LD data from CEU hg18

LD data from CEU hg18, based on ftp://ftp.ncbi.nlm.nih.gov/hapmap/ld_data/latest

Algo for computing:

import pandas as pd

rule ld_blocks:
    input:
        expand("blocks/{chromosome}_blocks.gz", chromosome=["chr{}".format(c) for c in list(range(1, 23)) + ["X"]])

rule get_blocks:
    output:
        "blocks/{chromosome}_blocks.gz"
    run:

        c = wildcards.chromosome
        f = r"ftp://ftp.ncbi.nlm.nih.gov/hapmap/ld_data/latest/ld_{}_CEU.txt.gz".format(c)
        print(f)
        df = pd.read_csv(f,
                         sep=" ", header=None, usecols=[0, 1, 8])
        print(df.head())

        df.columns = "Start End Block".split()
        ls = df.groupby("Block").agg({"Start": "first", "End": "last", "Block": ["first", "count"]}).reset_index(drop=True)
        ls.columns = "Start End LDBlock Count".split()
        lengths = ls["End"] - ls["Start"]
        ls.insert(ls.shape[1], "Length", lengths)
        ls.insert(0, "Chromosome", c)

        ls.to_csv(output[0], sep="\t", index=None)