Merge branch 'develop' into 'master'

Beta release v1.1.0b1

See merge request tron/addannot!231

.gitlab-ci.yml

@@ -67,4 +67,5 @@ publish_package:
     - python3 setup.py sdist bdist_wheel
     - TWINE_PASSWORD=${CI_JOB_TOKEN} TWINE_USERNAME=gitlab-ci-token python -m twine upload --repository-url https://gitlab.rlp.net/api/v4/projects/${CI_PROJECT_ID}/packages/pypi dist/*
   only:
+    # deploys in private gitlab package repository only the develop branch, the master branch is published in PyPI
     - develop

docs/source/02_installation.md

@@ -219,7 +219,7 @@ The test data can be downloaded here:
 * [test_patients.tsv](_static/test_patients.tsv)
 
 ````commandline
-neofox --candidate-file /path/to/test_data.txt --patient-data /path/to/test_patients.txt --output-folder  /path/to/outputfolder --with-table --with-json --output-prefix test
+neofox --input-file /path/to/test_data.txt --patient-data /path/to/test_patients.txt --output-folder  /path/to/outputfolder --output-prefix test
 ````
 
 The resulting output files can be compared to the following test output files:

docs/source/03_03_usage.md

@@ -15,7 +15,7 @@ neofox --input-file neoantigens_candidates.tsv \
     [--output-prefix out_prefix]  \
     [--organism human|mouse]  \
     [--rank-mhci-threshold 2.0] \
-    [--rank-mhcii-threshold 4.0] \
+    [--rank-mhcii-threshold 5.0] \
     [--num-cpus] \
     [--config] \
     [--patient-id] \
@@ -41,7 +41,7 @@ where:
 - if all expression values related to a patient are NA or `rnaExpression` is not given in the input file but the tumor type has been provided in the patient file, imputated expression will be used for the relevant features
 
 **EXAMPLE**  
-This is an example to call NeoFox with a candidate-file and obtaining the annotated neoantigen candidates in [tabular](03_02_output_data.md#tabular-format) format:  
+This is an example to call NeoFox with a candidate file and obtaining the annotated neoantigen candidates in [tabular](03_02_output_data.md#tabular-format) format:
 
 ````commandline
 neofox --input-file neoantigens_candidates.tsv \
@@ -287,7 +287,7 @@ patients_json = ModelConverter.objects2json(model_objects=patients)
 ```
 
