-
Notifications
You must be signed in to change notification settings - Fork 128
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'StaPH-B:master' into busco-slim
- Loading branch information
Showing
10 changed files
with
392 additions
and
3 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,39 @@ | ||
| FROM python:3.9.17-slim as app | ||
|
|
||
| ARG PYCIRCLIZE_VER="1.2.0" | ||
|
|
||
| # 'LABEL' instructions tag the image with metadata that might be important to the user | ||
| LABEL base.image="python:3.9.17-slim" | ||
| LABEL dockerfile.version="1" | ||
| LABEL software="pyCirclize" | ||
| LABEL software.version="${PYCIRCLIZE_VER}" | ||
| LABEL description="Circular visualization in Python" | ||
| LABEL website="https://github.com/moshi4/pyCirclize" | ||
| LABEL license="https://github.com/moshi4/pyCirclize/blob/main/LICENSE" | ||
| LABEL maintainer="Erin Young" | ||
| LABEL maintainer.email="[email protected]" | ||
|
|
||
| RUN apt-get update && apt-get install -y --no-install-recommends \ | ||
| procps && \ | ||
| apt-get autoclean && rm -rf /var/lib/apt/lists/* | ||
|
|
||
| RUN pip install --no-cache pycirclize==${PYCIRCLIZE_VER} | ||
|
|
||
| ENV PATH=$PATH \ | ||
| LC_ALL=C | ||
|
|
||
| CMD pip show pycirclize | ||
|
|
||
| WORKDIR /data | ||
|
|
||
| FROM app as test | ||
|
|
||
| WORKDIR /test | ||
|
|
||
| RUN pip show pycirclize | ||
|
|
||
| COPY /tests/* /test/ | ||
|
|
||
| RUN python example1.py && ls example01.png && \ | ||
| python example2.py && ls example02.png && \ | ||
| python example3.py && ls example03.png |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,61 @@ | ||
| # pyCirclize container | ||
|
|
||
| Main tool: [pyCirclize](https://pypi.org/project/pyCirclize/) | ||
|
|
||
| Code repository: https://github.com/moshi4/pyCirclize | ||
|
|
||
| Basic information on how to use this tool: | ||
| - executable: NA | ||
| - help: NA | ||
| - version: NA | ||
| - description: pyCirclize is a python package for creating visual images of circular genomes (like those of bacteria) | ||
|
|
||
| Full documentation: https://pypi.org/project/pyCirclize/ | ||
|
|
||
| ## Example Usage | ||
|
|
||
| This is for running containers with a specific python package, and is not really meant to be run from the command line. Instead, a bioinformatician could create a python script that uses pycirclize. | ||
|
|
||
| example1.py: | ||
| ```python | ||
| from pycirclize import Circos | ||
| import numpy as np | ||
| np.random.seed(0) | ||
|
|
||
| # Initialize Circos sectors | ||
| sectors = {"A": 10, "B": 15, "C": 12, "D": 20, "E": 15} | ||
| circos = Circos(sectors, space=5) | ||
|
|
||
| for sector in circos.sectors: | ||
| # Plot sector name | ||
| sector.text(f"Sector: {sector.name}", r=110, size=15) | ||
| # Create x positions & random y values | ||
| x = np.arange(sector.start, sector.end) + 0.5 | ||
| y = np.random.randint(0, 100, len(x)) | ||
| # Plot lines | ||
| track1 = sector.add_track((80, 100), r_pad_ratio=0.1) | ||
| track1.xticks_by_interval(interval=1) | ||
| track1.axis() | ||
| track1.line(x, y) | ||
| # Plot points | ||
| track2 = sector.add_track((55, 75), r_pad_ratio=0.1) | ||
| track2.axis() | ||
| track2.scatter(x, y) | ||
| # Plot bars | ||
| track3 = sector.add_track((30, 50), r_pad_ratio=0.1) | ||
| track3.axis() | ||
| track3.bar(x, y) | ||
|
|
||
| # Plot links | ||
| circos.link(("A", 0, 3), ("B", 15, 12)) | ||
| circos.link(("B", 0, 3), ("C", 7, 11), color="skyblue") | ||
| circos.link(("C", 2, 5), ("E", 15, 12), color="chocolate", direction=1) | ||
| circos.link(("D", 3, 5), ("D", 18, 15), color="lime", ec="black", lw=0.5, hatch="//", direction=2) | ||
