Phylogeny Partners

Last update: Sep 19, 2022

Related tags

Deep Learning Phylogeny-Partners

Overview

Phylogeny-Partners

Two states models

Instalation

You may need to install the cython, networkx, numpy, scipy package:

pip install cython, networkx, numpy, scipy

and do in the folder two_states :

cd 2_states/code_two_states
cythonize -i generation_sequences.pyx
cythonize -i mutual_info.pyx

To use the last part of the jupyter notebook figures.ipynb, you should install bmDCA :

https://github.com/ranganathanlab/bmDCA

The code works on linux and Mac. (It is possible to adapt it for windows, you need to change the drand48() or random() function by one available in windows distribution)

Utilisation

You can open figures.ipynb and different_graph.ipynb to see all figures generated with the simple model.

Twenty one states models

Installation

The code present in Code_for_cluster was present in the EPFL cluster. It is helpful to generate data and to infer contact and partners. The model has been inferred with bmDCA on the cluster and arDCA on my personal computer. If you want to reproduce the data, I advise you to copy the folder Code_for_cluster and to do :

cd 21_states/Code_for_cluster/cython_code/
cythonize -i generation_sequence.pyx
cythonize -i generation_sequence_arDCA.pyx
cythonize -i analyse_sequence.pyx

Generation of data

And after, you can generate MSA (data set of aligned sequences) :

sbatch generation_sequence_bmDCA.run
sbatch generation_sequence_arDCA.run

If you are not on a cluster and cannot use the function sbatch, you can replace sbatch by bash.

Inference

When these three programmes are completed, you can infer the contact with :

sbatch inference_contact.run

And for the partners :

sbatch inference_partners_generated_data.py

If you want to see the plot from the inference, you can run the jupyter notebook inside the folder 21_states.

Phylogeny Partners

Related tags

Overview

Phylogeny-Partners

Two states models

Instalation

Utilisation

Twenty one states models

Installation

Generation of data

Inference

2 states with sampling on a inferred model

Installation

Figures

You might also like...

Releases(v2.0)

v2.0(Apr 24, 2022)

Owner

The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".

BLEURT is a metric for Natural Language Generation based on transfer learning.

This repo contains the official code and pre-trained models for the Dynamic Vision Transformer (DVT).

Predict multi paths to a moving person depending on his trajectory history.

AOT-GAN for High-Resolution Image Inpainting (codebase for image inpainting)

Lightweight, Python library for fast and reproducible experimentation :microscope:

[AAAI 2021] EMLight: Lighting Estimation via Spherical Distribution Approximation and [ICCV 2021] Sparse Needlets for Lighting Estimation with Spherical Transport Loss

Spontaneous Facial Micro Expression Recognition using 3D Spatio-Temporal Convolutional Neural Networks

Learning Features with Parameter-Free Layers (ICLR 2022)

PyTorch Language Model for 1-Billion Word (LM1B / GBW) Dataset

Lava-DL, but with PyTorch-Lightning flavour

Code for the paper titled "Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks" (NeurIPS 2021 Spotlight).

TF2 implementation of knowledge distillation using the "function matching" hypothesis from the paper Knowledge distillation: A good teacher is patient and consistent by Beyer et al.

Galactic and gravitational dynamics in Python

[AAAI2021] The source code for our paper 《Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion》.

Controlling the MicriSpotAI robot from scratch

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

An implementation of based on pytorch and mmcv

Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning

Project page of the paper 'Analyzing Perception-Distortion Tradeoff using Enhanced Perceptual Super-resolution Network' (ECCVW 2018)