 - instead of creating neoantigen or patient models, tabular or json files containing this information can be passed:  
-  The neoantigen candidates can be provided in [candidate-file format](03_01_input_data.md#tabular-file-format)
+  The neoantigen candidates can be provided in [candidate file format](03_01_input_data.md#tabular-file-format)
 
 ```python
 model_file = "/path/to/neoantigen_candidates.tab"

docs/source/05_models.md

@@ -195,7 +195,6 @@ The metadata required for analysis for a given patient + its patient identifier
 | Field | Type | Label | Description |
 | ----- | ---- | ----- | ----------- |
 | identifier | [string](#string) |  | Patient identifier |
-| isRnaAvailable | [bool](#bool) |  | Is RNA expression available? |
 | tumorType | [string](#string) |  | Tumor entity in TCGA study abbrevation style as described here: https://gdc.cancer.gov/resources-tcga-users/tcga-code-tables/tcga-study-abbreviations |
 | mhc1 | [Mhc1](#neoantigen.Mhc1) | repeated | MHC I classic molecules |
 | mhc2 | [Mhc2](#neoantigen.Mhc2) | repeated | MHC II classic molecules |

neofox/__init__.py

@@ -18,8 +18,7 @@
 # along with this program. If not, see <http://www.gnu.org/licenses/>.#
 
 
-VERSION = "1.0.2"
-
+VERSION = "1.1.0b1"
 
 REFERENCE_FOLDER_ENV = "NEOFOX_REFERENCE_FOLDER"
 NEOFOX_BLASTP_ENV = "NEOFOX_BLASTP"

neofox/annotator/abstract_annotator.py

@@ -53,7 +53,7 @@ def __init__(
         self.priority_score_calculator = PriorityScore()
         self.iedb_immunogenicity = IEDBimmunogenicity()
         self.amplitude = Amplitude()
-        self.hex = Hex(runner=self.runner, configuration=configuration, references=references)
+        self.hex = Hex(references=references)
 
     def get_additional_annotations_neoepitope_mhci(
             self, epitope: PredictedEpitope, neoantigen: Neoantigen = None) -> PredictedEpitope:

neofox/command_line.py

@@ -213,16 +213,6 @@ def _read_data(input_file, patients_data, mhc_database: MhcDatabase) -> Tuple[Li
     else:
         raise ValueError('Not supported input file extension: {}'.format(input_file))
 
-    patients_dict : Dict[str, Patient]
-    patients_dict = {p.identifier: p for p in patients}
-
-    for n in neoantigens:
-        patient = patients_dict.get(n.patient_identifier)
-        if not patient.is_rna_available:
-            # removes RNA vaf if indicated in patient that this information is no good
-            # iCam legacy
-            n.rna_variant_allele_frequency = None
-
     return neoantigens, patients
 
 
@@ -386,16 +376,6 @@ def _read_data_epitopes(
     else:
         raise ValueError('Not supported input file extension: {}'.format(input_file))
 
-    patients_dict : Dict[str, Patient]
-    patients_dict = {p.identifier: p for p in patients}
-
-    for n in neoepitopes:
-        patient = patients_dict.get(n.patient_identifier)
-        if patient is not None and not patient.is_rna_available:
-            # removes RNA vaf if indicated in patient that this information is no good
-            # iCam legacy
-            n.rna_variant_allele_frequency = None
-
     return neoepitopes, patients
 
 

neofox/model/conversion.py

@@ -111,7 +111,6 @@ def parse_patients_file(patients_file: str, mhc_database: MhcDatabase) -> List[P
             patient_dict = row.to_dict()
             patient = PatientFactory.build_patient(
                 identifier=patient_dict.get("identifier"),
-                is_rna_available=patient_dict.get("isRnaAvailable", False),
                 tumor_type=patient_dict.get("tumorType"),
                 mhc_alleles=patient_dict.get("mhcIAlleles", []),
                 mhc2_alleles=patient_dict.get("mhcIIAlleles", []),

neofox/model/factories.py

@@ -173,11 +173,10 @@ def build_neoepitope(mutated_peptide=None, wild_type_peptide=None, patient_ident
 
 class PatientFactory(object):
     @staticmethod
-    def build_patient(identifier, is_rna_available=False, tumor_type=None, mhc_alleles: List[str] = [],
+    def build_patient(identifier, tumor_type=None, mhc_alleles: List[str] = [],
                       mhc2_alleles: List[str] = [], mhc_database: MhcDatabase =None):
         patient = Patient(
             identifier=identifier,
-            is_rna_available=is_rna_available,
             tumor_type=tumor_type,
             mhc1=MhcFactory.build_mhc1_alleles(mhc_alleles, mhc_database),
             mhc2=MhcFactory.build_mhc2_alleles(mhc2_alleles, mhc_database)

neofox/model/models.md

@@ -195,7 +195,6 @@ The metadata required for analysis for a given patient + its patient identifier
 | Field | Type | Label | Description |
 | ----- | ---- | ----- | ----------- |
 | identifier | [string](#string) |  | Patient identifier |
-| isRnaAvailable | [bool](#bool) |  | Is RNA expression available? |
 | tumorType | [string](#string) |  | Tumor entity in TCGA study abbrevation style as described here: https://gdc.cancer.gov/resources-tcga-users/tcga-code-tables/tcga-study-abbreviations |
 | mhc1 | [Mhc1](#neoantigen.Mhc1) | repeated | MHC I classic molecules |
 | mhc2 | [Mhc2](#neoantigen.Mhc2) | repeated | MHC II classic molecules |

neofox/model/neoantigen.proto

@@ -78,21 +78,17 @@ message Patient {
 	*/
 	string identifier = 1;
 	/**
-	Is RNA expression available?
-	*/
-	bool isRnaAvailable = 2;
-	/**
 	Tumor entity in TCGA study abbrevation style as described here: https://gdc.cancer.gov/resources-tcga-users/tcga-code-tables/tcga-study-abbreviations
 	*/
-	string tumorType = 3;
+	string tumorType = 2;
 	/**
 	MHC I classic molecules
 	*/
-	repeated Mhc1 mhc1 = 4;
+	repeated Mhc1 mhc1 = 3;
 	/**
 	MHC II classic molecules
 	*/
-	repeated Mhc2 mhc2 = 5;
+	repeated Mhc2 mhc2 = 4;
 }
 
 /**

neofox/neofox.py

@@ -110,10 +110,6 @@ def __init__(
         for neoantigen in self.neoantigens:
             expression_per_patient[neoantigen.patient_identifier].append(neoantigen.rna_expression)
 
-        for patient in self.patients:
-            self.patients[patient].is_rna_available = all(e is not None for e in
-                                                          expression_per_patient[self.patients[patient].identifier])
-
         # only performs the expression imputation for humans
         if self.reference_folder.organism == ORGANISM_HOMO_SAPIENS:
             # impute expresssion from TCGA, ONLY if isRNAavailable = False for given patient,
@@ -137,7 +133,7 @@ def _conditional_expression_imputation(self) -> List[Neoantigen]:
             gene_expression = expression_annotator.get_gene_expression_annotation(
                 gene_name=neoantigen.gene, tcga_cohort=patient.tumor_type
             )
-            if not patient.is_rna_available and patient.tumor_type is not None and patient.tumor_type != "":
+            if expression_value is None and patient.tumor_type is not None and patient.tumor_type != "":
                 expression_value = gene_expression
             neoantigen_transformed.rna_expression = expression_value
             neoantigen.imputed_gene_expression = gene_expression

neofox/neofox_epitope.py

@@ -211,8 +211,6 @@ def _conditional_expression_imputation(self) -> List[PredictedEpitope]:
                 neoepitope_transformed = neoepitope
                 gene_expression = expression_annotator.get_gene_expression_annotation(
                     gene_name=neoepitope.gene, tcga_cohort=patient.tumor_type)
-                if not patient.is_rna_available and patient.tumor_type is not None and patient.tumor_type != "":
-                    neoepitope_transformed.rna_expression = gene_expression
                 neoepitope.imputed_gene_expression = gene_expression
                 neoepitopes_transformed.append(neoepitope_transformed)
             else: