fix: changes the column headers in the phenotype.hpoa file, migrates …

.github/workflows/pythonpackage.yml

@@ -4,7 +4,6 @@ on: [push]
 
 jobs:
   build:
-
     runs-on: ubuntu-latest
     strategy:
       max-parallel: 4

Dockerfile

@@ -1,5 +1,5 @@
 # source image
-FROM python:3.7
+FROM python:3.9
 
 # set noninterative mode
 ENV DEBIAN_FRONTEND noninteractive

Pipfile

@@ -14,11 +14,9 @@ twine = "*"
 gensim = "<4.0"
 obonet = "*"
 fire = "*"
-lightgbm = "*"
 pandas = "*"
 numpy = "*"
 scipy = "*"
-joblib = "1.1.1"
 requests = "*"
 
 [requires]

README.md

@@ -4,7 +4,7 @@
 [![DOI](https://zenodo.org/badge/207335538.svg)](https://zenodo.org/badge/latestdoi/207335538)
 
 # phenopy
-`phenopy` is a Python package to perform phenotype similarity scoring by semantic similarity. `phenopy` is a
+`phenopy` is a Python (3.7) package to perform phenotype similarity scoring by semantic similarity. `phenopy` is a
 lightweight but highly optimized command line tool and library to efficiently perform semantic similarity scoring on
 generic entities with phenotype annotations from the [Human Phenotype Ontology (HPO)](https://hpo.jax.org/app/).
 
