diff --git a/docs/Makefile b/docs/Makefile
index aa11d1afd247eb30d0c339bc35a577558a16a014..d25e219d2aa941c919a995166fc22f2a118feab5 100644
--- a/docs/Makefile
+++ b/docs/Makefile
@@ -58,11 +58,16 @@ generate:
--out-models-architecture-png _build/_models_architecture.png \
--out-models-info-rst _build/_models_info.rst \
--out-models-supported-alleles-rst _build/_models_supported_alleles.rst
+
+
+# Added by Tim:
+.PHONY: readme
+readme: text
pandoc -B package_readme/readme_header.md \
-f rst \
-t gfm \
--base-header-level 2 \
- package_readme/readme.template.rst \
+ _build/text/package_readme/readme.template.txt \
-o package_readme/readme.generated.md
.PHONY: clean
diff --git a/docs/models.rst b/docs/models.rst
index bd31bbd17e95b549f6786245f4ef286c102b24ba..5287daf0c353b2f2a254a0b84c15efd650b4ad8b 100644
--- a/docs/models.rst
+++ b/docs/models.rst
@@ -15,11 +15,11 @@ Neural network architecture
The neural network architecture is quite simple, consisting of a locally
connected layer, a dense layer, and a sigmoid output.
-.. include:: _build/_models_info.rst
+.. include:: /_build/_models_info.rst
Architecture diagram:
-.. image:: _build/_models_architecture.png
+.. image:: /_build/_models_architecture.png
Cross validation performance
@@ -33,4 +33,4 @@ The AUC and F1 estimates use a 500 nM cutoff for distinguishing strong-binders
from weak- or non-binders. The Kendall Tau score gives the rank correlation
between the predicted and measured affinities; it uses no cutoff.
-.. include:: _build/_models_cv.rst
+.. include:: /_build/_models_cv.rst
diff --git a/docs/models_supported_alleles.rst b/docs/models_supported_alleles.rst
index 8fd2c3e57002467e4f5126268a8ef9e8e72b1074..3bca50762a7670418db9e8e2d9ca93bb6d2a0b34 100644
--- a/docs/models_supported_alleles.rst
+++ b/docs/models_supported_alleles.rst
@@ -1,4 +1,4 @@
Supported alleles and peptide lengths
=====================================
-.. include:: _build/_models_supported_alleles.rst
\ No newline at end of file
+.. include:: /_build/_models_supported_alleles.rst
\ No newline at end of file
diff --git a/docs/package_readme/readme.generated.md b/docs/package_readme/readme.generated.md
index d97d83cfd52cbd0c24c1b78d0a22be4a39ed9a3b..026e4c0d73c24bd7f7196032a513a3ac5da22883 100644
--- a/docs/package_readme/readme.generated.md
+++ b/docs/package_readme/readme.generated.md
@@ -32,30 +32,28 @@ If you find MHCflurry useful in your research please cite:
Install the package:
- pip install mhcflurry
+> pip install mhcflurry
Then download our datasets and trained models:
- mhcflurry-downloads fetch
+> mhcflurry-downloads fetch
From a checkout you can run the unit tests with:
- pip install nose
- nosetests .
+> pip install nose nosetests .
## Using conda
-You can alternatively get up and running with a
-[conda](https://conda.io/docs/) environment as follows. Some users have
-reported that this can avoid problems installing tensorflow.
+You can alternatively get up and running with a conda environment as
+follows. Some users have reported that this can avoid problems
+installing tensorflow.
- conda create -q -n mhcflurry-env python=3.6 'tensorflow>=1.1.2'
- source activate mhcflurry-env
+> conda create -q -n mhcflurry-env python=3.6 'tensorflow\>=1.1.2'
+> source activate mhcflurry-env
Then continue as above:
- pip install mhcflurry
- mhcflurry-downloads fetch
+> pip install mhcflurry mhcflurry-downloads fetch
### Command-line usage
@@ -70,27 +68,25 @@ some experimental models. To see what you have downloaded, run:
## mhcflurry-predict
-The `mhcflurry-predict` command generates predictions from the
+The "mhcflurry-predict" command generates predictions from the
command-line. It defaults to using the pre-trained models you downloaded
-above but this can be customized with the `--models` argument. See
-`mhcflurry-predict -h` for
-details.
