1. In Silico Methods for ADMET and Solubility Prediction
Dr John Mitchell
University of St Andrews

2. Outline
Part 1: Computational Toxicology
Part 2: Aqueous Solubility

3. 1. Toxicological Relationships Between Proteins Obtained From a Molecular Spam Filter
Florian Nigsch & John Mitchell
Now at Novartis Institutes, Boston

7. Spam Unsolicited (commercial) email
Approx. 90% of all traffic is spam
Where are the legitimate messages?
Filtering

8. Analogy to Drug Discovery
Huge number of possible candidates
Virtual screening to help in selection process

9. Properties of Drugs High affinity to protein target Soluble Permeable
Absorbable
High bioavailability
Specific rate of metabolism
Renal/hepatic clearance?
Volume of distribution?
Low toxicity
Plasma protein binding?
Blood-Brain-Barrier penetration?
Dosage (once/twice daily?)
Synthetic accessibility
Formulation (important in development)

10. Multiobjective Optimisation
Synthetic accessibility
Bioactivity
Solubility
Toxicity
Permeability
Metabolism
Huge number of candidates …

11. Multiobjective Optimisation
Synthetic accessibility
Bioactivity
Drug
Solubility
Toxicity
U S E L E S S
Permeability
Metabolism
Huge number of candidates … most of which are useless!

12. Feature Space - Chemical Space
m = (f1,f2,…,fn) f3 f3 f2
COX2
CDK2 f1
Feature spaces of high dimensionality
CDK1 f2
DHFR f1

13. Based on circular fingerprints
Features of Molecules
Based on circular fingerprints

14. Combinations of Features
Combinations of molecular features to account for synergies.

15. Winnow Algorithm

16. Protein Target Prediction
Which protein does a given molecule bind to?
Virtual Screening
Multiple endpoint drugs - polypharmacology
New targets for existing drugs
Prediction of adverse drug reactions (ADR)
Computational toxicology

17. Predicted Protein Targets
Selection of 233 classes from the MDL Drug Data Report
~90,000 molecules
15 independent 50%/50% splits into training/test set

18. Predicted Protein Targets
Cumulative probability of correct prediction within the three top-ranking predictions: 82.1% (±0.5%)

19. Computational Toxicology
Model for target prediction
Annotated library of toxic molecules
MDL Toxicity database
~150,000 molecules
For each molecule we predict the likely target
Correlations between predicted protein targets and known toxicity codes
Canonical (23)
Full (490)

20. Toxicological Relationships Outline (1)
Protein target prediction allows us to link (predictively) 150,000 toxic organic molecules to 233 specific protein targets
Each target is treated as a single protein, although may be sets of related proteins
Toxicological databases link (experimentally) these 150,000 molecules to 23 toxicity classes
Combining these two sources of data matches the 233 proteins with the 23 toxicity classes

21. Toxicity Annotations FULL TOXICITY CODES (490)
Y41 : Glycolytic < Metabolism (intermediary) < Biochemical
CANONICAL TOXICITY CODES (23)

22. Toxicological Relationships Outline (2)
For each protein target, we have a profile of association with the 23 toxicity classes
Proteins with similar profiles are clustered together
We demonstrate that these clusters of proteins can be physiologically meaningful.

23. ( ) Predictions Obtained
Highest ranking one IS predicted protein target
Protein code j
Target Prediction
L70 - Changes in liver weight<Liver
Y07 - Hepatic microsomal oxidase<Enzyme inhibition
M30 - Other changes<Kidney, Urether, and Bladder
L30 - Other changes<Liver
Toxicity codes i
Result matrix R = (rij)
rij incremented for each prediction.
Protein targets
Toxcodes ( )
r11
r12 …
r21

24. Proteins by Toxicity Kainic acid receptor Angiotensin II AT2
Cardiac - G
Kainic acid receptor
Adrenergic alpha2
Phosphodiesterase III
cAMP Phosphodiesterase
O6-Alkylguanine-DNA alkyltransferase
Vascular - H
Angiotensin II AT2
Dopamine (D2)
Bombesin
Adrenergic alpha2
5-HT antagonist