@@ -23,13 +23,6 @@ cd phenopy
 python setup.py install
 ```
 
-**To complete installation on macOS please install lightgbm using brew**
-```bash
-brew install lightgbm
-```
-
-or by following macOS installation instructions from [lightgbm documentation](https://lightgbm.readthedocs.io/en/latest/Installation-Guide.html#macos).
-
 ## Command Line Usage
 ### score
 `phenopy` is primarily used as a command line tool. An entity, as described here, is presented as a sample, gene, or
@@ -129,32 +122,6 @@ using `--output-file=/path/to/output_file.txt`
     phenopy score tests/data/test.score-short.txt  --summarization-method BMWA --threads 4
    ```
 
-### likelihood
-Phenopy can be used to predict the likelihood of a molecular diagnosis given an input set of HPO phenotypes. This functionality takes the same input records file as the `score` functionality. The likelhood command outputs a probability of finding a moleular diagnosis using a model trained on 46,674 probands primarily with the majority of them having a neurodevelopmental delay phenotype.
-
-To score a list of records with phenotypes:
-
-```bash
-phenopy likelihood tests/data/test.score-long.txt
-```
-
-If the `output_file` argument is not set, this command writes a file, `phenopy.likelihood_moldx.txt` to your current working directory. 
-Look at the predicted probabilities for the first five records:
-
-```bash
-$ head -5 phenopy.likelihood_moldx.txt
-```
-
-The columns are `record_id` and `probability_of_molecular_diagnosis`:
-
-```bash
-118200	0.34306641357469214
-118210	0.47593450032769
-118220	0.385742949333819
-118230	0.5833031588175435
-118300	0.5220058151734898
-```
-
 #### Parameters
 For a full list of command arguments use `phenopy [subcommand] --help`:
 ```bash
@@ -225,53 +192,6 @@ Output:
 0.11213185474495047
 ```
 
-### likelihood
-
-**Generate the hpo network and supporting objects**:
-
-```python
-import os
-from phenopy.build_hpo import generate_annotated_hpo_network
-from phenopy.util import read_phenotype_groups
-
-# data directory
-phenopy_data_directory = os.path.join(os.getenv('HOME'), '.phenopy/data')
-
-# files used in building the annotated HPO network
-obo_file = os.path.join(phenopy_data_directory, 'hp.obo')
-disease_to_phenotype_file = os.path.join(phenopy_data_directory, 'phenotype.hpoa')
-
-hpo_network, alt2prim, disease_records = \
-    generate_annotated_hpo_network(obo_file, disease_to_phenotype_file)
-```
-
-**Read the phenotype_groups file and the records file into a pandas DataFrame:**
-
-```python
-import pandas as pd
-
-phenotype_groups = read_phenotype_groups()
-
-df = pd.read_csv(
-    "tests/data/test.score-long.txt", 
-    sep="\t",
-    header=None,
-    names=["record_id", "info", "phenotypes"]
-)
-
-df["phenotypes"] = df["phenotypes"].apply(lambda row: row.split("|"))
-```
-
-**Predict probabilities from the phenotypes in the DataFrame:**
-
-```python
-from phenopy.likelihood import predict_likelihood_moldx
-
-probabilities = predict_likelihood_moldx(df["phenotypes"])
-print(probabilities[:5])
-[0.34306641 0.4759345  0.38574295 0.58330316 0.52200582]
-```
-
 ### miscellaneous
 
 The library can be used to prune parent phenotypes from the `phenotype.hpoa` and store pruned annotations as a file

phenopy/__init__.py

@@ -1,2 +1,2 @@
 __project__ = 'phenopy'
-__version__ = '0.5.2'
+__version__ = '0.5.4'

phenopy/__main__.py

@@ -1,14 +1,12 @@
 import fire
 import itertools
-import lightgbm as lgb
 import sys
 
 from configparser import NoOptionError, NoSectionError
 
 from phenopy.util import open_or_stdout
 from phenopy.build_hpo import generate_annotated_hpo_network
 from phenopy.config import config, logger
-from phenopy.likelihood import predict_likelihood_moldx
 from phenopy.score import Scorer
 from phenopy.util import parse_input, half_product
 from phenoseries.experiment import run_phenoseries_experiment
@@ -131,61 +129,10 @@ def validate_phenoseries(phenotypic_series_filepath, outdir=None, min_hpos=4, mi
         pairwise_mim_scores_file=pairwise_mim_scores_file,
         )
 
-def likelihood_moldx(input_file, output_file=None, k_phenotype_groups=1000):
-    """
-    :param input_file: The file path to a file containing three columns. [ID\tkey=value\thpodid,hpoid,hpoid]
-    :param output_file: The file path to an output file containing the predicted probabilities
-    :param k_phenotype_groups: The number of phenotype groups to use for encoding phenotypes. The CLI version of phenopy allows for one of [1000, 1500] 
-    """
-    try:
-        obo_file = config.get('hpo', 'obo_file')
-    except (NoSectionError, NoOptionError):
-        logger.critical(
-            'No HPO OBO file found in the configuration file. See "hpo:obo_file" parameter.')
-        sys.exit(1)
-    try:
-        disease_to_phenotype_file = config.get('hpo', 'disease_to_phenotype_file')
-    except (NoSectionError, NoOptionError):
-        logger.critical(
-            'No HPO annotated dataset file found in the configuration file.'
-            ' See "hpo:disease_to_phenotype_file" parameter.'
-        )
-        sys.exit(1)
-
-    logger.info(f'Loading HPO OBO file: {obo_file}')
-    hpo_network, alt2prim, _ = \
-        generate_annotated_hpo_network(obo_file,
-                                       disease_to_phenotype_file,
-                                       )
-
-    # parse input records
-    input_records = parse_input(input_file, hpo_network, alt2prim)
-    record_ids = [record["record_id"] for record in input_records]
