Merge pull request #4 from bbglab/dev/MANE_implementation

Adapt BoostDM pipeline to accept MANE transcript

Author: FedericaBrando

.gitignore

@@ -0,0 +1,201 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python
+
+# vscode
+.vscode/**
+!.vscode/launch.json
+
+# nextflow
+work/
+
+## nextflow hidden files
+.nextflow
+.nextflow.log*
+
+## nextflow output
+trace*
+timeline*
+report*
+
+
+# old file
+*_old*
+_trash
+
+# test directory
+tests/output
+database

.vscode/launch.json

@@ -0,0 +1,45 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "CreateDatasets",
+            "type": "python",
+            "request": "launch",
+            "program": "${workspaceFolder}/containers_build/boostdm/annotations/cohort.py",
+            "console": "integratedTerminal",
+            "justMyCode": true,
+            "cwd": "${workspaceFolder}/tests/output",
+            "env": {
+                "GENOME_BUILD": "hg38",
+                "INTOGEN_DATASETS": "/workspace/datasets/intogen/runs/v2024/20240409_ALL/",
+                "BOOSTDM_DIR": "/workspace/datasets/boostdm_runs/boostdm-cancer-output-2023",
+                "BOOSTDM_DATASETS": "/workspace/projects/intogen_plus/fixdatasets-20230223/containers/datasets_24/boostdm"
+            },
+            "args": [
+                "--cohort",
+                "TCGA_WXS_BRCA",
+                "--dndscv-path",
+                "/workspace/datasets/intogen/runs/v2024/20240409_ALL/steps/dndscv/TCGA_WXS_BRCA.dndscv.tsv.gz",
+                "--dndscv-annotmuts-path",
+                "/workspace/datasets/intogen/runs/v2024/20240409_ALL/steps/dndscv/TCGA_WXS_BRCA.dndscv_annotmuts.tsv.gz",
+                "--mutrate-path", 
+                "/workspace/datasets/intogen/runs/v2024/20240409_ALL/steps/boostDM/mutrate/TCGA_WXS_BRCA.mutrate.json",
+                "--clustl-group-path",
+                "/workspace/datasets/boostdm_runs/boostdm-cancer-output-2023/output_20230710/features_group/clustl.tsv.gz",
+                "--hotmaps-group-path",
+                "/workspace/datasets/boostdm_runs/boostdm-cancer-output-2023/output_20230710/features_group/hotmaps.tsv.gz",
+                "--smregions-group-path", 
+                "/workspace/datasets/boostdm_runs/boostdm-cancer-output-2023/output_20230710/features_group/smregions.tsv.gz",
+                "--splits",
+                "50", 
+                "--threshold",
+                "0.85",
+                "--out",
+                "TCGA_WXS_BRCA.regression_data.tsv"
+            ]
+        },
+    ]
+}

containers_build/boostdm/annotations/cohort.py

@@ -10,7 +10,7 @@
 
 from boostdm import BoostDMError
 from boostdm.annotations.utils import encode_consequence_type, rectify_synonymous, rectify_missense, rectify_splicing
-from boostdm.globals import CANONICAL_TRANSCRIPTS_FILE, MNVS_FILE, COHORTS_PATH, DRIVERS_PATH
+from boostdm.globals import MANE_TRANSCRIPTS_FILE, MNVS_FILE, COHORTS_PATH, DRIVERS_PATH
 from boostdm.oncotree import Oncotree
 from boostdm.features import phylop, consequence_type, aachange, exon, ptms, clustl, hotmaps, smregions, dndscv
 from boostdm.passengers import retrieve_exons, randomize
@@ -68,7 +68,7 @@ def retrieve_expectation(exp_dict, v):
 def set_string_chr(row):
     try:
         return str(int(row["chr"]))
-    except:
+    except ValueError:
         return str(row["chr"])
 
 
@@ -149,16 +149,16 @@ def mnvs_to_remove():
 
 def retrieve_transcript():
 
-    """Returns dataframe with canonical transcript regions"""
+    """Returns dataframe with mane transcript regions (cds + 25bp for splicing)"""
 
-    canonical_transcript_df = pd.read_csv(CANONICAL_TRANSCRIPTS_FILE,
+    mane_transcript_df = pd.read_csv(MANE_TRANSCRIPTS_FILE,
                          sep='\t', header=None, compression='gzip', low_memory=False, skiprows=1)
 
     # TODO: verify the columns we are selecting are the right ones
 
-    canonical_transcript_df = canonical_transcript_df[[0, 1, 2, 6]].copy()
-    canonical_transcript_df.columns = ['chr', 'start', 'end', 'gene']
-    return canonical_transcript_df
+    mane_transcript_df = mane_transcript_df[[0, 1, 2, 6]].copy()
+    mane_transcript_df.columns = ['chr', 'start', 'end', 'gene']
+    return mane_transcript_df
 
 
 def intersect_region_mutations(cds, pos):
@@ -228,8 +228,8 @@ def initialize_trainset(df, drivers):
 
 def build_positive_set(df_expect):
 
-    canonical_transcript = retrieve_transcript()
-    pos = intersect_region_mutations(canonical_transcript, df_expect)
+    mane_transcript = retrieve_transcript()
+    pos = intersect_region_mutations(mane_transcript, df_expect)
     pos['response'] = 1
     return pos
 

containers_build/boostdm/annotations/gene.py

@@ -27,7 +27,7 @@ def read_muts(path_data):
                          'Canonical': 'CANONICAL'}, inplace=True)
 
 
-    muts = muts[muts['CANONICAL'] == 'YES']
+    muts = muts[muts['MANE_SELECT'] != '-']
     if muts.shape[0] == 0:
         raise Exception('There are not mutations in the canonical transcript')
 

containers_build/boostdm/features/aachange.py

@@ -10,12 +10,12 @@
 def get_aachange(chr_, pos, alt, gene, reader):
 
     for data in reader.get(chr_, pos, pos):
-        alt_vep = (data[3] == alt)
-        canonical_vep = (data[-4] == 'YES')
-        correct_gene = (data[-7] == gene) # skip cases with antisense overlapping gene (gene is gene_symbol)
-        if alt_vep and canonical_vep and correct_gene:
-            aas = data[11]  # [11] -> amino-acids involved in change ("I/T")
-            aa_pos = data[10]  # [10] -> amino-acid position
+        alt_vep = (data['ALT'] == alt)
+        mane_vep = (data['MANE_SELECT'] != '-') # impose MANE transcript
+        correct_gene = (data['SYMBOL'] == gene) # skip cases with antisense overlapping gene (gene is gene_symbol)
+        if alt_vep and mane_vep and correct_gene:
+            aas = data['AA']  # [11] -> amino-acids involved in change ("I/T")
+            aa_pos = data['PROT_POS']  # [10] -> amino-acid position
             if '/' in aas:
                 aa_ref, aa_alt = tuple(aas.split('/'))
                 return aa_ref + aa_pos + aa_alt

containers_build/boostdm/features/consequence_type.py

@@ -9,11 +9,11 @@ def get_csqn_type(chr_, pos, alt, gene, reader):
 
     for data in reader.get(chr_, pos, pos):
 
-        alt_vep = (data[3] == alt)           # same alternate allele
-        canonical_vep = (data[-4] == 'YES')  # impose canonical transcript
-        correct_gene = (data[-7] == gene)    # skip cases with antisense overlapping genes
-        if alt_vep and canonical_vep and correct_gene:
-            csqn = CONSEQUENCES_LIST[min([CONSEQUENCES_DICT[c] for c in data[7].split(',')])]
+        alt_vep = (data['ALT'] == alt)           # same alternate allele
+        mane_vep = (data["MANE_SELECT"] != '-')  # impose mane transcript
+        correct_gene = (data["SYMBOL"] == gene)    # skip cases with antisense overlapping genes
+        if alt_vep and mane_vep and correct_gene:
+            csqn = CONSEQUENCES_LIST[min([CONSEQUENCES_DICT[c] for c in data["CNSQ"].split(',')])]
             return AGGREGATION_DICT.get(csqn, None)
 
     return None

containers_build/boostdm/features/exon.py

@@ -26,11 +26,11 @@ def nmd_rule(exon, total_exons):
 def get_exon(chr_, pos, alt,gene, reader):
 
     for data in reader.get(chr_, pos, pos):
-        alt_vep = (data[3] == alt)
-        canonical_vep = (data[-4] == 'YES')
-        correct_gene = (data[-7] == gene)  # skip cases with antisense overlapping gene
-        if alt_vep and canonical_vep and correct_gene:
-            exons = data[-2]
+        alt_vep = (data["ALT"] == alt)
+        mane_vep = (data["MANE_SELECT"] != '-') # impose mane transcript
+        correct_gene = (data["SYMBOL"] == gene)  # skip cases with antisense overlapping gene
+        if alt_vep and mane_vep and correct_gene:
+            exons = data["EXON"]
             if '/' in exons:
                 exon, total_exons = tuple(exons.split('/'))
             else: