The rapid development and spread of analytical tools in the biomedical sciences has produced a variety of information about all sorts of biological components and their functions. Though important individually, their biological characteristics need to be understood in relation to the interactions they have with other biological components, which requires the integration of vast amounts of complex, semantically-rich, heterogenous data.
Traditional systems are inadequate at accurately modelling and handling data at this scale and complexity, making solutions that speed up the integration and querying of such data a necessity.
In this talk, we present various approaches being used in organisations to build biomedical computational pipelines to address these problems using tools such as Machine Learning and TypeDB. In particular, we discuss how to create an accurate and scalable semantic representation of molecular level biomedical data by presenting examples from drug discovery, precision medicine and competitive intelligence.
Speaker: Tomás Sabat
Tomás is the Chief Operating Officer at Vaticle, dedicated to building a strongly-typed database for intelligent systems. He works directly with TypeDB's open source and enterprise users so they can fulfil their potential with TypeDB and change the world. He focuses mainly in life sciences, cyber security, finance and robotics.
3. 360 real time patient views In silico clinical trials
4. 360 real time patient views In silico clinical trials
Hyper-personalised medicine
5. 360 real time patient views In silico clinical trials
Hyper-personalised medicine De novo drug design
6. 360 real time patient views In silico clinical trials
Hyper-personalised medicine De novo drug design
Cell and gene therapy
7. 360 real time patient views In silico clinical trials
Hyper-personalised medicine De novo drug design
Cell and gene therapy Ageing research
8. 360 real time patient views In silico clinical trials
Hyper-personalised medicine De novo drug design
Cell and gene therapy Ageing research
Immunotherapy
9. 360 real time patient views In silico clinical trials
Hyper-personalised medicine De novo drug design
Cell and gene therapy Ageing research
Immunotherapy mRNA technology
31. protein
Choose the major entities
Identify the relationship types
drug
interaction
Data Modelling
32. Choose the major entities
Identify the relationship types
Determine which attributes belong to which entities
protein
uniprot-id
drug
chembl-id
interaction
Data Modelling
33. Choose the major entities
Identify the relationship types
Determine which attributes belong to which entities
Normalise
protein
uniprot-id
drug
chembl-id
interaction
Data Modelling
36. Choose the major entities
Identify the relationship types
Determine which attributes belong to which entities
Normalise
protein
uniprot-id
drug
chembl-id
interaction
Data Modelling
37. Choose the major entities
Identify the relationship types
Determine which attributes belong to which entities
Normalise
X
protein
uniprot-id
drug
chembl-id
interaction
Data Modelling
39. protein
uniprot-id
drug
chembl-id
interaction
define
protein sub entity,
owns uniprot-id,
plays interaction:interacted;
drug sub entity,
owns chembl-id,
plays interaction:interacting;
interaction sub relation,
relates interacting,
relates interacted;
uniprot-id sub attribute, value string;
chembl-id sub attribute, value string;
No need to normalise our data!
Data Modelling
41. drug
chembl-id
owns
protein
uniprot-id
drug
chembl-id
kinase ion-channel
interaction
define
protein sub entity,
owns uniprot-id,
plays interaction:interacted;
kinase sub protein;
ion-channel sub protein;
drug sub entity,
owns chembl-id,
plays interaction:interacting;
interaction sub relation,
relates interacting,
relates interacted;
uniprot-id sub attribute, value string;
chembl-id sub attribute, value string;
Data Modelling
43. interaction
protein
interacting interacted
match
$drug isa drug, has chembl-id "CHEMBL1193654";
$protein isa protein;
(interacted: $protein, interacting: $drug) isa interaction;
get $protein;
drug
interacting interacted
Return kinases and ion-channels connected to drugs
51. Drug Discovery
Data Harmonisation
Precision Medicine
Competitive Intelligence
Data Management
Supply Chain Optimisation
Clinical Trial
Cohort Selection
Disease Understanding
52. Who have run clinical trials on Ebola who also own patents?
What are the most likely gene targets for Melanoma?
Given someone’s biological and genetic profile, what clinical trials are they
eligible for?
Questions we can ask
73. Competitive Intelligence
Drug Discovery
Precision Medicine
Given someone’s biological and genetic profile, what clinical trials are they
eligible for?
What are the most likely gene targets for Melanoma?
Who have run clinical trials on Ebola who also own patents?
77. Competitive Intelligence Drug Discovery Precision Medicine
Public Data
Unstructured data
Structured Data
Molecular
Clinical Trials
Patents
Disease
…
78. Competitive Intelligence Drug Discovery Precision Medicine
Public Data
Unstructured data
Structured Data
Molecular
Clinical Trials
Patents
Disease
…
79. Competitive Intelligence Drug Discovery Precision Medicine
Public Data
Unstructured data
Structured Data
TypeDB
Loader
Custom
Loaders
Connectors
…
Molecular
Clinical Trials
Patents
Disease
…
80. Competitive Intelligence Drug Discovery Precision Medicine
Text Mining
coreNLP
…
Public Data
Unstructured data
Structured Data
TypeDB
Loader
Custom
Loaders
Connectors
…
Molecular
Clinical Trials
Patents
Disease
…
81. Client Drivers
(Python, Java,
NodeJS, etc)
Competitive Intelligence Drug Discovery Precision Medicine
Text Mining
coreNLP
…
Public Data
Unstructured data
Structured Data
TypeDB
Loader
Custom
Loaders
Connectors
…
Molecular
Clinical Trials
Patents
Disease
…
82. Who have run clinical trials on Ebola who also own patents?
Client Drivers
(Python, Java,
NodeJS, etc)
Competitive
Insights
Output
Competitive Intelligence Drug Discovery Precision Medicine
Text Mining
coreNLP
…
Public Data
Unstructured data
Structured Data
TypeDB
Loader
Custom
Loaders
Connectors
…
Molecular
Clinical Trials
Patents
Disease
…
83. Who have run clinical trials on Ebola who also own patents?
person
Competitive Intelligence Drug Discovery Precision Medicine
84. Who have run clinical trials on Ebola who also own patents?
patent person
clinical-trial
disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
85. Who have run clinical trials on Ebola who also own patents?
patent person
clinical-trial investigation
disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
investigator
investigated
86. Who have run clinical trials on Ebola who also own patents?
patent person
clinical-trial investigation
study disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
investigator
studied
investigated
studying
87. Who have run clinical trials on Ebola who also own patents?
patent
ownership
person
clinical-trial investigation
study disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
investigator
investigated
studying
studied
owned owner
88. Who have run clinical trials on Ebola who also own patents?
patent
ownership
person
clinical-trial investigation
study disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
match
$person isa person;
investigator
investigated
studying
studied
owned owner
89. Who have run clinical trials on Ebola who also own patents?
patent
ownership
person
clinical-trial investigation
study disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
match
$person isa person;
$patent isa patent;
investigator
investigated
studying
studied
owned owner
90. Who have run clinical trials on Ebola who also own patents?
patent
ownership
person
clinical-trial investigation
study disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
match
$person isa person;
$patent isa patent;
$trial isa clinical-trial;
investigator
investigated
studying
studied
owned owner
91. Who have run clinical trials on Ebola who also own patents?
patent
ownership
person
clinical-trial investigation
study disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
match
$person isa person;
$patent isa patent;
$trial isa clinical-trial;
$disease isa disease;
investigator
investigated
studying
studied
owned owner
92. Who have run clinical trials on Ebola who also own patents?
patent
ownership
person
clinical-trial investigation
study disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
match
$person isa person;
$patent isa patent;
$trial isa clinical-trial;
$disease isa disease, has name "Ebola";
investigator
investigated
studying
studied
owned owner
93. Who have run clinical trials on Ebola who also own patents?
patent
ownership
person
clinical-trial investigation
study disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
match
$person isa person;
$patent isa patent;
$trial isa clinical-trial;
$disease isa disease, has name "Ebola";
(owner: $person, owned: $patent) isa ownership;
investigator
investigated
studying
studied
owned owner
94. Who have run clinical trials on Ebola who also own patents?
patent
ownership
person
clinical-trial investigation
study disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
match
$person isa person;
$patent isa patent;
$trial isa clinical-trial;
$disease isa disease, has name "Ebola";
(owner: $person, owned: $patent) isa ownership;
(investigator: $person, investigated: $trial) isa
investigation;
investigator
investigated
studying
studied
owned owner
95. Who have run clinical trials on Ebola who also own patents?
patent
ownership
person
clinical-trial investigation
study disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
match
$person isa person;
$patent isa patent;
$trial isa clinical-trial;
$disease isa disease, has name "Ebola";
(owner: $person, owned: $patent) isa ownership;
(investigator: $person, investigated: $trial) isa
investigation;
(studying: $trial, studied: $disease) isa study;
