Chemistry and reactions from non- US patents. Daniel Lowe and Roger Sayle NextMove Software Cambridge, UK

Size: px

Start display at page:

Download "Chemistry and reactions from non- US patents. Daniel Lowe and Roger Sayle NextMove Software Cambridge, UK"

Vernon Wells
6 years ago
Views:

1 Chemistry and reactions from non- US patents Daniel Lowe and Roger Sayle NextMove Software Cambridge, UK

2 Topics Coverage of USPTO vs EPO patents Extraction of non-chemical-compound data Can text-mining provide insights into reaction informatics

3 What am I missing by only using the USPTO data? 248th ACS National Meeting, San Francisco CA, USA 10th August 2014

4 EPO and USPTO background USPTO: 303k grants published in 2013 EPO: 67k grants published in 2013 EPO patents must be in one or more of English, French or German USPTO documents are all in English

5 Epo/USPTO Compounds (using StdInChI) 445,588 3,345,877 2,674,069 USPTO = patent grants patent applications EPO = patent grants and applications

6 Epo/USPTO Reactions (using separately sorted StdInChIs for reactants/agents and products) 99, , ,533 USPTO = patent grants patent applications EPO = patent grants and applications

7 Effect of different Languages Number of structures extracted English German French Translation performed by Lexichem v2014.jun

8 First Disclosure Occurrence by Language All compounds Excluding compounds disclosed by USPTO ( ) patents

9 Timeliness Competitive intelligence requires up to date information Methodology: Consider compounds present in both EPO and USPTO date not disclosed by either prior to 2006 Compare the earliest publication date for each compound

10 Average lag between EPO/USPTO Mean: US 540 days Compound disclosures US more than 5 US 3-5 US 2-3 US 1-2 US 6-12 months US 3-6 months US 1-3 months US 1-4 weeks Within a week US 1-4 weeks US 1-3 months US 3-6 months US 6-12 months US 1-2 Compounds first disclosed between US 2-3 US 3-5 US more than 5

11 70000 Applications Vs Applications Mean: US 223 days Compound disclosures US more than 5 US 3-5 US 2-3 US 1-2 US 6-12 months US 3-6 months US 1-3 months US 1-4 weeks Within a week US 1-4 weeks US 1-3 months US 3-6 months US 6-12 months US 1-2 Compounds first disclosed between US 2-3 US 3-5 US more than 5

12 Grants vs Grants Mean: US 287 days Compound disclosures US more than 5 US 3-5 US 2-3 US 1-2 US 6-12 months US 3-6 months US 1-3 months US 1-4 weeks Within a week US 1-4 weeks US 1-3 months US 3-6 months US 6-12 months US 1-2 Compounds first disclosed between US 2-3 US 3-5 US more than 5

14 Epo/US and chembl19 overlap 1,155,034 6,278, ,486

15 10000 Average lag between Patents/CHEMbl Mean: Patents 345 days Patents 4-5 Patents 3-4 Patents 2-3 Patents 1-2 Patents 0-1 Patents 0-1 Patents 1-2 Patents 2-3 Patents 3-5 Patents 4-5 Compounds first disclosed between

16 Other data in patents Genes/proteins Reactions including role of reagents Physical quantities Spectra Diseases Organisms Companies

17 Gene/protein identification Identify trends in drug target popularity Count number of patents (in a year) mentioning a given gene or its gene products and map to the HGNC symbol Many genes are referenced by short ambiguous terms hence great care is required to have good precision

18 Gene/protein identification EGFR MET Percentage of protein/gene mentions in that year (Patents) 0.35% 0.30% 0.25% 0.20% 0.15% 0.10% 0.05% 0.00% % 0.80% 0.70% 0.60% 0.50% 0.40% 0.30% 0.20% 0.10% 0.00% Percentage of protein/gene mentions in that year (ChEMBL) Percentage of protein/gene mentions in that year (Patents) 0.14% 0.12% 0.10% 0.08% 0.06% 0.04% 0.02% 0.00% % 0.60% 0.50% 0.40% 0.30% 0.20% 0.10% 0.00% Percentage of protein/gene mentions in that year (ChEMBL) (Epidermal growth factor receptor) (Hepatocyte growth factor receptor)

19 Gene/protein identification MTOR PLAT Percentage of protein/gene mentions in that year (Patents) 0.14% 0.12% 0.10% 0.08% 0.06% 0.04% 0.02% 0.00% % 0.40% 0.35% 0.30% 0.25% 0.20% 0.15% 0.10% 0.05% 0.00% Percentage of protein/gene mentions in that year (ChEMBL) Percentage of protein/gene mentions in that year (Patents) 0.50% 0.45% 0.40% 0.35% 0.30% 0.25% 0.20% 0.15% 0.10% 0.05% 0.00% % 0.35% 0.30% 0.25% 0.20% 0.15% 0.10% 0.05% 0.00% Percentage of protein/gene mentions in that year (ChEMBL) (Mammalian target of rapamycin) (Tissue plasminogen activator)

21 Melting/Boiling Point Extraction

22 Melting/Boiling Point Extraction Over 99k so far!

23 CHEMICAL reactions 248th ACS National Meeting, San Francisco CA, USA 10th August 2014

24 Predicting yield Features to consider: 2D fingerprints (especially around the reaction centers) Reaction type Temperature Time Change in complexity e.g. chiral centres

25 Data extraction Can pull out yields, quantities, times and temperatures Can sanity check text-mined yield by calculating from amounts (or even masses) mmmm oo cccccccc(g) mmmmm mmmm [cccc ffff sssssssss](gggg 1 ) = mmmm oo cccccccc mmmm oo ppppppp mmmm oo llllllll rrrrrrrr = %yyyyy

26 Outliers inevitable

27 scale vs yield US applications, Suzuki couplings 248th ACS National Meeting, San Francisco CA, USA 10th August 2014

28 Temperatures

29 Identify Synthetic Routes Occurrences Intermediates Terminal Products Intermediates Terminal Products Number of steps

30 Number of steps vs Complexity ringcomplexityscore = log 10 (nringbridgeatoms + 1) + log 10 (nspiroatoms + 1) stereocomplexityscore = log 10 (nstereocenters + 1) macrocyclepenalty = log 10 (nmacrocycles + 1) sizepenalty = natoms natoms Ertl & Schuffenhauer 2009 doi: /

31 Number of steps vs Complexity Number of product heavy atoms Average number of heavy atoms Number of steps

Yield vs Change in Complexity 2001-2013 US applications, all

32 Yield vs Change in Complexity US applications, all reactions 248th ACS National Meeting, San Francisco CA, USA 10th August 2014

33 Trends in Reaction Types 8.0% Suzuki couplings as a percentage of reactions in a year 7.0% 6.0% 5.0% 4.0% 3.0% 2.0% 1.0% 0.0% Classification performed using NameRXN

34 Trends In Solvent Use 20.0% Percentage of reactions in that year 15.0% 10.0% 5.0% Tetrahydrofuran Dichloromethane Water Dimethylformamide Methanol Ethyl acetate Ethanol 1,4-Dioxane Toluene Acetonitrile Acetic acid Chloroform Acetone Benzene 0.0%

35 Are solvents getting greener? Water (21%) Tetrahydrofuran (15%) Ethanol (11%) Dichloromethane (14%) Benzene (8%) Water (13%) Methanol (7%) Dimethylformamide (10%) Tetrahydrofuran (5%) Methanol (8%) Dichloromethane (4%) Ethyl acetate (7%) Dimethylformamide (4%) Ethanol (5%) Acetic acid (4%) 1,4-Dioxane (4%) Chloroform (3%) Toluene (3%) Acetone (3%) Acetonitrile (3%) Total for top 10: 71% 82%

36 Conclusions A significant amount of novel chemistry, from EPO patents, comes from the non-english patents Compounds disclosed by both the USPTO and EPO are on average published by the USPTO but for many compounds an EPO patent will be the disclosure Gene/protein identification can identify clear changes in patenting behaviour over time Text mining provides the tools to answer many reaction informatics questions

37 Acknowledgements Funding provided by:

38 Thank you for your time!

Honeywell Research Chemicals ACS Grade Solvents

Honeywell Research Chemicals ACS Grade Solvents Research Chemicals Research Chemicals ACS Grade Solvents The American Chemical Society (ACS) Committee on Analytical Reagents sets the specifications for many chemicals used in analytical testing. These