install base packages for downloading source code.
RUN apt-get update && apt-get install -y --no-install-recommends \
wget \
ca-certificates \
procps && \
apt-get autoclean && rm -rf /var/lib/apt/lists/*

# Install packages needed for Clair3 and for make files.
RUN micromamba install \
-c conda-forge \
-c bioconda \
python=3.11 \
samtools \
whatshap \
parallel \
zstd \
xz \
zlib \
bzip2 \
automake \
make \
gcc \
gxx \
curl \
pigz \
binutils \
boost-cpp \
-y && \
micromamba clean -a -f -y

# Set environmental variables for PATH and installation with respect to appropriate micromamba directories.
ENV CONDA_PREFIX=/opt/conda
ENV PATH=${CONDA_PREFIX}/bin:/opt/conda/bin:/opt/bin:${PATH} LC_ALL=C.UTF-8 LANG=C.UTF-8

# Install uv for faster installation, then install relevant pytorch libraries and required packages.
RUN pip install --no-cache-dir uv && \
uv pip install --python ${CONDA_PREFIX}/bin/python \
torch torchvision \
--index-url https://download.pytorch.org/whl/cpu && \
uv pip install --python ${CONDA_PREFIX}/bin/python \
numpy \
h5py \
hdf5plugin \
numexpr \
tqdm \
cffi \
torchmetrics

# Get Clair3 Source code and extract
RUN wget -q https://github.com/HKU-BAL/Clair3/archive/refs/tags/v${CLAIR3_VER}.tar.gz && \
tar -xzf v${CLAIR3_VER}.tar.gz && \
cp -a Clair3-${CLAIR3_VER}/. /opt/bin/ && \
rm -rf v${CLAIR3_VER}.tar.gz Clair3-${CLAIR3_VER}

# Use makefile to build Clair3
RUN make PREFIX=${CONDA_PREFIX} PYTHON=${CONDA_PREFIX}/bin/python && \
cd /opt/bin/preprocess/realign && \
g++ -std=c++14 -O1 -shared -fPIC -o realigner ssw_cpp.cpp ssw.c realigner.cpp && \
g++ -std=c++11 -shared -fPIC -o debruijn_graph -O3 debruijn_graph.cpp && \
rm -rf /opt/bin/samtools-* /opt/bin/longphase-*

# Download required pypy3 tools
RUN wget -q https://downloads.python.org/pypy/pypy3.11-v7.3.20-linux64.tar.bz2 && \
tar -xjf pypy3.11-v7.3.20-linux64.tar.bz2 && \
rm pypy3.11-v7.3.20-linux64.tar.bz2 && \
ln -sf /opt/bin/pypy3.11-v7.3.20-linux64/bin/pypy3 ${CONDA_PREFIX}/bin/pypy3 && \
ln -sf /opt/bin/pypy3.11-v7.3.20-linux64/bin/pypy3 ${CONDA_PREFIX}/bin/pypy && \
pypy3 -m ensurepip && \
pypy3 -m pip install --no-cache-dir mpmath==1.2.1

# Download models for different sequencing approaches
ARG CLAIR3_MODELS_URL=https://www.bio8.cs.hku.hk/clair3/clair3_models_pytorch/
RUN set -eux; \
mkdir -p /opt/models /tmp/clair3-models; \
base_url="${CLAIR3_MODELS_URL%/}"; \
wget -r -np -nH --cut-dirs=2 -R "index.html*" -P /tmp/clair3-models "${base_url}/"; \
if [ -d /tmp/clair3-models/clair3_models_pytorch ]; then \
cp -a /tmp/clair3-models/clair3_models_pytorch/. /opt/models/; \
else \
cp -a /tmp/clair3-models/. /opt/models/; \
fi; \
rm -rf /tmp/clair3-models


