# Virtual screening

Figure 1. Flow Chart of Virtual Screening[1]

Virtual screening (VS) is a computational technique used in drug discovery to search libraries of small molecules in order to identify those structures which are most likely to bind to a drug target, typically a protein receptor or enzyme.[2][3]

Virtual screening has been defined as the "automatically evaluating very large libraries of compounds" using computer programs.[4] As this definition suggests, VS has largely been a numbers game focusing on how the enormous chemical space of over 1060 conceivable compounds[5] can be filtered to a manageable number that can be synthesized, purchased, and tested. Although searching the entire chemical universe may be a theoretically interesting problem, more practical VS scenarios focus on designing and optimizing targeted combinatorial libraries and enriching libraries of available compounds from in-house compound repositories or vendor offerings. As the accuracy of the method has increased, virtual screening has become an integral part of the drug discovery process.[6][1] Virtual Screening can be used to select in house database compounds for screening, choose compounds that can be purchased externally, and to choose which compound should be synthesized next.

## Methods

There are two broad categories of screening techniques: ligand-based and structure-based.[7] The remainder of this page will reflect Figure 1 Flow Chart of Virtual Screening.

### Ligand-based methods

Given a set of structurally diverse ligands that binds to a receptor, a model of the receptor can be built by exploiting the collective information contained in such set of ligands. Different computational techniques explore the structural, electronic, molecular shape, and physicochemical similarities of different ligands that could imply their mode of action against a specific molecular receptor or cell lines.[8] A candidate ligand can then be compared to the pharmacophore model to determine whether it is compatible with it and therefore likely to bind.[9] Different 2D chemical similarity analysis methods[10] have been used to scan a databases to find active ligands. Another popular approach used in ligand-based virtual screening consist on searching molecules with shape similar to that of known actives, as such molecules will fit the target's binding site and hence will be likely to bind the target. There are a number of prospective applications of this class of techniques in the literature.[11][12][13] Pharmacophoric extensions of these 3D methods are also freely-available as webservers.[14][15] Also shape based virtual screening has gained significant popularity.[16]

### Structure-based methods

Structure-based virtual screening approach includes different computational techniques that consider the structure of the receptor that is the molecular target of the investigated active ligands. Some of these techniques include molecular docking, structure-based pharmacophore prediction, and molecular dynamics simulations.[17][18][8] Molecular docking is the most used structure-based technique, and it applies a scoring function to estimate the fitness of each ligand against the binding site of the macromolecular receptor, helping to choose the ligands with the most high affinity.[19][20][21] Currently, there are some webservers oriented to prospective virtual screening.[22][23]

### Hybrid methods

Hybrid methods that rely on structural and ligand similarity were also developed to overcome the limitations of traditional VLS approaches. This methodologies utilizes evolution‐based ligand‐binding information to predict small-molecule binders[24][25] and can employ both global structural similarity and pocket similarity.[24] A global structural similarity based approach employs both an experimental structure or a predicted protein model to find structural similarity with proteins in the PDB holo‐template library. Upon detecting significant structural similarity, 2D fingerprint based Tanimoto coefficient metric is applied to screen for small-molecules that are similar to ligands extracted from selected holo PDB templates.[26][27] The predictions from this method have been experimentally assessed and shows good enrichment in identifying active small molecules.

The above specified method depends on global structural similarity and is not capable of a priori selecting a particular ligand‐binding site in the protein of interest. Further, since the methods rely on 2D similarity assessment for ligands, they are not capable of recognizing stereochemical similarity of small-molecules that are substantially different but demonstrate geometric shape similarity. To address these concerns, a new pocket centric approach, PoLi, capable of targeting specific binding pockets in holo‐protein templates, was developed and experimentally assessed.

## Computing Infrastructure

The computation of pair-wise interactions between atoms, which is a prerequisite for the operation of many virtual screening programs, scales by ${\displaystyle O(N^{2})}$, N is the number of atoms in the system. Due to the quadratic scaling, the computational costs increase quickly.

