functionality_table.tex

\begin{tblr}[
        long,
        caption={Overview of tskit's functionality, grouped into eight
            broad categories. Every operation listed is implemented in
            tskit; the columns indicate whether each comparison library
            offers a comparable feature: \checkmark{} denotes full
            support, $\circ$ denotes partial or restricted support, and
            a blank cell denotes none.
            }
     ]{
        colspec=Xccc,
        rowhead=1,
        width=\linewidth,
        colsep=3pt,
         }
\hline
Operation & ARGneedle-lib & matUtils (BTE) & DendroPy \\
\hline
\SetCell[c=4]{c} \textbf{Data model}\\
\hline[dashed]
Lossless ARG representation & \checkmark & & \\
Mutations integrated with topology & \checkmark & \checkmark & \\
Integrated reference sequence & & & \\
Individual / ploidy abstraction & $\circ$ & & \\
Population structure encoding & & & \\
Columnar (NumPy) data access & & & \\
\hline[dashed]
\SetCell[c=4]{c} \textbf{File formats}\\
\hline[dashed]
Efficient binary format & \checkmark & \checkmark & \\
VCF export & & \checkmark & \\
Newick export & \checkmark & \checkmark & \checkmark \\
FASTA export & & & \checkmark \\
NEXUS export & & & \checkmark \\
\hline[dashed]
\SetCell[c=4]{c} \textbf{Tree operations}\\
\hline[dashed]
Iterate trees along a genome & & & \\
Tree traversal (pre-/post-order) & & \checkmark & \checkmark \\
MRCA and common-ancestor queries & \checkmark & \checkmark & \checkmark \\
Branch length and total branch length & $\circ$ & \checkmark & \checkmark \\
Tree topology comparison (KC, RF) & \checkmark & & \checkmark \\
Tree balance and shape statistics & & $\circ$ & \checkmark \\
\hline[dashed]
\SetCell[c=4]{c} \textbf{ARG/tree editing}\\
\hline[dashed]
Simplify (sample-restricted history) & & & \\
Subset by sample or clade & & \checkmark & \checkmark \\
Union of tree sequences & & & \\
Keep / delete genomic intervals & $\circ$ & & \\
Trim flanking regions & \checkmark & & \\
\hline[dashed]
\SetCell[c=4]{c} \textbf{Population-genetic statistics}\\
\hline[dashed]
Nucleotide diversity ($\pi$), segregating sites & & $\circ$ & \checkmark \\
Tajima's $D$ & & & \checkmark \\
$F_{ST}$ and divergence & & & \\
$f$-statistics ($f_2$, $f_3$, $f_4$, Patterson's $D$) & & & \\
Allele frequency spectrum (one-way and joint) & & & $\circ$ \\
Linkage disequilibrium & & & \\
Branch-mode statistics on trees & & & \\
\hline[dashed]
\SetCell[c=4]{c} \textbf{Ancestry and relatedness}\\
\hline[dashed]
Link ancestors & & & \\
IBD segment extraction & & & \\
Genealogical nearest neighbours (GNN) & & & \\
Genetic relatedness matrix & \checkmark & & \\
Pairwise divergence / coalescence times & \checkmark & $\circ$ & $\circ$ \\
Mean descendants & & $\circ$ & \\
Extend haplotypes & & & \\
\hline[dashed]
\SetCell[c=4]{c} \textbf{Mutations and variants}\\
\hline[dashed]
Variant / genotype iteration & $\circ$ & \checkmark & \\
Haplotype reconstruction & & \checkmark & \\
Mutation placement / parsimony & \checkmark & \checkmark & \\
\hline[dashed]
\SetCell[c=4]{c} \textbf{Visualisation}\\
\hline[dashed]
SVG tree drawing & & & \\
Tree-sequence (multi-tree) visualisation & & & \\
ASCII / text tree rendering & & & \checkmark \\
\hline[dashed]
\SetCell[c=4]{c} \textbf{Metadata and provenance}\\
\hline[dashed]
Structured metadata with schemas & & $\circ$ & \\
Provenance recording and validation & & & \\
\hline
\end{tblr}