evolutionary-constraint
FishCaduceus-Evolutionary-Constraint-Benchmark
FishCaduceus Evolutionary Constraint Benchmark
Dataset description
This dataset contains sequence-based benchmarks for evaluating whether FishCaduceus representations capture evolutionary constraint in fish genomes.
Constraint labels were derived from a 26-fish whole-genome alignment generated with Progressive Cactus. Grass carp (Ctenopharyngodon idella) was used as the primary reference genome for defining aligned and conserved positions. The resulting labeled… See the full description on the dataset page: https://huggingface.co/datasets/FishCaduceus/FishCaduceus-Evolutionary-Constraint-Benchmark.evolutionary-constraint
Evolutionary constraint prediction
Reproducing this dataset
import pandas as pd
CENTER_POSITION = 255
NUCLEOTIDES = list("ACGT")
df = pd.read_csv("hf://datasets/kuleshov-group/cross-species-single-nucleotide-annotation/Evolutionary_constraint/valid.tsv", sep="\t")
df = df.rename(columns={"sequences": "seq"})
df["chrom_pos"] = df.pos
df["pos"] = CENTER_POSITION
df["ref"] = df.seq.str[CENTER_POSITION]
def subsample(df, n, seed):
return (… See the full description on the dataset page: https://huggingface.co/datasets/plantcad/evolutionary-constraint.