### Ligand-based Approach

Ligand-based methods typically require a fraction of a second for a single structure comparison operation. Sometimes a single CPU is enough to perform a large screening within hours. However, several comparisons can be made in parallel in order to expedite the processing of a large database of compounds.

### Structure-based Approach

The size of the task requires a parallel computing infrastructure, such as a cluster of Linux systems, running a batch queue processor to handle the work, such as Sun Grid Engine or Torque PBS.

A means of handling the input from large compound libraries is needed. This requires a form of compound database that can be queried by the parallel cluster, delivering compounds in parallel to the various compute nodes. Commercial database engines may be too ponderous, and a high speed indexing engine, such as Berkeley DB, may be a better choice. Furthermore, it may not be efficient to run one comparison per job, because the ramp up time of the cluster nodes could easily outstrip the amount of useful work. To work around this, it is necessary to process batches of compounds in each cluster job, aggregating the results into some kind of log file. A secondary process, to mine the log files and extract high scoring candidates, can then be run after the whole experiment has been run.

## Accuracy

The aim of virtual screening is to identify molecules of novel chemical structure that bind to the macromolecular target of interest. Thus, success of a virtual screen is defined in terms of finding interesting new scaffolds rather than the total number of hits. Interpretations of virtual screening accuracy should, therefore, be considered with caution. Low hit rates of interesting scaffolds are clearly preferable over high hit rates of already known scaffolds.

Most tests of virtual screening studies in the literature are retrospective. In these studies, the performance of a VS technique is measured by its ability to retrieve a small set of previously known molecules with affinity to the target of interest (active molecules or just actives) from a library containing a much higher proportion of assumed inactives or decoys. There are several distinct ways to select decoys by matching the properties of the corresponding active molecule[28] and more recently decoys are also selected in a property-unmatched manner.[29] The actual impact of decoy selection, either for training or testing purposes, has also been discussed.[29][30]

By contrast, in prospective applications of virtual screening, the resulting hits are subjected to experimental confirmation (e.g., IC50 measurements). There is consensus that retrospective benchmarks are not good predictors of prospective performance and consequently only prospective studies constitute conclusive proof of the suitability of a technique for a particular target.[31][32][33][34][35]

## Application to drug discovery

Virtual screening is a very useful application when it comes to identifying hit molecules as a beginning for medicinal chemistry. As the virtual screening approach begins to become a more vital and substantial technique within the medicinal chemistry industry the approach has had an expeditious increase.[36]

## Ligand-based methods

While not knowing the structure trying to predict how the ligands will bind to the receptor. With the use of pharmacophore features each ligand identified donor, and acceptors. Equating features are overlaid, however given it is unlikely there is a single correct solution.[1]

### Pharmacophore models

This technique is used when merging the results of searches by using unlike reference compounds, same descriptors and coefficient, but different active compounds. This technique is beneficial because it is more efficient than just using a single reference structure along with the most accurate performance when it comes to diverse actives.[1]

Pharmacophore is an ensemble of steric and electronic features that are needed to have an optimal supramolecular interaction or interactions with a biological target structure in order to precipitate its biological response. Choose a representative as a set of actives, most methods will look for similar bindings.[37] It is preferred to have multiple rigid molecules and the ligands should be diversified, in other words ensure to have different features that don't occur during the binding phase.[1]

### Shape-Based Virtual Screening

Shape-based molecular similarity approaches have been established as important and popular virtual screening techniques. At present, the highly optimized screening platform ROCS (Rapid Overlay of Chemical Structures) is considered the de facto industry standard for shape-based, ligand-centric virtual screening.[38][39][40] It uses a Gaussian function to define molecular volumes of small organic molecules. The selection of the query conformation is less important, rendering shape-based screening ideal for ligand-based modeling: As the availability of a bioactive conformation for the query is not the limiting factor for screening — it is more the selection of query compound(s) that is decisive for screening performance.[16]

