Code Monkey home page Code Monkey logo

aminox's Introduction

AminoX

AminoX is a Natural Language Processing (NLP) Recurrent Neural Network (RNN) making use of a Long Short Term Memory (LSTM) architecture for the determination of a single missing aminoacid in a given input primary sequence:

'SPSSLSTNTTSA ? PTLTSEPR' โ†’ 'SPSSLSTNTTSA S PTLTSEPR'

The input dataset is generated with ProtGPT2, a language model trained on protein space (https://huggingface.co/nferruz/ProtGPT2). Protgpt2_seq_gen.py allows for the generation of N different aminoacid sequences, of length comprised between a settable minimum (100) and a settable maximum (300).

The input data is then organised in minibatches of length 100, corresponding to the minimum length of the sequences. Each minibatch correspond to a sequence where, in turn, each aminoacid is substituted with the character '?' to represent a missing aminoacid, and its target output will be the unmodified sequence.

After training epochs, predictions are made over the test set. For each amino acid in this dataset, the whole list of aminoacids is shown, in decreasing order of prediction likelihood. A confusion matrix is also plotted, in order to show how aminoacids are correctly/incorrectly predicted.

AminoX is adapted from Unit 6/7 of this NLP tutorial: https://learn.microsoft.com/en-us/training/modules/intro-natural-language-processing-pytorch/1-introduction

Required Libraries

Python modules required:

Example Confusion Matrix

aminox's People

Contributors

alescrnjar avatar

Stargazers

Jin Xiao avatar

Watchers

Kostas Georgiou avatar  avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.