%global _empty_manifest_terminate_build 0
Name: python-ABlooper
Version: 1.1.2
Release: 1
Summary: Set of functions to predict CDR structure
License: BSD 3-clause license
URL: https://pypi.org/project/ABlooper/
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/c4/36/249210f22e68f6f78f868af3cfa93ab3a566aa3df3f7bb147cb0ae059d62/ABlooper-1.1.2.tar.gz
BuildArch: noarch
Requires: python3-numpy
Requires: python3-einops
Requires: python3-torch
%description
# ABlooper
Antibodies are a key component of the immune system and have been extensively used as biotherapeutics. Accurate knowledge of their structure is central to understanding their antigen binding function. The key area for antigen binding and the main area of structural variation in antibodies is concentrated in the six complementarity determining regions (CDRs), with the most important for binding and most variable being the CDR-H3 loop. The sequence and structural variability of CDR-H3 make it particularly challenging to model. Recently deep learning methods have offered a step change in our ability to predict protein structures. In this work we present ABlooper, an end-to-end equivariant deep-learning based CDR loop structure prediction tool. ABlooper rapidly predicts the structure of CDR loops with high accuracy and provides a confidence estimate for each of its predictions. On the models of the Rosetta Antibody Benchmark, ABlooper makes predictions with an average CDR-H3 RMSD of 2.49Å, which drops to 2.05Å when considering only its 76% most confident predictions.
## Install
To install via PyPi:
```bash
$ pip install ABlooper
```
To download and install the latest version from github:
```bash
$ git clone https://github.com/brennanaba/ABlooper.git
$ pip install ABlooper/
```
This package requires PyTorch. If you do not already have PyTorch installed, you can do so following these instructions.
Either OpenMM or PyRosetta are required for the optional refinement and side-chain prediction steps.
OpenMM and pdbfixer can be installed via conda using:
```bash
$ conda install -c conda-forge openmm pdbfixer
```
If you want to use PyRosetta for refinement and do not have it installed, it can be obtained from here.
## Usage
To use ABlooper, you will need an IMGT numbered antibody model. If you do not already have an antibody model, you can generate one using ABodyBuilder.
To remodel the CDRs of an existing antibody model using the command line:
```bash
$ ABlooper my_antibody_model.pdb --output ABlooper_model.pdb --heavy_chain H --light_chain L
```
To remodel the CDRs of an existing model using the python API:
```python
from ABlooper import CDR_Predictor
input_path = "my_antibody_model.pdb"
output_path = "ABlooper_model.pdb"
pred = CDR_Predictor(input_path, chains = ("H", "L"))
pred.write_predictions_in_pdb_format(output_path)
```
Two pretrained models are available. The default predicts CDRs defined by the Chothia numbering scheme (This is the model described in the paper). To get predictions of CDRs defined by the IMGT numbering scheme use:
```python
pred = CDR_Predictor(input_path, chains = ("H", "L"), model = 'imgt')
pred.write_predictions_in_pdb_format(output_path)
```
I would recommend using the command line if you just want a quick antibody model. If speed is a priority, it is probably best to just use the trained pytorch model. The python class will work best if you want to incorporate CDR prediction into a pipeline or access other details such as confidence score or RMSD to original model. Both of which can be obtained as follows:
```python
rmsd_from_input = pred.calculate_BB_rmsd_wrt_input()
confidence_score = pred.decoy_diversity
```
I have been made aware that ABlooper will occasionally generate abnormal geometries. To fix this, and to generate side-chains you can do (Only works if you have PyRosetta or OpenMM installed):
```bash
$ ABlooper my_antibody_model.pdb --output ABlooper_model.pdb --model chothia --side_chains
```
As a default this will use OpenMM if it is installed.