-
-``` sourceCode shell
-$ mhcflurry-predict --alleles HLA-A0201 HLA-A0301 --peptides SIINFEKL SIINFEKD SIINFEKQ
-allele,peptide,mhcflurry_prediction,mhcflurry_prediction_low,mhcflurry_prediction_high
-HLA-A0201,SIINFEKL,5326.541919062165,3757.86675352994,7461.37693353508
-HLA-A0201,SIINFEKD,18763.70298522213,13140.82000240037,23269.82139560844
-HLA-A0201,SIINFEKQ,18620.10057358322,13096.425874678192,23223.148184869413
-HLA-A0301,SIINFEKL,24481.726678691946,21035.52779725433,27245.371837497867
-HLA-A0301,SIINFEKD,24687.529360239587,21582.590014592537,27749.39869616437
-HLA-A0301,SIINFEKQ,25923.062203902562,23522.5793450799,28079.456657427705
-```
-
-The predictions returned are affinities (KD) in nM. The `prediction_low`
-and `prediction_high` fields give the 5-95 percentile predictions across
-the models in the ensemble. The predictions above were generated with
-MHCflurry 0.9.2.
+above but this can be customized with the "--models" argument. See
+"mhcflurry-predict -h" for details.
+
+> $ mhcflurry-predict --alleles HLA-A0201 HLA-A0301 --peptides SIINFEKL
+> SIINFEKD SIINFEKQ
+> allele,peptide,mhcflurry\_prediction,mhcflurry\_prediction\_low,mhcflurry\_prediction\_high
+> HLA-A0201,SIINFEKL,5326.541919062165,3757.86675352994,7461.37693353508
+> HLA-A0201,SIINFEKD,18763.70298522213,13140.82000240037,23269.82139560844
+> HLA-A0201,SIINFEKQ,18620.10057358322,13096.425874678192,23223.148184869413
+> HLA-A0301,SIINFEKL,24481.726678691946,21035.52779725433,27245.371837497867
+> HLA-A0301,SIINFEKD,24687.529360239587,21582.590014592537,27749.39869616437
+> HLA-A0301,SIINFEKQ,25923.062203902562,23522.5793450799,28079.456657427705
+
+The predictions returned are affinities (KD) in nM. The
+"prediction\_low" and "prediction\_high" fields give the 5-95 percentile
+predictions across the models in the ensemble. The predictions above
+were generated with MHCflurry 0.9.2.
Your exact predictions may vary slightly from these (up to about 1 nM)
depending on the Keras backend in use and other numerical details.
@@ -98,7 +94,7 @@ Different versions of MHCflurry can of course give results considerably
different from these.
You can also specify the input and output as CSV files. Run
-`mhcflurry-predict -h` for details.
+"mhcflurry-predict -h" for details.
## Fitting your own models
@@ -106,205 +102,213 @@ You can also specify the input and output as CSV files. Run
The MHCflurry Python API exposes additional options and features beyond
those supported by the commandline tools. This tutorial gives a basic
-overview of the most important functionality. See the
-<span data-role="ref">API-documentation</span> for further details.
+overview of the most important functionality. See the API Documentation
+for further details.
-The ~mhcflurry.Class1AffinityPredictor class is the primary user-facing
+The "Class1AffinityPredictor" class is the primary user-facing
interface.
