Open Resources of LucaProt

Welcome to our data repository. You can download the datasets and model files below:

• All_Contigs/
  Including all contig sequences.
• All_Protein_Sequences/
  All input protein sequences of prediction (length >= 300aa).
• Benchmark/
  LucaProtApp: prediction on unlabeled sequences and performance metrics.
• Known_RdRPs/
  All known RdRPs (5979) for ClstrSearch and LucaProt.
• LucaProt/
  Raw data, training datasets, model code, trained models, and identification results.
• Results/
  All the results obtained in our study.
• SG_predicted_protein_structure_supplementation/
  AlphaFold2 predicted structures.
• Self_Sequencing_Proteins/
  Translated protein sequences from self-sequenced data.
• Self_Sequencing_Reads/
  Raw RNA/DNA reads. (Also available on NCBI SRA: PRJNA956286, PRJNA956287)
• Serratus/
  Serratus RdRPs and LucaProt prediction results.
• README.md
  Project documentation.