## Citing this work
The code and data in this package is based on the following paper ABlooper. If you use it, please cite:
```tex
@article{10.1093/bioinformatics/btac016,
author = {Abanades, Brennan and Georges, Guy and Bujotzek, Alexander and Deane, Charlotte M},
title = {ABlooper: fast accurate antibody CDR loop structure prediction with accuracy estimation},
journal = {Bioinformatics},
volume = {38},
number = {7},
pages = {1877-1880},
year = {2022},
month = {01},
issn = {1367-4803},
doi = {10.1093/bioinformatics/btac016},
url = {https://doi.org/10.1093/bioinformatics/btac016},
```
%package -n python3-ABlooper
Summary: Set of functions to predict CDR structure
Provides: python-ABlooper
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-ABlooper
# ABlooper
Antibodies are a key component of the immune system and have been extensively used as biotherapeutics. Accurate knowledge of their structure is central to understanding their antigen binding function. The key area for antigen binding and the main area of structural variation in antibodies is concentrated in the six complementarity determining regions (CDRs), with the most important for binding and most variable being the CDR-H3 loop. The sequence and structural variability of CDR-H3 make it particularly challenging to model. Recently deep learning methods have offered a step change in our ability to predict protein structures. In this work we present ABlooper, an end-to-end equivariant deep-learning based CDR loop structure prediction tool. ABlooper rapidly predicts the structure of CDR loops with high accuracy and provides a confidence estimate for each of its predictions. On the models of the Rosetta Antibody Benchmark, ABlooper makes predictions with an average CDR-H3 RMSD of 2.49Å, which drops to 2.05Å when considering only its 76% most confident predictions.
## Install
To install via PyPi:
```bash
$ pip install ABlooper
```
To download and install the latest version from github:
```bash
$ git clone https://github.com/brennanaba/ABlooper.git
$ pip install ABlooper/
```
This package requires PyTorch. If you do not already have PyTorch installed, you can do so following these instructions.
Either OpenMM or PyRosetta are required for the optional refinement and side-chain prediction steps.
OpenMM and pdbfixer can be installed via conda using:
```bash
$ conda install -c conda-forge openmm pdbfixer
```
If you want to use PyRosetta for refinement and do not have it installed, it can be obtained from here.
## Usage
To use ABlooper, you will need an IMGT numbered antibody model. If you do not already have an antibody model, you can generate one using ABodyBuilder.
To remodel the CDRs of an existing antibody model using the command line:
```bash
$ ABlooper my_antibody_model.pdb --output ABlooper_model.pdb --heavy_chain H --light_chain L
```
To remodel the CDRs of an existing model using the python API:
```python
from ABlooper import CDR_Predictor
input_path = "my_antibody_model.pdb"
output_path = "ABlooper_model.pdb"
pred = CDR_Predictor(input_path, chains = ("H", "L"))
pred.write_predictions_in_pdb_format(output_path)
```
Two pretrained models are available. The default predicts CDRs defined by the Chothia numbering scheme (This is the model described in the paper). To get predictions of CDRs defined by the IMGT numbering scheme use:
```python
pred = CDR_Predictor(input_path, chains = ("H", "L"), model = 'imgt')
pred.write_predictions_in_pdb_format(output_path)
```
I would recommend using the command line if you just want a quick antibody model. If speed is a priority, it is probably best to just use the trained pytorch model. The python class will work best if you want to incorporate CDR prediction into a pipeline or access other details such as confidence score or RMSD to original model. Both of which can be obtained as follows:
```python
rmsd_from_input = pred.calculate_BB_rmsd_wrt_input()
confidence_score = pred.decoy_diversity
```
I have been made aware that ABlooper will occasionally generate abnormal geometries. To fix this, and to generate side-chains you can do (Only works if you have PyRosetta or OpenMM installed):
```bash
$ ABlooper my_antibody_model.pdb --output ABlooper_model.pdb --model chothia --side_chains
```
As a default this will use OpenMM if it is installed.