25. Top 5 Proteins by Toxicity
68 distinct proteins for 23 toxicity classes, i.e., 3 proteins per canonical toxicity code.
Lanosterol 14alpha-Methyl Demethylase 5
Glucose-6-phosphate Translocase 4
IL-6 4
Benzodiazepine Antagonist 3
Kainic Acid Receptor 3
Proteins and their connectivities

26. Correlation Between Proteins
Correlations between proteins: 233 by 233 correlation matrix
Cluster 1 (proteins 6-11)

27. Carbonic Anhydrase Inhibitor Estrogen Receptor Modulator LHRH Agonist
Cluster 1
Carbonic Anhydrase Inhibitor
Estrogen Receptor Modulator
LHRH Agonist
Aromatase Inhibitor
Cysteine Protease Inhibitor
DHFR Inhibitor
Cluster 1
Within-cluster correlation (without auto-correlation)
r = 0.95
Proteins involved in breast cancer

28. Cluster 1
Proteins involved in breast cancer

29. Literature-based links between these proteins
Tissue-specific transcripts of human steroid sulfatase are under control of estrogen signaling pathways in breast carcinoma, Zaichuk 2007
“aim of this study was to characterize carbonic anhydrase II (CA2), as novel estrogen responsive gene” Caldarelli 2005 CA
This led to premature expression of CAII, a possible explanation for the toxic effects of overexpressed ER.
The Transactivation Domain AF-2 but not the DNA-Binding Domain of the Estrogen Receptor Is Required to Inhibit Differentiation of Avian Erythroid Progenitors, Marieke von Lindern 1998 ER
LHRH
Controversies of adjuvant endocrine treatment for breast cancer and recommendations of the 2007 St Gallen conference, Rabaglio 2007
Cathepsin L Gene Expression and Promoter Activation in Rodent Granulosa Cells, Sriraman 2004
showed that cathepsin L expression in granulosa cells of small, growing follicles in- creased in periovulatory follicles after human chorionic gonadotropin stimulation.
Merchenthaler 2005
Summary of aromatase inhibitor trials: The past and future, Goss 2007
Regulation of collagenolytic cysteine protease synthesis by estrogen in osteoclasts, Furuyama 2000
Aromatase
Cysteine Prot.
Induction by estrogens of methotrexate resistance in MCF-7 breast cancer cells, Thibodeau 1998
DHFR
Antimalarials?

30. Breast Cancer Proteins

31. Cluster 4

32. This cluster links treatment of stomach ulcers to loss of bone mass!

33. Proton Pump Inhibitors etc.
Correlation above 0.98

34. Proton Pump Inhibitors etc.
Correlation above 0.98
Correlation above 0.99

35. Proton Pump Inhibitors etc.
PTH = Parathyroid hormone (84 aa mini-protein)
Proton pump inhibitors used to limit production of gastric acid
PTH is important in the developent/regulation of osteoclasts (cells for bone resorption)
PTH controls levels of Ca2+ in the blood; increased PTH levels are associated with age-related decrease of bone mass
Recent clinical studies showed increased risk of hip fractures resulting from long-term use of proton pump inhibitors. Hence link between PTH and proton pump inhibitors.

36. Conclusions from Part 1
Successful adaptation of algorithm formerly not used in chemoinformatics
Can find correct protein targets for molecules
Hence link proteins together via ligand-binding properties and associations of ligands with toxicities
Identify clinically relevant toxicological relationships between proteins

37. 2. In silico calculation of aqueous solubility
Dr John Mitchell
University of St Andrews

38. Our Methods …
(a) Random Forest (informatics)

39. References

40. Our Random Forest Model …
We want to construct a model that will predict
solubility for druglike molecules …
We don’t expect our model either to use real physics and chemistry or to be easily interpretable …
We do expect it to be fast and reasonably accurate …

41. Random Forest
Machine Learning Method

42. Random Forest for Predicting Solubility
A Forest of Regression Trees
Dataset is partitioned into consecutively smaller subsets (of similar solubility)
Each partition is based upon the value of one descriptor
The descriptor used at each split is selected so as to minimise the MSE
High predictive accuracy
Includes descriptor selection
No training problems – largely immune from overfitting
“Out-of-bag” validation – using those molecules not in the bootstrap samples.
Leo Breiman, "Random Forests“, Machine Learning 45, 5-32 (2001).

