Initial commit

aggregate_SBG.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#    This program is free software: you can redistribute it and/or modify
+#    it under the terms of the GNU General Public License as published by
+#    the Free Software Foundation, either version 3 of the License, or
+#    (at your option) any later version.
+#    This program is distributed in the hope that it will be useful,
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#    GNU General Public License for more details.
+#    A copy of the GNU General Public License is available at
+#    http://www.gnu.org/licenses/gpl-3.0.html
+import argparse
+import pandas as pd
+from pathlib import Path
+
+parser = argparse.ArgumentParser()
+parser.add_argument("metaphlan_file", type=Path)
+parser.add_argument("metaphlan_len", type=Path)
+parser.add_argument("sample_name", type=str)
+parser.add_argument("output_file", type=Path)
+args = parser.parse_args()
+
+core_content = pd.read_csv(args.metaphlan_file, delimiter="\t", names=["gene", "count"], low_memory=False )
+metaphlan_len = pd.read_csv(args.metaphlan_len, delimiter="\t", compression="gzip", names=["gene", "len"])
+core_content = core_content.merge(metaphlan_len[["gene", "len"]],on="gene", how="inner")
+core_content["SGB"] = core_content['gene'].str.split('|').str[-1]
+#print(core_content)
+core_content['len'] = pd.to_numeric(core_content['len'])
+core_content['count'] = pd.to_numeric(core_content['count'])
+core_content[args.sample_name] = core_content["count"]/core_content["len"]*1000
+del core_content["len"]
+del core_content["count"]
+del core_content["gene"]
+#print(core_content)
+res = core_content.groupby("SGB")[args.sample_name].mean()
+#res = core_content.groupby("SGB").agg("mean")
+res = res.round(0).astype(int)
+#print(res)
+res.to_csv(args.output_file,sep="\t")

build_matrix.py

+import pandas as pd
+import argparse
+from pathlib import Path
+import numpy as np
+
+# create the top-level parser
+parser = argparse.ArgumentParser()
+parser.add_argument("--sgbtaxo", help="SGB taxonomy (GTDB format)", default=Path("mpa_vOct22_CHOCOPhlAnSGB_202212_SGB2GTDB.tsv.gz"),
+                    type=Path)
+parser.add_argument("--keepZeros", help="Do not remove SGB that have a null count in the final matrix",
+                    action="store_false")
+parser.add_argument('metaphlan_SBG_agg', type=Path, nargs='+')
+parser.add_argument('output_matrix', type=Path, default="matrix.tsv", help="Combine all metaphlan SGB data into a contengency matrix")
+parser.add_argument('output_taxo_table', type=Path, default="taxonomy.tsv", help="If sgbtaxo available, output the taxonomy of existing SGB")
+args = parser.parse_args()
+dataframes = [pd.read_csv(f, delimiter="\t") for f in args.metaphlan_SBG_agg]
+
+# Now you can concatenate them into one DataFrame
+df = dataframes[0]
+for dataframe in dataframes[1:]:
+    df = pd.merge(df, dataframe, on='SGB')
+
+
+# Remove rows with only zeros
+if args.keepZeros:
+    df = df[df.select_dtypes(include=[np.number]).sum(axis=1) != 0]
+
+df.to_csv(args.output_matrix, sep="\t", index=False)
+
+if args.sgbtaxo:
+    taxo = pd.read_csv(args.sgbtaxo, compression="gzip", delimiter="\t", names=["SGB", "Annotation"])
+    # print(taxo)
+    taxo = taxo[taxo['SGB'].isin(df['SGB'])]
+    taxo['Annotation'] = taxo['Annotation'].str.replace(r'\w__', '', regex=True)
+    # Split 'Annotation' into multiple columns
+    # print(taxo['Annotation'].str.split(';', expand=True))
+    taxo[['Domain', 'Phylum', 'Class', 'Order', 'Family', 'Genus', 'Species']] = taxo['Annotation'].str.split(';', expand=True)
+    # Add 'marker_SGB' column
+    taxo['marker_SGB'] = taxo['SGB'] + '_' + taxo['Annotation'].apply(lambda x: [i for i in x.split(';') if i][-1])
+    del taxo['Annotation']
+    taxo.to_csv(args.output_taxo_table, sep="\t", index=False)

pyproject.toml

+[tool.poetry]
+name = "metaphlan-script"
+version = "0.1.0"
+description = "Convert metaphlan marker_counts output to raw count matrix"
+authors = ["Amine Ghozlane <amine.ghozlane@pasteur.fr>"]
+license = "GPL-3"
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.10"
+pandas = "^2.2.1"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

requirements.txt

+numpy==1.26.4 ; python_version >= "3.10" and python_version <= "3.11" or python_version >= "3.12" and python_version < "4.0" \
+    --hash=sha256:03a8c78d01d9781b28a6989f6fa1bb2c4f2d51201cf99d3dd875df6fbd96b23b \
+    --hash=sha256:08beddf13648eb95f8d867350f6a018a4be2e5ad54c8d8caed89ebca558b2818 \
+    --hash=sha256:1af303d6b2210eb850fcf03064d364652b7120803a0b872f5211f5234b399f20 \
+    --hash=sha256:1dda2e7b4ec9dd512f84935c5f126c8bd8b9f2fc001e9f54af255e8c5f16b0e0 \
+    --hash=sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010 \
+    --hash=sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a \
+    --hash=sha256:3373d5d70a5fe74a2c1bb6d2cfd9609ecf686d47a2d7b1d37a8f3b6bf6003aea \
+    --hash=sha256:47711010ad8555514b434df65f7d7b076bb8261df1ca9bb78f53d3b2db02e95c \
+    --hash=sha256:4c66707fabe114439db9068ee468c26bbdf909cac0fb58686a42a24de1760c71 \
+    --hash=sha256:50193e430acfc1346175fcbdaa28ffec49947a06918b7b92130744e81e640110 \
+    --hash=sha256:52b8b60467cd7dd1e9ed082188b4e6bb35aa5cdd01777621a1658910745b90be \
+    --hash=sha256:60dedbb91afcbfdc9bc0b1f3f402804070deed7392c23eb7a7f07fa857868e8a \
+    --hash=sha256:62b8e4b1e28009ef2846b4c7852046736bab361f7aeadeb6a5b89ebec3c7055a \
+    --hash=sha256:666dbfb6ec68962c033a450943ded891bed2d54e6755e35e5835d63f4f6931d5 \
+    --hash=sha256:675d61ffbfa78604709862923189bad94014bef562cc35cf61d3a07bba02a7ed \
+    --hash=sha256:679b0076f67ecc0138fd2ede3a8fd196dddc2ad3254069bcb9faf9a79b1cebcd \
+    --hash=sha256:7349ab0fa0c429c82442a27a9673fc802ffdb7c7775fad780226cb234965e53c \
+    --hash=sha256:7ab55401287bfec946ced39700c053796e7cc0e3acbef09993a9ad2adba6ca6e \
+    --hash=sha256:7e50d0a0cc3189f9cb0aeb3a6a6af18c16f59f004b866cd2be1c14b36134a4a0 \
+    --hash=sha256:95a7476c59002f2f6c590b9b7b998306fba6a5aa646b1e22ddfeaf8f78c3a29c \
+    --hash=sha256:96ff0b2ad353d8f990b63294c8986f1ec3cb19d749234014f4e7eb0112ceba5a \
+    --hash=sha256:9fad7dcb1aac3c7f0584a5a8133e3a43eeb2fe127f47e3632d43d677c66c102b \
+    --hash=sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0 \
+    --hash=sha256:a354325ee03388678242a4d7ebcd08b5c727033fcff3b2f536aea978e15ee9e6 \
+    --hash=sha256:a4abb4f9001ad2858e7ac189089c42178fcce737e4169dc61321660f1a96c7d2 \
+    --hash=sha256:ab47dbe5cc8210f55aa58e4805fe224dac469cde56b9f731a4c098b91917159a \
+    --hash=sha256:afedb719a9dcfc7eaf2287b839d8198e06dcd4cb5d276a3df279231138e83d30 \
+    --hash=sha256:b3ce300f3644fb06443ee2222c2201dd3a89ea6040541412b8fa189341847218 \
+    --hash=sha256:b97fe8060236edf3662adfc2c633f56a08ae30560c56310562cb4f95500022d5 \
+    --hash=sha256:bfe25acf8b437eb2a8b2d49d443800a5f18508cd811fea3181723922a8a82b07 \
+    --hash=sha256:cd25bcecc4974d09257ffcd1f098ee778f7834c3ad767fe5db785be9a4aa9cb2 \
+    --hash=sha256:d209d8969599b27ad20994c8e41936ee0964e6da07478d6c35016bc386b66ad4 \
+    --hash=sha256:d5241e0a80d808d70546c697135da2c613f30e28251ff8307eb72ba696945764 \
+    --hash=sha256:edd8b5fe47dab091176d21bb6de568acdd906d1887a4584a15a9a96a1dca06ef \
+    --hash=sha256:f870204a840a60da0b12273ef34f7051e98c3b5961b61b0c2c1be6dfd64fbcd3 \
+    --hash=sha256:ffa75af20b44f8dba823498024771d5ac50620e6915abac414251bd971b4529f
+pandas==2.2.1 ; python_version >= "3.10" and python_version < "4.0" \
+    --hash=sha256:04f6ec3baec203c13e3f8b139fb0f9f86cd8c0b94603ae3ae8ce9a422e9f5bee \
