U.S. patent application number 17/162479 was filed with the patent office on 2021-08-12 for artificial intelligence engine for generating candidate drugs.
This patent application is currently assigned to PEPTILOGICS, INC.. The applicant listed for this patent is PEPTILOGICS, INC.. Invention is credited to Hannes HOLSTE, Francis LEE, Jonathan D. STECKBECK.
Application Number | 20210249108 17/162479 |
Document ID | / |
Family ID | 1000005389263 |
Filed Date | 2021-08-12 |
United States Patent
Application |
20210249108 |
Kind Code |
A1 |
LEE; Francis ; et
al. |
August 12, 2021 |
ARTIFICIAL INTELLIGENCE ENGINE FOR GENERATING CANDIDATE DRUGS
Abstract
An artificial intelligence engine for generating drug compounds
is disclosed. In one embodiment, a method may include generating a
biological context representation of a set of drug compounds. The
biological context representation includes a first data structure
having a first format. The method may also include translating, by
the artificial intelligence engine, the first data structure having
the first format to a second data structure having a second format.
The method may also include generating, based on the second data
structure having the second format, a set of candidate drug
compounds. The method may also include classifying a candidate drug
compound from the set of candidate drug compounds as a selected
candidate drug compound.
Inventors: |
LEE; Francis; (Cambridge,
MA) ; STECKBECK; Jonathan D.; (Cranberry Township,
PA) ; HOLSTE; Hannes; (Los Angeles, CA) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
PEPTILOGICS, INC. |
Pittsburgh |
PA |
US |
|
|
Assignee: |
PEPTILOGICS, INC.
Pittsburgh
PA
|
Family ID: |
1000005389263 |
Appl. No.: |
17/162479 |
Filed: |
January 29, 2021 |
Related U.S. Patent Documents
|
|
|
|
|
|
Application
Number |
Filing Date |
Patent Number |
|
|
62975470 |
Feb 12, 2020 |
|
|
|
Current U.S.
Class: |
1/1 |
Current CPC
Class: |
G06N 3/08 20130101; G06N
3/0427 20130101; G06N 3/0445 20130101; G16C 20/70 20190201; G06N
3/0454 20130101 |
International
Class: |
G16C 20/70 20060101
G16C020/70; G06N 3/04 20060101 G06N003/04; G06N 3/08 20060101
G06N003/08 |
Claims
1. A method comprising: generating a biological context
representation of a plurality of drug compounds, wherein the
biological context representation comprises a first data structure
having a first format; translating, by an artificial intelligence
engine, the first data structure having the first format to a
second data structure having a second format; generating, based on
the second data structure having the second format, a plurality of
candidate drug compounds; and classifying a candidate drug compound
from the plurality of candidate drug compounds as a selected
candidate drug compound.
2. The method of claim 1, wherein the biological context
representation comprises, for each of the plurality of drug
compounds, one or more relationships between or among: physical
properties data, chemical data, biological data, clinical outcome
data, or some combination thereof.
3. The method of claim 1, wherein the translating the first data
structure further comprises: converting the first data structure
having the first format to the second data structure having the
second format according to a specific set of rules executed by the
artificial intelligence engine.
4. The method of claim 1, wherein converting the biological context
representation to the second data structure having the second
format further comprises: obtaining a higher-dimensional vector
from the biological context representation; and compressing the
higher-dimensional vector to a lower-dimensional vector, wherein
the compressing is performed by a machine learning model trained to
perform deep auto-encoding via a recurrent neural network
configured to output the lower-dimensional vector.
5. The method of claim 4, further comprising: training the machine
learning model by using a second machine learning model to recreate
the higher-dimensional vector, wherein the second machine learning
model is trained to perform a decoding operation to recreate the
higher-dimensional vector, wherein the decoding operation is
performed on the lower-dimensional vector.
6. The method of claim 1, wherein: the translating is performed by
a recurrent neural network, the generating of the plurality of
candidate drug compounds is performed by a generative adversarial
network, and the classifying of the candidate drug compound is
performed by a classifier trained using supervised learning.
7. The method of claim 1, further comprising: generating a
plurality of views comprising a representation of a design space;
and causing the plurality of views to be presented on a computing
device, wherein the representation pertains to: antimicrobial
activity, immunomodulatory activity, neuromodulatory activity,
cytotoxic activity, or some combination thereof.
8. The method of claim 7, wherein the design space is antimicrobial
for prosthetic joint infections.
9. The method of claim 7, wherein each view of the plurality of
views presents an optimized sequence representing the selected
candidate drug compound.
10. The method of claim 9, wherein each view presents a
topographical heatmap comprising the optimized sequence overlaid on
indicators ranging from an at least one least active property to an
at least one most active property.
11. The method of claim 1, further comprising: performing one or
more modifications pertaining to the biological context
representation, the second data structure having the second format,
or some combination thereof; and using causal inference to
determine whether the one or more modifications provide one or more
desired performance results.
12. The method of claim 11, wherein using causal inference further
comprises: using counterfactuals to calculate alternative scenarios
based on past actions, occurrences, results, regressions,
regression analyses, correlations, or some combination thereof.
13. The method of claim 1, further comprising: causing the selected
candidate drug compound to be formulated.
14. The method of claim 1, further comprising: causing the selected
candidate drug compound to be created.
15. The method of claim 1, further comprising: causing the selected
candidate drug compound to be presented on a computing device.
16. A tangible, non-transitory computer-readable medium storing
instructions that, when executed, cause a processing device to:
generate a biological context representation of a plurality of drug
compounds, wherein the biological context representation comprises
a first data structure having a first format; translate the first
data structure having the first format to a second data structure
having a second format; generate, based on the second data
structure having the second format, a plurality of candidate drug
compounds; and classify a candidate drug compound from the
plurality of candidate drug compounds as a selected candidate drug
compound.
17. The computer-readable medium of claim 16, wherein the
biological context representation comprises, for each of the
plurality of drug compounds, one or more relationships between or
among: physical properties data, chemical data, biological data,
clinical outcome data, or some combination thereof.
18. The computer-readable medium of claim 16, wherein translating
the biological context representation to the second data structure
having the second format further comprises: obtaining a
higher-dimensional vector from the biological context
representation; and compressing the higher-dimensional vector to a
lower-dimensional vector, wherein the compressing is performed by a
machine learning model trained to perform deep auto-encoding via a
recurrent neural network configured to output the lower-dimensional
vector.
19. The computer-readable medium of claim 18, wherein the
processing device further: trains the machine learning model by
using a second machine learning model to recreate the
higher-dimensional vector, wherein the second machine learning
model is trained to perform a decoding operation to recreate the
higher-dimensional vector, wherein the decoding operation is
performed on the lower-dimensional vector.
20. The computer-readable medium of claim 16, wherein: the
translating is performed by a recurrent neural network, the
generating of the plurality of candidate drug compounds is
performed by a generative adversarial network, and the classifying
of the candidate drug compound is performed by a classifier trained
using supervised learning.
21. The computer-readable medium of claim 16, wherein the
processing device further: generates a plurality of views
comprising a representation of a design space, wherein the
representation pertains to: antimicrobial activity,
immunomodulatory activity, neuromodulatory activity, cytotoxic
activity, or some combination thereof.
22. The computer-readable medium of claim 21, wherein the
processing device further: causes each view of the plurality of
views to be presented, wherein each such view comprises an
optimized sequence representing the selected candidate drug
compound, and causes each view of the plurality of views to be
presented, wherein each such view comprises the optimized sequence
overlaid on indicators ranging from an at least one least active
property to an at least one most active property.
23. The computer-readable medium of claim 16, wherein the
processing device further: performs one or more modifications
pertaining to the biological context representation, the second
data structure having the second format, or some combination
thereof and uses causal inference to determine whether the one or
more modifications provide a desired performance result.
24. The computer-readable medium of claim 23, wherein the
processing device employs causal inference to further: use
counterfactuals to calculate alternative scenarios based on past
actions, occurrences, results, regressions, regression analyses,
correlations, or some combination thereof.
25. A system comprising: a memory device storing instructions; and
a processing device communicatively coupled to the memory device,
the processing device executes the instructions to: generate a
biological context representation of a plurality of drug compounds,
wherein the biological context representation comprises a first
data structure having a first format; translate the first data
structure having the first format to a second data structure having
a second format; generate, based on the second data structure
having the second format, a plurality of candidate drug compounds;
and classify a candidate drug compound from the plurality of
candidate drug compounds as a selected candidate drug compound.
26. A computing device comprising: a display screen; a memory
device storing instructions; and a processing device
communicatively coupled to the memory device and the display
screen, the processing device executes the instructions to:
receive, from an artificial intelligence engine, a candidate drug
compound generated by the artificial intelligence engine; generate
a view comprising the candidate drug compound overlaid on a
representation of a design space, wherein the view presents a
topographical heatmap of the representation of the design space,
and the topographical heatmap includes the candidate drug compound
overlaid on indicators ranging from an at least one least active
property to an at least one most active property; and present the
view on the display screen.
27. A method comprising: generating a biological context
representation of a plurality of drug compounds, wherein the
biological context representation comprises a first data structure
having a first format; translating, by an artificial intelligence
engine, the first data structure having the first format to a
second data structure having a second format; generating, based on
the second data structure having the second format, a plurality of
candidate anti-biofilm compounds; and classifying a candidate
anti-biofilm compound from the plurality of candidate anti-biofilm
compounds as a selected candidate anti-biofilm compound.
28. A method comprising: generating a biological context
representation of a plurality of drug compounds, wherein the
biological context representation comprises a first data structure
having a first format; translating, by an artificial intelligence
engine, the first data structure having the first format to a
second data structure having a second format; generating, based on
the second data structure having the second format, a plurality of
candidate anti-cancer compounds; and classifying a candidate
anti-cancer compound from the plurality of candidate anti-cancer
compounds as a selected candidate anti-cancer compound.
29. A method comprising: generating a biological context
representation of a plurality of drug compounds, wherein the
biological context representation comprises a first data structure
having a first format; translating, by an artificial intelligence
engine, the first data structure having the first format to a
second data structure having a second format; generating, based on
the second data structure having the second format, a plurality of
candidate antimicrobial compounds; and classifying a candidate
antimicrobial compound from the plurality of candidate
antimicrobial compounds as a selected candidate antimicrobial
compound.
Description
CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims the benefit of U.S. Provisional
Application Ser. No. 62/975,470 filed Feb. 12, 2020 titled
"Artificial Intelligence Engine for Generating Candidate Drugs."
The provisional application is incorporated by reference herein as
if reproduced in full below.
TECHNICAL FIELD
[0002] This disclosure relates generally to drug discovery. More
specifically, this disclosure relates to an artificial intelligence
engine for generating candidate drugs.
BACKGROUND
[0003] Therapeutics may refer to a branch of medicine concerned
with the treatment of disease and the action of remedial agents
(e.g., drugs). Therapeutics includes, but is not limited to, the
field of ethical pharmaceuticals. Entities in the therapeutics
industry may discover, develop, produce, and market drugs for use
as medications to be administered or self-administered to patients.
Goals of administering or self-administering the drugs may include
curing the patient of a disease, causing an active disease to enter
a state of remission, vaccinating the patient by stimulating the
immune system to better protect against the disease, and/or
alleviating, mitigating or ameliorating a symptom. Existing drug
discoveries may be based on any combination of human design,
high-throughput screening, synthetic products and natural
substances.
SUMMARY
[0004] In general, the present disclosure provides an artificial
intelligence engine for generating candidate drug.
[0005] In one aspect, a method may include generating a biological
context representation of a set of drug compounds. The biological
context representation includes a first data structure having a
first format. The method may also include translating, by the
artificial intelligence engine, the first data structure having the
first format to a second data structure having a second format. The
method may also include generating, based on the second data
structure having the second format, a set of candidate drug
compounds. The method may also include classifying a candidate drug
compound from the set of candidate drug compounds as a selected
candidate drug compound.
[0006] In another aspect, a method may include receiving, from an
artificial intelligence engine, a candidate drug compound generated
by the artificial intelligence engine. The method may also include
generating a view comprising the candidate drug compound overlaid
on a representation of a design space. The view may present a
topographical heatmap of the representation of the design space,
and the topographical heatmap may include the candidate drug
compound overlaid on indicators ranging from an at least one least
active property to an at least one most active property. The method
may also include presenting the view on a display screen of a
computing device.
[0007] In another aspect, a system may include a memory device
storing instructions and a processing device communicatively
coupled to the memory device. The processing device may execute the
instructions to perform one or more operations of any method
disclosed herein.
[0008] In another aspect, a tangible, non-transitory
computer-readable medium may store instructions and a processing
device may execute the instructions to perform one or more
operations of any method disclosed herein.
[0009] Other technical features may be readily apparent to one
skilled in the art from the following figures, descriptions, and
claims.
[0010] Before undertaking the DETAILED DESCRIPTION below, it may be
advantageous to set forth definitions of certain words and phrases
used throughout this patent document. The term "couple" and its
derivatives refer to any direct or indirect communication between
two or more elements, independent of whether those elements are in
physical contact with one another. The terms "transmit," "receive,"
and "communicate," as well as derivatives thereof, encompass both
direct and indirect communication. The terms "transmit," "receive,"
and "communicate," as well as derivatives thereof, encompass both
communication with remote systems and communication within a
system, including reading and writing to different portions of a
memory device. The terms "include" and "comprise," as well as
derivatives thereof, mean inclusion without limitation. The term
"or" is inclusive, meaning and/or. The phrase "associated with," as
well as derivatives thereof, means to include, be included within,
interconnect with, contain, be contained within, connect to or
with, couple to or with, be communicable with, cooperate with,
interleave, juxtapose, be proximate to, be bound to or with, have,
have a property of, have a relationship to or with, or the like.
The term "translate" may refer to any operation performed wherein
data is input in one format, representation, language (computer,
purpose-specific, such as drug design or integrated circuit
design), structure, appearance or other written, oral or
representable instantiation and data is output in a different
format, representation, language (computer, purpose-specific, such
as drug design or integrated circuit design), structure, appearance
or other written, oral or representable instantiation, wherein the
data output has a similar or identical meaning, semantically or
otherwise, to the data input. Translation as a process includes but
is not limited to substitution (including macro substitution),
encryption, hashing, encoding, decoding or other mathematical or
other operations performed on the input data. The same means of
translation performed on the same input data will consistently
yield the same output data, while a different means of translation
performed on the same input data may yield different output data
which nevertheless preserves all or part of the meaning or function
of the input data, for a given purpose. Notwithstanding the
foregoing, in a mathematically degenerate case, a translation can
output data identical to the input data. The term "controller"
means any device, system or part thereof that controls at least one
operation. Such a controller may be implemented in hardware or a
combination of hardware and software and/or firmware. The
functionality associated with any particular controller may be
centralized or distributed, whether locally or remotely. The phrase
"at least one of," when used with a list of items, means that
different combinations of one or more of the listed items may be
used, and only one item in the list may be needed. For example, "at
least one of: A, B, and C" includes any of the following
combinations: A, B, C, A and B, A and C, B and C, and A and B and
C.
[0011] Moreover, various functions described below can be
implemented or supported by one or more computer programs, each of
which is formed from computer readable program code and embodied in
a computer readable storage medium. The terms "application" and
"program" refer to one or more computer programs, software
components, sets of instructions, procedures, functions, objects,
classes, instances, related data, or a portion thereof adapted for
implementation in a suitable computer readable program code. The
phrase "computer readable program code" includes any type of
computer code, including source code, object code, and executable
code. The phrase "computer readable storage medium" includes any
type of medium capable of being accessed by a computer, such as
read only memory (ROM), random access memory (RAM), a hard disk
drive, a compact disc (CD), a digital video disc (DVD), solid state
drive (SSD), or any other type of memory. A "non-transitory"
computer readable storage medium excludes wired, wireless, optical,
or other communication links that transport transitory electrical
or other signals. A non-transitory computer readable storage medium
includes media where data can be permanently stored and media where
data can be stored and later overwritten, such as a rewritable
optical disc or an erasable memory device.
[0012] The terms "candidate drugs" and "candidate drug compounds"
may be used interchangeably herein.
[0013] Definitions for other certain words and phrases are provided
throughout this patent document. Those of ordinary skill in the art
should understand that in many if not most instances, such
definitions apply to prior as well as future uses of such defined
words and phrases.
BRIEF DESCRIPTION OF THE DRAWINGS
[0014] For a more complete understanding of this disclosure and its
advantages, reference is now made to the following description,
taken in conjunction with the accompanying drawings, in which:
[0015] FIG. 1 illustrates a high-level component diagram of an
illustrative system architecture according to certain embodiments
of this disclosure;
[0016] FIG. 2 illustrates a data structure storing a biological
context representation according to certain embodiments of this
disclosure;
[0017] FIGS. 3A-3B illustrate a high-level flow diagram according
to certain embodiments of this disclosure;
[0018] FIG. 4 illustrates example operations of a method for
generating and classifying a candidate drug compound according to
certain embodiments of this disclosure;
[0019] FIGS. 5A-5D provide illustrations of generating a first data
structure including a biological context representation of a
plurality of drug compounds according to certain embodiments of
this disclosure;
[0020] FIG. 6 illustrates example operations of a method for
translating the first data structure of FIGS. 5A-5D into a second
data structure having a second format according to certain
embodiments of this disclosure;
[0021] FIG. 7 provide illustrations of translating the first data
structure of FIGS. 5A-5D into the second data structure having the
second format according to certain embodiments of this
disclosure;
[0022] FIG. 8A-8C provide illustrations of views of a selected
candidate drug compound according to certain embodiments of this
disclosure;
[0023] FIG. 9 illustrates example operations of a method for
presenting a view including a selected candidate drug compound
according to certain embodiments of this disclosure;
[0024] FIG. 10A illustrates example operations of a method for
using causal inference during the generation of candidate drug
compounds according to certain embodiments of this disclosure;
[0025] FIG. 10B illustrates another example of operations of a
method for using causal inference during the generation of
candidate drug compounds according to certain embodiments of this
disclosure; and
[0026] FIG. 11 illustrates an example computer system according to
certain embodiments of this disclosure.
DETAILED DESCRIPTION
[0027] Conventional drug discoveries based on human design,
high-throughput screening, and/or natural substances may be
inefficient, riven with noise, limited in application, not
efficacious, dangerous or poisonous, and/or not defensible.
Further, in some instances, there are instances of certain diseases
(e.g., instances of prosthetic joint infections) that do not have a
corresponding existing therapeutic to treat the certain diseases or
which provide temporary results against which the disease is
refractory. One reason for the lack of an existing therapeutic may
be the conventional drug discovery techniques are incapable of
discovering the therapeutic needed to treat the certain diseases.
By "treat," we mean that the disease at hand is cured inter alia,
that it is not refractory to treatment. The amount of knowledge,
data, assumptions, and queries that is used to discover a
therapeutic to treat the certain disease may be unattainable,
overwhelming, and/or inefficient, such that conventional drug
discovery techniques cannot overcome these obstacles. Improvement
is desired in the field of therapeutics.
[0028] Accordingly, aspects of the present disclosure generally
relate to an artificial intelligence engine for generating
candidate drugs. The artificial intelligence (AI) engine may use a
combination of rational algorithmic discovery and machine learning
models (e.g., generative deep learning methods) to produce enhanced
therapeutics that may treat any suitable target disease and/or
medical condition. The AI engine may discover, translate, design,
generate, create, develop, formulate, classify, and/or test
candidate drug compounds that exhibit desired activity (e.g.,
antimicrobial, immunomodulatory, cytotoxic, neuromodulatory, etc.)
in design spaces for target diseases and/or medical conditions.
Such candidate drug compounds that exhibit desired activity in a
design space may effectively treat the disease and/or medical
condition associated with that design space. In some embodiments, a
selected candidate drug compound that effectively treats the
disease and/or medical condition may be formulated into an actual
drug for administration and may be tested in a lab and/or at a
clinical stage.