## Quantitative-Structure Activity Relationship

Quantitative-Structure Activity Relationship (QSAR) models consist of predictive models based on information extracted from a set of known active and known inactive compounds.[41] SAR's (Structure Activity Relationship) where data is treated qualitatively and can be used with structural classes and more than one binding mode. Models prioritize compounds for lead discovery.[1]

## Machine learning algorithms

Machine learning algorithms have been widely used in virtual screening approaches. Supervised learning techniques use a training and test datasets composed of known active and known inactive compounds. Different ML algorithms have been applied with success in virtual screening strategies, such as recursive partitioning, support vector machines, k-nearest neighbors and neural networks.[42][43][44] These models find the probability that a compound is active and then ranking each compound based on its probability.[1]

### Substructural analysis in Machine Learning

The first Machine Learning model used on large datasets is the Substructure Analysis that was created in 1973. Each fragment substructure make a continuous contribution an activity of specific type.[1] Substructure is a method that overcomes the difficulty of massive dimensionality when it comes to analyzing structures in drug design. An efficient substructure analysis is used for structures that have similarities to a multi-level building or tower. Geometry is used for numbering boundary joints for a given structure in the onset and towards the climax. When the method of special static condensation and substitutions routines are developed this method is proved to be more productive than the previous substructure analysis models.[45]

### Recursive partitioning

Recursively partitioning is method that creates a decision tree using qualitative data. Understanding the way rules break classes up with a low error of misclassification while repeating each step until no sensible splits can be found. However, recursive partitioning can have poor prediction ability potentially creating fine models at the same rate.[1]

## Structure-based methods known protein ligand docking

Ligand can bind into an active site within a protein by using a docking search algorithm, and scoring function in order to identify the most likely cause for an individual ligand while assigning a priority order.[1][46]