| circos.link(("D", 8, 10), ("E", 2, 8), color="violet", ec="red", lw=1.0, ls="dashed") | ||
|
|
||
| circos.savefig("example01.png") | ||
| ``` | ||
|
|
||
| ```bash | ||
| python example1.py | ||
| ``` |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,36 @@ | ||
| from pycirclize import Circos | ||
| import numpy as np | ||
| np.random.seed(0) | ||
|
|
||
| # Initialize Circos sectors | ||
| sectors = {"A": 10, "B": 15, "C": 12, "D": 20, "E": 15} | ||
| circos = Circos(sectors, space=5) | ||
|
|
||
| for sector in circos.sectors: | ||
| # Plot sector name | ||
| sector.text(f"Sector: {sector.name}", r=110, size=15) | ||
| # Create x positions & random y values | ||
| x = np.arange(sector.start, sector.end) + 0.5 | ||
| y = np.random.randint(0, 100, len(x)) | ||
| # Plot lines | ||
| track1 = sector.add_track((80, 100), r_pad_ratio=0.1) | ||
| track1.xticks_by_interval(interval=1) | ||
| track1.axis() | ||
| track1.line(x, y) | ||
| # Plot points | ||
| track2 = sector.add_track((55, 75), r_pad_ratio=0.1) | ||
| track2.axis() | ||
| track2.scatter(x, y) | ||
| # Plot bars | ||
| track3 = sector.add_track((30, 50), r_pad_ratio=0.1) | ||
| track3.axis() | ||
| track3.bar(x, y) | ||
|
|
||
| # Plot links | ||
| circos.link(("A", 0, 3), ("B", 15, 12)) | ||
| circos.link(("B", 0, 3), ("C", 7, 11), color="skyblue") | ||
| circos.link(("C", 2, 5), ("E", 15, 12), color="chocolate", direction=1) | ||
| circos.link(("D", 3, 5), ("D", 18, 15), color="lime", ec="black", lw=0.5, hatch="//", direction=2) | ||
| circos.link(("D", 8, 10), ("E", 2, 8), color="violet", ec="red", lw=1.0, ls="dashed") | ||
|
|
||
| circos.savefig("example01.png") |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,42 @@ | ||
| from pycirclize import Circos | ||
| from pycirclize.utils import fetch_genbank_by_accid | ||
| from pycirclize.parser import Genbank | ||
|
|
||
| # Download `NC_002483` E.coli plasmid genbank | ||
| gbk_fetch_data = fetch_genbank_by_accid("NC_002483") | ||
| gbk = Genbank(gbk_fetch_data) | ||
|
|
||
| # Initialize Circos instance with genome size | ||
| circos = Circos(sectors={gbk.name: gbk.range_size}) | ||
| circos.text(f"Escherichia coli K-12 plasmid F\n\n{gbk.name}", size=14) | ||
| circos.rect(r_lim=(90, 100), fc="lightgrey", ec="none", alpha=0.5) | ||
| sector = circos.sectors[0] | ||
|
|
||
| # Plot forward strand CDS | ||
| f_cds_track = sector.add_track((95, 100)) | ||
| f_cds_feats = gbk.extract_features("CDS", target_strand=1) | ||
| f_cds_track.genomic_features(f_cds_feats, plotstyle="arrow", fc="salmon", lw=0.5) | ||
|
|
||
| # Plot reverse strand CDS | ||
| r_cds_track = sector.add_track((90, 95)) | ||
| r_cds_feats = gbk.extract_features("CDS", target_strand=-1) | ||
| r_cds_track.genomic_features(r_cds_feats, plotstyle="arrow", fc="skyblue", lw=0.5) | ||
|
|
||
| # Plot 'gene' qualifier label if exists | ||
| labels, label_pos_list = [], [] | ||
| for feat in gbk.extract_features("CDS"): | ||
| start = int(str(feat.location.start)) | ||
| end = int(str(feat.location.end)) | ||
| label_pos = (start + end) / 2 | ||
| gene_name = feat.qualifiers.get("gene", [None])[0] | ||
| if gene_name is not None: | ||
| labels.append(gene_name) | ||
| label_pos_list.append(label_pos) | ||
| f_cds_track.xticks(label_pos_list, labels, label_size=6, label_orientation="vertical") | ||
|
|
||
| # Plot xticks (interval = 10 Kb) | ||
| r_cds_track.xticks_by_interval( | ||
| 10000, outer=False, label_formatter=lambda v: f"{v/1000:.1f} Kb" | ||
| ) | ||
|
|
||
| circos.savefig("example02.png") |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,23 @@ | ||
| from pycirclize import Circos | ||
| import pandas as pd | ||
|
|
||
| # Create matrix dataframe (3 x 6) | ||
| row_names = ["F1", "F2", "F3"] | ||