[0029] In general, the disclosed embodiments may enable rationally
discovering drug compounds for a larger design space at a larger
scale, higher accuracy, and/or higher efficiency than conventional
techniques. The AI engine may use various machine learning models
to discover, translate, design, generate, create, develop,
formulate, classify, and/or test candidate drug compounds. Each of
the various machine learning models may perform certain specific
operations. The types of machine learning models may include
various neural networks that perform deep learning, computational
biology, and/or algorithmic discovery. Examples of such neural
networks may include generative adversarial networks, recurrent
neural networks, convolutional neural networks, fully connected
neural networks, etc. as described further below; and such networks
may also additionally employ methods of or incorporating causal
inference, including counterfactuals, in the process of
discovery.
[0030] In some embodiments, a biological context representation of
a set of drug compounds may be generated. The biological context
representation may be a continuous representation of a biological
setting that is updated as knowledge is acquired and/or data is
updated. The biological context representation may be stored in a
first data structure having a format (e.g., a knowledge graph) that
includes both various nodes pertaining to health artifacts and
various relationships connecting the nodes. The nodes and
relationships may form logical structures having subjects and
predicates. For example, one logical structure between two nodes
having a relationship may be "Genes are associated with Diseases"
where "Genes" and "Diseases" are the subjects of the logical
structure and "are associated with" is the relationship. In such a
way, the knowledge graph may encompass actual knowledge, rather
than simply statistical inferences, pertaining to a biological
setting.
[0031] The information in the knowledge graph may be continuously
or periodically updated and the information may be received from
various sources curated by the AI engine. The knowledge in the
biological context representation goes well beyond "dumb" data that
just includes quantities of a value because the knowledge
represents the relationships between or among numerous different
types of data, as well as any or all of direct, indirect, causal,
counterfactual or inferred relationships. In some embodiments, the
biological context representation may not be stored, and instead,
based on the stream of knowledge included in the biological context
representation, may be streamed from data sources into the AI
engine that generates the machine learning models.
[0032] The biological context representation may be used to
generate candidate drug compounds by translating the first data
format to a second data structure having a second format (e.g., a
vector). The second format may be more computationally efficient
and/or suitable for generating candidate drug compounds that
include sequences of ingredients that provide desired activity in a
design space. "Ingredients" as used herein may refer, without
limitation, to substances, compounds, elements, activities (such as
the application or removal of electrical charge or a magnetic field
for a specific maximum, minimum or discrete amount of time), and
mixtures. Further, the second format may enable generating views of
the levels of activity provided by the sequence of ingredients in a
certain design space, as described further below.
[0033] At a high level, the AI engine may include at least one
machine learning model that is trained to use causal inference to
generate candidate drug compounds. One of the challenges with
discovering new therapeutics may include determining whether
certain ingredients are causal agents with respect to certain
activity in a design space. The sheer number of possible sequences
of ingredients may be extraordinarily large due to mathematical
combinatorics, such that identifying a cause and effect
relationship between ingredients and activity may be impossible or,
at best, extremely unlikely, to identify without the disclosed
embodiments. (For example, in public-key encryption, it is
theoretically possible to discover and unlock a private key, but
doing this would presently require all the computing power in the
world to work longer than the age of the universe: this is an
example of what is mathematically possible, but impossible within
human time frames and computing power. Identifying a
cause-and-effect relationship between ingredients and activity,
while a different problem, may be similarly mathematically
possible, but impossible within human time frames and computer
power.) Based on advances in computing hardware (e.g., graphic
processing unit processing cores) and the AI techniques using
causal inference described herein, the disclosed embodiments may
enable the efficient solving of the task of generating candidate
drug compounds at scale.
[0034] Causal inference may refer to a process, based on conditions
of an occurrence of an effect, of drawing a conclusion about a
causal connection. Causal inference may analyze a response of an
effect variable when a cause is changed. Causation may be defined
thusly: a variable X is a cause of Y if Y "listens" to X and
determines its response based on what it "hears." The process of
causal inference in the field of AI may be particularly beneficial
for generating and testing candidate drug compounds for certain
diseases and/or medical conditions because of the use of what are
termed counterfactuals. A counterfactual posits and examines
conditions contrary to what has actually occurred in reality. For
example, if someone takes aspirin for a headache, the headache may
go away. The counterfactual asks what would have happened if the
person had not taken aspirin. Would the headache still have gone
away or would it have remained or even gotten worse? Accordingly,
counterfactuals may refer to calculating alternative scenarios
based on past actions, occurrences, results, regressions,
regression analyses, correlations, or some combination thereof. A
counterfactual may enable determining whether a response should
stay the same or instead change if something in a sequence does not
occur. For example, one counterfactual may include asking: "Would a
certain level of activity be the same if a certain ingredient is
not included in a sequence of a candidate drug compound?"
[0035] By simulating numerous alternative scenarios to further
optimize and hone the accuracy of a sequence of ingredients in the
candidate drug compounds, such techniques may enable reducing the
number of viable candidate drug compounds. As a result, the
embodiments may provide technical benefits, such as reducing
resources consumed (e.g., processing, memory, network bandwidth) by
reducing a number of candidate drug compounds that may be
considered for classification as a selected candidate drug compound
by another machine learning model.
[0036] In some embodiments, one application for the AI engine to
design, discover, develop, formulate, create, and/or test candidate
drug compounds may pertain to peptide therapeutics. A peptide may
refer to a compound consisting of two or more amino acids linked in
a chain. Example peptides may include dipeptides, tripeptides,
tetrapeptides, etc. a polypeptide may refer to a long, continuous,
and unbranched peptide chain. Peptides may be simple to manufacture
at discovery scale, include drug-like characteristics of small
molecules, include safety and high specificity of biologics, and/or
provide greater administration flexibility than some other
biologics.
[0037] The disclosed techniques provide numerous benefits over
conventional techniques for designing, developing, and/or testing
candidate drug compounds. For example, the AI engine may
efficiently use a biological context representation of a set of
drug compounds and one or more machine learning models to generate
a set of candidate drug compounds and classify one of the set of
candidate drug compounds as a selected candidate drug compound.
Some embodiments may use causal inference to remove a number of
potential candidate drug compounds from classification, thereby
reducing the computational complexity and processing burden of
classifying a selected candidate drug compound.
[0038] Further, additional benefits of the embodiments disclosed
herein may include using the AI engine to produce algorithmically
designed drug compounds that have been validated in vivo and in
vitro and that provide (i) a broad-spectrum activity against
greater than 900 multi-drug resistant bacteria, (ii) at least a
2-to-10 times improvement in exposure time required to generate a
drug resistance profile, (iii) effectiveness across four key animal
infection models (both Gram-positive and Gram-negative bacteria),
and/or (iv) effectiveness against biofilms.
