mgnify-pipelines-toolkit 0.0.5__tar.gz

mgnify_pipelines_toolkit-0.0.5/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

mgnify_pipelines_toolkit-0.0.5/PKG-INFO

@@ -0,0 +1,84 @@
+Metadata-Version: 2.1
+Name: mgnify_pipelines_toolkit
+Version: 0.0.5
+Summary: Collection of scripts and tools for MGnify pipelines
+Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
+License: Apache Software License 2.0
+Keywords: bioinformatics,pipelines,metagenomics
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: biopython==1.81
+Requires-Dist: numpy==1.24.3
+Requires-Dist: pandas==2.0.2
+
+# mgnify-pipelines-toolkit
+
+This Python package contains a collection of scripts and tools for including in MGnify pipelines. Scripts stored here are mainly for:
+
+- One-off production scripts that perform specific tasks in pipelines
+- Scripts that have few dependencies
+- Scripts that don't have existing containers built to run them
+- Scripts for which building an entire container would be too bulky of a solution to deploy in pipelines
+
+This package can be built and uploaded to PyPi, to be installed using pip. The package bundles scripts and makes them executable from the command-line when this package is installed.
+
+> **Soon: this repository will be made available on bioconda for even easier integration in nextflow/nf-core pipelines**.
+
+## How to install
+
+Currently this package is only available on TestPyPi and is installed like this:
+
+`pip install -i https://test.pypi.org/simple/ --no-deps mgnify-pipelines-toolkit`
+
+You should then be able to run the packages from the command-line. For example to run the `get_subunits.py` script:
+
+`get_subunits -i ${easel_coords} -n ${meta.id}`
+
+
+## Building and uploading to PyPi
+This command this build the package:
+
+`python3 -m build`
+
+Then this command will upload it to Test-PyPi (you will need to generate an API token)
+
+`python3 -m twine upload --repository testpypi dist/mgnify_pipelines_toolkit-0.0.x*`
+
+To upload it to actual PyPi:
+
+`python3 -m twine upload dist/*`
+
+## Adding a new script to the package
+
+### New script requirements
+
+There are a few requirements for your script:
+- It needs to have a named main function of some kind. See `mgnify_pipelines_toolkit/v6/get_subunits.py` and the `main()` function for an example
+- Because this package is meant to be run from the command-line, make sure your script can easily pass arguments using tools like `argparse` or `click`
+- A small amount of dependencies. This requirement is subjective, but for example if your script only requires a handful of basic packages like `Biopython`, `numpy`, `pandas`, etc., then it's fine. However if the script has a more extensive list of dependencies, a container is probably a better fit.
+
+### How to add a new script
+
+To add a new Python script, first copy it over to the `mgnify_pipelines_toolkit` directory in this repository, specifically to the subdirectory that makes the most sense. If none of the subdirectories make sense for your script, create a new one. If your script doesn't have a `main()` type function yet, write one. 
+
+Then, open `pyproject.toml` as you will need to add some bits. First, any dependencies required (include the version) to the `dependencies` field.
+
+Then, scroll down to the `[project.scripts]` line. Here, you will create an alias command for running your script from the command-line. In the example line:
+
+`get_subunits = "mgnify_pipelines_toolkit.v6.get_subunits:main"`
+
+- `get_subunits` is the alias
+- `mgnify_pipelines_toolkit.v6.get_subunits` will link the alias to the script with the path `mgnify_pipelines_toolkit/v6/get_subunits.py`
+- `:main` will specifically call the function named `main()` when the alias is run. 
+
+When you have setup this command, executing `get_subunits` on the command-line will be the equivalent of doing:
+
+`from mgnify_pipelines_toolkit.v6.get_subunits import main; main()`
+
+Finally, you will need to bump up the version in the `version` line. How/when we bump versions is to be determined.
+
+At the moment, these should be the only steps required to setup your script in this package (which is subject to change).

