Recommended
Recommended
More Related Content
Similar to Computational tools for drug discovery
Similar to Computational tools for drug discovery (20)
More from Eszter Szabó
More from Eszter Szabó (7)
Recently uploaded
Recently uploaded (20)
Computational tools for drug discovery
- 1. Computational tools for drug discovery Akos Tarcsay
- 3. Motivation
- 7. Fate of drugs in the human body https://doi.org/10.1038/nrd1032
- 9. ~20k non-modified (canonical) human proteins 1 target to engage with Target, the William Tell’s challenge https://doi.org/10.1038/nrd892
- 10. Rubik cube for medicinal chemists - Medicinal chemistry optimization is multi-dimensional problem - Each chemical modification corresponds to a series of biological activity changes - Rubik’s cube has 43 252 003 274 489 856 000 (1019 ) different configurations - All configurations can be solved in ~20 steps - Druggable chemical space is ~1060 https://doi.org/10.1016/j.drudis.2011.05.005
- 12. Practice of in silico methods
- 14. Challenge
- 17. Interactions
- 18. Scale Ki or IC50 or EC50 M [mol/dm3] ΔG [kJ/mol] ΔG [kCal/mol] Affinity 0.1 100 mM -5,7 -1,4 Weak 0.01 10 mM -11,4 -2,7 0.001 1 mM -17,1 -4,1 0.0001 100 uM -22,8 -5,5 0.00001 10 uM -28,5 -6,8 Medium 1.00E-06 1 uM -34,2 -8,2 1.00E-07 100 nM -39,9 -9,5 Strong 1.00E-08 10 nM -45,6 -10,9 1.00E-09 1 nM -51,3 -12,3 1.00E-10 100 pM -57,0 -13,6 Very strong 1.00E-11 10 pM -62,8 -15,0 1.00E-12 1 pM -68,5 -16,4
- 19. Ki or IC50 or EC50 M [mol/dm3] ΔG [kJ/mol] ΔG [kCal/mol] Affinity 0.1 100 mM -5,7 -1,4 Weak 0.01 10 mM -11,4 -2,7 0.001 1 mM -17,1 -4,1 0.0001 100 uM -22,8 -5,5 0.00001 10 uM -28,5 -6,8 Medium 1.00E-06 1 uM -34,2 -8,2 1.00E-07 100 nM -39,9 -9,5 Strong 1.00E-08 10 nM -45,6 -10,9 1.00E-09 1 nM -51,3 -12,3 1.00E-10 100 pM -57,0 -13,6 Very strong 1.00E-11 10 pM -62,8 -15,0 1.00E-12 1 pM -68,5 -16,4 Scale https://doi.org/10.1021/jm100112j
- 20. Ki of 1 nM. Replacing the isopropyl group (marked in red) by hydrogen reduces the affinity to 39 μM. https://doi.org/10.1021/jm100112j Ki or IC50 or EC50 M [mol/dm3] ΔG [kJ/mol] ΔG [kCal/mol] Affinity 0.1 100 mM -5,7 -1,4 Weak 0.01 10 mM -11,4 -2,7 0.001 1 mM -17,1 -4,1 0.0001 100 uM -22,8 -5,5 0.00001 10 uM -28,5 -6,8 Medium 1.00E-06 1 uM -34,2 -8,2 1.00E-07 100 nM -39,9 -9,5 Strong 1.00E-08 10 nM -45,6 -10,9 1.00E-09 1 nM -51,3 -12,3 1.00E-10 100 pM -57,0 -13,6 Very strong 1.00E-11 10 pM -62,8 -15,0 1.00E-12 1 pM -68,5 -16,4 Scale
- 24. Non-additivity
- 27. The Nature of Chemistry Environment: pH, solvent, … Impacts: - Tautomerism - Ionization, microspecies - Solubility - Lipophilicity By IconMark, PH from the Noun Project
- 28. Histidine, a simple amino acid Strongest basic pKa: 9.44 Strongest acidic pKa: 1.85
- 29. Histidine, a simple amino acid Basic pKa: 9.44, 6.61 Acidic pKa: 1.85, 12.94
- 30. Histidine, a simple amino acid https://disco.chemaxon.com/calculators/demo/playground/
- 32. https://pubs.acs.org/doi/10.1021/acs.jcim.0c00232 Tautomerization effect CBR14->CBR18: QM-based rule update Calculated phys-chem properties
- 33. „The fundamental laws necessary for the mathematical treatment of a large part of physics and the whole of chemistry are thus completely known
- 34. „The fundamental laws necessary for the mathematical treatment of a large part of physics and the whole of chemistry are thus completely known, and the difficulty lies only in the fact that application of these laws leads to equations that are too complex to be solved. „ (Paul Dirac, 1929)
- 36. - Ligand only QM: ESP, torsional scan, tautomers, interactions MM: flexible-rigid alignment - Flexible ligand and rigid protein Docking, scoring functions Levels of approximations
- 37. QM application: Halogen bond https://pubs.acs.org/doi/10.1021/jm3012068
- 39. B3LYP, 6-311++ G(2d,2p) https://doi.org/10.1021/ml100016x QM application: Site of metabolism prediction:SMARTCyp
- 40. https://doi.org/10.1021/ml100016x QM application: Site of metabolism prediction:SMARTCyp
- 44. https://doi.org/10.1007/s10822-015-9883-y Docking into MD frames: 5HT6
- 45. - Flexible ligand flexible protein Induced fit docking MD - Ensemble docking Free energy perturbation
- 46. Free energy perturbation Thermodynamic cycle https://doi.org/10.1007/978-1-4939-9608-7
- 47. Alchemical transformation FEP + - Hamiltonian replica exchange method - region surrounding the protein binding pocket is “heated up” - the rest of the system stays “cold” - GPU calculation involving ~6000 atoms requires ~6h (4/day) https://doi.org/10.1007/978-1-4939-9608-7
- 49. 1. Availability of at least one high-quality crystal structure with co-crystallized series ligand. 2. A reasonable expectation of a conserved binding mode across the series. 3. Minimal tautomeric, ionization state, and stereochemistry uncertainties across the series. 4. High reliability experimental binding data from the same assay for all compounds. 5. Assay data and crystal structures are for the same protein construct. Constraints https://doi.org/10.1007/978-1-4939-9608-7
- 51. In God we trust, all others bring data. William Edwards Deming Trevor Hastie, Robert Tibshirani, Jerome Friedman The Elements of Statistical Learning Data Mining, Inference, and Prediction
- 52. Drug discovery data is expensive https://doi.org/10.1038/nrd4128
- 53. Drug discovery data is expensive
- 61. Validation and error prediction
- 65. Z = (z1 , z2 , . . . , zN ) where zi = (xi , yi ) B times producing B bootstrap datasets with replacement S(Z) is any quantity computed from the data Z Bootstrap methods
- 67. Conformal prediction Proper Training Set Model Error model Calibration set Error Prediction Training Set P(80%) calibration factor (ɑ)
- 68. Classification validation: confusion matrix https://doi.org/10.1186/s12864-019-6413-7
- 70. P(A|B)=P(B|A)xP(A)/P(B) 99% sensitivity 99% specificity 0.5% positive cases Bayes theorem
- 71. P(A|B)=P(B|A)xP(A)/P(B) 99% sensitivity 99% specificity 0.5% positive cases P(TP|+)=0.99*0.005/[0.99*0.005+0.01*0.995]=33.2% If the test is positive, still there is only 33.2% chance to be true positive. 1000 cases, 995 negative, 5 positive 995*0.01 = 10 false positive 5*0.99~5 Sum positive 15, true positive = 5 (33%) Bayes theorem
- 72. Drug discovery data is expensive
- 73. Generating models on confidential data https://arxiv.org/pdf/1610.05755.pdf
- 75. Phys-chem: lipophilicity (logP/logD), pka, solubility, donors, acceptors Topological: polar surface are, ring count, bond counts, fsp3, graph distance indices, donor count, acceptor count Descriptors
- 79. T= AND(A,B)/OR(A,B) A=24, B:21, A&B:19 T=0.73 T>0.85 similar A=40, B=30, A&B=30 T=0.75 (can be a substructure) Similarity definitions: Tanimoto
- 84. 808 x 977 M ~ 8 x 1011 dissimilarity data points https://chemaxon.com/poster/similarity-implicated- exploration-of-the-fragment-galaxy
- 87. - Linear regression (PLS, LASSO) - Decision tree (CART) and Random forest - Support Vector Machine - Neural Network (Deep, Convolutional Neural Network) Model building
- 89. Decision tree (CART) Depth Node size
- 93. Support vector machine (SVM) https://doi.org/10.1517/17460441.2014.866943
- 95. 2D not separable problem https://doi.org/10.1517/17460441.2014.866943
- 96. SVR
- 102. Hierarchical composition of complex features. https://doi.org/10.3389/fenvs.2015.00080
- 103. Feature Construction by Deep Learning. https://doi.org/10.3389/fenvs.2015.00080
- 106. Workflow overview Training data (sdf, with labelled data) Training module Build - Descriptor generation - Model building - Validation Model management - Persistence - Execution New model Icon by Aficons from Noun Project https://disco.chemaxon.com/calculators/trainer-engine/