[0039] It should be noted that the embodiments disclosed herein may
not only apply to the anti-infective market (e.g., for prosthetic
joint infections, urinary tract infections, intra-abdominal or
peritoneal infections, otitis media, cardiac infections,
respiratory infections including but not limited to sequelae from
diseases such as cystic fibrosis, neurological infections (e.g.,
meningitis), dental infections (including periodontal), other organ
infections, digestive and intestinal infections (e.g., C.
difficile), other physiological system infections, wound and soft
tissue infections (e.g., cellulitis), etc.), but numerous other
suitable markets and/or industries. For example, the embodiments
may be used in the animal health/veterinary industry, for example,
to treat certain animal diseases (e.g., bovine mastitis). Also, the
embodiments may be used for industrial applications, such as
anti-biofouling, and/or generating optimized control action
sequences for machinery. The embodiments may also benefit a market
for new therapeutic indications, such as eczema, inflammatory bowel
disease, Crohn's Disease, rheumatoid arthritis, asthma, auto-immune
diseases and disease processes in general, inflammatory disease
progressions or processes, and/or oncology treatments and
palliatives. The video game industry may also benefit from the
disclosed techniques to improve the AI used for generating
sequences of decisions that non-player controlled (NPC) characters
make during gameplay. The integrated circuit/chip industry may also
benefit from the disclosed techniques to improve the mask works
generation and routing processes used for generating the most
efficient, highest performance, lowest power, lowest heat
generating systems on a chip or solid state devices. Accordingly,
it should be understood that the disclosed embodiments may benefit
any market and/or industry that is associated with a sequence
(e.g., items, objects, decisions, actions, ingredients, etc.) that
can be optimized.
[0040] FIGS. 1 through 11, discussed below, and the various
embodiments used to describe the principles of this disclosure are
by way of illustration only and should not be construed in any way
to limit the scope of the disclosure.
[0041] FIG. 1 illustrates a high-level component diagram of an
illustrative system architecture 100 according to certain
embodiments of this disclosure. In some embodiments, the system
architecture 100 may include a computing device 102 communicatively
coupled to a cloud-based computing system 116. Each of the
computing device 102 and components included in the cloud-based
computing system 116 may include one or more processing devices,
memory devices, and/or network interface cards. The network
interface cards may enable communication via a wireless protocol
for transmitting data over short distances, such as Bluetooth,
ZigBee, NFC, etc. Additionally, the network interface cards may
enable communicating data over long distances, and in one example,
the computing device 102 and the cloud-based computing system 116
may communicate with a network 112. Network 112 may be a public
network (e.g., connected to the Internet via wired (Ethernet) or
wireless (WiFi)), a private network (e.g., a local area network
(LAN) or wide area network (WAN)), or a combination thereof.
Network 112 may also comprise a node or nodes on the Internet of
Things (IoT).
[0042] The computing device 102 may be any suitable computing
device, such as a laptop, tablet, smartphone, or computer. The
computing device 102 may include a display that is capable of
presenting a user interface of an application 118. The application
118 may be implemented in computer instructions stored on the one
or more memory devices of the computing device 102 and executable
by the one or more processing devices of the computing device 102.
The application 118 may present various screens to a user that
present various views (e.g., topographical heatmaps) including
measures, gradients, or levels of certain types of activity and
optimized sequences of selected candidate drug compounds,
information pertaining to the selected candidate drug compounds
and/or other candidate drug compounds, options to modify the
sequence of ingredients in the selected candidate drug compound,
and so forth, as described in more detail below. The computing
device 102 may also include instructions stored on the one or more
memory devices that, when executed by the one or more processing
devices of the computing device 102, perform operations of any of
the methods described herein.
[0043] In some embodiments, the cloud-based computing system 116
may include one or more servers 128 that form a distributed
computing architecture. The servers 128 may be a rackmount server,
a router computer, a personal computer, a portable digital
assistant, a mobile phone, a laptop computer, a tablet computer, a
camera, a video camera, a netbook, a desktop computer, a media
center, any other device capable of functioning as a server, or any
combination of the above. Each of the servers 128 may include one
or more processing devices, memory devices, data storage, and/or
network interface cards. The servers 128 may be in communication
with one another via any suitable communication protocol. The
servers 128 may execute an artificial intelligence (AI) engine 140
that uses one or more machine learning models 132 to perform at
least one of the embodiments disclosed herein. The cloud-based
computing system 128 may also include a database 150 that stores
data, knowledge, and data structures used to perform various
embodiments. For example, the database 150 may store a knowledge
graph containing the biological context representation described
further below. Further, the database 150 may store generated
candidate drug compounds, selected candidate drug compounds,
information pertaining to the selected candidate drug compounds
(e.g., activity for certain types of ingredients, sequences of
ingredients, test results, correlations, etc.). Although depicted
separately from the server 128, in some embodiments, the database
150 may be hosted on one or more of the servers 128.
[0044] In some embodiments the cloud-based computing system 116 may
include a training engine 130 capable of generating the one or more
machine learning models 132. The machine learning models 132 may be
trained to discover, translate, design, generate, create, develop,
classify, and/or test candidate drug compounds, among other things.
The one or more machine learning models 132 may be generated by the
training engine 130 and may be implemented in computer instructions
executable by one or more processing devices of the training engine
130 and/or the servers 128. To generate the one or more machine
learning models 132, the training engine 130 may train the one or
more machine learning models 132.
[0045] The training engine 130 may be a rackmount server, a router
computer, a personal computer, a portable digital assistant, a
smartphone, a laptop computer, a tablet computer, a netbook, a
desktop computer, any other desired computing device, or any
combination of the above. The training engine 130 may be
cloud-based, be a real-time software platform, include privacy
software or protocols, and/or include security software or
protocols.
[0046] To generate the one or more machine learning models 132, the
training engine 130 may train the one or more machine learning
models 132. The training engine 130 may use a base data set of
biological context representation (e.g., physical properties data,
peptide activity data, microbe data, antimicrobial data,
anti-neurodegenerative compound data, pro-neuroplasticity compound
data, clinical outcome data, etc.) for a set of drug compounds. For
example, the biological context representation may include
sequences of ingredients for the drug compounds. The results may
include information indicating levels of certain types of activity
associated with certain design spaces. In one embodiment, the
results may include causal inference information pertaining to
whether certain ingredients in the drug compounds are correlated
with or determined by certain effects (e.g., activity levels) in
the design space.
[0047] The one or more machine learning models 132 may refer to
model artifacts created by the training engine 130 using training
data that includes training inputs and corresponding target
outputs. The training engine 130 may find patterns in the training
data wherein such patterns map the training input to the target
output, and generate the machine learning models 132 that capture
these patterns. Although depicted separately from the server 128,
in some embodiments, the training engine 130 may reside on server
128. Further, in some embodiments, the artificial intelligence
engine 140, the database 150, and/or the training engine 130 may
reside on the computing device 102.
