Skip to content

Commit 6e9864d

Browse files
MrtinoRGMrtinoRG
committed
feat: add final version
1 parent 53ba396 commit 6e9864d

142 files changed

Lines changed: 20105 additions & 1753 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎convert_book/convert_to_quarto_book.py‎

Lines changed: 102 additions & 394 deletions
Large diffs are not rendered by default.

‎convert_book/new_table.md‎

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
**Representation** **Encoded information** **Description** **Example**
2+
---------------------------------------------------------------------------------------------------------------- -------------------------------------------------------------------------- ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
3+
Elemental composition Stoichiometry Always available, but non-unique. C9H8O4
4+
iupac name Stoichiometry, bonding, geometry Universally understood, systematic nomenclature, unmanageable for large molecules, and lacks detailed 3D information. 2-acetyloxybenzoic acid
5+
smiles (weininger1988smiles) Stoichiometry, bonding Massive public corpora and tooling support, however, there are several valid strings per molecule, and it does not contain spatial information. `CC(=O)OC1=CC=CC=C1C(=O)O`, `O=C(O)c1ccccc1OC(C)=O`, *etc.*
6+
selfies (krenn2020self; @cheng2023group) Stoichiometry, bonding 100% syntactic and semantic validity by construction, including meaningful grouping. `[C][C][=Branch1][C][=O][O][C][=C][C][=C][C][=C][Ring1][=Branch1][C][=Branch1][C][=O][O]`
7+
inchi Stoichiometry, bonding Canonical one-to-one identifier; encodes stereochemistry layers. `InChI=1S/C9H8O4/c1-6(10)13-8-5-3-2-4-7(8)9(11)12/h2-5H,1H3,(H,11,12)`
8+
Graphs Stoichiometry, bonding, geometry Strong inductive bias that works with gnns. Symmetry-equivariant variants available. Long-range interactions are implicit. *[Image: figures/Aspirin.png]*
9+
xyz representation Stoichiometry, geometry Exact spatial detail. It is high dimensional, and orientation alignment is needed. 1.2333 0.5540 0.7792 O -0.6952 -2.7148 -0.7502 O 0.7958 -2.1843 0.8685 O 1.7813 0.8105 -1.4821 O -0.0857 0.6088 0.4403 C ...
10+
Multimodal Stoichiometry, bonding, geometry, symmetry, periodicity, coarse graining Combines complementary signals; boosts robustness and coverage. It is hard to implement, the complexity scales with the amount of representations, some modalities are data-scarce, and the information encoded totally depends on the modalities included. *[Image: figures/60031761.jpeg]*
11+
cif (hall1991crystallographic) Stoichiometry, bonding, geometry, periodicity Standardized and widely supported, however, it carries heterogeneous keyword sets and parser overhead `data_Si _symmetry_space_group_name_H-M ’P 1’ _cell_length_a 3.85 …_cell_angle_alpha 60.0 …_symmetry_Int_Tables_number 1 _chemical_formula_structural Si _chemical_formula_sum Si2 _cell_volume 40.33 _cell_formula_units_Z 2 loop_ _symmetry_equiv_pos_site_id _symmetry_equiv_pos_as_xyz 1 ’x, y, z’ loop_ _atom_type_symbol _atom_type_oxidation_number Si0+ 0.0loop_ _atom_site_type_symbol _atom_site_label _atom_site_symmetry_multiplicity _atom_site_fract_x …_atom_site_occupancy Si0+ Si0 1 0.75 0.75 0.75 1.0 Si0+ Si1 1 0.0 0.0 0.0 1.0`
12+
Condensed cif (gruver2024finetuned; @antunes2024crystal) Stoichiometry, geometry, symmetry, periodicity Good for crystal generation tasks. It omits occupancies and defects, custom tooling is needed, and only works for crystals `3.8 3.8 3.8 59 59 59 Si0+ 0.75 0.75 0.75 Si0+ 0.00 0.00 0.00`
13+
SLICES (Xiao_2023) Stoichiometry, bonding, periodicity Invertible, symmetry-invariant and compact for general crystals. However, it carries ambiguity for disordered sites `Si Si 0 1 + + + 0 1 + + o 0 1 + o + 0 1 o + +`
14+
Local-Env (alampara2024mattext) Stoichiometry, bonding, symmetry, coarse graining Treats each coordination polyhedron as a "molecule", it is transferable and compact; but it ignores long-range order and its reconstruction requires post-processing `R-3m Si (2c) [Si][Si]([Si])[Si]`
15+
Natural-language description (ganose2019robocrystallographer) Stoichiometry, bonding, geometry, symmetry, periodicity, coarse graining It is human-readable and more intuitive tokenizable by llms. However, trying to encode all the information can lead to verbose, ambiguous descriptions. "Silicon crystallizes in the diamond-cubic structure, a lattice you can picture as two face-centred-cubic frameworks gently interpenetrating..."

‎convert_book/new_table.tex‎

Whitespace-only changes.

‎convert_book/simple_table.tex‎

Lines changed: 39 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,39 @@
1+
\begin{tabular}{%
2+
>{\raggedright\arraybackslash}p{0.20\textwidth}
3+
>{\raggedright\arraybackslash}p{0.15\textwidth}
4+
>{\raggedright\arraybackslash}p{0.25\textwidth}
5+
>{\raggedright\arraybackslash}p{0.32 \textwidth}
6+
}
7+
8+
\toprule
9+
\textbf{Representation} & \textbf{Encoded information} & \textbf{Description} & \textbf{Example} \\
10+
\midrule
11+
12+
\midrule
13+
14+
Elemental composition & Stoichiometry & Always available, but non-unique. & C9H8O4 \\
15+
\addlinespace
16+
\gls{iupac} name & Stoichiometry, bonding, geometry & Universally understood, systematic nomenclature, unmanageable for large molecules, and lacks detailed 3D information. & 2-acetyloxybenzoic acid \\
17+
\addlinespace
18+
\gls{smiles} \autocite{weininger1988smiles} & Stoichiometry, bonding & Massive public corpora and tooling support, however, there are several valid strings per molecule, and it does not contain spatial information. & \footnotesize \texttt{CC(=O)OC1=CC=CC=C1C(=O)O}, \texttt{O=C(O)c1ccccc1OC(C)=O}, \emph{etc.} \\
19+
\addlinespace
20+
\gls{selfies} \autocite{krenn2020self,cheng2023group} & Stoichiometry, bonding & 100\% syntactic and semantic validity by construction, including meaningful grouping. & \footnotesize \texttt{[C][C][=Branch1][C][=O][O][C][=C][C][=C][C][=C][Ring1][=Branch1][C][=Branch1][C][=O][O]} \\
21+
\addlinespace
22+
\gls{inchi} & Stoichiometry, bonding & Canonical one-to-one identifier; encodes stereochemistry layers. & \footnotesize \texttt{InChI=1S/C9H8O4/c1-6(10)13-8-5-3-2-4-7(8)9(11)12/h2-5H,1H3,(H,11,12)} \\
23+
\addlinespace
24+
Graphs & Stoichiometry, bonding, geometry & Strong inductive bias that works with \glspl{gnn}. Symmetry-equivariant variants available. Long-range interactions are implicit. & [Image: figures/Aspirin.png] \\
25+
\addlinespace
26+
xyz representation & Stoichiometry, geometry & Exact spatial detail. It is high dimensional, and orientation alignment is needed. & \footnotesize 1.2333 0.5540 0.7792 O -0.6952 -2.7148 -0.7502 O 0.7958 -2.1843 0.8685 O 1.7813 0.8105 -1.4821 O -0.0857 0.6088 0.4403 C \ldots \\
27+
\addlinespace
28+
Multimodal & Stoichiometry, bonding, geometry, symmetry, periodicity, coarse graining & Combines complementary signals; boosts robustness and coverage. It is hard to implement, the complexity scales with the amount of representations, some modalities are data-scarce, and the information encoded totally depends on the modalities included. & [Image: figures/60031761.jpeg] \\
29+
\addlinespace
30+
\gls{cif} \autocite{hall1991crystallographic} & Stoichiometry, bonding, geometry, periodicity & Standardized and widely supported, however, it carries heterogeneous keyword sets and parser overhead & \footnotesize \texttt{data\_Si \_symmetry\_space\_group\_name\_H-M 'P 1' \_cell\_length\_a 3.85 \ldots \_cell\_angle\_alpha 60.0 \ldots \_symmetry\_Int\_Tables\_number 1 \_chemical\_formula\_structural Si \_chemical\_formula\_sum Si2 \_cell\_volume 40.33 \_cell\_formula\_units\_Z 2 loop\_ \_symmetry\_equiv\_pos\_site\_id \_symmetry\_equiv\_pos\_as\_xyz 1 'x, y, z' loop\_ \_atom\_type\_symbol \_atom\_type\_oxidation\_number Si0+ 0.0loop\_ \_atom\_site\_type\_symbol \_atom\_site\_label \_atom\_site\_symmetry\_multiplicity \_atom\_site\_fract\_x \ldots \_atom\_site\_occupancy Si0+ Si0 1 0.75 0.75 0.75 1.0 Si0+ Si1 1 0.0 0.0 0.0 1.0}\\
31+
\addlinespace
32+
Condensed \gls{cif} \autocite{gruver2024finetuned, antunes2024crystal} & Stoichiometry, geometry, symmetry, periodicity & Good for crystal generation tasks. It omits occupancies and defects, custom tooling is needed, and only works for crystals & \footnotesize \texttt{3.8 3.8 3.8 59 59 59 Si0+ 0.75 0.75 0.75 Si0+ 0.00 0.00 0.00}\\
33+
\addlinespace
34+
\glslink{slices}{SLICES} \autocite{Xiao_2023} & Stoichiometry, bonding, periodicity & Invertible, symmetry-invariant and compact for general crystals. However, it carries ambiguity for disordered sites & \footnotesize \texttt{Si Si 0 1 + + + 0 1 + + o 0 1 + o + 0 1 o + +} \\
35+
\addlinespace
36+
\glslink{localenv}{Local-Env}\autocite{alampara2024mattext} & Stoichiometry, bonding, symmetry, coarse graining & Treats each coordination polyhedron as a \enquote{molecule}, it is transferable and compact; but it ignores long-range order and its reconstruction requires post-processing & \footnotesize \texttt{R-3m Si (2c) [Si][Si]([Si])[Si]} \\
37+
\addlinespace
38+
Natural-language description \autocite{ganose2019robocrystallographer} & Stoichiometry, bonding, geometry, symmetry, periodicity, coarse graining & It is human-readable and more intuitive tokenizable by \glspl{llm}. However, trying to encode all the information can lead to verbose, ambiguous descriptions. & \enquote{Silicon crystallizes in the diamond-cubic structure, a lattice you can picture as two face-centred-cubic frameworks gently interpenetrating\ldots} \\
39+
\end{tabular}

0 commit comments

Comments
 (0)