-<div class="runblock">
-
-pycon
-
-\>\>\> import mhcflurry \>\>\> print("MHCflurry version: %s" %
-(mhcflurry.\_\_version\_\_)) \>\>\> \>\>\> \# Load downloaded predictor
-\>\>\> predictor = mhcflurry.Class1AffinityPredictor.load() \>\>\>
-print(predictor.supported\_alleles)
-
-</div>
-
-:
-
- # coding: utf-8
-
- # In[22]:
-
- import pandas
- import numpy
- import seaborn
- import logging
- from matplotlib import pyplot
-
- import mhcflurry
-
-
-
- # # Download data and models
-
- # In[2]:
-
- get_ipython().system('mhcflurry-downloads fetch')
-
-
- # # Making predictions with `Class1AffinityPredictor`
-
- # In[3]:
-
- help(mhcflurry.Class1AffinityPredictor)
-
-
- # In[4]:
-
- downloaded_predictor = mhcflurry.Class1AffinityPredictor.load()
-
-
- # In[5]:
-
- downloaded_predictor.predict(allele="HLA-A0201", peptides=["SIINFEKL", "SIINFEQL"])
-
-
- # In[6]:
-
- downloaded_predictor.predict_to_dataframe(allele="HLA-A0201", peptides=["SIINFEKL", "SIINFEQL"])
-
-
- # In[7]:
-
- downloaded_predictor.predict_to_dataframe(alleles=["HLA-A0201", "HLA-B*57:01"], peptides=["SIINFEKL", "SIINFEQL"])
-
-
- # In[8]:
-
- downloaded_predictor.predict_to_dataframe(
- allele="HLA-A0201",
- peptides=["SIINFEKL", "SIINFEQL"],
- include_individual_model_predictions=True)
-
-
- # In[9]:
-
- downloaded_predictor.predict_to_dataframe(
- allele="HLA-A0201",
- peptides=["SIINFEKL", "SIINFEQL", "TAAAALANGGGGGGGG"],
- throw=False) # Without throw=False, you'll get a ValueError for invalid peptides or alleles
-
-
- # # Instantiating a `Class1AffinityPredictor` from a saved model on disk
-
- # In[10]:
-
- models_dir = mhcflurry.downloads.get_path("models_class1", "models")
- models_dir
-
-
- # In[11]:
-
- # This will be the same predictor we instantiated above. We're just being explicit about what models to load.
- downloaded_predictor = mhcflurry.Class1AffinityPredictor.load(models_dir)
- downloaded_predictor.predict(["SIINFEKL", "SIQNPEKP", "SYNFPEPI"], allele="HLA-A0301")
-
-
- # # Fit a model: first load some data
-
- # In[12]:
-
- # This is the data the downloaded models were trained on
- data_path = mhcflurry.downloads.get_path("data_curated", "curated_training_data.csv.bz2")
- data_path
-
-
- # In[13]:
-
- data_df = pandas.read_csv(data_path)
- data_df
-
-
- # # Fit a model: Low level `Class1NeuralNetwork` interface
-
- # In[14]:
-
- # We'll use mostly the default hyperparameters here. Could also specify them as kwargs.
- new_model = mhcflurry.Class1NeuralNetwork(layer_sizes=[16])
- new_model.hyperparameters
-
-
- # In[16]:
-
- train_data = data_df.loc[
- (data_df.allele == "HLA-B*57:01") &
- (data_df.peptide.str.len() >= 8) &
- (data_df.peptide.str.len() <= 15)
- ]
- get_ipython().magic('time new_model.fit(train_data.peptide.values, train_data.measurement_value.values)')
-
-
- # In[17]:
-
- new_model.predict(["SYNPEPII"])
-
-
- # # Fit a model: high level `Class1AffinityPredictor` interface
-
- # In[18]:
-
- affinity_predictor = mhcflurry.Class1AffinityPredictor()
-
- # This can be called any number of times, for example on different alleles, to build up the ensembles.
- affinity_predictor.fit_allele_specific_predictors(
- n_models=1,
- architecture_hyperparameters={"layer_sizes": [16], "max_epochs": 10},
- peptides=train_data.peptide.values,
- affinities=train_data.measurement_value.values,
- allele="HLA-B*57:01",
- )
-
-
- # In[19]:
-
- affinity_predictor.predict(["SYNPEPII"], allele="HLA-B*57:01")
-
-
- # # Save and restore the fit model
-
- # In[20]:
-
- get_ipython().system('mkdir /tmp/saved-affinity-predictor')
- affinity_predictor.save("/tmp/saved-affinity-predictor")
- get_ipython().system('ls /tmp/saved-affinity-predictor')
-
-
- # In[21]:
-
- affinity_predictor2 = mhcflurry.Class1AffinityPredictor.load("/tmp/saved-affinity-predictor")
- affinity_predictor2.predict(["SYNPEPII"], allele="HLA-B*57:01")
+> \>\>\> import mhcflurry \>\>\> print("MHCflurry version: %s" %
+> (mhcflurry.\_\_version\_\_)) MHCflurry version: 1.0.0 \>\>\> \>\>\> \#
+> Load downloaded predictor \>\>\> predictor =
+> mhcflurry.Class1AffinityPredictor.load() \>\>\>
+> print(predictor.supported\_alleles) \['BoLA-6\*13:01',
+> 'Eqca-1\*01:01', 'H-2-Db', 'H-2-Dd', 'H-2-Kb', 'H-2-Kd', 'H-2-Kk',
+> 'H-2-Ld', 'HLA-A\*01:01', 'HLA-A\*02:01', 'HLA-A\*02:02',
+> 'HLA-A\*02:03', 'HLA-A\*02:05', 'HLA-A\*02:06', 'HLA-A\*02:07',
+> 'HLA-A\*02:11', 'HLA-A\*02:12', 'HLA-A\*02:16', 'HLA-A\*02:17',
+> 'HLA-A\*02:19', 'HLA-A\*02:50', 'HLA-A\*03:01', 'HLA-A\*11:01',
+> 'HLA-A\*23:01', 'HLA-A\*24:01', 'HLA-A\*24:02', 'HLA-A\*24:03',
+> 'HLA-A\*25:01', 'HLA-A\*26:01', 'HLA-A\*26:02', 'HLA-A\*26:03',
+> 'HLA-A\*29:02', 'HLA-A\*30:01', 'HLA-A\*30:02', 'HLA-A\*31:01',
+> 'HLA-A\*32:01', 'HLA-A\*32:07', 'HLA-A\*33:01', 'HLA-A\*66:01',
+> 'HLA-A\*68:01', 'HLA-A\*68:02', 'HLA-A\*68:23', 'HLA-A\*69:01',
+> 'HLA-A\*80:01', 'HLA-B\*07:01', 'HLA-B\*07:02', 'HLA-B\*08:01',
+> 'HLA-B\*08:02', 'HLA-B\*08:03', 'HLA-B\*14:02', 'HLA-B\*15:01',
+> 'HLA-B\*15:02', 'HLA-B\*15:03', 'HLA-B\*15:09', 'HLA-B\*15:17',
+> 'HLA-B\*15:42', 'HLA-B\*18:01', 'HLA-B\*27:01', 'HLA-B\*27:03',
+> 'HLA-B\*27:04', 'HLA-B\*27:05', 'HLA-B\*27:06', 'HLA-B\*27:20',
+> 'HLA-B\*35:01', 'HLA-B\*35:03', 'HLA-B\*35:08', 'HLA-B\*37:01',
+> 'HLA-B\*38:01', 'HLA-B\*39:01', 'HLA-B\*40:01', 'HLA-B\*40:02',
+> 'HLA-B\*42:01', 'HLA-B\*44:01', 'HLA-B\*44:02', 'HLA-B\*44:03',
+> 'HLA-B\*45:01', 'HLA-B\*45:06', 'HLA-B\*46:01', 'HLA-B\*48:01',
+> 'HLA-B\*51:01', 'HLA-B\*53:01', 'HLA-B\*54:01', 'HLA-B\*57:01',
+> 'HLA-B\*58:01', 'HLA-B\*73:01', 'HLA-B\*83:01', 'HLA-C\*03:03',
+> 'HLA-C\*03:04', 'HLA-C\*04:01', 'HLA-C\*05:01', 'HLA-C\*06:02',
+> 'HLA-C\*07:01', 'HLA-C\*07:02', 'HLA-C\*08:02', 'HLA-C\*12:03',
+> 'HLA-C\*14:02', 'HLA-C\*15:02', 'Mamu-A\*01:01', 'Mamu-A\*02:01',
+> 'Mamu-A\*02:0102', 'Mamu-A\*07:01', 'Mamu-A\*07:0103',
+> 'Mamu-A\*11:01', 'Mamu-A\*22:01', 'Mamu-A\*26:01', 'Mamu-B\*01:01',
+> 'Mamu-B\*03:01', 'Mamu-B\*08:01', 'Mamu-B\*10:01', 'Mamu-B\*17:01',
+> 'Mamu-B\*17:04', 'Mamu-B\*39:01', 'Mamu-B\*52:01', 'Mamu-B\*66:01',
+> 'Mamu-B\*83:01', 'Mamu-B\*87:01', 'Patr-A\*01:01', 'Patr-A\*03:01',
+> 'Patr-A\*04:01', 'Patr-A\*07:01', 'Patr-A\*09:01', 'Patr-B\*01:01',