[0048] As described in more detail below, the one or more machine
learning models 132 may comprise, e.g., a single level of linear or
non-linear operations (e.g., a support vector machine [SVM]) or the
machine learning models 132 may be a deep network, i.e., a machine
learning model comprising multiple levels of non-linear operations.
Examples of deep networks are neural networks including generative
adversarial networks, convolutional neural networks, recurrent
neural networks with one or more hidden layers, and fully connected
neural networks (e.g., each neuron may transmit its output signal
to the input of the remaining neurons, as well as to itself). For
example, the machine learning model may include numerous layers
and/or hidden layers that perform calculations (e.g., dot products)
using various neurons. In some embodiments, one or more of the
machine learning models 132 may be trained to use causal inference
and counterfactuals.
[0049] For example, the machine learning model 132 trained to use
causal inference may accept one or more inputs, such as (i)
assumptions, (ii) queries, and (iii) data. The machine learning
model 132 may be trained to output one or more outputs, such as (i)
a decision as to whether a query may be answered, (ii) an objective
function (also referred to as an estimand) that provides an answer
to the query for any received data, and (iii) an estimated answer
to the query and an estimated uncertainty of the answer, where the
estimated answer is based on the data and the objective function,
and the estimated uncertainty reflects the quality of data (i.e., a
measure which takes into account the degree and/or salience of
incorrect data and/or missing data). The assumptions may also be
referred to as constraints and may be simplified into statements
used in the machine learning model 132. The queries may refer to
scientific questions for which the answers are desired.
[0050] The answers estimated using causal inference by the machine
learning model may include optimized sequences of ingredients in
selected candidate drug compounds. As the machine learning model
estimates answers (e.g., candidate drug compounds), certain causal
diagrams may be generated, as well as logical statements, and
patterns may be detected. For example, one pattern may indicate
that "there is no path connecting ingredient D and activity P,"
which may translate to a statistical statement "D and P are
independent." If alternative calculations using counterfactuals
contradict or do not support that statistical statement, then the
machine learning model 132 and/or the biological context
representation may be updated. For example, another machine
learning model 132 may be used to compute a degree of fitness which
represents a degree to which the data is compatible with the
assumptions used by the machine learning model that uses causal
inference. There are certain techniques that may be employed by the
other machine learning model 132 to reduce the uncertainty and
increase the degree of compatibility. The techniques may include
those for maximum likelihood, propensity scores, confidence
indicators, and/or significance tests, among others.
[0051] Using causal inference, a generative adversarial network
(GAN) may be used to generate a set of candidate drug compounds. A
GAN refers to a class of deep learning algorithms including two
neural networks, a generator and a discriminator, that both compete
with one another to achieve a goal. For example, regarding
candidate drug compound generation, the generator goal may include
generating candidate drug compounds, including
compatible/incompatible sequences of ingredients, and
effective/ineffective sequences of ingredients, etc. that the
discriminator classifies as feasible candidate drug compounds,
including compatible and effective sequences of ingredients that
may produce desired activity levels for a design space. The
generator may use causal inference, including counterfactuals, to
calculate numerous alternative scenarios that indicate whether a
certain result (e.g., activity level) still follows when any
element or aspect of a sequence changes. The discriminator goal may
include distinguishing candidate drug compounds which include
undesirable sequences of ingredients from candidate drug compounds
which include desirable sequences of ingredients.
[0052] In some embodiments, the generator initially generates
candidate drug compounds and continues to generate better candidate
drug compounds after each iteration until the generator eventually
begins to generate candidate drug compounds that are valid drug
compounds which produce certain levels of activity within a design
space. A candidate drug compound may be "valid" when it produces a
certain level of effectiveness (e.g., above a threshold activity
level as determined by a standard (e.g., regulatory entity)) in a
design space. In order to classify the candidate drug compounds as
a valid drug compound or invalid candidate drug compound, the
discriminator may receive real drug compound information from a
dataset and the candidate drug compounds generated by the
generator. The generator obtains the results from the discriminator
and applies the results in order to generate better (e.g., valid)
candidate drug compounds.
[0053] General details regarding the GAN are now discussed. The two
neural networks, the generator and the discriminator, may be
trained simultaneously. The discriminator may receive an input and
then output a scalar indicating whether a candidate drug compound
is an actual and/or viable drug compound. In some embodiments, the
discriminator may resemble an energy function that outputs a low
value (e.g., close to 0) when input is a valid drug compound and a
positive value when the input is not a valid drug compound (e.g.,
if it includes an incorrect sequence of ingredients for certain
activity levels pertaining to a design space).
[0054] There are two functions that may be used, the generator
function (G(V)), and the discriminator function (D(Y)). The
generator function may be denoted as G(V), where V is generally a
vector randomly sampled in a standard distribution (e.g.,
Gaussian). The vector may be any suitable dimension and may be
referred to as an embedding herein. The role of the generator is to
produce candidate drug candidates so as to train the discriminator
function (D(Y)) to output the values indicating the candidate drug
candidate is valid (e.g., a low value).
[0055] During training, the discriminator is presented with a valid
drug compound and adjusts its parameters (e.g., weights and biases)
to output a value indicative of the validity of the candidate drug
compounds that produce real activity levels in certain design
spaces. Next, the discriminator may receive a modified candidate
drug compound (e.g., modified using counterfactuals) generated by
the generator and adjust its parameters to output a value
indicative of whether the modified candidate drug compound provides
the same or a different activity level in the design space.
[0056] The discriminator may use a gradient of an objective
function to increase the value of the output. The discriminator may
be trained as an unsupervised "density estimator," i.e., a contrast
function produces a low value for desired data (e.g., candidate
drug compounds that include sequences producing desired levels of
certain types of activity in a design space) and higher output for
undesired data (e.g., candidate drug compounds that include
sequences producing undesirable levels of certain types of activity
in a design space). The generator may receive the gradient of the
discriminator with respect to each modified candidate drug compound
it produces. The generator uses the gradient to train itself to
produce modified candidate drug compounds that the discriminator
determines include sequences producing desired levels of certain
types of activity in a design space.
[0057] Recurrent neural networks include the functionality, in the
context of a hidden layer, to process information sequences and
store information about previous computations. As such, recurrent
neural networks may have or exhibit a "memory." Recurrent neural
networks may include connections between nodes that form a directed
graph along a temporal sequence. Keeping and analyzing information
about previous states enables recurrent neural networks to process
sequences of inputs to recognize patterns (e.g., such as sequences
of ingredients and correlations with certain types of activity
level). Recurrent neural networks may be similar to Markov chains.
For example, Markov chains may refer to stochastic models
describing sequences of possible events in which the probability of
any given event depends only on the state information contained in
the previous event. Thus, Markov chains also use an internal memory
to store at least the state of the previous event. These models may
be useful in determining causal inference, such as whether an event
at a current node changes as a result of the state of a previous
node changing.
[0058] The set of candidate drug compounds generated may be input
into another machine learning model 132 trained to classify of the
set of candidate drug compounds as a selected candidate drug
compound. The classifier may be trained to rank the set of
candidate drug compounds using any suitable ranking (i.e., for
example, non-parametric) technique. For example, in some
embodiments, one or more clustering techniques may be used to
cluster the set of candidate drug compounds. To classify the
selected candidate drug compound, the machine learning model 132
may also perform objective optimization techniques while
clustering. To classify the selected candidate drug compound having
desired levels of certain types of activity, the objective
optimization may include using a minimization and/or maximization
function for each candidate drug compound in the clusters.
[0059] A cluster may refer to a group of data objects similar to
one another within the same cluster, but dissimilar to the objects
in the other clusters. Cluster analysis may be used to classify the
data into relative groups (clusters). One example of clustering may
include K-means clustering where "K" defines the number of
clusters. Performing K-means clustering may comprise specifying the
number of clusters, specifying the cluster seeds, assigning each
point to a centroid, and adjusting the centroid.
[0060] Additional clustering techniques may include hierarchical
clustering and density based spatial clustering. Hierarchy
clustering may be used to identify the groups in the set of
candidate drug compounds where there is no set number of clusters
to be generated. As a result, a tree-based representation of the
objects in the various groups may be generated. Density-based
spatial clustering may be used to identify clusters of any shape in
a dataset having noise and outliers. This form of clustering also
does not require specifying the number of clusters to be
generated.
[0061] FIG. 2 illustrates a data structure storing a biological
context representation 200 according to certain embodiments of this
disclosure. Biology is context-dependent and dynamic. For example,
the same molecule can manifest multiple, potentially competing,
phenotypes. Further, data on an existing drug labeled as
antimicrobial can suggest a null behavior in applications against
different microbes or even against the same microbes but in
different contexts, e.g., temperature, pressure, environmental,
contextual, comorbid. To accurately predict candidate drug
compounds that provide desirable activity levels in design spaces,
the machine learning models 132 are trained to handle evolving
knowledge maps of biology and drug compounds. Further, conventional
techniques for discovery and generating drug compounds may be
ineffective for biological data because such data is non-Euclidian.
For example, machine learning models used for computer vision,
image classification, and language models compute on Euclidian data
and cannot therefore be applied to make useful inferences about
non-Euclidian data in biology.
[0062] In some embodiments, the biological context representation
200 generated by the disclosed techniques may be used to
graphically model the continually or continuously modifying
biological and drug compound knowledge. That is, the biology may be
represented as graphs within a comprehensive knowledge graph (e.g.,
biological context representation 200), where the graphs have
complex relationships and interdependencies between nodes.
[0063] The biological context representation 200 may be stored in a
first data structure having a first format. The first format may be
a graph, an array, a linked list, or any suitable data format
capable of storing the biological context representation. In
particular, FIG. 2 illustrates various types of data received from
various sources, including physical properties data 202, peptide
activity data 204, microbe data 206, antimicrobial compound data
208, clinical outcome data 210, evidence-based guidelines 212,
disease association data 214, pathway data 216, compound data 218,
gene interaction data 220, anti-neurodegenerative compound data
222, and/or pro-neuroplasticity compound data 224.
[0064] These example data may be curated by the AI engine 140
and/or a person having a certain degree (e.g., a degree in data
science, molecular biology, microbiology, etc.), certification,
license (e.g., a licensed medical doctor (e.g., M.D. or D.O.),
and/or credential. Further, the data in the biological context
representation 200 may be retrieved from any suitable data source
(e.g., digital libraries, websites, databases, files, or the like).
These examples are not meant to be limiting. Thus, the example
types of data are also not meant to be limiting and other types of
data may be stored within the biological context representation
without departing from the scope of this disclosure. Further, the
various data included in the biological context representation 200
may be linked based on one or more relationships between or among
the data, in order to represent knowledge pertaining to the
biological context and/or drug compound.
[0065] The physical properties data 202 includes physical
properties exhibited by the drug compound. The physical properties
may refer to characteristics that provide a physical description of
the drug such as color, particle size, crystalline structure,
melting point, solubility. In some instances, the physical
properties data 202 may also include chemical property data, such
as the structure, form, and reactivity of a substance. In some
embodiments, biological data may also be included (e.g.,
anti-neurodegenerative compound data, pro-neuroplasticity compound
data, anti-cancer data) in the biological context representation
200.
[0066] The peptide activity data 204 may include various types of
activity exhibited by the drug. For example, the activity may be
hormonal, antimicrobial, immunomodulatory, cytotoxic, neurological,
and the like. A peptide may refer to a short chain of amino acids
linked by peptide bonds.
[0067] The microbe data 206 may include information pertaining to
cellular structure (e.g., unicellular, multicellular, etc.) of a
microscopic organism. The microbes may refer to bacteria,
parasites, fungi, viruses, prions, or any combination of these,
etc.
[0068] The antimicrobial compound data 208 may include information
pertaining to agents that kill microbes or stop their growth. This
data may include classifications based on the microorganisms
against which the antimicrobial compound acts (e.g., antibiotics
act against bacteria but not against viruses; anti-virals act
against viruses but not against bacteria). The antimicrobial
compound may also be classified according to function (e.g.,
microbicidal, meaning "that which kills, vitiates, inactivates or
otherwise impairs the activity of certain microbes").
[0069] The clinical outcome data 210 may include information
pertaining to the administration of a drug compound to a subject in
a clinical setting. For example, upon or subsequent to
administration of the drug compound, the outcome may be a prevented
disease, cured disease, treated symptom, etc.
[0070] The evidence-based guidelines 212 may include information
pertaining to guidelines based upon clinical studies for acceptable
treatment and/or therapeutics for certain diseases and/or medical
conditions. Evidence-based guidelines data 212 may include data
specific to various specialties within healthcare such as, for
example, obstetrics, anesthesiology, hepatology, gastroenterology,
neurology, pulmonology, orthopaedics, pediatrics, trauma care
(including but not limited to burns and post-burn infections),
histology, oncology, ophthalmology, endocrinology, rheumatology,
internal medicine, surgery, vascular medicine, radiology,
psychiatry, cardiology, urology, gynecology, genetics, and
dermatology. In the example described herein, the evidence-based
guidelines 212 include systematically developed statements to
assist practitioner and patient decisions about appropriate health
care (e.g., types of drugs to prescribe for treatment) for specific
clinical circumstances.
[0071] The disease association data 214 may include information
about which disease and/or medical condition the drug compounds are
associated with. For example, the drug compound Metformin may be
associated with the disease type 2 diabetes.
[0072] The pathway data 216 may include information pertaining in a
design space to the relationships or paths between ingredients
(e.g., chemicals) and activity levels.