mgnify_pipelines_toolkit-0.0.5/README.md

@@ -0,0 +1,67 @@
+# mgnify-pipelines-toolkit
+
+This Python package contains a collection of scripts and tools for including in MGnify pipelines. Scripts stored here are mainly for:
+
+- One-off production scripts that perform specific tasks in pipelines
+- Scripts that have few dependencies
+- Scripts that don't have existing containers built to run them
+- Scripts for which building an entire container would be too bulky of a solution to deploy in pipelines
+
+This package can be built and uploaded to PyPi, to be installed using pip. The package bundles scripts and makes them executable from the command-line when this package is installed.
+
+> **Soon: this repository will be made available on bioconda for even easier integration in nextflow/nf-core pipelines**.
+
+## How to install
+
+Currently this package is only available on TestPyPi and is installed like this:
+
+`pip install -i https://test.pypi.org/simple/ --no-deps mgnify-pipelines-toolkit`
+
+You should then be able to run the packages from the command-line. For example to run the `get_subunits.py` script:
+
+`get_subunits -i ${easel_coords} -n ${meta.id}`
+
+
+## Building and uploading to PyPi
+This command this build the package:
+
+`python3 -m build`
+
+Then this command will upload it to Test-PyPi (you will need to generate an API token)
+
+`python3 -m twine upload --repository testpypi dist/mgnify_pipelines_toolkit-0.0.x*`
+
+To upload it to actual PyPi:
+
+`python3 -m twine upload dist/*`
+
+## Adding a new script to the package
+
+### New script requirements
+
+There are a few requirements for your script:
+- It needs to have a named main function of some kind. See `mgnify_pipelines_toolkit/v6/get_subunits.py` and the `main()` function for an example
+- Because this package is meant to be run from the command-line, make sure your script can easily pass arguments using tools like `argparse` or `click`
+- A small amount of dependencies. This requirement is subjective, but for example if your script only requires a handful of basic packages like `Biopython`, `numpy`, `pandas`, etc., then it's fine. However if the script has a more extensive list of dependencies, a container is probably a better fit.
+
+### How to add a new script
+
+To add a new Python script, first copy it over to the `mgnify_pipelines_toolkit` directory in this repository, specifically to the subdirectory that makes the most sense. If none of the subdirectories make sense for your script, create a new one. If your script doesn't have a `main()` type function yet, write one. 
+
+Then, open `pyproject.toml` as you will need to add some bits. First, any dependencies required (include the version) to the `dependencies` field.
+
+Then, scroll down to the `[project.scripts]` line. Here, you will create an alias command for running your script from the command-line. In the example line:
+
+`get_subunits = "mgnify_pipelines_toolkit.v6.get_subunits:main"`
+
+- `get_subunits` is the alias
+- `mgnify_pipelines_toolkit.v6.get_subunits` will link the alias to the script with the path `mgnify_pipelines_toolkit/v6/get_subunits.py`
+- `:main` will specifically call the function named `main()` when the alias is run. 
+
+When you have setup this command, executing `get_subunits` on the command-line will be the equivalent of doing:
+
+`from mgnify_pipelines_toolkit.v6.get_subunits import main; main()`
+
+Finally, you will need to bump up the version in the `version` line. How/when we bump versions is to be determined.
+
+At the moment, these should be the only steps required to setup your script in this package (which is subject to change).