# App Stage
FROM mambaorg/micromamba:2.5.0-ubuntu24.04 AS app
ARG CLAIR3_VER="2.0.0"
USER root
WORKDIR /opt/bin

LABEL base.image="mambaorg/micromamba:2.5.0-ubuntu24.04"
LABEL dockerfile.version="1"
LABEL software="CLAIR3"
LABEL software.version="${CLAIR3_VER}"
LABEL description="A deep learning-based germline small variant caller for long-reads."
LABEL website="https://github.com/HKU-BAL/Clair3"
LABEL license="https://github.com/HKU-BAL/Clair3/blob/master/LICENSE.md"
LABEL maintainer="Kutluhan Incekara"
LABEL maintainer.email="kutluhan.incekara@ct.gov"
LABEL maintainer2="Raheel Ahmed"
LABEL maintainer2.email="raheelsyedahmed@gmail.com"

RUN apt-get update && apt-get install -y --no-install-recommends \
ca-certificates \
procps && \
apt-get autoclean && rm -rf /var/lib/apt/lists/*

# Install packages needed for Clair3.
RUN micromamba install \
-c conda-forge \
-c bioconda \
python=3.11 \
samtools \
whatshap \
parallel \
zstd \
xz \
zlib \
bzip2 \
pigz \
boost-cpp \
-y && \
micromamba clean -a -f -y

ENV CONDA_PREFIX=/opt/conda
ENV PATH=${CONDA_PREFIX}/bin:/opt/conda/bin:/opt/bin:/clair3:/clair3/models:${PATH} LC_ALL=C.UTF-8 LANG=C.UTF-8

# Copy conda env and built binaries from builder
COPY --from=builder /opt/bin /opt/bin
COPY --from=builder /opt/models /opt/models

# Install uv for faster installation, then install relevant pytorch libraries and required packages.
RUN pip install --no-cache-dir uv && \
uv pip install --python ${CONDA_PREFIX}/bin/python \
torch torchvision \
--index-url https://download.pytorch.org/whl/cpu && \
uv pip install --python ${CONDA_PREFIX}/bin/python \
numpy \
h5py \
hdf5plugin \
numexpr \
tqdm \
cffi \
torchmetrics

# Relink required pypy3 tools
RUN ln -sf /opt/bin/pypy3.11-v7.3.20-linux64/bin/pypy3 ${CONDA_PREFIX}/bin/pypy3 && \
ln -sf /opt/bin/pypy3.11-v7.3.20-linux64/bin/pypy3 ${CONDA_PREFIX}/bin/pypy


# Generate symlinks for /opt and /clair3
RUN ln -s /opt /clair3

RUN mkdir /data
WORKDIR /data


FROM app AS test

RUN apt-get update && \
apt-get install -y wget && \
apt-get autoclean && rm -rf /var/lib/apt/lists/*

RUN run_clair3.sh --help && \
run_clair3.sh --version

# Download ont_quick_test script and run with prespecified arguments
RUN wget -q https://raw.githubusercontent.com/StaPH-B/docker-builds/master/build-files/clair3/1.0.9/ont_quick_test.sh && \
chmod +x ont_quick_test.sh &&\
./ont_quick_test.sh

# list models
RUN ls /clair3/models

# list tools installed with micromamba
RUN micromamba list
168 changes: 168 additions & 0 deletions build-files/clair3/2.0.0/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,168 @@
# Clair3 container

Main tool: [clair3](https://github.com/HKU-BAL/Clair3)


