Code Monkey home page Code Monkey logo

int2cart's Introduction

Int2Cart

An algorithm for predicting protein backbone bond lengths and bond angles from torsion angles and amino acid sequence, so that reconstruction of protein structure with torsion angles only can be more accurate.

Authors

  • Jie Li
  • Oufan Zhang
  • Seokyoung Lee
  • Ashley Namini
  • Zi Hao Liu
  • João Miguel Correia Teixeira
  • Julie D Forman-Kay
  • Teresa Head-Gordon

Installation

Required packages

Installation steps

Go to the root folder of the repository (where setup.py resides) and run pip install -e .. Make sure to switch to the target virtual environment before installation if you want to install the code in a separate environment.

Using pretrained model

Go into the run_scripts folder and run with: python predict.py [seq] [torsion_addr] [output]

positional arguments:
  seq                   the one-letter amino acid sequence of the protein to
                        be predicted
  torsion_addr          the address to a numpy file that stores the backbone
                        torsion angles for the protein to be predicted.
                        Expected to be in size of Nx3, where N is the sequence
                        length, and 3 corresponds to phi, psi and omega.
  output                The output file name, excluding file extension

optional arguments:
  --from_pdb FROM_PDB   extract amino acid sequence and torsion angles from
                        the pdb file instead of providing them through
                        arguments
  --build, -b           build the structure after predicting bond lengths and
                        bond angles
  --units UNITS, -u UNITS
                        the units for angles used for inputs and outputs.
                        Should be one of [degree](default) or [radian]
  --device DEVICE, -d DEVICE
                        the device used for running the model, could be
                        [cpu](default) or [cuda:x] for GPU
  --config CONFIG, -c CONFIG
                        configuration file specifying model structure
  --model_addr MODEL_ADDR, -m MODEL_ADDR
                        a path specifying the position of trained model

Training new models

  • Make sure SidechainNet package is installed and patching script (under tools folder have been executed)
  • Prepare a yml file similar to configs/debug.yml and change parameters as needed
  • run run_scripts/train.py [config_file] to train the model

int2cart's People

Contributors

jerryjohnsonlee avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.