+    --hash=sha256:06cf591dbaefb6da9de8472535b185cba556d0ce2e6ed28e21d919704fef1a9e \
+    --hash=sha256:0ab90f87093c13f3e8fa45b48ba9f39181046e8f3317d3aadb2fffbb1b978572 \
+    --hash=sha256:0f573ab277252ed9aaf38240f3b54cfc90fff8e5cab70411ee1d03f5d51f3944 \
+    --hash=sha256:101d0eb9c5361aa0146f500773395a03839a5e6ecde4d4b6ced88b7e5a1a6403 \
+    --hash=sha256:11940e9e3056576ac3244baef2fedade891977bcc1cb7e5cc8f8cc7d603edc89 \
+    --hash=sha256:1ba21b1d5c0e43416218db63037dbe1a01fc101dc6e6024bcad08123e48004ab \
+    --hash=sha256:4aa1d8707812a658debf03824016bf5ea0d516afdea29b7dc14cf687bc4d4ec6 \
+    --hash=sha256:4acf681325ee1c7f950d058b05a820441075b0dd9a2adf5c4835b9bc056bf4fb \
+    --hash=sha256:53680dc9b2519cbf609c62db3ed7c0b499077c7fefda564e330286e619ff0dd9 \
+    --hash=sha256:739cc70eaf17d57608639e74d63387b0d8594ce02f69e7a0b046f117974b3019 \
+    --hash=sha256:76f27a809cda87e07f192f001d11adc2b930e93a2b0c4a236fde5429527423be \
+    --hash=sha256:7d2ed41c319c9fb4fd454fe25372028dfa417aacb9790f68171b2e3f06eae8cd \
+    --hash=sha256:88ecb5c01bb9ca927ebc4098136038519aa5d66b44671861ffab754cae75102c \
+    --hash=sha256:8df8612be9cd1c7797c93e1c5df861b2ddda0b48b08f2c3eaa0702cf88fb5f88 \
+    --hash=sha256:94e714a1cca63e4f5939cdce5f29ba8d415d85166be3441165edd427dc9f6bc0 \
+    --hash=sha256:9bd8a40f47080825af4317d0340c656744f2bfdb6819f818e6ba3cd24c0e1397 \
+    --hash=sha256:9d1265545f579edf3f8f0cb6f89f234f5e44ba725a34d86535b1a1d38decbccc \
+    --hash=sha256:a935a90a76c44fe170d01e90a3594beef9e9a6220021acfb26053d01426f7dc2 \
+    --hash=sha256:af5d3c00557d657c8773ef9ee702c61dd13b9d7426794c9dfeb1dc4a0bf0ebc7 \
+    --hash=sha256:c2ce852e1cf2509a69e98358e8458775f89599566ac3775e70419b98615f4b06 \
+    --hash=sha256:c38ce92cb22a4bea4e3929429aa1067a454dcc9c335799af93ba9be21b6beb51 \
+    --hash=sha256:c391f594aae2fd9f679d419e9a4d5ba4bce5bb13f6a989195656e7dc4b95c8f0 \
+    --hash=sha256:c70e00c2d894cb230e5c15e4b1e1e6b2b478e09cf27cc593a11ef955b9ecc81a \
+    --hash=sha256:df0c37ebd19e11d089ceba66eba59a168242fc6b7155cba4ffffa6eccdfb8f16 \
+    --hash=sha256:e97fbb5387c69209f134893abc788a6486dbf2f9e511070ca05eed4b930b1b02 \
+    --hash=sha256:f02a3a6c83df4026e55b63c1f06476c9aa3ed6af3d89b4f04ea656ccdaaaa359 \
+    --hash=sha256:f821213d48f4ab353d20ebc24e4faf94ba40d76680642fb7ce2ea31a3ad94f9b \
+    --hash=sha256:f9d3558d263073ed95e46f4650becff0c5e1ffe0fc3a015de3c79283dfbdb3df
+python-dateutil==2.8.2 ; python_version >= "3.10" and python_version < "4.0" \
+    --hash=sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86 \
+    --hash=sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9
+pytz==2024.1 ; python_version >= "3.10" and python_version < "4.0" \
+    --hash=sha256:2a29735ea9c18baf14b448846bde5a48030ed267578472d8955cd0e7443a9812 \
+    --hash=sha256:328171f4e3623139da4983451950b28e95ac706e13f3f2630a879749e7a8b319
+six==1.16.0 ; python_version >= "3.10" and python_version < "4.0" \
+    --hash=sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926 \
+    --hash=sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254
+tzdata==2024.1 ; python_version >= "3.10" and python_version < "4.0" \
+    --hash=sha256:2674120f8d891909751c38abcdfd386ac0a5a1127954fbc332af6b5ceae07efd \
+    --hash=sha256:9068bc196136463f5245e51efda838afa15aaeca9903f49050dfa2679db4d252