| col_names = ["T1", "T2", "T3", "T4", "T5", "T6"] | ||
| matrix_data = [ | ||
| [10, 16, 7, 7, 10, 8], | ||
| [4, 9, 10, 12, 12, 7], | ||
| [17, 13, 7, 4, 20, 4], | ||
| ] | ||
| matrix_df = pd.DataFrame(matrix_data, index=row_names, columns=col_names) | ||
|
|
||
| # Initialize Circos from matrix for plotting Chord Diagram | ||
| circos = Circos.initialize_from_matrix( | ||
| matrix_df, | ||
| space=5, | ||
| cmap="tab10", | ||
| label_kws=dict(size=12), | ||
| link_kws=dict(ec="black", lw=0.5, direction=1), | ||
| ) | ||
|
|
||
| circos.savefig("example03.png") |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,46 @@ | ||
| FROM python:3.9.17-slim as app | ||
|
|
||
| ARG PYGENOMEVIZ_VER="0.4.4" | ||
|
|
||
| LABEL base.image="python:3.9.17-slim" | ||
| LABEL dockerfile.version="1" | ||
| LABEL software="pyGenomeViz" | ||
| LABEL software.version=$PYGENOMEVIZ_VER | ||
| LABEL description="genome visualization python package for comparative genomics" | ||
| LABEL website="https://moshi4.github.io/pyGenomeViz/" | ||
| LABEL license="MIT License" | ||
| LABEL license.url="https://github.com/moshi4/pyGenomeViz/blob/main/LICENSE" | ||
| LABEL maintainer="Erin Young" | ||
| LABEL maintainer.email="[email protected]" | ||
|
|
||
| #mmseqs2=14-7e284+ds-1+b2 | ||
| #mummer=3.23+dfsg-8 | ||
| #progressivemauve=1.2.0+4713+dfsg-5+b1 | ||
| RUN apt-get update && apt-get install -y --no-install-recommends \ | ||
| ca-certificates \ | ||
| procps \ | ||
| mmseqs2 \ | ||
| mummer \ | ||
| progressivemauve && \ | ||
| apt-get autoclean && rm -rf /var/lib/apt/lists/* | ||
|
|
||
| RUN pip install --no-cache-dir pygenomeviz==$PYGENOMEVIZ_VER | ||
|
|
||
| ENV LC_ALL=C.UTF-8 | ||
|
|
||
| CMD pgv-simpleplot --help && pgv-mmseqs --help && pgv-mummer --help && pgv-pmauve --help | ||
|
|
||
| WORKDIR /data | ||
|
|
||
| FROM app as test | ||
|
|
||
| WORKDIR /test | ||
|
|
||
| RUN pgv-simpleplot --help && pgv-mmseqs --help && pgv-mummer --help && pgv-pmauve --help | ||
|
|
||
| RUN pgv-download-dataset -n erwinia_phage && \ | ||
| pgv-mummer --gbk_resources MT939486.gbk MT939487.gbk MT939488.gbk LT960552.gbk -o mummer_test --tick_style axis --align_type left --feature_plotstyle arrow && \ | ||
| pgv-mmseqs --gbk_resources MT939486.gbk MT939487.gbk MT939488.gbk LT960552.gbk -o mmseqs_test --tick_style axis --align_type left --feature_plotstyle arrow && \ | ||
| pgv-download-dataset -n escherichia_coli && \ | ||
| pgv-pmauve --seq_files NC_000913.gbk NC_002695.gbk NC_011751.gbk NC_011750.gbk -o pmauve_test --tick_style bar && \ | ||
| ls mummer_test/result.png mmseqs_test/result.png pmauve_test/result.png |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,50 @@ | ||
| # pyGenomeViz container | ||
|
|
||
| Main tool : [pyGenomeViz](https://moshi4.github.io/pyGenomeViz/) | ||
|
|
||
| Additional tools: | ||
| - MMseqs2 v14-7e284+ds-1+b2 | ||
| - MUMmer v3.23+dfsg-8 | ||
| - progressiveMauve v1.2.0+4713+dfsg-5+b1 | ||
|
|
||
| Full documentation: https://moshi4.github.io/pyGenomeViz/ | ||
|
|
||
| > pyGenomeViz is a genome visualization python package for comparative genomics implemented based on matplotlib. This package is developed for the purpose of easily and beautifully plotting genomic features and sequence similarity comparison links between multiple genomes. | ||
| ## Example Usage | ||
|
|
||
| Using the CLI | ||
|
|
||
| ```bash | ||
| # Download four Erwinia phage genbank files | ||
| pgv-download-dataset -n erwinia_phage | ||
|
|
||
| # run pyGenomeViz to visualize MUMmer alignment | ||
| pgv-mummer --gbk_resources MT939486.gbk MT939487.gbk MT939488.gbk LT960552.gbk -o mummer_example1 --tick_style axis --align_type left --feature_plotstyle arrow | ||
|
|
||
| # run pyGenomeViz to visualize MMseqs2 alignment | ||
| pgv-mmseqs --gbk_resources MT939486.gbk:250000-358115 MT939487.gbk:250000-355376 MT939488.gbk:250000-356948 LT960552.gbk:270000-340000 -o mmseqs_example2 --tick_style bar --feature_plotstyle arrow | ||
|
|
||
| # Download four E.coli genbank files | ||
| pgv-download-dataset -n escherichia_coli | ||
|
|
||
| # run pyGenomeViz to visualize progressiveMauve alignment | ||
| pgv-pmauve --seq_files NC_000913.gbk NC_002695.gbk NC_011751.gbk NC_011750.gbk -o pmauve_example1 --tick_style bar | ||
| ``` | ||
|
|
||
| This container contains the pygenomeviz python package, so custom scripts can import pygenomeviz | ||
|
|
||
| ```python | ||
| from pygenomeviz import GenomeViz | ||
|
|
||
| name, genome_size = "Tutorial 01", 5000 | ||
| cds_list = ((100, 900, -1), (1100, 1300, 1), (1350, 1500, 1), (1520, 1700, 1), (1900, 2200, -1), (2500, 2700, 1), (2700, 2800, -1), (2850, 3000, -1), (3100, 3500, 1), (3600, 3800, -1), (3900, 4200, -1), (4300, 4700, -1), (4800, 4850, 1)) | ||
|
|
||
| gv = GenomeViz() | ||
| track = gv.add_feature_track(name, genome_size) | ||
| for idx, cds in enumerate(cds_list, 1): | ||
| start, end, strand = cds | ||
| track.add_feature(start, end, strand, label=f"CDS{idx:02d}") | ||
|
|
||
| fig = gv.plotfig() | ||
| ``` |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,64 @@ | ||
| ARG SYLPH_VER="0.5.1" | ||
|
|
||
| ## Builder ## | ||
| FROM rust:1.74 as builder | ||
|
|
||
| ARG SYLPH_VER | ||
|
|
||
| RUN apt update && \ | ||
| apt install -y cmake && \ | ||
| wget -q https://github.com/bluenote-1577/sylph/archive/refs/tags/v${SYLPH_VER}.tar.gz && \ | ||
| tar -xvf v${SYLPH_VER}.tar.gz && \ | ||
| cd sylph-${SYLPH_VER} && \ | ||
| cargo install --path . --root ~/.cargo && \ | ||
| chmod +x /root/.cargo/bin/sylph | ||
|
|
||
| ## App ## | ||
| FROM ubuntu:jammy as app | ||
|
|
||
| ARG SYLPH_VER | ||
|
|
||
| LABEL base.image="ubuntu:jammy" | ||
| LABEL dockerfile.version="1" | ||
| LABEL software="sylph" | ||
| LABEL software.version=${SYLPH_VER} | ||
| LABEL description="sylph is a program that can perform ultrafast (1) ANI querying or (2) metagenomic profiling for metagenomic shotgun samples." | ||
| LABEL website="https://github.com/bluenote-1577/sylph" | ||
| LABEL license="https://github.com/bluenote-1577/sylph/blob/main/LICENSE" | ||
| LABEL maintainer="Stephen Turner" | ||
| LABEL maintainer.email="[email protected]" | ||
|
|
||
| # copy app from builder stage | ||
| COPY --from=builder /root/.cargo/bin/sylph /usr/local/bin/sylph | ||
|
|
||
| # default run command | ||
| CMD sylph -h | ||
|
|
||
| # singularity compatibility | ||
| ENV LC_ALL=C | ||
|
|
||
| # final working directory in app layer is /data | ||
| WORKDIR /data | ||
|
|
||
| ## Test ## | ||
| FROM app as test | ||
|
|
||
| # making sure sylph is in PATH | ||
| RUN sylph -h | ||
|
|
||
| ARG SYLPH_VER | ||
|
|
||
| RUN apt update && apt install -y wget | ||
|
|
||
| RUN wget -q https://github.com/bluenote-1577/sylph/raw/v${SYLPH_VER}/test_files/e.coli-EC590.fasta && \ | ||
| wget -q https://github.com/bluenote-1577/sylph/raw/v${SYLPH_VER}/test_files/e.coli-K12.fasta && \ | ||
| wget -q https://github.com/bluenote-1577/sylph/raw/v${SYLPH_VER}/test_files/e.coli-o157.fasta && \ | ||
| wget -q https://github.com/bluenote-1577/sylph/raw/v${SYLPH_VER}/test_files/o157_reads.fastq | ||
|
|
||
| RUN date && \ | ||
| sylph sketch -i e.coli-*.fasta -o database && \ | ||
| sylph sketch o157_reads.fastq && \ | ||
| sylph query database.syldb *.sylsp > ani_queries.tsv && \ | ||
| sylph profile database.syldb *.sylsp > profiling.tsv && \ | ||
| cat *.tsv && \ | ||
| date |
Oops, something went wrong.