-    phenotypes = [record["terms"] for record in input_records]
-
-    # predict likelihood of molecular diagnosis
-    positive_probabilities = predict_likelihood_moldx(
-        phenotypes,
-        phenotype_groups=None, 
-        hpo_network=hpo_network, 
-        alt2prim=alt2prim,
-        k_phenotype_groups=k_phenotype_groups,
-        )
-
-    if output_file is None:
-        output_file = "phenopy.likelihood_moldx.txt"
-    try:
-        with open(output_file, "w") as f:
-            for sample_id, probability in zip(record_ids, positive_probabilities):
-                f.write(f"{sample_id}\t{probability}\n")
-    except IOError:
-        sys.exit("Something went wrong writing the probabilities to file")
-
 
 def main():
     fire.Fire({
         'score': score,
-        'likelihood': likelihood_moldx,
         'validate-phenoseries': validate_phenoseries,
     })
 

phenopy/config.py

@@ -134,7 +134,6 @@ def download(url, file_path):
 
     config['models'] = {
         'phenopy.wv.model': w2v_vw_path,
-        'likelihood.model': lmd_data_path,
         }
     config['age'] = {
         'open_access_phenotype_age': os.path.join(

phenopy/d2p.py

@@ -18,28 +18,41 @@ def read_hpo_annotation_file(phenotype_annotations_file, hpo_network, logger=Non
     :return: records
     """
     try:
-        with open(phenotype_annotations_file, 'r') as tsv_fh:
+        with open(phenotype_annotations_file, "r") as tsv_fh:
             [next(tsv_fh) for _ in range(4)]
             reader = csv.DictReader(tsv_fh, delimiter='\t')
             # this removes the leading hash
-            reader.fieldnames[0] = 'DatabaseID'
+            reader.fieldnames[0] = reader.fieldnames[0].lstrip("#")
 
             records = []
 
             for row in reader:
                 # phenotype term id
-                term_id = row['HPO_ID']
+                term_id = row.get("HPO_ID") if "HPO_ID" in row else row.get("hpo_id")
                 if term_id not in hpo_network.nodes():
                     continue
                 # parse disease id, currently only supports omim entries
-                db, disease_accession = row['DatabaseID'].split(':')
-                if db not in ['OMIM']:
+                database_id = (
+                    row.get("DatabaseID")
+                    if "DatabaseID" in row
+                    else row.get("database_id")
+                )
+                db, disease_accession = database_id.split(":")
+                if db not in ["OMIM"]:
                     continue
                 # For now, skip negative phenotype annotations
-                if row['Qualifier'] == 'NOT':
+                qualifier = (
+                    row.get("Qualifier") if "Qualifier" in row else row.get("qualifier")
+                )
+                if qualifier == "NOT":
                     continue
 
-                records.append((term_id, disease_accession, frequency_converter(row['Frequency'])))
+                frequency = (
+                    row.get("Frequency") if "Frequency" in row else row.get("frequency")
+                )
+                records.append(
+                    (term_id, disease_accession, frequency_converter(frequency))
+                )
 
         return records
 

phenopy/util.py

@@ -1,5 +1,4 @@
 import csv
-import os
 import sys
 import networkx as nx
 import pandas as pd
@@ -45,10 +44,16 @@ def export_phenotype_hpoa_with_no_parents(phenotype_hpoa_file, phenotype_hpoa_no
         exit(1)
 
     no_parents_df = df.copy()
-    for gene, annotations in df.groupby('#DatabaseID'):
-        termlist = [node for node in annotations['HPO_ID'].tolist() if node in hpo_network.nodes()]
+    # Establish the proper column headers (different for various versions)
+    database_id = "#DatabaseID" if "#DatabaseID" in df.columns else "database_id"
+    hpo_id = "HPO_ID" if "HPO_ID" in df.columns else "hpo_id"
+
+    for gene, annotations in df.groupby(database_id):
+        termlist = [
+            node for node in annotations[hpo_id].tolist() if node in hpo_network.nodes()
+        ]
         termlist = remove_parents(termlist, hpo_network)
-        parent_idx = annotations.loc[~annotations['HPO_ID'].isin(termlist)].index
+        parent_idx = annotations.loc[~annotations[hpo_id].isin(termlist)].index
         no_parents_df.drop(parent_idx, inplace=True)
 
     try:

setup.py

@@ -14,7 +14,7 @@
     description='Phenotype comparison scoring by semantic similarity.',
     long_description=long_description,
     long_description_content_type='text/markdown',
-    author='Kevin Arvai <karvai@genedx.com>, Kyle Retterer <retterer@genedx.com>, Carlos Borroto <cborroto@genedx.com>, Vlad Gainullin <vgainullin@genedx.com>, Vincent Ustach <vustach@genedx.com>',
+    author='Kevin Arvai <karvai@genedx.com>, Kyle Retterer <retterer@genedx.com>, Carlos Borroto <cborroto@genedx.com>, Vlad Gainullin <vgainullin@genedx.com>, Vincent Ustach <vustach@genedx.com>, Stephen McGee <smcgee@genedx.com',
     author_email='<datascience@genedx.com>',
     license='',
     entry_points={
@@ -24,15 +24,13 @@
     },
     include_package_data=True,
     install_requires=[
-        'fire',
-        'gensim<4.0 ',
-        'networkx',
-        'numpy',
+        'fire==0.5.0',
+        'gensim<4.0',
+        'networkx==2.6.3',
+        'numpy==1.21.6',
         'obonet',
-        'pandas',
-        'joblib',
-        'scipy',
-        'lightgbm',
-        'requests',
+        'pandas==1.3.5',
+        'scipy==1.7.3',
+        'requests==2.31.0',
     ]
 )