investigator
investigated
studying
studied
owned owner
96. Who have run clinical trials on Ebola who also own patents?
patent
ownership
person
clinical-trial investigation
study disease
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
match
$person isa person;
$patent isa patent;
$trial isa clinical-trial;
$disease isa disease, has name "Ebola";
(owner: $person, owned: $patent) isa ownership;
(investigator: $person, investigated: $trial) isa
investigation;
(studying: $trial, studied: $disease) isa study;
get $person;
investigator
investigated
studying
studied
owned owner
97. Who have run clinical trials on Ebola who also own patents?
patent
ownership
person
clinical-trial investigation
study disease
match
$person isa person, has name $name;
$patent isa patent;
$trial isa clinical-trial;
$disease isa disease, has name "Ebola";
(owner: $person, owned: $patent) isa ownership;
(investigator: $person, investigated: $trial) isa
investigation;
(studying: $trial, studied: $disease) isa study;
get $name;
name: “Ebola”
Competitive Intelligence Drug Discovery Precision Medicine
investigator
investigated
studying
studied
owned owner
100. Competitive Intelligence Drug Discovery Precision Medicine
Public Data
Unstructured data
Structured Data
Legacy data
Lab data
Internal Data
101. Competitive Intelligence Drug Discovery Precision Medicine
Client Drivers
(Python, Java,
NodeJS, etc)
Text Mining
coreNLP
…
Public Data
Unstructured data
Structured Data
Legacy data
Lab data
Internal Data
TypeDB
Loader
Custom
Loaders
Connectors
…
102. Competitive Intelligence Drug Discovery Precision Medicine
Client Drivers
(Python, Java,
NodeJS, etc) KGCN
Text Mining
coreNLP
…
Public Data
Unstructured data
Structured Data
Legacy data
Lab data
Internal Data
TypeDB
Loader
Custom
Loaders
Connectors
…
103. Query Result, a subgraph
Graph
Learning
Algorithm
Learner
TypeQL Query Subgraph Predictions
match
$p isa protein;
$d isa disease, has disease-
group "Cancer", has disease-id
$did;
$t isa tissue;
$g isa gene, has gene-id $gid;
($p, $t);
($t, $d);
($g, $t);
104. Competitive Intelligence Drug Discovery Precision Medicine
Client Drivers
(Python, Java,
NodeJS, etc) KGCN
List of targets
Output
What are the most likely gene targets for Melanoma?
Text Mining
coreNLP
…
Public Data
Unstructured data
Structured Data
Legacy data
Lab data
Internal Data
TypeDB
Loader
Custom
Loaders
Connectors
…
105. > match $g isa gene, has gene-id $gid;
$d isa disease, has disease-name "melanoma";
What are the most likely gene targets for Melanoma?
106. > match $g isa gene, has gene-id $gid;
$d isa disease, has disease-name "melanoma";
($g, $d) isa gene-disease-association, has kgcn-prob $p;
What are the most likely gene targets for Melanoma?
107. > match $g isa gene, has gene-id $gid;
$d isa disease, has disease-name "melanoma";
($g, $d) isa gene-disease-association, has kgcn-prob $p;
get $gid; sort desc $p;
What are the most likely gene targets for Melanoma?
108. > match $g isa gene, has gene-id $gid;
$d isa disease, has disease-name "melanoma";
($g, $d) isa gene-disease-association, has kgcn-prob $p;
get $gid; sort desc $p;
{$gid "DDXIIL1" isa gene-id;}
{$gid "WASH7P" isa gene-id;}
{$gid "MIR1302-10" isa gene-id;}
{$gid "MIR1302-11" isa gene-id;}
{$gid "OR4F5" isa gene-id;}
{$gid "FAM138D" isa gene-id;}
{$gid "FAM41C" isa gene-id;}
{$gid "NOC2L" isa gene-id;}
{$gid "HES4" isa gene-id;}
{$gid "RNF223" isa gene-id;}
{$gid "TNFRSF4" isa gene-id;}
...
What are the most likely gene targets for Melanoma?
