Bioinformatika, mint a mesterséges intelligencia és a

Preview:

Citation preview

1

From chemoinformatics to repositioning

Péter Antal

Computational Biomedicine (Combine) workgroupDepartment of Measurement and Information Systems,

Budapest University of Technology and Economics

Overview• Chemoinformatics• The „big data”/omic era of chemo- and bioinformatics• Data and knowledge fusion in biomedicine• The semantic unification of pharmacological spaces• Multi-aspect virtual screening• Drug repositioning

2

Chemoinformatics• Gasteiger, Johann, and Thomas Engel, eds.

Chemoinformatics: a textbook. John Wiley & Sons, 2006.• Bajorath, Jürgen. Chemoinformatics for Drug Discovery.

John Wiley & Sons, 2013.• Karthikeyan, Muthukumarasamy, and Renu Vyas.

Practical Chemoinformatics. Springer, 2014.• Brown, Nathan. In Silico Medicinal Chemistry:

Computational Methods to Support Drug Design. No. 8. Royal Society of Chemistry, 2015.

3

Practical chemoinformatics

4

1. Open-Source Tools, Techniques, and Data in Chemoinformatics

2. Chemoinformatics Approach for the Design and Screening of Focused Virtual Libraries

3. Machine Learning Methods in Chemoinformatics for Drug Discovery

4. Docking and Pharmacophore Modelling for Virtual Screening

5. Active Site-Directed Pose Prediction Programs for Efficient Filtering of Molecules

6. Representation, Fingerprinting, and Modelling of Chemical Reactions

7. Predictive Methods for Organic Spectral Data Simulation

8. Chemical Text Mining for Lead Discovery 9. Integration of Automated Workflow in

Chemoinformatics for Drug Discovery10. Cloud Computing Infrastructure

Development for Chemoinformatics

In Silico Medicinal Chemistry: Computational Methods to Support Drug Design

5

In Silico Medicinal Chemistry

6

In Silico Medicinal Chemistry

7

E D. Green et al. Nature 470, 204-213 (2011) doi:10.1038/nature09764

Accomplishments of genomics research

Big „omic” data sets in biomed.

9

Multiple levels in biomedicine

Genome(s)

Phenome (disease, side effect)

Transcriptome

Proteome

Metabolome

Environment&life style

Drugs

Moore’s Law for Data Explosion (Carlson’s law)

Sequencing costs per mill.

base

Publicly available

genetic data

NATURE, Vol 464, April 2010

• x10 every 2-3 years

• Data volumes and complexity that IT has never faced before…

Large-scale cohorts in UK

12

UK Biobank:• 1million< adults• aged 40-69,• 2006-2036<• genes x lifestyle x environment diseases

• open 2012-

Number of genome-wide association studiesTo

tal N

umbe

rof P

ublic

atio

ns

Calendar Quarter

0

200

400

600

800

1000

1200

1400

2005 2006 2007 2008 2009 2010 2011 2012

1350

NHGRI GWA Catalogwww.genome.gov/GWAStudies

Published Genome-Wide Associations through 12/2012Published GWA at p≤5X10-8 for 17 trait categories

Disease network

L.A.Barabási:PNAS, 2007, The human disease network

Repositories for gene expression• Gene Expression Omnibus (NCBI)• http://www.ncbi.nlm.nih.gov/geo/

Gene expression profiles

• Justin Lamb: The Connectivity Map: a new tool for biomedical research, Nature, 7,pp 54-60, 2007

Compounds Cell lines

Each cell is transcriptional

proifle

STRING - Protein-Protein Interactions

• http://string-db.org/

Unification of biology: Gene Ontology

• Ontologies:– Gene Ontology (GO): http://www.geneontology.org/– Enzyme Classification (EC)– Unified Medical Language Systems (UMLS)– OBO

The Human Phenotype Ontology

http://human-phenotype-ontology.github.io/

Number of biomedical publications

21Little Science, Big Science, by Derek J. de Solla Price, 1963

0

200000

400000

600000

800000

1000000

1200000

1950 1960 1970 1980 1990 2000 2010

Number of annual papers

The fusion bottleneck(~limits of personal cognition)

The

phar

ma

gap

Semantic publishing:papers vs DBs/KBs

M. Gerstein, "E-publishing on the Web: Promises, pitfalls, and payoffs for bioinformatics," Bioinformatics, 1999M. Gerstein: Blurring the boundaries between scientific 'papers' and biological databases, Nature, 2001P. Bourne, "Will a biological database be different from a biological journal?," Plos Computational Biology, 2005M. Gerstein et al: "Structured digital abstract makes text mining easy," Nature, 2007.M. Seringhaus et al: "Publishing perishing? Towards tomorrow's information architecture," Bmc Bioinformatics,

