Bump version to v0.3.1 for release

ivanwilliammd · Apr 6, 2024 · 1df1b3a · 1df1b3a
1 parent 9593bd5
commit 1df1b3a
Show file tree

Hide file tree

Showing 13 changed files with 101 additions and 22,804 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## Unreleased
 
+## [v0.3.1](https://github.com/ivanwilliammd/iderare-pheno/releases/tag/v0.3.1) - 2024-04-07
+- Fixing of utils list2tsv function
+- Fix relative path of the data folder
+
 ## [v0.3.0](https://github.com/ivanwilliammd/iderare-pheno/releases/tag/v0.3.0) - 2024-04-07
 - Join the similarity and recommendation class to share the same Ontology data from [hpo3 library](https://github.com/anergictcell/hpo3)
 - Refactor the utils.py to be more readable and maintainable

diff --git a/Playbook.ipynb b/Playbook.ipynb
diff --git a/README.md b/README.md
@@ -86,7 +86,9 @@ pip install -e .
 ## Usage
 
 ```python
-from iderare_pheno import iderare_pheno
+from iderare_pheno.converter import term2omim, term2orpha, term2hpo, batchconvert
+from iderare_pheno.simrec import hpo2omim_similarity, omim_recommendation, hpo2name
+from iderare_pheno.utils import linkage_dendrogram, list2tsv
 ```
 
 ## Team

diff --git a/iderare_pheno/converter.py b/iderare_pheno/converter.py
@@ -1,15 +1,16 @@
+import os
 import pandas as pd
 
 # Declare the folder path for phenotype data source
-phenotype_folder = "phenotype/subset"
+phenotype_folder = os.path.dirname(__file__)
 
 # Declare database useds for mapping
-icd10omim = "icd102omim_subset.tsv"
-loinc2hpo = "loinc2hpo_standardized.tsv"
-orpha2omim = "orpha2omim_subset.tsv"
-omim2hpo = "omim2hpo_subset.tsv"
-snomed2hpo = "snomed2hpo_subset.tsv"
-snomed2orpha = "snomed2orpha_subset.tsv"
+icd10omim = os.path.join(phenotype_folder, "phenotype", "subset", "icd102omim_subset.tsv")
+loinc2hpo = os.path.join(phenotype_folder, "phenotype", "subset", "loinc2hpo_standardized.tsv")
+orpha2omim = os.path.join(phenotype_folder, "phenotype", "subset", "orpha2omim_subset.tsv")
+omim2hpo = os.path.join(phenotype_folder, "phenotype", "subset", "omim2hpo_subset.tsv")
+snomed2hpo = os.path.join(phenotype_folder, "phenotype", "subset", "snomed2hpo_subset.tsv")
+snomed2orpha = os.path.join(phenotype_folder, "phenotype", "subset", "snomed2orpha_subset.tsv")
 
 # iderare yaml configuration file
 yaml_file = "iderare.yaml"
@@ -18,12 +19,12 @@
 clinical_data = "clinical_data.txt"
 
 # Read the clinical data and parse the data
-icd10omim_df = pd.read_csv(phenotype_folder + "/" + icd10omim, sep="\t")
-loinc2hpo_df = pd.read_csv(phenotype_folder + "/" + loinc2hpo, sep="\t")
-orpha2omim_df = pd.read_csv(phenotype_folder + "/" + orpha2omim, sep="\t")
-omim2hpo_df = pd.read_csv(phenotype_folder + "/" + omim2hpo, sep="\t")
-snomed2hpo_df = pd.read_csv(phenotype_folder + "/" + snomed2hpo, sep="\t")
-snomed2orpha_df = pd.read_csv(phenotype_folder + "/" + snomed2orpha, sep="\t")
+icd10omim_df = pd.read_csv(icd10omim, sep="\t")
+loinc2hpo_df = pd.read_csv(loinc2hpo, sep="\t")
+orpha2omim_df = pd.read_csv(orpha2omim, sep="\t")
+omim2hpo_df = pd.read_csv(omim2hpo, sep="\t")
+snomed2hpo_df = pd.read_csv(snomed2hpo, sep="\t")
+snomed2orpha_df = pd.read_csv(snomed2orpha, sep="\t")
 
 
 # Convert SNOMED to ORPHA First

diff --git a/...ype/rawdl_20240310/genes_to_phenotype.txt → ...eno/phenotype/data/genes_to_phenotype.txt b/...ype/rawdl_20240310/genes_to_phenotype.txt → ...eno/phenotype/data/genes_to_phenotype.txt
diff --git a/...are_pheno/phenotype/rawdl_20240310/hp.obo → iderare_pheno/phenotype/data/hp.obo b/...are_pheno/phenotype/rawdl_20240310/hp.obo → iderare_pheno/phenotype/data/hp.obo
diff --git a/...o/phenotype/rawdl_20240310/phenotype.hpoa → iderare_pheno/phenotype/data/phenotype.hpoa b/...o/phenotype/rawdl_20240310/phenotype.hpoa → iderare_pheno/phenotype/data/phenotype.hpoa
diff --git a/iderare_pheno/phenotype/rawdl_20240310/ORDO.csv b/iderare_pheno/phenotype/rawdl_20240310/ORDO.csv
diff --git a/iderare_pheno/phenotype/rawdl_20240310/loinc2hpo-annotations.tsv b/iderare_pheno/phenotype/rawdl_20240310/loinc2hpo-annotations.tsv
diff --git a/iderare_pheno/simrec.py b/iderare_pheno/simrec.py
@@ -1,6 +1,7 @@
+import os
 from pyhpo import HPOSet, Omim, Ontology, stats
 
-Ontology("phenotype/rawdl_20240310")
+Ontology(os.path.join(os.path.dirname(__file__), "phenotype", "data"))
 
 
 # Convert OMIM code to OMIM Class Object

diff --git a/iderare_pheno/utils.py b/iderare_pheno/utils.py
@@ -19,7 +19,7 @@ def list2tsv(
         rank = [i + 1 for i in range(len(name))]
         data = {"rank": rank, "id": term_id, "name": name, "score": sim_score}
     df = pd.DataFrame(data)
-    df.to_csv("output/{}.tsv".format(filename), index=False, sep="\t")
+    df.to_csv("{}.tsv".format(filename), index=False, sep="\t")
     return df
 
 

diff --git a/iderare_pheno/version.py b/iderare_pheno/version.py
@@ -2,7 +2,7 @@
 _MINOR = "3"
 # On main and in a nightly release the patch should be one ahead of the last
 # released build.
-_PATCH = "0"
+_PATCH = "1"
 # This is mainly for nightly builds which have the suffix ".dev$DATE". See
 # https://semver.org/#is-v123-a-semantic-version for the semantics.
 _SUFFIX = ""

diff --git a/pyproject.toml b/pyproject.toml
@@ -67,7 +67,6 @@ exclude = [
     "docs*",
     "scripts*"
 ]
-include = ["iderare_pheno", "phenotype", "phenotype.*"]
 
 [tool.setuptools]
 include-package-data = true