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

[NeurIPS 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

[CVPR2021] DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets

Automated Attendance Project Using Face Recognition

The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

Breast cancer is been classified into benign tumour and malignant tumour.

Opinionated code formatter, just like Python's black code formatter but for Beancount

Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide range of illumination variants of a single image.

An unofficial styleguide and best practices summary for PyTorch

Pytorch implementation of our paper LIMUSE: LIGHTWEIGHT MULTI-MODAL SPEAKER EXTRACTION.

NALSM: Neuron-Astrocyte Liquid State Machine

Repository of best practices for deep learning in Julia, inspired by fastai

Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation

ANEA: Distant Supervision for Low-Resource Named Entity Recognition

OpenMMLab Image Classification Toolbox and Benchmark

Reimplementation of the paper `Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words? (ACL2020)`

Exploring the link between uncertainty estimates obtained via "exact" Bayesian inference and out-of-distribution (OOD) detection.

An implementation of based on pytorch and mmcv

Fast image augmentation library and an easy-to-use wrapper around other libraries

PyTorch Implement for Path Attention Graph Network