## References

1. Gillet V (2013). "Ligand-Based and Structure-Based Virtual Screening" (PDF). The University of Sheffield.
2. ^ Rester U (July 2008). "From virtuality to reality - Virtual screening in lead discovery and lead optimization: a medicinal chemistry perspective". Current Opinion in Drug Discovery & Development. 11 (4): 559–68. PMID 18600572.
3. ^ Rollinger JM, Stuppner H, Langer T (2008). "Virtual screening for the discovery of bioactive natural products". Natural Compounds as Drugs Volume I. Progress in Drug Research. Fortschritte der Arzneimittelforschung. Progrès des Recherches Pharmaceutiques. Progress in Drug Research. 65. pp. 211, 213–49. doi:10.1007/978-3-7643-8117-2_6. ISBN 978-3-7643-8098-4. PMC 7124045. PMID 18084917.
4. ^ Walters WP, Stahl MT, Murcko MA (1998). "Virtual screening – an overview". Drug Discov. Today. 3 (4): 160–178. doi:10.1016/S1359-6446(97)01163-X.
5. ^ Bohacek RS, McMartin C, Guida WC (1996). "The art and practice of structure-based drug design: a molecular modeling perspective". Med. Res. Rev. 16 (1): 3–50. doi:10.1002/(SICI)1098-1128(199601)16:1<3::AID-MED1>3.0.CO;2-6. PMID 8788213.
6. ^ McGregor MJ, Luo Z, Jiang X (June 11, 2007). "Chapter 3: Virtual screening in drug discovery". In Huang Z (ed.). Drug Discovery Research. New Frontiers in the Post-Genomic Era. Wiley-VCH: Weinheim, Germany. pp. 63–88. ISBN 978-0-471-67200-5.
7. ^ McInnes C (October 2007). "Virtual screening strategies in drug discovery". Current Opinion in Chemical Biology. 11 (5): 494–502. doi:10.1016/j.cbpa.2007.08.033. PMID 17936059.
8. ^ a b Santana K, do Nascimento LD, Lima e Lima A, Damasceno V, Nahum C, Braga RC, Lameira J (2021-04-29). "Applications of Virtual Screening in Bioprospecting: Facts, Shifts, and Perspectives to Explore the Chemo-Structural Diversity of Natural Products". Frontiers in Chemistry. 9: 662688. Bibcode:2021FrCh....9..155S. doi:10.3389/fchem.2021.662688. ISSN 2296-2646. PMC 8117418. PMID 33996755.
9. ^ Sun H (2008). "Pharmacophore-based virtual screening". Current Medicinal Chemistry. 15 (10): 1018–24. doi:10.2174/092986708784049630. PMID 18393859.
10. ^ Willet P, Barnard JM, Downs GM (1998). "Chemical similarity searching". Journal of Chemical Information and Computer Sciences. 38 (6): 983–996. CiteSeerX 10.1.1.453.1788. doi:10.1021/ci9800211.
11. ^ Rush TS, Grant JA, Mosyak L, Nicholls A (March 2005). "A shape-based 3-D scaffold hopping method and its application to a bacterial protein-protein interaction". Journal of Medicinal Chemistry. 48 (5): 1489–95. CiteSeerX 10.1.1.455.4728. doi:10.1021/jm040163o. PMID 15743191.
12. ^ Ballester PJ, Westwood I, Laurieri N, Sim E, Richards WG (February 2010). "Prospective virtual screening with Ultrafast Shape Recognition: the identification of novel inhibitors of arylamine N-acetyltransferases". Journal of the Royal Society, Interface. 7 (43): 335–42. doi:10.1098/rsif.2009.0170. PMC 2842611. PMID 19586957.
13. ^ Kumar A, Zhang KY (2018). "Advances in the Development of Shape Similarity Methods and Their Application in Drug Discovery". Frontiers in Chemistry. 6: 315. Bibcode:2018FrCh....6..315K. doi:10.3389/fchem.2018.00315. PMC 6068280. PMID 30090808.
14. ^ Li H, Leung KS, Wong MH, Ballester PJ (July 2016). "USR-VS: a web server for large-scale prospective virtual screening using ultrafast shape recognition techniques". Nucleic Acids Research. 44 (W1): W436–41. doi:10.1093/nar/gkw320. PMC 4987897. PMID 27106057.
15. ^ Sperandio O, Petitjean M, Tuffery P (July 2009). "wwLigCSRre: a 3D ligand-based server for hit identification and optimization". Nucleic Acids Research. 37 (Web Server issue): W504–9. doi:10.1093/nar/gkp324. PMC 2703967. PMID 19429687.
16. ^ a b Kirchmair J, Distinto S, Markt P, Schuster D, Spitzer GM, Liedl KR, Wolber G (2009). "How To Optimize Shape-Based Virtual Screening: Choosing the Right Query and Including Chemical Information". Journal of Chemical Information and Modeling. 49: 678–692. doi:10.1021/ci8004226.
17. ^ Toledo Warshaviak D, Golan G, Borrelli KW, Zhu K, Kalid O (July 2014). "Structure-based virtual screening approach for discovery of covalently bound ligands". Journal of Chemical Information and Modeling. 54 (7): 1941–50. doi:10.1021/ci500175r. PMID 24932913.
18. ^ Maia EH, Assis LC, de Oliveira TA, da Silva AM, Taranto AG (2020-04-28). "Structure-Based Virtual Screening: From Classical to Artificial Intelligence". Frontiers in Chemistry. 8: 343. Bibcode:2020FrCh....8..343M. doi:10.3389/fchem.2020.00343. PMC 7200080. PMID 32411671.
19. ^ Kroemer RT (August 2007). "Structure-based drug design: docking and scoring". Current Protein & Peptide Science. 8 (4): 312–28. CiteSeerX 10.1.1.225.959. doi:10.2174/138920307781369382. PMID 17696866.
20. ^ Cavasotto CN, Orry AJ (2007). "Ligand docking and structure-based virtual screening in drug discovery". Current Topics in Medicinal Chemistry. 7 (10): 1006–14. doi:10.2174/156802607780906753. PMID 17508934.
21. ^ Kooistra AJ, Vischer HF, McNaught-Flores D, Leurs R, de Esch IJ, de Graaf C (June 2016). "Function-specific virtual screening for GPCR ligands using a combined scoring method". Scientific Reports. 6: 28288. Bibcode:2016NatSR...628288K. doi:10.1038/srep28288. PMC 4919634. PMID 27339552.
22. ^ Irwin JJ, Shoichet BK, Mysinger MM, Huang N, Colizzi F, Wassam P, Cao Y (September 2009). "Automated docking screens: a feasibility study". Journal of Medicinal Chemistry. 52 (18): 5712–20. doi:10.1021/jm9006966. PMC 2745826. PMID 19719084.
23. ^ Li H, Leung KS, Ballester PJ, Wong MH (2014-01-24). "istar: a web platform for large-scale protein-ligand docking". PLOS ONE. 9 (1): e85678. Bibcode:2014PLoSO...985678L. doi:10.1371/journal.pone.0085678. PMC 3901662. PMID 24475049.
24. ^ a b Zhou H, Skolnick J (January 2013). "FINDSITE(comb): a threading/structure-based, proteomic-scale virtual ligand screening approach". Journal of Chemical Information and Modeling. 53 (1): 230–40. doi:10.1021/ci300510n. PMC 3557555. PMID 23240691.
25. ^ Roy A, Skolnick J (February 2015). "LIGSIFT: an open-source tool for ligand structural alignment and virtual screening". Bioinformatics. 31 (4): 539–44. doi:10.1093/bioinformatics/btu692. PMC 4325547. PMID 25336501.
26. ^ Gaulton A, Bellis LJ, Bento AP, Chambers J, Davies M, Hersey A, Light Y, McGlinchey S, Michalovich D, Al-Lazikani B, Overington JP (January 2012). "ChEMBL: a large-scale bioactivity database for drug discovery". Nucleic Acids Research. 40 (Database issue): D1100–7. doi:10.1093/nar/gkr777. PMC 3245175. PMID 21948594.
27. ^ Wishart DS, Knox C, Guo AC, Shrivastava S, Hassanali M, Stothard P, Chang Z, Woolsey J (January 2006). "DrugBank: a comprehensive resource for in silico drug discovery and exploration". Nucleic Acids Research. 34 (Database issue): D668–72. doi:10.1093/nar/gkj067. PMC 1347430. PMID 16381955.
28. ^ Réau M, Langenfeld F, Zagury JF, Lagarde N, Montes M (2018). "Decoys Selection in Benchmarking Datasets: Overview and Perspectives". Frontiers in Pharmacology. 9: 11. doi:10.3389/fphar.2018.00011. PMC 5787549. PMID 29416509.
29. ^ a b Ballester PJ (December 2019). "Selecting machine-learning scoring functions for structure-based virtual screening". Drug Discovery Today: Technologies. 32–33: 81–87. doi:10.1016/j.ddtec.2020.09.001. PMID 33386098. S2CID 224968364.
30. ^ Li H, Sze KH, Lu G, Ballester PJ (2021). "Machine-learning scoring functions for structure-based virtual screening". WIREs Computational Molecular Science. 11 (1): e1478. doi:10.1002/wcms.1478. ISSN 1759-0884. S2CID 219089637.
31. ^ Wallach I, Heifets A (2018). "Most Ligand-based classification benchmarks reward memorization rather than generalization". Journal of Chemical Information and Modeling. 58 (5): 916–932. arXiv:1706.06619. doi:10.1021/acs.jcim.7b00403. PMID 29698607. S2CID 195345933.
32. ^ Irwin JJ (2008). "Community benchmarks for virtual screening". Journal of Computer-Aided Molecular Design. 22 (3–4): 193–9. Bibcode:2008JCAMD..22..193I. doi:10.1007/s10822-008-9189-4. PMID 18273555. S2CID 26260725.
33. ^ Good AC, Oprea TI (2008). "Optimization of CAMD techniques 3. Virtual screening enrichment studies: a help or hindrance in tool selection?". Journal of Computer-Aided Molecular Design. 22 (3–4): 169–78. Bibcode:2008JCAMD..22..169G. doi:10.1007/s10822-007-9167-2. PMID 18188508. S2CID 7738182.
34. ^ Schneider G (April 2010). "Virtual screening: an endless staircase?". Nature Reviews. Drug Discovery. 9 (4): 273–6. doi:10.1038/nrd3139. PMID 20357802. S2CID 205477076.
35. ^ Ballester PJ (January 2011). "Ultrafast shape recognition: method and applications". Future Medicinal Chemistry. 3 (1): 65–78. doi:10.4155/fmc.10.280. PMID 21428826.
36. ^ Lavecchia A, Di Giovanni C (2013). "Virtual screening strategies in drug discovery: a critical review". Current Medicinal Chemistry. 20 (23): 2839–60. doi:10.2174/09298673113209990001. PMID 23651302.
37. ^ Spitzer GM, Heiss M, Mangold M, Markt P, Kirchmair J, Wolber G, Liedl KR (2010). "One concept, three implementations of 3D pharmacophore-based virtual screening: distinct coverage of chemical search space". Journal of Chemical Information and Modeling. 50 (7): 1241–1247. doi:10.1021/ci100136b.
38. ^ Grant JA, Gallard MA, Pickup BT (1996). "A fast method of molecular shape comparison: a simple application of a Gaussian description of molecular shape". Journal of Computational Chemistry. 17: 1653–1666. doi:10.1002/(SICI)1096-987X(19961115)17:14<1653::AID-JCC7>3.0.CO;2-K.
39. ^ Nicholls A, Grant JA (2005). "Molecular shape and electrostatics in the encoding of relevant chemical information". Journal of Computer-Aided Molecular Design. 19: 661–686. doi:10.1007/s10822-005-9019-x.
40. ^ Rush TS, Grant JA, Mosyak L, Nicholls A (2005). "A shape-based 3-D scaffold hopping method and its application to a bacterial protein-protein interaction". Journal of Medicinal Chemistry. 48: 1489–1495. doi:10.1021/jm040163o.
41. ^ Neves BJ, Braga RC, Melo-Filho CC, Moreira-Filho JT, Muratov EN, Andrade CH (2018-11-13). "QSAR-Based Virtual Screening: Advances and Applications in Drug Discovery". Frontiers in Pharmacology. 9: 1275. doi:10.3389/fphar.2018.01275. PMC 6262347. PMID 30524275.
42. ^ Alsenan S, Al-Turaiki I, Hafez A (December 2020). "A Recurrent Neural Network model to predict blood-brain barrier permeability". Computational Biology and Chemistry. 89: 107377. doi:10.1016/j.compbiolchem.2020.107377. PMID 33010784.
43. ^ Dimitri GM, Lió P (June 2017). "DrugClust: A machine learning approach for drugs side effects prediction". Computational Biology and Chemistry. 68: 204–210. doi:10.1016/j.compbiolchem.2017.03.008. PMID 28391063.
44. ^ Shoombuatong W, Schaduangrat N, Pratiwi R, Nantasenamat C (June 2019). "THPep: A machine learning-based approach for predicting tumor homing peptides". Computational Biology and Chemistry. 80: 441–451. doi:10.1016/j.compbiolchem.2019.05.008. PMID 31151025.
45. ^ Gurujee CS, Deshpande VL (February 1978). "An improved method of substructure analysis". Computers & Structures. 8 (1): 147–152. doi:10.1016/0045-7949(78)90171-2.
46. ^ Pradeepkiran JA, Reddy PH (March 2019). "Structure Based Design and Molecular Docking Studies for Phosphorylated Tau Inhibitors in Alzheimer's Disease". Cells. 8 (3): 260. doi:10.3390/cells8030260. PMC 6468864. PMID 30893872.