+> 'Patr-B\*13:01', 'Patr-B\*24:01'\]
+>
+> \# coding: utf-8
+>
+> \# In\[22\]:
+>
+> import pandas import numpy import seaborn import logging from
+> matplotlib import pyplot
+>
+> import mhcflurry
+>
+> \# \# Download data and models
+>
+> \# In\[2\]:
+>
+> get\_ipython().system('mhcflurry-downloads fetch')
+>
+> \# \# Making predictions with Class1AffinityPredictor
+>
+> \# In\[3\]:
+>
+> help(mhcflurry.Class1AffinityPredictor)
+>
+> \# In\[4\]:
+>
+> downloaded\_predictor = mhcflurry.Class1AffinityPredictor.load()
+>
+> \# In\[5\]:
+>
+> downloaded\_predictor.predict(allele="HLA-A0201",
+> peptides=\["SIINFEKL", "SIINFEQL"\])
+>
+> \# In\[6\]:
+>
+> downloaded\_predictor.predict\_to\_dataframe(allele="HLA-A0201",
+> peptides=\["SIINFEKL", "SIINFEQL"\])
+>
+> \# In\[7\]:
+>
+> downloaded\_predictor.predict\_to\_dataframe(alleles=\["HLA-A0201",
+> "HLA-B\*57:01"\], peptides=\["SIINFEKL", "SIINFEQL"\])
+>
+> \# In\[8\]:
+>
+> - downloaded\_predictor.predict\_to\_dataframe(
+> allele="HLA-A0201", peptides=\["SIINFEKL", "SIINFEQL"\],
+> include\_individual\_model\_predictions=True)
+>
+> \# In\[9\]:
+>
+> - downloaded\_predictor.predict\_to\_dataframe(
+> allele="HLA-A0201", peptides=\["SIINFEKL", "SIINFEQL",
+> "TAAAALANGGGGGGGG"\], throw=False) \# Without throw=False, you'll
+> get a ValueError for invalid peptides or alleles
+>
+> \# \# Instantiating a Class1AffinityPredictor from a saved model on
+> disk
+>
+> \# In\[10\]:
+>
+> models\_dir = mhcflurry.downloads.get\_path("models\_class1",
+> "models") models\_dir
+>
+> \# In\[11\]:
+>
+> \# This will be the same predictor we instantiated above. We're just
+> being explicit about what models to load. downloaded\_predictor =
+> mhcflurry.Class1AffinityPredictor.load(models\_dir)
+> downloaded\_predictor.predict(\["SIINFEKL", "SIQNPEKP", "SYNFPEPI"\],
+> allele="HLA-A0301")
+>
+> \# \# Fit a model: first load some data
+>
+> \# In\[12\]:
+>
+> \# This is the data the downloaded models were trained on data\_path =
+> mhcflurry.downloads.get\_path("data\_curated",
+> "curated\_training\_data.csv.bz2") data\_path
+>
+> \# In\[13\]:
+>
+> data\_df = pandas.read\_csv(data\_path) data\_df
+>
+> \# \# Fit a model: Low level Class1NeuralNetwork interface
+>
+> \# In\[14\]:
+>
+> \# We'll use mostly the default hyperparameters here. Could also
+> specify them as kwargs. new\_model =
+> mhcflurry.Class1NeuralNetwork(layer\_sizes=\[16\])
+> new\_model.hyperparameters
+>
+> \# In\[16\]:
+>
+> - train\_data = data\_df.loc\[
+> (data\_df.allele == "HLA-B\*57:01") & (data\_df.peptide.str.len()
+> \>= 8) & (data\_df.peptide.str.len() \<= 15)
+>
+> \] get\_ipython().magic('time
+> new\_model.fit(train\_data.peptide.values,
+> train\_data.measurement\_value.values)')
+>
+> \# In\[17\]:
+>
+> new\_model.predict(\["SYNPEPII"\])
+>
+> \# \# Fit a model: high level Class1AffinityPredictor interface
+>
+> \# In\[18\]:
+>
+> affinity\_predictor = mhcflurry.Class1AffinityPredictor()
+>
+> \# This can be called any number of times, for example on different
+> alleles, to build up the ensembles.