2007.M. Seringhaus: "Manually structured digital abstracts: A scaffold for automatic text mining," Febs Letters, 2008.D. Shotton: "Semantic publishing: the coming revolution in scientific journal publishing," Learned Publishing, 2009

24

Network of databases and knowledge bases in biomedicine

25

• 10k< relevant biological databases and knowledge-bases• Petabytes of sequence and high-throughput gene/protein data• ~10.000.000 concepts and relations explicitly in knowledge bases

Combination of elements

genege

ne

target

com

poun

d

gene

disease

binding site

com

poun

d

target protein

bind

ing

site

product

gene

gene

TFBS

pathway

gene

disease

path

way

transcription factor binding site

prod

uct

ATC

GO

EC

HPO

“Compound” Google?

27

“The Science Behind an Answer”

artificial intelligence, natural language processing..(???)

abacavir didanosine lamivudine

Why Can’t My Computer Understand Me?http://www.newyorker.com/tech/elements/why-cant-my-computer-understand-me

28

E-science, data-intensive science, the fourth paradigm

Approaches to fusion• Encyclopedists:

– Wikipedia, Wikidata,– Linked Open Data (LOD),– Semantic publishing

• Automated cross-domain querying– Forms– Workflow systems– Natural language understanding, Machine reading

• Automated reasoning– Watson

• Automated discovery systems („Automation of science”)– Adam, Eve

• Large-scale similarity-based fusion (applied in repositioning) 29

OPS: scientific pharma questions

30

A problem with public data: parallel works on cleaning...integration

31

A Resource Description Framework (RDF) háttér

• The data model of the Semantic Web• RDF statement

– subject: resource identified by an IRI– predicate (property): resource identified by an

IRI– object: resource or literal (constant value)

• Graph databases of RDF triples

32

Relational databases vs. Triplestores (graph databases)Relational databases• Relations are separated from data (cases)• Tables&keys define the formal model (syntax)

for the data (cases)• Model-based (~predefined)• Meaning (semantics) is informal (out of scope

of the DB)• Singular databases (~they are separated)

Triplestores• Unified representation of relations and data• Triples („graph database”) stores the dynamic

model for the data, together with the factual data

• Model-free (~relations as data)• Meaning is defined by the (explicit) relations

(~ontology)• Linked open data space (using universal

identifiers & ontologies)

33

Cf. Neumann’s principle: instructions is data

SPARQL

• a query language specification for querying over RDF triples

34

/Linked data

35

• Bio2RDF• ~11 billion triples• 35 datasets:

clinicaltrials, dbSNP, DrugBank, KEGG, PIR, GOA, OrphaNet, PubMed, SIDER..)

• local: chembl, pathwaycommons, reactome, wikipathways

• http://download.bio2rdf.org/release/3/release.html

Chem2Bio2RDF I.

36

Chem2Bio2RDF II.

37

• Discovery Platform for cross-domain fusion. • Public, curated, linked data.

– The data sources you already use, integrated and linked together: compounds, targets, pathways, diseases and tissues.

• Everything in triples: Subject-predicate-object

38

Open Pharmacological Space

Precursor: Gene Ontology: tool for the unification of biology, Nature, 2000

@gray_alasdair Big Data Integration 39

• Discovery Platform to cross barriers. • The data sources you already use, integrated

and linked together: compounds, targets, pathways, diseases and tissues.

• ChEBI, ChEMBL, ChemSpider, ConceptWiki, DisGeNET, DrugBank, Gene Ontology, neXtProt, UniProt and WikiPathways.

• For questions in drug discovery, answers from publications in peer reviewed scientific journals.

40

Top questions in the pharma industry I. (Open PHACTS)

41

Top questions II.

42

Open PHACTS: databases

43

Dataset Downloaded Version Licence TriplesBio Assay Ontology CC-By 10,360CALOHA 8 Apr 2015 2014-01-22 CC-By-ND 14,552ChEBI 4 Mar 2015 125 CC-By-SA 1,012,056ChEMBL 18 Feb 2015 20.0 CC-By-SA 445,732,880ConceptWiki 12 Dec 2013 CC-By-SA 4,331,760DisGeNET 31 Mar 2015 2.1.0 ODbL 15,011,136Disease Ontology 2015-05-21 CC-By 188,062DrugBank 19 Feb 2015 4.1 Non-commercial 4,028,767ENZYME 2015_11 CC-By-ND 61,467FDA Adverse Events 9 Jul 2012 CC0 13,557,070

Total: ~3 Billion triples

Dataset Downloaded Version Licence TriplesGene Ontology 4 Mar 2015 CC-By 1,366,494Gene Ontology Annotations 17 Feb 2015 CC-By 879,448,347NCATS OPDDR Nov 2015 Oct 2015 2,643neXTProt (NP) 1 Feb 2014 1.0 CC-By-ND 215,006,108OPS Chemical Registry 4 Nov 2014 CC-By-SA 241,986,722

HMDB 3.6 HMDB

MeSH 2015 MeSH

PDB Ligands 2 PDB

OPS Metadata CC-By-SA 2,053UniProt 2015_11 CC-By-ND 1,131,186,434WikiPathways 20151118 CC-By 11,781,627

Total: ~3 Billion triples

OPS: open tools for free academic use

46

Open PHACTS with non-shared, private data for commercial users

47

Open PHACTS: advantages I.

48

Open PHACTS: advantages II.

49

Attrition in drug discovery

De novo drug discovery and development10-17 years process and around 1B USD~10% probability of success from Phase 1 to Market

Drug repositioning3-12 years process and up to 80% cost reductionSignificantly higher probability of success from Phase 1 to Market due to reduced safety and pharmacokinetic uncertainty

De novo discovery vs. repositioning

Scientific motivations for repositioning/rescue

L.A.Barabási:PNAS, 2007,

M.Campillos:Science, 2008Ingenuity Pathway Analysis

A disease-disease similarity network

A drug-drug networkA gene regulatory network

1, Multiple targets

2, Multifactorial diseases

4, Complex pathways (accumulating knowledge)

3, Personalized aspects: 3a, pharmaceutical/phenotypic: efficacy, side effects 3b, genetic/epigenetic

5, New measurements (accumulating omic data)

ENCODE: tissue specific regulation

6, Drugome (2000-7000, 1941) + failed drugs (~2000, +100 new yearly)

Scientific motivations for repositioning II.

• Magic bullet vs. Promiscuous/dirty drugs• Monogenic vs multifactorial disease• Selective optimisation of side activities (SOSA)• Network pharmacy• Personalized („precision”) drugs (for sub-

populations)– Special external applicability conditions– „Pathway” drugs

53

Repositioning publications

54

Ashburn TT, Thor KB: Drug repositioning: identifying and developing new uses for existing drugs. Nat Rev Drug Discov

2004, 3(8):673-683.

Campillos M, Kuhn M, Gavin AC, Jensen LJ, Bork P: Drug target identification using side-effect similarity. Science 2008, 321(5886):263-266.

Joachim von Eichborn Manuela S. Murgueitio, Mathias Dunkel, Soeren Koerner,Philip E. Bourne, Robert Preissner: PROMISCUOUS: a database for network-based drug-repositioning, Nucleic Acids Research, 2010, 1–7

Michael Kuhn, Monica Campillos, Ivica Letunic, Lars Juhl Jensen, Peer Bork,*SIDER: A side effect resource to capture

phenotypic effects of drugs, Molecular Systems Biology 6:343, 2010……..

0

20

40

60

80

2004200520062007200820092010201120122013

Repositioning: examples

55Li and Jones: Drug repositioning for personalized medicine, Genome Medicine 2012, 4:27

Information sources in repositioning and lead discovery.

Profile Repositioning HTS-based Dimension

Chemical X X 100-10000

Target protein X X n x 10000

Taxonomy X 3 (depth)

Side effect X 10000

Literature X 100000

Gene Expression X X k x 1000

Off-label use X 10000

Chemical fingerprints• MACCS 2D, Molcon-Z, Dragon, 3D,..

• Schrödinger Canvas using Tanimoto distance

•Structurefingerprint

810 drugs

011001001011010101...

001010000001110100...

Target profiles I.

58

•Targets: 10,774•Compound records: 1,715,667•Distinct compounds: 1,463,270•Activities: 13,520,737•Publications: 59,610

ChEMBL is a database of bioactive drug-like small molecules, it contains 2-D structures, calculated properties (e.g. logP, Molecular Weight, Lipinski Parameters, etc.) and abstracted bioactivities (e.g. binding constants, pharmacology and ADMET data).

https://www.ebi.ac.uk/chembl

Target profiles II.

Compounds: 68,280,589Tested Compounds: 2,081,593Substances: 196,539,272Tested Substances: 3,121,708BioAssays: 1,112,184RNAi BioAssays: 62BioActivities: 228,469,266Protein Targets: 9,847Gene Targets: 41,361

59

SdPcsubstance contains more than 180 million records. Pccompound contains more than 63 million unique structures. PCBioAssay contains more than 1 million BioAssays. Each BioAssay contains a various number of data points.

Side-effect profiles• DailyMed textmining

– qualitative:SIDER adatbázis (http://sideeffects.embl.de)– quantitative: exact prevalences

• E.g. Olanzapine

514 drugs

Taxonomies

• Anatomical Therapeutic Chemical Classification System (ATC)– 5 levels:

• Main anatomic, • Main therapeutic • therapeutic/pharmacological subgroup • chemical/therapeutic/pharmacological subgroup

• Drugs.com– http://www.drugs.com/

• RxNorm, Aetionomy 61

Chemical

Target

Pathway

“Disease”

Side effect

drugi

drugj

Combination of chemical and side effect information for better target prediction

M.Campillos: Drug target identification using side-effect similarity, Science, 2008

Potential avenues of drug repositioning

63Li and Jones: Drug repositioning for personalized medicine, Genome Medicine 2012, 4:27

In silico/virtual screening using LOD

Chemical Side-effects Target prot. MMoA Pathways

Tanimoto

Linked Open Data (LOD), e.g. Open PHACTS

Representation

Surrogate

Compound representations

Compound-compound similaritiesDavis,Shrobe,Szolovits, 1993

Similarity-based virtual screening1, The “One-One-One” phaseHenrickson J, Johnson M, Maggiori G: Concepts and applications of molecular similarity. 1991, New York: John

Willey & Sons.Willett P, Barnard J, Downs G: Chemical similarity searching. Journal of Chemical Information and Computer

Sciences 1998, 38(6):983-996.

2, The „data fusion” phase “One-Many-One”Ginn C, Willett P, Bradshaw J: Combination of molecular similarity measures using data fusion. Perspectives in

Drug Discovery and Design 2000, 20(1):1-16.

3, The „group fusion” phase “Many-Many-One”Whittle M, Gillet V, Willett P, Loesel J: Analysis of data fusion methods in virtual screening: Similarity and group

fusion. Journal of Chemical Information and Modeling 2006, 46(6):2206-2219.Keiser M, Roth B, Armbruster B, Ernsberger P, Irwin J, Shoichet B: Relating protein pharmacology by ligand

chemistry. Nature Biotechnology 2007, 25(2):197-206.Chen B, Mueller C, Willett P: Combination rules for group fusion in similarity-based virtual screening. Molecular

Informatics 2010, 29(6-7):533-541.Gardiner E, Holliday J, O'Dowd C, Willett P: Effectiveness of 2D fingerprints for scaffold hopping. Future Medicinal

Chemistry 2011, 3(4):405-414.Svensson F, Karlén A, Sköld C: Virtual screening data fusion using both structure- and ligand-based methods.

Journal of Chemical Information and Modeling 2011, 52(1):225-232.

B

A

S1S2S3S4 S5

B

A

S*

B

Q2

S S S

B

S*

Q3

Q1

Q2

Q3

Q1

B

S*

Q2

Q3

Q1

B

Q2

S1 S2S3S4 S5

Q1

S2S3S4 S5

Q3

S2S3S4 S5

Q2

Q1

Q3

S*

B

A

S

1, Similarity-basedapproach

2, Data fusion

3, Group fusion

4, Query Driven Fusion Framework

Similarity-based fusion in drug repositioning

Chemical Side-effects Target prot. MMoA Pathways

Query-based optimal fusion

Tanimoto

Query: set of corresponding drugs

QDF2

On the use of query analysis• The information content of

– the query,– the information resources,– and the unknown observations(!)

• allow a one-class analysis of the query(data description)

• and this induction is used in prioritization.JOINTLY OPTIMIZED:1. weighting the members in the query (e.g. detection of outliers in the question),

GETTING THE RIGHT/IMPROVED QUESTION

2. weighting the similarity measures (e.g.information resources),GETTING THE SCORING (SIMILARITY) FOR THE RIGHT/IMPROVED QUESTION

3. scoring/ranking the aggregate similarity of the unknown data points to the.

QDF2

The repositome

The „repositome” of FDA approved drugs (row) for the ATC level 4 classes (columns).

Thank you for your attention!

Recommended