## Citing this work
The code and data in this package is based on the following paper ABlooper. If you use it, please cite:
```tex
@article{10.1093/bioinformatics/btac016,
author = {Abanades, Brennan and Georges, Guy and Bujotzek, Alexander and Deane, Charlotte M},
title = {ABlooper: fast accurate antibody CDR loop structure prediction with accuracy estimation},
journal = {Bioinformatics},
volume = {38},
number = {7},
pages = {1877-1880},
year = {2022},
month = {01},
issn = {1367-4803},
doi = {10.1093/bioinformatics/btac016},
url = {https://doi.org/10.1093/bioinformatics/btac016},
```
%package help
Summary: Development documents and examples for ABlooper
Provides: python3-ABlooper-doc
%description help
# ABlooper
Antibodies are a key component of the immune system and have been extensively used as biotherapeutics. Accurate knowledge of their structure is central to understanding their antigen binding function. The key area for antigen binding and the main area of structural variation in antibodies is concentrated in the six complementarity determining regions (CDRs), with the most important for binding and most variable being the CDR-H3 loop. The sequence and structural variability of CDR-H3 make it particularly challenging to model. Recently deep learning methods have offered a step change in our ability to predict protein structures. In this work we present ABlooper, an end-to-end equivariant deep-learning based CDR loop structure prediction tool. ABlooper rapidly predicts the structure of CDR loops with high accuracy and provides a confidence estimate for each of its predictions. On the models of the Rosetta Antibody Benchmark, ABlooper makes predictions with an average CDR-H3 RMSD of 2.49Å, which drops to 2.05Å when considering only its 76% most confident predictions.
## Install
To install via PyPi:
```bash
$ pip install ABlooper
```
To download and install the latest version from github:
```bash
$ git clone https://github.com/brennanaba/ABlooper.git
$ pip install ABlooper/
```
This package requires PyTorch. If you do not already have PyTorch installed, you can do so following these instructions.
Either OpenMM or PyRosetta are required for the optional refinement and side-chain prediction steps.
OpenMM and pdbfixer can be installed via conda using:
```bash
$ conda install -c conda-forge openmm pdbfixer
```
If you want to use PyRosetta for refinement and do not have it installed, it can be obtained from here.
## Usage
To use ABlooper, you will need an IMGT numbered antibody model. If you do not already have an antibody model, you can generate one using ABodyBuilder.
To remodel the CDRs of an existing antibody model using the command line:
```bash
$ ABlooper my_antibody_model.pdb --output ABlooper_model.pdb --heavy_chain H --light_chain L
```
To remodel the CDRs of an existing model using the python API:
```python
from ABlooper import CDR_Predictor
input_path = "my_antibody_model.pdb"
output_path = "ABlooper_model.pdb"
pred = CDR_Predictor(input_path, chains = ("H", "L"))
pred.write_predictions_in_pdb_format(output_path)
```
Two pretrained models are available. The default predicts CDRs defined by the Chothia numbering scheme (This is the model described in the paper). To get predictions of CDRs defined by the IMGT numbering scheme use:
```python
pred = CDR_Predictor(input_path, chains = ("H", "L"), model = 'imgt')
pred.write_predictions_in_pdb_format(output_path)
```
I would recommend using the command line if you just want a quick antibody model. If speed is a priority, it is probably best to just use the trained pytorch model. The python class will work best if you want to incorporate CDR prediction into a pipeline or access other details such as confidence score or RMSD to original model. Both of which can be obtained as follows:
```python
rmsd_from_input = pred.calculate_BB_rmsd_wrt_input()
confidence_score = pred.decoy_diversity
```
I have been made aware that ABlooper will occasionally generate abnormal geometries. To fix this, and to generate side-chains you can do (Only works if you have PyRosetta or OpenMM installed):
```bash
$ ABlooper my_antibody_model.pdb --output ABlooper_model.pdb --model chothia --side_chains
```
As a default this will use OpenMM if it is installed.
## Citing this work
The code and data in this package is based on the following paper ABlooper. If you use it, please cite:
```tex
@article{10.1093/bioinformatics/btac016,
author = {Abanades, Brennan and Georges, Guy and Bujotzek, Alexander and Deane, Charlotte M},
title = {ABlooper: fast accurate antibody CDR loop structure prediction with accuracy estimation},
journal = {Bioinformatics},
volume = {38},
number = {7},
pages = {1877-1880},
year = {2022},
month = {01},
issn = {1367-4803},
doi = {10.1093/bioinformatics/btac016},
url = {https://doi.org/10.1093/bioinformatics/btac016},
```
%prep
%autosetup -n ABlooper-1.1.2
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-ABlooper -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Wed May 10 2023 Python_Bot - 1.1.2-1
- Package Spec generated