1.get_neighbors

将两个蛋白质之间所有alphaC计算距离，然后保留小于 cutoff 的那些对确定邻居。
return r1, r2, is_neighbor(r1[i], r2[i]) == True

def _get_ca_neighbors(df0, df1, cutoff):
    """Get neighbors for alpha-carbon based distance."""
    ca0 = df0[df0['atom_name'] == 'CA']
    ca1 = df1[df1['atom_name'] == 'CA']

    dist = spa.distance.cdist(ca0[['x', 'y', 'z']], ca1[['x', 'y', 'z']])
    pairs = np.array(np.where(dist < cutoff)).T
    if len(pairs) == 0:
        return [], []
    res0 = ca0.iloc[pairs[:, 0]][['pdb_name', 'model', 'chain', 'residue']]
    res1 = ca1.iloc[pairs[:, 1]][['pdb_name', 'model', 'chain', 'residue']]
    res0 = res0.reset_index(drop=True)
    res1 = res1.reset_index(drop=True)
    return res0, res1

2.get_pair

从复合物（complex）中生成配对信息, $n^2$的遍历复合物中所有链，找匹配

def _get_all_chain_pairs(complex, df, nb_fn, filename, full):
    """Get all possible chain pairs from provided dataframe."""

    pairs = []
    # We reset the index here so each's chain dataframe can be treated
    # independently.
    groups = [(x[0], x[1].reset_index(drop=True))
              for x in df.groupby(['chain', 'model'])]
    num_chains = len(groups)
    num_pairs = 0
    pair_idx = 0
    for i in range(num_chains):
        (chain0, df0) = groups[i]
        for j in range(i + 1, num_chains):
            (chain1, df1) = groups[j]
            res0, res1 = nb_fn(df0, df1)
            if len(res0) == 0:
                # No neighbors between these 2 chains.
                continue
            else:
                num_pairs += 1
            pos0 = struct.get_ca_pos_from_residues(df0, res0)
            pos1 = struct.get_ca_pos_from_residues(df1, res1)
            pos_idx, neg_idx = _get_positions(df0, pos0, df1, pos1, full)
            srcs = {'src0': filename, 'src1': filename}
            pair = Pair(complex=complex.name, df0=df0, df1=df1,
                        pos_idx=pos_idx, neg_idx=neg_idx, srcs=srcs,
                        id=pair_idx)
            pairs.append(pair)
            pair_idx += 1
    return pairs, num_chains