An algorithm for solving protein sequence alignment which aims to find optimum matching between two amino acid sequences

FASTA file processor is a CMake Project written in modern C++ and designed to take advantage of the new C++17 standard. It is designed to read and write FASTA files quickly and efficiently, and it can be used as a library or a stand-alone program. The project comes with a set of tests using the Catch2 framework.

Adaptation of the official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks [CVPR 2021] to ESM.

from protein alignments to deep learning preparatory.

Scripts to run benchmarks of BLAST and PLAST on a supercomputer

Finds sequences of nucleotide triplets, called codons, that specifies which amino acid will be added next during protein synthesis.

An open source and cross platform application to fix, and find problems in protein FASTA sequence files.

High-throughput prediction of disordered flexible linker regions in proteins

For viewing, analyzing, and generating figures of protein sequence alignments.

Property Prediction for Intrinsically Disordered Proteins (IDPs) using Language Model

Map the peptides to its corresponding protein sequence and locate the modification sites

Repo for running command line-based HH-suite3 software in Jupyter environment provided via Binder.

Code and dataset for paper "Proteasomal cleavage prediction: state-of-the-art and future directions"

a ruby gem for protein alignments. index the protein alignments, extract the regions of interest, extract the locus, extract the alignments

A collection of projects in bioinformatics.

NLP Recurrent Neural Network for missing aminoacid determination

The repository contains the codes to predict protein crotonylation, existing methods like DEEPKCR and performance values of existing approaches also have been provided here.

The provided code snippet forms a critical component of an automated script aimed at facilitating the prediction of protein structures using the AlphaFold model within a Google Colab environment. The script is tailored to handle the simultaneous upload of multiple input files, each containing multiple protein sequences for prediction.