+> affinity\_predictor.fit\_allele\_specific\_predictors( n\_models=1,
+> architecture\_hyperparameters={"layer\_sizes": \[16\], "max\_epochs":
+> 10}, peptides=train\_data.peptide.values,
+> affinities=train\_data.measurement\_value.values,
+> allele="HLA-B\*57:01", )
+>
+> \# In\[19\]:
+>
+> affinity\_predictor.predict(\["SYNPEPII"\], allele="HLA-B\*57:01")
+>
+> \# \# Save and restore the fit model
+>
+> \# In\[20\]:
+>
+> get\_ipython().system('mkdir /tmp/saved-affinity-predictor')
+> affinity\_predictor.save("/tmp/saved-affinity-predictor")
+> get\_ipython().system('ls /tmp/saved-affinity-predictor')
+>
+> \# In\[21\]:
+>
+> affinity\_predictor2 =
+> mhcflurry.Class1AffinityPredictor.load("/tmp/saved-affinity-predictor")
+> affinity\_predictor2.predict(\["SYNPEPII"\], allele="HLA-B\*57:01")
### Supported alleles and peptide lengths
Models released with the current version of MHCflurry (1.0.0) support
peptides of length 8-15 and the following 124 alleles:
- BoLA-6*13:01, Eqca-1*01:01, H-2-Db, H-2-Dd, H-2-Kb, H-2-Kd, H-2-Kk,
- H-2-Ld, HLA-A*01:01, HLA-A*02:01, HLA-A*02:02, HLA-A*02:03,
- HLA-A*02:05, HLA-A*02:06, HLA-A*02:07, HLA-A*02:11, HLA-A*02:12,
- HLA-A*02:16, HLA-A*02:17, HLA-A*02:19, HLA-A*02:50, HLA-A*03:01,
- HLA-A*11:01, HLA-A*23:01, HLA-A*24:01, HLA-A*24:02, HLA-A*24:03,
- HLA-A*25:01, HLA-A*26:01, HLA-A*26:02, HLA-A*26:03, HLA-A*29:02,
- HLA-A*30:01, HLA-A*30:02, HLA-A*31:01, HLA-A*32:01, HLA-A*32:07,
- HLA-A*33:01, HLA-A*66:01, HLA-A*68:01, HLA-A*68:02, HLA-A*68:23,
- HLA-A*69:01, HLA-A*80:01, HLA-B*07:01, HLA-B*07:02, HLA-B*08:01,
- HLA-B*08:02, HLA-B*08:03, HLA-B*14:02, HLA-B*15:01, HLA-B*15:02,
- HLA-B*15:03, HLA-B*15:09, HLA-B*15:17, HLA-B*15:42, HLA-B*18:01,
- HLA-B*27:01, HLA-B*27:03, HLA-B*27:04, HLA-B*27:05, HLA-B*27:06,
- HLA-B*27:20, HLA-B*35:01, HLA-B*35:03, HLA-B*35:08, HLA-B*37:01,
- HLA-B*38:01, HLA-B*39:01, HLA-B*40:01, HLA-B*40:02, HLA-B*42:01,
- HLA-B*44:01, HLA-B*44:02, HLA-B*44:03, HLA-B*45:01, HLA-B*45:06,
- HLA-B*46:01, HLA-B*48:01, HLA-B*51:01, HLA-B*53:01, HLA-B*54:01,
- HLA-B*57:01, HLA-B*58:01, HLA-B*73:01, HLA-B*83:01, HLA-C*03:03,
- HLA-C*03:04, HLA-C*04:01, HLA-C*05:01, HLA-C*06:02, HLA-C*07:01,
- HLA-C*07:02, HLA-C*08:02, HLA-C*12:03, HLA-C*14:02, HLA-C*15:02,
- Mamu-A*01:01, Mamu-A*02:01, Mamu-A*02:0102, Mamu-A*07:01,
- Mamu-A*07:0103, Mamu-A*11:01, Mamu-A*22:01, Mamu-A*26:01,
- Mamu-B*01:01, Mamu-B*03:01, Mamu-B*08:01, Mamu-B*10:01, Mamu-B*17:01,
- Mamu-B*17:04, Mamu-B*39:01, Mamu-B*52:01, Mamu-B*66:01, Mamu-B*83:01,
- Mamu-B*87:01, Patr-A*01:01, Patr-A*03:01, Patr-A*04:01, Patr-A*07:01,
- Patr-A*09:01, Patr-B*01:01, Patr-B*13:01, Patr-B*24:01
+> BoLA-6\*13:01, Eqca-1\*01:01, H-2-Db, H-2-Dd, H-2-Kb, H-2-Kd, H-2-Kk,
+> H-2-Ld, HLA-A\*01:01, HLA-A\*02:01, HLA-A\*02:02, HLA-A\*02:03,
+> HLA-A\*02:05, HLA-A\*02:06, HLA-A\*02:07, HLA-A\*02:11, HLA-A\*02:12,
+> HLA-A\*02:16, HLA-A\*02:17, HLA-A\*02:19, HLA-A\*02:50, HLA-A\*03:01,
+> HLA-A\*11:01, HLA-A\*23:01, HLA-A\*24:01, HLA-A\*24:02, HLA-A\*24:03,
+> HLA-A\*25:01, HLA-A\*26:01, HLA-A\*26:02, HLA-A\*26:03, HLA-A\*29:02,
+> HLA-A\*30:01, HLA-A\*30:02, HLA-A\*31:01, HLA-A\*32:01, HLA-A\*32:07,
+> HLA-A\*33:01, HLA-A\*66:01, HLA-A\*68:01, HLA-A\*68:02, HLA-A\*68:23,
+> HLA-A\*69:01, HLA-A\*80:01, HLA-B\*07:01, HLA-B\*07:02, HLA-B\*08:01,
+> HLA-B\*08:02, HLA-B\*08:03, HLA-B\*14:02, HLA-B\*15:01, HLA-B\*15:02,
+> HLA-B\*15:03, HLA-B\*15:09, HLA-B\*15:17, HLA-B\*15:42, HLA-B\*18:01,
+> HLA-B\*27:01, HLA-B\*27:03, HLA-B\*27:04, HLA-B\*27:05, HLA-B\*27:06,
+> HLA-B\*27:20, HLA-B\*35:01, HLA-B\*35:03, HLA-B\*35:08, HLA-B\*37:01,
+> HLA-B\*38:01, HLA-B\*39:01, HLA-B\*40:01, HLA-B\*40:02, HLA-B\*42:01,
+> HLA-B\*44:01, HLA-B\*44:02, HLA-B\*44:03, HLA-B\*45:01, HLA-B\*45:06,
+> HLA-B\*46:01, HLA-B\*48:01, HLA-B\*51:01, HLA-B\*53:01, HLA-B\*54:01,
+> HLA-B\*57:01, HLA-B\*58:01, HLA-B\*73:01, HLA-B\*83:01, HLA-C\*03:03,
+> HLA-C\*03:04, HLA-C\*04:01, HLA-C\*05:01, HLA-C\*06:02, HLA-C\*07:01,
+> HLA-C\*07:02, HLA-C\*08:02, HLA-C\*12:03, HLA-C\*14:02, HLA-C\*15:02,
+> Mamu-A\*01:01, Mamu-A\*02:01, Mamu-A\*02:0102, Mamu-A\*07:01,
+> Mamu-A\*07:0103, Mamu-A\*11:01, Mamu-A\*22:01, Mamu-A\*26:01,
+> Mamu-B\*01:01, Mamu-B\*03:01, Mamu-B\*08:01, Mamu-B\*10:01,
+> Mamu-B\*17:01, Mamu-B\*17:04, Mamu-B\*39:01, Mamu-B\*52:01,
+> Mamu-B\*66:01, Mamu-B\*83:01, Mamu-B\*87:01, Patr-A\*01:01,
+> Patr-A\*03:01, Patr-A\*04:01, Patr-A\*07:01, Patr-A\*09:01,
+> Patr-B\*01:01, Patr-B\*13:01, Patr-B\*24:01
diff --git a/docs/package_readme/readme.template.rst b/docs/package_readme/readme.template.rst
index e763d171b15d3b062db2b27d5f9c798b4a18c87d..0041ce76b9cad7acfde8930fdd11e37cf17fbcb6 100644
--- a/docs/package_readme/readme.template.rst
+++ b/docs/package_readme/readme.template.rst
@@ -1,10 +1,10 @@
.. readme_header.md will be inserted first by pandoc
-.. include:: intro.rst
+.. include:: /intro.rst
:start-line: 3
-.. include:: commandline_tutorial.rst
+.. include:: /commandline_tutorial.rst
-.. include:: python_tutorial.rst
+.. include:: /python_tutorial.rst
-.. include:: models_supported_alleles.rst
+.. include:: /models_supported_alleles.rst