Skip to content

Migrated trrosetta and rhofold shs evaluation - #5

Open
scheuerdo wants to merge 2 commits into
mainfrom
repo-migration
Open

Migrated trrosetta and rhofold shs evaluation#5
scheuerdo wants to merge 2 commits into
mainfrom
repo-migration

Conversation

@scheuerdo

Copy link
Copy Markdown
Collaborator

No description provided.

@scheuerdo
scheuerdo marked this pull request as ready for review September 4, 2026 17:07
Copilot AI lite review requested due to automatic review settings September 4, 2026 17:07

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🔵 Needs a closer look

It adds a very large amount of dataset content directly to git, which can have significant repository-size and CI/operational impact and should be validated by a human reviewer.

Pull request overview

This PR migrates the input datasets used for trRosetta/RhoFold SHS evaluation into the repository by adding many prepared RNA sequence files (FASTA) and MSA inputs (A3M) across multiple dataset variants (e.g., spotRNA, RNAfold, RNAformer, denoised monomers).

Changes:

  • Add prepared SHS input FASTA files for multiple upstream sources (spotRNA/RNAfold/RNAformer and monomer-denoise variants).
  • Add prepared DB MSA inputs as both FASTA and A3M (query + alignments where available).
  • Add prepared “MSA + SHS” input datasets for RNAformerN100.
File summaries
File Description
tr_rhofold_shs_eval/prepared_shs_inputs_from_spotrna_folder/fasta/* Adds spotRNA-derived SHS evaluation FASTA inputs.
tr_rhofold_shs_eval/prepared_shs_inputs_from_rnaformerN100_folder/fasta/* Adds RNAformerN100-derived SHS evaluation FASTA inputs.
tr_rhofold_shs_eval/prepared_shs_inputs_from_rnafold_folder/fasta/* Adds RNAfold-derived SHS evaluation FASTA inputs.
tr_rhofold_shs_eval/prepared_shs_inputs_from_rna_monomers_spotrna_denoise_folder/fasta/* Adds denoised monomer FASTA inputs derived from spotRNA.
tr_rhofold_shs_eval/prepared_shs_inputs_from_rna_monomers_rnafold_denoise_folder/fasta/* Adds denoised monomer FASTA inputs derived from RNAfold.
tr_rhofold_shs_eval/prepared_shs_inputs_from_rna_monomers_dssrN100_folder/fasta/* Adds DSSR N100 monomer FASTA inputs for evaluation.
tr_rhofold_shs_eval/prepared_msa_plus_shs_from_rnaformerN100_folder/fasta/* Adds RNAformerN100 “MSA + SHS” FASTA inputs.
tr_rhofold_shs_eval/prepared_db_msa_inputs/fasta/* Adds FASTA inputs used as query sequences for DB MSA preparation.
tr_rhofold_shs_eval/prepared_db_msa_inputs/a3m/* Adds A3M MSA outputs (query plus alignments when available).
Review details
  • Files reviewed: 209/1789 changed files
  • Comments generated: 1
  • Review effort level: Lite

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

Comment on lines +1 to +2
>9DE8
GGUCUCUCUGGUUAAGCCAGAUCUGAGCCGAAAAGCUCUCUGGCUAACUAGGGAAC
The folder carried settings from the cluster it was run on:

- envs/*.yml ended with a `prefix:` line pointing at a personal conda
  env path (conda ignores it on `env create`, so nothing is lost).
- The `json_file` column of every prepared_*/metadata manifest held
  absolute workspace paths; they are now relative to the repo
  (../data/datafiles/...) or to this folder (./...), keeping the
  provenance without the machine.
- Three job scripts had a disabled --mail-user with a real address,
  now a placeholder.

The remaining site-specific settings (SLURM partitions, CUDA module,
GPU types, conda env names, walltimes) are part of how the jobs run, so
README section 1.5 documents each one and how to override it instead.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Fjk8bfcYyYrUY6xcfn2yFd
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants