Merge branch 'develop' into 'master'

Release v1.2.0

See merge request tron/addannot!281

.github/workflows/release.yml

@@ -14,11 +14,12 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install setuptools wheel twine
+        pip install poetry==1.8.2 twine
     - name: Build and publish
       env:
         TWINE_USERNAME: __token__
         TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
       run: |
-        python setup.py sdist bdist_wheel
-        twine upload dist/*
+        poetry install
+        poetry build
+        twine upload dist/*.whl

.gitlab-ci.yml

@@ -18,7 +18,7 @@
 ## along with this program. If not, see <http://www.gnu.org/licenses/>.##
 
 # this image contains multiple Python interpreters
-image: python:3.8.14-buster
+image: python:3.11.9-bookworm
 
 # Change pip's cache directory to be inside the project directory since we can
 # only cache local items.
@@ -37,6 +37,7 @@ before_script:
   - apt-get update
   - apt-get --assume-yes install gcc gfortran build-essential wget libfreetype6-dev libpng-dev libopenblas-dev
   - python -V
+  - pip install poetry==1.8.2
 
 stages:
   - validation
@@ -48,7 +49,7 @@ check_version_changes:
   script:
     # if the version number does not change between this branch and develop it fails
     - git fetch origin develop
-    - if git diff origin/develop -- neofox/__init__.py | grep VERSION; then exit 0; else echo "Version needs to be increased!"; exit -1; fi
+    - if git diff origin/develop -- pyproject.toml | grep version; then exit 0; else echo "Version needs to be increased!"; exit -1; fi
   except:
     - develop
     - master
@@ -63,7 +64,8 @@ publish_package:
   stage: deploy
   script:
     - pip install twine
-    - python3 setup.py sdist bdist_wheel
+    - poetry install
+    - poetry build
     - 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

README.md

@@ -8,7 +8,7 @@
 
 NeoFox annotates neoantigen candidate sequences with published neoantigen features. 
 
-For a detailed documentation, please check out [https://neofox.readthedocs.io](https://neofox.readthedocs.io/)
+**For a detailed documentation, please check out [https://neofox.readthedocs.io](https://neofox.readthedocs.io/)**
 
 If you use NeoFox, please cite the following publication:  
 Franziska Lang, Pablo Riesgo-Ferreiro, Martin Löwer, Ugur Sahin, Barbara Schrörs, **NeoFox: annotating neoantigen candidates with neoantigen features**, Bioinformatics, Volume 37, Issue 22, 15 November 2021, Pages 4246–4247, https://doi.org/10.1093/bioinformatics/btab344   
@@ -28,7 +28,7 @@ NeoFox covers the following neoantigen features and prediction algorithms:
 | Name                                                    | Reference                                                                | DOI                                                                                       |
 |---------------------------------------------------------|--------------------------------------------------------------------------|-------------------------------------------------------------------------------------------|
 | MHC I binding affinity/rank score (netMHCpan-v4.1)      | Reynisson et al, 2020, Nucleic Acids Research                             | https://doi.org/10.4049/jimmunol.1700893                                                  |
-| MHC II binding affinity/rank score (netMHCIIpan-v4.0)   | Reynisson et al, 2020, Nucleic Acids Research                                           | https://doi.org/10.1111/imm.12889                                                         |
+| MHC II binding affinity/rank score (netMHCIIpan-v4.3)   | Nilsson et al, 2023, Science Adv.                                           | https://doi.org/10.1126/sciadv.adj6367                                                         |
 | MixMHCpred score v2.2  §                              | Bassani-Sternberg et al., 2017, PLoS Comp Bio; Gfeller, 2018, J Immunol. | https://doi.org/10.1371/journal.pcbi.1005725 ,   https://doi.org/10.4049/jimmunol.1800914 |
 | MixMHC2pred score v2.0.2  §                              | Racle et al, 2019, Nat. Biotech. 2019                                    | https://doi.org/10.1038/s41587-019-0289-6                                                 |
 | Differential Agretopicity Index (DAI)                   | Duan et al, 2014, JEM; Ghorani et al., 2018, Ann Oncol.                  | https://doi.org/10.1084/jem.20141308                                                      |
@@ -41,7 +41,6 @@ NeoFox covers the following neoantigen features and prediction algorithms:
 | Recognition potential   §                                | Łuksza et al, 2017, Nature; Balachandran et al, 2017, Nature             | https://doi.org/10.1038/nature24473 , https://doi.org/10.1038/nature24462                 |
 | Vaxrank                                                 | Rubinsteyn, 2017, Front Immunol                                          | https://doi.org/10.3389/fimmu.2017.01807                                                  |
 | Priority score                                          | Bjerregaard et al, 2017, Cancer Immunol Immunother.                      | https://doi.org/10.1007/s00262-017-2001-3                                                 |
-| Tcell predictor                                         | Besser et al, 2019, Journal for ImmunoTherapy of Cancer                  | https://doi.org/10.1186/s40425-019-0595-z                                                 |
 | PRIME  §                                                 | Schmidt et al., 2021, Cell Reports Medicine                            | https://doi.org/10.1016/j.xcrm.2021.100194                                             |
 | HEX §                                                   | Chiaro et al., 2021, Cancer Immunology Research                            | https://doi.org/10.1158/2326-6066.CIR-20-0814                                             |
 
@@ -52,10 +51,9 @@ NeoFox covers the following neoantigen features and prediction algorithms:
 NeoFox depends on the following tools:  
 
 - Python >=3.7, <=3.8
-- R 3.6.0
 - BLAST 2.10.1
 - netMHCpan 4.1
-- netMHCIIpan 4.0
+- netMHCIIpan 4.3
 - MixMHCpred 2.2 (optional)
 - MixMHC2pred 2.0.2 (optional)
 - PRIME 2.0 (optional)
@@ -76,30 +74,41 @@ conda install bioconda::neofox
 NeoFox can be used from the command line as shown below or programmatically (see [https://neofox.readthedocs.io](https://neofox.readthedocs.io/) for more information).
 
 ````commandline
-neofox --candidate-file/--json-file neoantigens_candidates.tab/neoantigens_candidates.json --patient-data/--patient-data-json patient_data.txt/patient_data.json --output-folder /path/to/out --output-prefix out_prefix [--patient-id] [--with-table] [--with-json] [--num-cpus] [--affinity-threshold]
+neofox --input-file neoantigens_candidates.tsv \
+    --patient-data patient_data.txt \
+    --output-folder /path/to/out \
+    [--output-prefix out_prefix]  \
+    [--organism human|mouse]  \
+    [--rank-mhci-threshold 2.0] \
+    [--rank-mhcii-threshold 5.0] \
+    [--num-cpus] \
+    [--config] \
+    [--patient-id] \
+    [--with-all-neoepitopes] \
+    [--verbose]
 ````
-- `--candidate-file`: tab-separated values table with neoantigen candidates represented by long mutated peptide sequences as described [here](#41-neoantigen-candidates-in-tabular-format)
-- `--json-file`: JSON file neoantigens in NeoFox model format as  described [here](#42-neoantigen-candidates-in-json-format)
-- `--patient-id`: patient identifier (*optional*, this will be used if the column `patientIdentifier` is missing in the candidate input file)
-- `--patient-data`: a table of tab separated values containing metadata on the patient as  described [here](#43-patient-data-format)
+- `--input-file`: tab-separated values table with neoantigen candidates represented by long mutated peptide sequences 
+ as described [here](03_01_input_data.md#tabular-file-format) (extensions .txt and .tsv) or JSON file neoantigens in 
+ NeoFox model format as  described [here](03_01_input_data.md#json-file-format) (extension .json)
+- `--patient-data`: a table of tab separated values containing metadata on the patient as  described [here](03_01_input_data.md#file-with-patient-information)
 - `--output-folder`: path to the folder to which the output files should be written 
 - `--output-prefix`: prefix for the output files (*optional*)
-- `--with-table`: output file in tab-separated format (*default*)
-- `--with-json`: output file in JSON format (*optional*)
+- `--with-all-neoepitopes`: output annotations for all MHC-I and MHC-II neoepitopes on all HLA alleles (*optional*)
+- `--rank-mhci-threshold`: MHC-I epitopes with a netMHCpan predicted rank greater than or equal than this threshold will be filtered out (*optional*)
+- `--rank-mhcii-threshold`: MHC-II epitopes with a netMHCIIpan predicted rank greater than or equal than this threshold will be filtered out (*optional*)
+- `--organism`: the organism to which the data corresponds. Possible values: [human, mouse]. Default value: human
 - `--num-cpus`: number of CPUs to use (*optional*)
 - `--config`: a config file with the paths to dependencies as shown below  (*optional*)
-- `--organism`: the organism to which the data corresponds. Possible values: [human, mouse]. Default value: human
-- `--affinity-threshold`: a affinity value (*optional*) neoantigen candidates with a best predicted affinity greater than or equal than this threshold will be not annotated with features that specifically model
-                        neoepitope recognition. A threshold that is commonly used is 500 nM. 
+- `--patient-id`: patient identifier (*optional*, this is only relevant if the column `patientIdentifier` is missing in the candidate input file)
+- `--verbose`: get detailed logs
 
 
 The optional config file with the paths to the dependencies can look like this:  
 ````commandline
 NEOFOX_REFERENCE_FOLDER=path/to/reference/folder
-NEOFOX_RSCRIPT=`which Rscript`
 NEOFOX_BLASTP=path/to/ncbi-blast-2.10.1+/bin/blastp
 NEOFOX_NETMHCPAN=path/to/netMHCpan-4.1/netMHCpan
-NEOFOX_NETMHC2PAN=path/to/netMHCIIpan-4.0/netMHCIIpan
+NEOFOX_NETMHC2PAN=path/to/netMHCIIpan-4.3/netMHCIIpan
 NEOFOX_MIXMHCPRED=path/to/MixMHCpred-2.2/MixMHCpred
 NEOFOX_MIXMHC2PRED=path/to/MixMHC2pred-2.0.1/MixMHC2pred_unix
 NEOFOX_MAKEBLASTDB=path/to/ncbi-blast-2.8.1+/bin/makeblastdb
@@ -158,9 +167,9 @@ where:
 - `identifier`: the patient identifier
 - `mhcIAlleles`: comma separated MHC I alleles of the patient for HLA-A, HLA-B and HLA-C. If homozygous, the allele should be added twice.
 - `mhcIIAlleles`: comma separated  MHC II alleles of the patient for HLA-DRB1, HLA-DQA1, HLA-DQB1, HLA-DPA1 and HLA-DPB1. If homozygous, the allele should be added twice.
-- `tumorType`: tumour entity in TCGA study abbreviation format (https://gdc.cancer.gov/resources-tcga-users/tcga-code-tables/tcga-study-abbreviations). This field is required for expression imputation and at the moment the following tumor types are supported:
+- `tumorType`: tumour entity in TCGA study abbreviation format (https://gdc.cancer.gov/resources-tcga-users/tcga-code-tables/tcga-study-abbreviations). This field is required for expression imputation. The supported tumor types are listed under "Input data" in the [documentation](https://neofox.readthedocs.io/en/latest/03_01_input_data.html).
 
 
 ## 5 Output data
 
-The output data is returned by default in a short wide tab separated values file (`--with-table`). Optionally, it can be provided in JSON format (`--with-json`).  
+The output data is returned by default in tsv and json format. With the command line flag `--with-all-neoepitopes`, two additional files are generated containing the epitope candidates for MHCI and MHCII with NetMHCpan predictions below the given thresholds.

docs/requirements.txt

@@ -8,4 +8,5 @@ ipykernel==6.4.1
 #insipid_sphinx_theme==0.2.1
 pydata-sphinx-theme==0.11.0
 Jinja2==3.1.2
-markupsafe==2.1.1
+markupsafe==2.1.1
+lxml-html-clean==0.1.1

docs/source/01_overview.md

@@ -22,14 +22,14 @@ in the last years.
 NeoFox supports annotation of neoantigen candidates derived from SNVs (single nucleotide variant) and alternative mutation classes such as INDELs or fusion genes. Furthermore, NeoFox supports both human and mouse derived neoantigen candidates.  
 
 NeoFox covers neoepitope prediction by MHC binding and ligand prediction, similarity/foreignness of a neoepitope candidate sequence, combinatorial features and machine learning approaches. 
-A list of implemented features and their references are given in Table 1. Please not that some features are currently not available for mouse.    
+A list of implemented features and their references are given in Table 1. Please note that some features are currently not available for mouse.    
 
 **Table 1**: Neoantigen features and prioritization algorithms (*§ currently not supported for mouse*)
 
 | Name                                                    | Reference                                                                | DOI                                                                                       |
 |---------------------------------------------------------|--------------------------------------------------------------------------|-------------------------------------------------------------------------------------------|
 | MHC I binding affinity/rank score (netMHCpan-v4.1)      | Reynisson et al., 2020, Nucleic Acids Res.                             | https://doi.org/10.1093/nar/gkaa379                                                  |
-| MHC II binding affinity/rank score (netMHCIIpan-v4.0)   | Reynisson et al., 2020, Nucleic Acids Res.                                            | https://doi.org/10.1093/nar/gkaa379                                                         |
+| MHC II binding affinity/rank score (netMHCIIpan-v4.3)   | Nilsson et al., 2023, Science Adv.                                            | https://doi.org/10.1126/sciadv.adj6367                                                         |
 | MixMHCpred score v2.2 §                                   | Bassani-Sternberg et al., 2017, PLoS Comp Bio; Gfeller, 2018, J Immunol. | https://doi.org/10.1371/journal.pcbi.1005725 ,   https://doi.org/10.4049/jimmunol.1800914 |
 | MixMHC2pred score v2.0.2 §                                 | Racle et al., 2019, Nat. Biotech. 2019                                    | https://doi.org/10.1038/s41587-019-0289-6                                                 |
 | Differential Agretopicity Index (DAI)                   | Duan et al., 2014, JEM; Ghorani et al., 2018, Ann Oncol.                  | https://doi.org/10.1084/jem.20141308                                                      |
@@ -42,7 +42,6 @@ A list of implemented features and their references are given in Table 1. Please
 | Recognition potential §                                  | Łuksza et al., 2017, Nature; Balachandran et al, 2017, Nature             | https://doi.org/10.1038/nature24473 , https://doi.org/10.1038/nature24462                 |
 | Vaxrank                                                 | Rubinsteyn, 2017, Front Immunol                                          | https://doi.org/10.3389/fimmu.2017.01807                                                  |
 | Priority score                                          | Bjerregaard et al., 2017, Cancer Immunol Immunother.                      | https://doi.org/10.1007/s00262-017-2001-3                                                 |
-| Tcell predictor                                         | Besser et al., 2019, Journal for ImmunoTherapy of Cancer                  | https://doi.org/10.1186/s40425-019-0595-z                                                 |
 | PRIME v2.0 §                                                  | Schmidt et al., 2021, Cell Reports Medicine                            | https://doi.org/10.1016/j.xcrm.2021.100194                                             |
 | HEX §                                                  | Chiaro et al., 2021, Cancer Immunology Research                            | https://doi.org/10.1158/2326-6066.CIR-20-0814                                             | 
 
@@ -67,4 +66,4 @@ Happy annotation and modelling!
 For questions, please contact Franziska Lang ([[email protected]](mailto:[email protected])) or Pablo Riesgo Ferreiro ([[email protected]](mailto:[email protected])).
 
 ## How to cite
-Franziska Lang, Pablo Riesgo-Ferreiro, Martin Löwer, Ugur Sahin, Barbara Schrörs, **NeoFox: annotating neoantigen candidates with neoantigen features**, Bioinformatics, Volume 37, Issue 22, 15 November 2021, Pages 4246–4247, [https://doi.org/10.1093/bioinformatics/btab344](https://doi.org/10.1093/bioinformatics/btab344)
+Franziska Lang, Pablo Riesgo-Ferreiro, Martin Löwer, Ugur Sahin, Barbara Schrörs, **NeoFox: annotating neoantigen candidates with neoantigen features**, Bioinformatics, Volume 37, Issue 22, 15 November 2021, Pages 4246–4247, [https://doi.org/10.1093/bioinformatics/btab344](https://doi.org/10.1093/bioinformatics/btab344)