Leandro de Mattos Pereira's repositories
Annotation-genome-graphics
R scripts for genome annotation graphs
Microbiota-MetaAnalyser
Microbiota Coral 16S MetaAnalyser
alphafold
Open source code for AlphaFold.
Aminoacid-cost-of-protein
genomic analysis
applied-ml
đź“š Papers & tech blogs by companies sharing their work on data science & machine learning in production.
awesome-AI-based-protein-design
A collection of research papers for AI-based protein design
bigslice
A highly scalable, user-interactive tool for the large scale analysis of Biosynthetic Gene Clusters data
BioAutoMATED
Automated machine learning for analyzing, interpreting, and designing biological sequences
ColabFold
Making Protein folding accessible to all!
deept2
DeepT2 utilizes deep learning techniques to identify type II polyketide (T2PK) synthases KSβ and their corresponding T2PK product within bacterial genomes. The method leverages ESM2 to transform KSβ sequences into embeddings, which are employed to train two separate classifiers using multi-layer perceptron for both KSβ and T2PKs classification.
druggpt
DrugGPT: A GPT-based Strategy for Designing Potential Ligands Targeting Specific Proteins
evodiff
Generation of protein sequences and evolutionary alignments via discrete diffusion models
exbert
A Visual Analysis Tool to Explore Learned Representations in Transformers Models
GPT_protein_design
Efficient protein de novo design pipeline with GPT-based generator and transfer learning-based discrminator
HGTector
HGTector2: Genome-wide prediction of horizontal gene transfer based on distribution of sequence homology patterns.
MJPythonNotebooks
Visualizing gene tree conflict using Phyparts, and ETE3
ncbi-genome-download
Scripts to download genomes from the NCBI FTP servers
openai-cookbook
Examples and guides for using the OpenAI API
papers_for_protein_design_using_DL
List of papers about Proteins Design using Deep Learning
pb-metagenomics-tools
pb-metagenomics-tools
ProtTrans
ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.
rodeo2
This isn't our first RODEO. The new and improved RODEO is written in Python and supports lasso peptide, class I lanthipeptide, sactipeptide and thiopeptide precursor prediction.
start-llms
A complete guide to start and improve your LLM skills in 2023 with little background in the field and stay up-to-date with the latest news and state-of-the-art techniques!