Protein abundance from coding sequence (E. coli)

Overview

Protein abundance (PaxDb, parts per million) of 3,333 Escherichia coli genes predicted from their coding sequence alone, the protein-abundance task of CaLM (Outeiral & Deane, Nature Machine Intelligence 2024): Spearman correlation of a model's zero-shot pseudo-log-likelihood and of a ridge probe on frozen embeddings, plus the probe's RMSE. Comparable across codon, RNA and DNA language models, on a permissively licensed source.

Leaderboard

Ranked results, with their source, uncertainty and floors, the protocol and a sample of the data are on the Leaderboard tab.