mgnify_pipelines_toolkit-0.0.5/mgnify_pipelines_toolkit/v6/get_subunits.py

@@ -0,0 +1,96 @@
+#!/usr/bin/env python3
+
+import argparse
+import os
+from Bio import SeqIO
+
+
+SSU = "SSU_rRNA"
+LSU = "LSU_rRNA"
+Seq5S = "mtPerm-5S"
+Seq5_8S = "5_8S_rRNA"
+
+SSU_rRNA_archaea = "SSU_rRNA_archaea"
+SSU_rRNA_bacteria = "SSU_rRNA_bacteria"
+SSU_rRNA_eukarya = "SSU_rRNA_eukarya"
+SSU_rRNA_microsporidia = "SSU_rRNA_microsporidia"
+
+LSU_rRNA_archaea = "LSU_rRNA_archaea"
+LSU_rRNA_bacteria = "LSU_rRNA_bacteria"
+LSU_rRNA_eukarya = "LSU_rRNA_eukarya"
+
+
+def set_model_names(prefix, name):
+    pattern_dict = {}
+    pattern_dict[SSU] = os.path.join(directory, f'{name}_SSU.fasta')
+    pattern_dict[SSU_rRNA_archaea] = os.path.join(directory, f'{prefix}{name}_{SSU_rRNA_archaea}.RF01959.fa')
+    pattern_dict[SSU_rRNA_bacteria] = os.path.join(directory, f'{prefix}{name}_{SSU_rRNA_bacteria}.RF00177.fa')
+    pattern_dict[SSU_rRNA_eukarya] = os.path.join(directory, f'{prefix}{name}_{SSU_rRNA_eukarya}.RF01960.fa')
+    pattern_dict[SSU_rRNA_microsporidia] = os.path.join(directory, f'{prefix}{name}_{SSU_rRNA_microsporidia}.RF02542.fa')
+    pattern_dict[LSU] = os.path.join(directory, f'{name}_LSU.fasta')
+    pattern_dict[LSU_rRNA_archaea] = os.path.join(directory, f'{prefix}{name}_{LSU_rRNA_archaea}.RF02540.fa')
+    pattern_dict[LSU_rRNA_bacteria] = os.path.join(directory, f'{prefix}{name}_{LSU_rRNA_bacteria}.RF02541.fa')
+    pattern_dict[LSU_rRNA_eukarya] = os.path.join(directory, f'{prefix}{name}_{LSU_rRNA_eukarya}.RF02543.fa')
+    pattern_dict[Seq5S] = os.path.join(directory, f'{name}_5S.fa')
+    pattern_dict[Seq5_8S] = os.path.join(directory, f'{name}_5_8S.fa')
+    return pattern_dict
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Extract lsu, ssu and 5s and other models"
+    )
+    parser.add_argument(
+        "-i", "--input", dest="input", help="Input fasta file", required=True
+    )
+    parser.add_argument(
+        "-p", "--prefix", dest="prefix", help="prefix for models", required=False
+    )
+    parser.add_argument("-n", "--name", dest="name", help="Accession", required=True)
+
+    args = parser.parse_args()
+    prefix = args.prefix if args.prefix else ""
+    name = args.name if args.name else "accession"
+
+    directory = "sequence-categorisation"
+    if not os.path.exists(directory):
+        os.makedirs(directory)
+    directory_ncRNA = os.path.join("sequence-categorisation", "ncRNA")
+    if not os.path.exists(directory_ncRNA):
+        os.makedirs(directory_ncRNA)
+
+    print('Start fasta mode')
+    pattern_dict = set_model_names(prefix, name)
+    coding_rna = [SSU_rRNA_archaea, SSU_rRNA_bacteria, SSU_rRNA_eukarya, SSU_rRNA_microsporidia,
+                  LSU_rRNA_archaea, LSU_rRNA_bacteria, LSU_rRNA_eukarya, Seq5S, Seq5_8S]
+    open_files = {}
+    for record in SeqIO.parse(args.input, "fasta"):
+        model = '-'.join(record.id.split('/')[0].split('-')[1:])
+        if model in coding_rna:
+            filename = pattern_dict[model]
+        else:
+            filename = os.path.join(directory_ncRNA, f'{prefix}{name}_{model}.fasta')
+        if model not in open_files:
+            file_out = open(filename, 'w')
+            open_files[model] = file_out
+        SeqIO.write(record, open_files[model], "fasta")
+
+        if model in (SSU_rRNA_archaea, SSU_rRNA_bacteria, SSU_rRNA_eukarya, SSU_rRNA_microsporidia):
+            if SSU not in open_files:
+                file_out = open(pattern_dict[SSU], 'w')
+                open_files[SSU] = file_out
+            SeqIO.write(record, open_files[SSU], "fasta")
+        if model in (LSU_rRNA_archaea, LSU_rRNA_bacteria, LSU_rRNA_eukarya):
+            if LSU not in open_files:
+                file_out = open(pattern_dict[LSU], 'w')
+                open_files[LSU] = file_out
+            SeqIO.write(record, open_files[LSU], "fasta")
+
+    for item in open_files:
+        open_files[item].close()
+
+    if len(os.listdir(directory_ncRNA)) == 0:
+        os.rmdir(directory_ncRNA)
+
+if __name__ == "__main__":
+    main()

mgnify_pipelines_toolkit-0.0.5/mgnify_pipelines_toolkit/v6/get_subunits_coords.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+
+import argparse
+import sys
+import os
+import gzip
+from Bio import SeqIO
+
+
+SSU_coords = "SSU_coords"
+LSU_coords = "LSU_coords"
+SSU_count = 0
+LSU_count = 0
+
+def main():
+    parser = argparse.ArgumentParser(description="Extract lsu, ssu and 5s")
+    parser.add_argument("-i", "--input", dest="input", help="Input fasta file", required=True)
+    parser.add_argument("-l", "--lsu", dest="lsu", help="LSU pattern", required=True)
+    parser.add_argument("-s", "--ssu", dest="ssu", help="SSU pattern", required=True)
+
+    if len(sys.argv) == 1:
+        parser.print_help()
+    else:
+        args = parser.parse_args()
+
+        with open(SSU_coords, 'w') as out_ssu, open(LSU_coords, 'w') as out_lsu, open(args.input, 'r') as input:
+            for line in input:
+                if args.lsu in line:
+                    out_lsu.write(line)
+                    LSU_count += 1
+                elif args.ssu in line:
+                    out_ssu.write(line)
+                    SSU_count += 1
+        with open("RNA-counts", 'w') as count:
+            count.write("LSU count\t" + str(LSU_count) + "\nSSU count\t" + str(SSU_count))
+
+    out_ssu.close()
+    out_lsu.close()
+    count.close()
+
+if __name__ == "__main__":
+    main()