- 107. - Feature engineering ChemAxon descriptors User defined descriptors - Model building Type: regression, classification Models: RF, SVR, GB, GC Hyperparameter optimization: pre-optimized preset, optimizer Precise automatic models: under the hood Icon by modgekar from Noun Project
- 108. - Validation statistics and report Training test set split Retrospective accuracy - Reliability - Applicability domain: most similar structures - Prediction error: Conformal prediction - Overfitting - Scramble Y Quality assessment
- 109. Application Study on ChEMBL Dataset: Journal of Cheminformatics volume 9, Article number: 45 (2017) https://jcheminf.biomedcentral.com/articles/10.1186/s13321-017-0232-0 - 163 ChEMBL targets - Data points in range: 500-4703 per target - 10-90% test-training set split - Target pAct - Pearson, RMSE
- 110. Test set results
- 111. Pearson (R) RMSE (pAct) Average 0.804 0.671 Median 0.817 0.672 Count 163 163 STDev 0.071 0.100 Min 0.569 0.421 Max 0.936 1.030 Test set results
- 112. hERG Random Forest model
- 115. Challenge of data volume
- 118. Specs: - Using MadFast dev version - machine: a single Amazon EC2 x1.16xlarge instance (976 GiB RAM, 64 cores, 2T SSD, $6.7 / h on-demand) - dataset: Enamine Real 2019q34, 1.2B molecules, - fingerprint: CFP7, 512 bit Importing: - importing time was 6h 16m (ran concurrently with an ECFP import, using half of the cores) - result binary blob: 167 GiB Server startup - 448 s (~7.5 min) to read 167 GiB to memory (~380 MB/s throughput) - Of which 169 s for mols, 74 s for ids, 203 s for fingerprints Fast similarity search Dissim limit Hit count limit Runs Avg search time 0.4 1 500 0.45 s 0.4 9 500 0.96 s 0.4 81 500 1.16 s 0.4 729 500 1.25 s 0.4 2187 500 1.26 s 0.4 6561 500 1.42 s 0.4 15000 500 1.89 s 1.0 1 50 0.61 s 1.0 9 50 0.98 s 1.0 81 50 1.29 s 1.0 729 50 1.39 s 1.0 2187 50 1.65 s 1.0 6561 50 3.22 s 1.0 15000 50 9.67 s
- 119. - Pre-screen Fingerprint match all query bits present in target Descriptor screen (Mw, counts) - Graph isomorph check A graph S is a subgraph of a graph G if S is isomorphic to a subgraph of G (Ullmann, VF2, VF2+) Substructure search Tutorials in Chemoinformatics, 395-448 John Wiley & Sons Ltd, Chichester, UK, 2017; https://doi.org/10.1186/1758-2946-4-13
- 120. ● Data set: The Enamine library containing 1.2 billion structures was imported in the database cluster. ● Hardware: ○ Citus cluster was set up in AWS to use a distributed PostgreSQL database. ○ The cluster included one coordinator node and 20 worker nodes. ■ Coordinator node was installed on a t2.xlarge type EC2 instance was used (4 cores, 16 GiB memory) ■ Worker nodes were installed on c5a.4xlarge type instances (16 cores and 32 GiB memory per instance) ● Data upload and chemical indexing: ○ Upload of the data took ~12h; ○ Chemical index creation with JChem PostgreSQL Cartridge: 19.3h ● Search types: ○ Full structure, substructure and similarity search, as well as different combined queries were used with one, two or three additional properties. ○ The number of records returned by the queries was limited to return only the top 100 results. JChem PostgreSQL cartridge test runs
- 122. Drug design
- 123. Array of services - Data access - Preprocessed data MMPA - Derived models QSAR Docking, AI, Machine Learning Gather information
- 125. Design Hub
- 126. Design cockpit
- 127. Summary
- 128. ● Complexity of the human body ○ Single target to interact ○ Multiple targets to avoid ● Complexity of the binding interactions ○ Influence of small structural changes ○ Balancing speed and accuracy ○ Need for structural information ● Pitfalls of machine learning ○ Validation strategy ○ Overfitting ● Size of chemical space ○ Searching in the (multi)billion chemical space ● Accessibility ○ Connecting all the models with designers and medicinal chemists Challenges
- 129. „ Essentially, all models are wrong, but some are useful. ” Box, G. E. P., and Draper, N. R., (1987), Empirical Model Building and Response Surfaces John Wiley & Sons, New York, NY.