43. Dataset
Literature Data
Compiled from Huuskonen dataset and AquaSol database – pharmaceutically relevant molecules
All molecules solid at room temperature
n = 988 molecules
Training = 658 molecules
Test = 330 molecules
MOE descriptors 2D/3D
● Intrinsic aqueous solubility – the thermodynamic solubility of the neutral form in unbuffered water at 25oC
Datasets compiled from diverse literature data may have significant random and systematic errors.

44. Random Forest: Solubility Results
These results are competitive with any other informatics or QSPR solubility prediction method
Random Forest: Solubility Results
RMSE(tr)=0.27
r2(tr)=0.98
Bias(tr)=0.005
RMSE(oob)=0.68
r2(oob)=0.90
Bias(oob)=0.01
RMSE(te)=0.69
r2(te)=0.89
Bias(te)=-0.04
DS Palmer et al., J. Chem. Inf. Model., 47, (2007)

45. Part 2a, Solubility by Random Forest: Conclusions
● Random Forest gives an RMS error of 0.69 logS units.
● These results are competitive with any other informatics or QSPR solubility prediction method.
● The nature of the model is predictive, without offering much insight.

46. Our Methods …
(b) Thermodynamic Cycle (A hybrid of theoretical chemistry & informatics)

47. Reference

48. Our Thermodynamic Cycle method …
We want to construct a theoretical model that will predict solubility for druglike molecules …
We expect our model to use real physics and chemistry and to give some insight …
We may need to include some empirical parameters…
We don’t expect it to be fast by informatics or QSPR standards, but it should be reasonably accurate …

49. For this study Toni Llinàs measured 30 solubilities using the CheqSol method and took another 30 from other high quality studies (Bergstrom & Rytting).
We use a Sirius glpKa instrument

50. Can we use theoretical chemistry to calculate solubility via a thermodynamic cycle?

51. Gsub comes mostly from lattice energy minimisation based on the experimental crystal structure.

52. Gsolv comes from a semi-empirical solvation model (SCRF B3LYP/6-31G
Gsolv comes from a semi-empirical solvation model (SCRF B3LYP/6-31G* in Jaguar)
This is likely to be the least accurate term in our equation.
We also tried SM5.4 with AM1 & PM3 in Spartan, with similar results.

53. Gtr comes from ClogP
ClogP is a fragment-based (informatics) method of estimating the octanol-water partition coefficient.

55. What Error is Acceptable?
For typically diverse sets of druglike molecules, a “good” QSPR will have an RMSE ≈ 0.7 logS units.
An RMSE > 1.0 logS unit is probably unacceptable.
This corresponds to an error range of 4.0 to 5.7 kJ/mol in Gsol.

56. What Error is Acceptable?
A useless model would have an RMSE close to the SD of the test set logS values: ~ 1.4 logS units;
The best possible model would have an RMSE close to the SD resulting from the experimental error in the underlying data:
~ 0.5 logS units?

57. Results from Theoretical Calculations
● Direct calculation was a nice idea, but didn’t quite work – errors larger than QSPR
● “Why not add a correction factor to account for the difference between the theoretical methods?”
● This was originally intended to calibrate the different theoretical approaches, but …

58. …
● Within a week this had become a hybrid method, essentially a QSPR with the theoretical energies as descriptors

59. Results from Hybrid Model

60. This regression equation gives r2=0.77 and RMSE=0.71

61. How Well Did We Do?
For a training-test split of 34:26, we obtain an RMSE of 0.71 logS units for the test set.
This is comparable with the performance of “pure” QSPR models.
This corresponds to an error of about 4.0 kJ/mol in Gsol.

62. Drug Disc.Today, 10 (4), 289 (2005)
Gsolv & ClogP
Ssub & b_rotR
Ulatt

63. Part 2b, Solubility by TD Cycle: Conclusions
● We have a hybrid part-theoretical, part-empirical method.
● An interesting idea, but relatively low throughput - and an experimental (or possibly predicted?) crystal structure is needed.
● Similarly accurate to pure QSPR for a druglike set.
● Instructive to compare with literature of theoretical solubility studies.

64. Thanks Unilever Dr Florian Nigsch Pfizer & PIPMS Dr Dave Palmer
Pfizer (Dr Iñaki Morao, Dr Nick Terrett & Dr Hua Gao)