mgnify_pipelines_toolkit-0.0.5/mgnify_pipelines_toolkit/v6/mapseq2biom.py

@@ -0,0 +1,157 @@
+#!/usr/bin/env python3
+
+import argparse
+import csv
+
+
+def main():
+    parser = argparse.ArgumentParser(add_help="Convert the mapseq otutable to biome")
+    parser.add_argument(
+        "--otu-table",
+        required=True,
+        help=(
+            "The OTU table produced for the taxonomies found in"
+            " the reference databases that was used with MAPseq."
+        ),
+    )
+    parser.add_argument(
+        "--query",
+        required=True,
+        help="The output from the MAPseq that assigns a taxonomy to a sequence.",
+    )
+    parser.add_argument(
+        "--out-file", required=True, help="The file storing the tsv file."
+    )
+    parser.add_argument(
+        "--krona", required=False, help="Output file name for the Krona text"
+    )
+    parser.add_argument(
+        "--label",
+        required=False,
+        default="Unspecified",
+        help="Label to add to the top of the outfile OTU table.",
+    )
+    parser.add_argument("--no-tax-id-file", required=True, help="TODO")
+    parser.add_argument("--taxid", action="store_true")
+
+    args = parser.parse_args()
+
+    tax_counter = {}
+
+    with open(args.query, "r") as query_fh:
+        tax = ""
+        for line in query_fh.readlines():
+            if line.startswith("#"):
+                # Skip counts
+                continue
+            # Pull out the fields that we need
+            line = line.strip()
+            fields = line.split("\t")
+            
+            if len(fields) < 14:
+                tax = "Unclassified"
+            else:
+                if not fields[13]:
+                    tax = "Unclassified"
+                else:
+                    tax = fields[13]
+                    while tax.endswith("__"):
+                        fds = tax.split(";")
+                        fds = fds[:-1]
+                        tax = ";".join(fds)
+
+            if tax in tax_counter:
+                tax_counter[tax]["count"] += 1
+            else:
+                tax_counter[tax] = {"count": 1, "otu": 1, "taxid": ""}
+
+    with open(args.otu_table, "r") as otu_table_fh:
+        csv_reader = csv.reader(otu_table_fh, delimiter="\t")
+        next(csv_reader)
+        for row in csv_reader:
+            # Simple two column table, OTU code and taxonomy string.
+            otu = row[0]
+            tax = row[1]
+            tax_id = row[2] if len(row) >= 3 else None
+            # Have we seen this tax string? Store the OTU
+            if tax in tax_counter:
+                tax_counter[tax]["otu"] = otu
+                if tax_id:
+                    tax_counter[tax]["taxid"] = tax_id
+
+    for tax in tax_counter.keys():
+        if tax_counter[tax]["otu"] is None:
+            raise ValueError(f"Fatal, |{tax}| has not got an OTU code assigned")
+
+    output_header = []
+    notaxidfile_header = []
+
+    if args.taxid:
+        if args.label.startswith("UNITE"):
+            output_header = [
+                "# OTU ID",
+                args.label,
+                "taxonomy",
+            ]
+        else:
+            output_header = [
+                "# OTU ID",
+                args.label,
+                "taxonomy",
+                "taxid",
+            ]
+        notaxidfile_header = [
+            "# OTU ID",
+            args.label,
+            "taxonomy",
+        ]
+    else:
+        output_header = [
+            "# OTU ID",
+            args.label,
+            "taxonomy",
+        ]
+        notaxidfile_header = [
+            "# OTU ID",
+            args.label,
+            "taxonomy",
+        ]
+
+    with open(args.out_file, "w") as output_fh:
+        output_fh.write("# Constructed from biom file\n")
+        output_csv = csv.writer(output_fh, delimiter="\t")
+        output_csv.writerow(output_header)
+        for tax in sorted(tax_counter.keys()):
+            row = [
+                tax_counter[tax]["otu"],
+                f"{float(tax_counter[tax]['count']):.1f}",
+                tax,
+            ]
+            if args.taxid:
+                row.append(tax_counter[tax]["taxid"])
+            output_csv.writerow(row)
+
+    if args.taxid:
+        with open(args.no_tax_id_file, "w") as notaxidfile_fh:
+            notaxidfile_fh.write("# Constructed from biom file\n")
+            csv_writer = csv.writer(notaxidfile_fh, delimiter="\t")
+            csv_writer.writerow(notaxidfile_header)
+            for tax in sorted(tax_counter.keys()):
+                csv_writer.writerow(
+                    [
+                        tax_counter[tax]["otu"],
+                        f"{float(tax_counter[tax]['count']):.1f}",
+                        tax,
+                    ]
+                )
+
+    if args.krona:
+        with open(args.krona, "w") as k:
+            for tax in sorted(tax_counter.keys()):
+                tax_mod = tax.replace(r"\D_\d{1}__", "")
+                tax_mod = "\t".join(tax_mod.split(";"))
+                k.write(f"{tax_counter[tax]['count']}\t{tax_mod}\n")
+
+
+if __name__ == "__main__":
+    main()