1. Automated extraction of reaction data from text Daniel Lowe, Lezan Hawizy, David Jessop, Peter Murray-Rust

2. Summary Millions of reactions published each year (articles, patents, theses) Open-Source Software can extract >90% with >90% accuracy 100,000 reactions/day on a desktop It works in an Open environment. The only remaining barrier is human will and organization

3. Typical experimental description To a solution of 3-bromobenzophenone (1.00 g, 4 mmol) in MeOH (15 mL) was added sodium borohydride (0.3 mL, 8 mmol) portionwise at rt and the suspension was stirred at rt for 1-24 h. The reaction was diluted slowly with water and extracted with CH2Cl2. The organic layer was washed successively with water, brine, dried over Na2SO4, and concentrated to give the title compound as oil (0.8 g, 79%), which was used in the next reaction without further purification. MS (ESI, pos. ion) m/z: 247.1 (M-OH).

4. Chemical tagging To a solution of 3-bromobenzophenone ( 1.00 g, 4 mmol )

5. To a solution of 3-bromobenzophenone (1.00 g, 4 mmol) in MeOH (15 mL) was added sodium borohydride (0.3 mL, 8 mmol) portionwise at rt and the suspension was stirred at rt for 1-24 h. The reaction was diluted slowly with water and extracted with CH2Cl2. The organic layer was washed successively with water, brine, dried over Na2SO4, and concentrated to give the title compound as oil (0.8 g, 79%), which was used in the next reaction without further purification. MS (ESI, pos. ion) m/z: 247.1 (M-OH).

6. Phase type can be used to identify products of a reaction and those that are involved in workup

7. Sample of XML output title compound 0.8 79.0 BrC=1C=C(C=CC1)C(O)C1=CC=CC=C1 InChI=1/C13H11BrO/c14-12-8-4-7-11(9-12)13(15)10-5-2-1-3-6-10/h1-9,13,15H product definiteReference oil 3-bromobenzophenone 4 1.00 BrC=1C=C(C(=O)C2=CC=CC=C2)C=CC1 InChI=1/C13H9BrO/c14-12-8-4-7-11(9-12)13(15)10-5-2-1-3-6-10/h1-9H reactant exact Quantities including yield are extracted SMILES and InChI generated where possible Entity is classified as an exact compound, definite reference, chemical class or polymer

8. Atom mapped graphical output

9. A more complicated example Step c: 2-[4-(3,4-dichlorophenyl)-2-methylamino-thieno[2,3- d]pyrimidine-6-yl]-propan-2-ol. The crude sulfone from step (b) was dissolved in THF (5 mL). To this solution was added MeNH2 (2M in THF, 5 mL). The mixture was stirred in a sealed tube at 70° C. for 12 hours. The reaction mixture was then cooled, concentrated, and subjected to preparatory HPLC for purification (30-80% CH3CN/H2O gradient over 30 minutes). The desired fractions were concentrated and then subjected to extraction with CHCl3 (20 mL) and NaOH (5% aq, 20 mL). The chloroform solution was dried (Na2SO4), filtered, and concentrated to afford the title compound as a white solid (0.055 g, 33% over 3 steps).1H NMR (CDCl3, 400 MHz) d 7.94 (d, 1H, J=2.0 Hz), 7.66 (dd, 1H, J1=8.4 Hz, J2=2.0 Hz), 7.56 (d, 1H, J=8.4 Hz), 7.01 (s, 1H), 5.37 (q, 1H, J=4.8 Hz), 3.07 (d, 3H, J=4.8 Hz), 2.50 (br s, 1H), 1.67 (s, 6H). LCMS (M+H=368.1 @ 7.37 minutes). Identified as an inline heading Resolved to product from step B

10. Atom mapped graphical output

11. Summary Automated synthesis absolutely requires complete capture of the literature. The technology is solved. It’s up to you whether you want it to happen. http://wwmm.ch.cam.ac.uk/ OSCAR, OPSIN, ChemicalTagger http://wwmm.ch.cam.ac.uk/