<details>
<summary>Additional tools installed via micromamba:</summary>

```
Name Version Build Channel
────────────────────────────────────────────────────────────────────────
Jinja2 3.1.6 pypi_0 pypi
MarkupSafe 3.0.2 pypi_0 pypi
_openmp_mutex 4.5 20_gnu conda-forge
amply 0.1.6 pyhd8ed1ab_1 conda-forge
biopython 1.86 py311h49ec1c0_1 conda-forge
boost-cpp 1.85.0 h3c6214e_4 conda-forge
bzip2 1.0.8 hda65f42_9 conda-forge
c-ares 1.34.6 hb03c661_0 conda-forge
ca-certificates 2026.2.25 hbd8a1cb_0 conda-forge
cffi 2.0.0 py311h03d9500_1 conda-forge
coin-or-cbc 2.10.13 h4d16d09_0 conda-forge
coin-or-cgl 0.60.10 hc46dffc_0 conda-forge
coin-or-clp 1.17.11 hc03379b_0 conda-forge
coin-or-osi 0.108.12 hf4fecb4_0 conda-forge
coin-or-utils 2.11.13 hc93afbd_0 conda-forge
docutils 0.22.4 pyhd8ed1ab_0 conda-forge
filelock 3.20.0 pypi_0 pypi
fsspec 2025.12.0 pypi_0 pypi
h5py 3.16.0 pypi_0 pypi
hdf5plugin 6.0.0 pypi_0 pypi
htslib 1.23 h566b1c6_0 bioconda
icu 75.1 he02047a_0 conda-forge
importlib-metadata 8.7.0 pyhe01879c_1 conda-forge
isa-l 2.31.1 hb9d3cd8_1 conda-forge
keyutils 1.6.3 hb9d3cd8_0 conda-forge
krb5 1.22.2 ha1258a1_0 conda-forge
ld_impl_linux-64 2.45.1 default_hbd61a6d_101 conda-forge
libblas 3.11.0 5_h4a7cf45_openblas conda-forge
libboost 1.85.0 h0ccab89_4 conda-forge
libboost-devel 1.85.0 h00ab1b0_4 conda-forge
libboost-headers 1.85.0 ha770c72_4 conda-forge
libcblas 3.11.0 5_h0358290_openblas conda-forge
libcurl 8.19.0 hcf29cc6_0 conda-forge
libdeflate 1.22 hb9d3cd8_0 conda-forge
libedit 3.1.20250104 pl5321h7949ede_0 conda-forge
libev 4.33 hd590300_2 conda-forge
libexpat 2.7.4 hecca717_0 conda-forge
libffi 3.5.2 h3435931_0 conda-forge
libgcc 15.2.0 he0feb66_18 conda-forge
libgcc-ng 15.2.0 h69a702a_18 conda-forge
libgfortran 15.2.0 h69a702a_18 conda-forge
libgfortran5 15.2.0 h68bc16d_18 conda-forge
libgomp 15.2.0 he0feb66_18 conda-forge
liblapack 3.11.0 5_h47877c9_openblas conda-forge
liblapacke 3.11.0 5_h6ae95b6_openblas conda-forge
liblzma 5.8.2 hb03c661_0 conda-forge
liblzma-devel 5.8.2 hb03c661_0 conda-forge
libnghttp2 1.67.0 had1ee68_0 conda-forge
libnsl 2.0.1 hb9d3cd8_1 conda-forge
libopenblas 0.3.30 pthreads_h94d23a6_4 conda-forge
libsqlite 3.52.0 h0c1763c_0 conda-forge
libssh2 1.11.1 hcf80075_0 conda-forge
libstdcxx 15.2.0 h934c35e_18 conda-forge
libstdcxx-ng 15.2.0 hdf11a46_18 conda-forge
libuuid 2.41.3 h5347b49_0 conda-forge
libxcrypt 4.4.36 hd590300_1 conda-forge
libzlib 1.3.1 hb9d3cd8_2 conda-forge
lightning-utilities 0.15.3 pypi_0 pypi
mpmath 1.3.0 pypi_0 pypi
ncurses 6.5 h2d0b736_3 conda-forge
networkx 3.6.1 pyhcf101f3_0 conda-forge
numexpr 2.14.1 pypi_0 pypi
numpy 2.4.2 py311h2e04523_1 conda-forge
openssl 3.6.1 h35e630c_1 conda-forge
packaging 26.0 pyhcf101f3_0 conda-forge
parallel 20260122 ha770c72_0 conda-forge
pbzip2 1.1.13 h1fcc475_2 conda-forge
perl 5.32.1 7_hd590300_perl5 conda-forge
pigz 2.8 h421ea60_2 conda-forge
pillow 12.0.0 pypi_0 pypi
pip 26.0.1 pyh8b19718_0 conda-forge
pulp 2.8.0 py311h77a8cca_3 conda-forge
pycparser 2.22 pyh29332c3_1 conda-forge
pyfaidx 0.9.0.3 pyhdfd78af_0 bioconda
pyparsing 3.3.2 pyhcf101f3_0 conda-forge
pysam 0.23.3 py311hb456a96_1 bioconda
python 3.11.15 hd63d673_0_cpython conda-forge
python-isal 1.8.0 py311h49ec1c0_1 conda-forge
python-zlib-ng 1.0.0 py311h15805fc_1 conda-forge
python_abi 3.11 8_cp311 conda-forge
pyvcf3 1.0.4 py311haab0aaa_0 bioconda
readline 8.3 h853b02a_0 conda-forge
samtools 1.23 h96c455f_0 bioconda
scipy 1.17.1 py311hbe70eeb_0 conda-forge
setuptools 82.0.1 pyh332efcf_0 conda-forge
six 1.17.0 pyhe01879c_1 conda-forge
sympy 1.14.0 pypi_0 pypi
tk 8.6.13 noxft_h366c992_103 conda-forge
torch 2.10.0+cpu pypi_0 pypi
torchmetrics 1.9.0 pypi_0 pypi
torchvision 0.25.0+cpu pypi_0 pypi
tqdm 4.67.3 pypi_0 pypi
typing_extensions 4.15.0 pypi_0 pypi
tzdata 2025c hc9c84f9_1 conda-forge
uv 0.10.10 pypi_0 pypi
whatshap 2.8 py311he264feb_0 bioconda
wheel 0.46.3 pyhd8ed1ab_0 conda-forge
xopen 2.0.2 pyh707e725_2 conda-forge
xz 5.8.2 ha02ee65_0 conda-forge
xz-gpl-tools 5.8.2 ha02ee65_0 conda-forge
xz-tools 5.8.2 hb03c661_0 conda-forge
zipp 3.23.0 pyhcf101f3_1 conda-forge
zlib 1.3.1 hb9d3cd8_2 conda-forge
zlib-ng 2.3.3 hceb46e0_1 conda-forge
zstandard 0.25.0 py311haee01d2_1 conda-forge
zstd 1.5.7 hb78ec9c_6 conda-forge
```
</details>
</br>

Code repository: https://github.com/HKU-BAL/Clair3

Basic information on how to use this tool:
- executable: run_clair3.sh
- help: `-h`, `--help`
- version: `-v`, `--version`
- description: A germline small variant caller for long-reads.

Additional information:

- This container includes the following models in `/clair3/models` and `/opt/models`
- This container has no GPU support!

List of models:
```
hifi
hifi_revio
hifi_sequel2
ilmn
ont
ont_guppy5
r1041_e82_400bps_hac_v410
r1041_e82_400bps_hac_v500
r1041_e82_400bps_hac_with_mv
r1041_e82_400bps_sup_v410
r1041_e82_400bps_sup_v430_bacteria_finetuned
r1041_e82_400bps_sup_v500
r941_prom_hac_g360+g422
r941_prom_sup_g5014
```

Full documentation: https://github.com/HKU-BAL/Clair3

## Example Usage

```bash
run_clair3.sh \
--bam_fn=${BAM} \
--ref_fn=${REF} \
--threads=${THREADS} \
--platform="ont" \ ## options: {ont,hifi,ilmn}
--model_path=${MODEL_PREFIX} \ ## absolute model path prefix
--output=${OUTPUT_DIR} ## absolute output path prefix
## pileup output file: ${OUTPUT_DIR}/pileup.vcf.gz
## full-alignment output file: ${OUTPUT_DIR}/full_alignment.vcf.gz
## Clair3 final output file: ${OUTPUT_DIR}/merge_output.vcf.gz
```
Loading