110. Competitive Intelligence Drug Discovery Precision Medicine
Public Data
Unstructured data
Structured Data
Molecular
Clinical Trials
…
Precision DBs
…
111. Competitive Intelligence Drug Discovery Precision Medicine
Public Data
Unstructured data
Structured Data
Molecular
Clinical Trials
…
Precision DBs
…
112. Competitive Intelligence Drug Discovery Precision Medicine
Public Data
Unstructured data
Structured Data
Molecular
Clinical Trials
…
Precision DBs
…
114. Competitive Intelligence Drug Discovery Precision Medicine
Text Mining
coreNLP
…
TypeDB
Loader
Custom
Loaders
Connectors
…
Public Data
Unstructured data
Structured Data
Molecular
Clinical Trials
…
Precision DBs
…
Competitive Intelligence Drug Discovery Precision Medicine
115. Client Drivers
(Python, Java,
NodeJS, etc)
Competitive Intelligence Drug Discovery Precision Medicine
Text Mining
coreNLP
…
TypeDB
Loader
Custom
Loaders
Connectors
…
Public Data
Unstructured data
Structured Data
Molecular
Clinical Trials
…
Precision DBs
…
116. Client Drivers
(Python, Java,
NodeJS, etc)
Competitive Intelligence Drug Discovery Precision Medicine
Personalised-
therapies
Output
Text Mining
coreNLP
…
TypeDB
Loader
Custom
Loaders
Connectors
…
Public Data
Unstructured data
Structured Data
Molecular
Clinical Trials
…
Precision DBs
…
117. Client Drivers
(Python, Java,
NodeJS, etc)
Personalised-
therapies
Output
Competitive Intelligence Drug Discovery Precision Medicine
Given someone’s biological and genetic profile, what clinical trials are they
eligible for?
Text Mining
coreNLP
…
TypeDB
Loader
Custom
Loaders
Connectors
…
Public Data
Unstructured data
Structured Data
Molecular
Clinical Trials
…
Precision DBs
…
118. trial
personalised-
therapy
person
match
$person isa person, has name "Alice";
$trial isa clinical-trial, has nct-id $nct;
($person, $trial) isa personalised-therapy;
get $nct;
Competitive Intelligence Drug Discovery Precision Medicine
Given someone’s biological and genetic profile, what clinical trials are they
eligible for?
119. Given someone’s biological and genetic profile, what clinical trials are they
eligible for?
Relevance for a clinical trial Eligibility for a clinical trial
Patient has the same gene and variant
mentioned in the clinical trial
Patient is within the right age bracket and
gender for the trial
Competitive Intelligence Drug Discovery Precision Medicine
124. Given someone’s biological and genetic profile, what clinical trials are they
eligible for?
Relevance for a clinical trial
Patient has the same gene and variant
mentioned in the clinical trial
relevant-
trial
Competitive Intelligence Drug Discovery Precision Medicine
127. trial person
gene assoc
variant assoc
mention
mention
relevant-
trial
Competitive Intelligence Drug Discovery Precision Medicine
128. trial person
gene
symbol: $gs
assoc
variant assoc
symbol: $vs
mention
mention
relevant-
trial
rule trial-participant-relevance:
when {
$person isa person;
$gene isa gene;
$variant isa variant;
$trial isa clinical-trial;
($person, $gene);
($person, $variant);
($trial, $gene);
($trial, $variant);
} then {
($person, $trial) isa relevant-trial;
};
Competitive Intelligence Drug Discovery Precision Medicine
129. Given someone’s biological and genetic profile, what clinical trials are they
eligible for?
Eligibility for a clinical trial
Patient is within the right age bracket and
gender for the trial
eligible-trial
Competitive Intelligence Drug Discovery Precision Medicine
133. trial person
disease assoc
assoc
eligible-trial
max-age
gender
age
min-age
greater than
less than
rule trial-participant-eligibility:
when {
$person isa person, has age $age, has gender $gender;
$trial isa clinical-trial,
has min-age <= $age,
has max-age >= $age,
has gender = $gender;
$disease isa disease;
($disease, $person);
($disease, $trial);
} then {
($person, $trial) isa eligible-trial;
};
Competitive Intelligence Drug Discovery Precision Medicine
134. Given someone’s biological and genetic profile, what clinical trials are they
eligible for?
Relevance for a clinical trial Eligibility for a clinical trial
Patient has the same gene and variant
mentioned in the clinical trial
Patient is within the right age bracket and
gender for the trial
Competitive Intelligence Drug Discovery Precision Medicine
135. Drug Discovery
Data Harmonisation
Precision Medicine
Competitive Intelligence
Data Management
Supply Chain Optimisation
Clinical Trial
Cohort Selection
Disease Understanding