[0073] The compound data 218 may include information pertaining to
the compound such as the sequence of ingredients (e.g., type,
amount, etc.) in the compound. In the therapeutics industry, for
example, the compound data 218 can include data specific to the
various types of drug compounds that are designed, defined,
developed, and/or distributed.
[0074] The gene interaction data 220 may include information
pertaining to which gene the drug compound and/or a disease may
interact with.
[0075] The anti-neurodegenerative compound data 222 may include
information pertaining to characteristics of anti-neurodegenerative
compounds, such as their physical and chemical properties and
activities on portions of tissue. For example, the activity may
include anti-inflammatory and/or neuro-protective actions.
[0076] The pro-neuroplasticity compound data 224 may include
information pertaining to characteristics of pro-neuroplasticity
compound, such as their physical and chemical properties and
activities on portions of tissue. For example, the activity may
enhance the capacity of motor systems by upregulation of
neurotrophins.
[0077] FIGS. 3A-3B illustrate a high-level flow diagram according
to certain embodiments of this disclosure. Regarding FIG. 3A, a
flow diagram 300 begins with obtaining heterogeneous datasets, such
as the biological context representation 200. Heterogeneous
datasets may refer to populations or samples of data that are
different (e.g., as opposed to homogenous datasets where the data
is the same). The heterogeneous datasets may include compound data
(e.g., peptide sequence data), clinical outcome data, and/or
activity data (in vitro and in vivo activity), as well as any other
suitable data depicted in FIG. 2.
[0078] The data structure storing the heterogeneous datasets may be
translated to a second data structure having a second format (e.g.,
a 2-dimensional vector) that the AI engine 140 may use to generate
the candidate drug compounds. The next step in the flow diagram 300
includes training the one or more machine learning models 132 using
the heterogeneous datasets. The one or more machine learning models
132 (e.g., generative models) may generate a set of candidate drug
compounds based on the heterogeneous datasets. As described herein,
a machine learning model may use causal inference and
counterfactuals when generating the set of candidate drug
compounds. Further, a GAN may be used in conjunction with causal
inference to generate the set of candidate drug compounds. In some
embodiments, a certain number (e.g., over 100,000 candidate drug
compounds) of novel candidate drug compounds may be generated in a
set. That is, each candidate drug compound in the set of candidate
drug compounds is intended to be unique.
[0079] The next step in the flow diagram 300 includes inputting the
set of candidate drug compounds into one or more machine learning
models 132 trained to classify the set of candidate drug compounds.
The machine learning models 132 may perform supervised and/or
unsupervised filtering. In some embodiments, the machine learning
models 132 may perform clustering to rank the various candidate
drug compounds to classify one candidate drug compound as a
selected candidate drug compound. In some embodiments, the machine
learning models 132 may output a subset (e.g., 1,000 to 10,000, or
more, or fewer) of candidate drug compounds.
[0080] The next step in the flow diagram 300 may include performing
experimental validation by validating whether each candidate drug
compound in the subset of candidate drug compounds provides the
desired level of certain types of activity in a design space. The
results of the experimental validation may be fed back into the
heterogeneous dataset to reinforce and expand the experimental
dataset.
[0081] The next step in the flow diagram 300 may include performing
peptide drug optimization. The optimizations may include performing
gradient descent and/or ascent using the sequence of ingredients in
the candidate drug compounds to attempt to increase and/or decrease
certain activity levels in a design space. The results of the
peptide drug optimization may be fed back into the heterogeneous
datasets to reinforce and expand the experimental dataset.
[0082] FIG. 3B illustrates another high-level flow diagram 310
according to some embodiments. As depicted, a heterogeneous network
of biology may be included in a knowledge graph of a biological
context representation 200. Various paths or meta-paths may be
expressed between nodes in the biological context representation
200. For example, the meta-paths may include indications for
compound upregulates, pathway participates, disease associations,
gene interactions, and compound data.
[0083] The biological context representation 200 may be translated
from a first format (e.g., knowledge graph) to a format (e.g.,
vector) that may be processed by the AI engine 140. The AI engine
140 may use one or more machine learning models to traverse the
knowledge graph by performing random walks until a corpus of random
walks is generated, wherein such random walks include the
indications associated with the meta-paths representing sequences
of ingredients. The corpus of random walks may be referred to as a
set of candidate drug compounds. A generative adversarial network
using causal inference may be used to generate the set of candidate
drug compounds. The set of candidate drug compounds may be stored
in a higher-dimensional vector.
[0084] The AI engine 140 may compress the higher-dimensional vector
of the set of candidate drug compounds into a lower-dimensional
vector of the set of candidate drug compounds, depicted as
biological embeddings in FIG. 3B. In some embodiments, the
lower-dimensional vector may include fewer dimensions (e.g., 2, 3,
. . . N) than the higher-dimensional vector (e.g., greater than N).
As depicted, the nodes may be organized by the meta-path indicators
and by dimension.
[0085] To output a subset of candidate drug compounds, the
lower-dimensional vector of the set of candidate drug compounds may
be input to one or more machine learning models 132 trained to
perform classification. The classification techniques may include
using clustering to filter out candidate drug compounds that
produce undesirable levels of types of activity. In some
embodiments, to enable the AI engine 140 to perform the
classification, views presenting the levels of types of activity of
each candidate drug compound in a design space may be generated
using the lower-dimensional vectors. These views may also be
presented to a user via the computing device 102. The machine
learning models 132 may output a candidate drug candidate
classified as a selected candidate drug candidate based on the
clustering. For example, the selected candidate drug candidate may
include an optimized sequence of ingredients that provides the most
desirable levels of a certain type of activity in a design
space.
[0086] FIG. 4 illustrates example operations of a method 400 for
generating and classifying a candidate drug candidate compound
according to certain embodiments of this disclosure. The method 400
is performed by processing logic that may include hardware
(circuitry, dedicated logic, etc.), software (such as is run on a
general purpose computer system or a dedicated machine), or a
combination of both. The method 400 and/or each of their individual
functions, routines, subroutines, or operations may be performed by
one or more processors of a computing device (e.g., any component
of FIG. 1, such as server 128 executing the artificial intelligence
engine 140). In certain implementations, the method 400 may be
performed by a single processing thread. Alternatively, the method
400 may be performed by two or more processing threads, each thread
implementing one or more individual functions, routines,
subroutines, or operations of the methods. One or more operations
of the method 400 may be performed by the training engine 130 of
FIG. 1.
[0087] For simplicity of explanation, the method 400 is depicted
and described as a series of operations. However, operations in
accordance with this disclosure can occur in various orders and/or
concurrently, and with other operations not presented and described
herein. For example, the operations depicted in the method 400 may
occur in combination with any other operation of any other method
disclosed herein. Furthermore, not all illustrated operations may
be required to implement the method 400 in accordance with the
disclosed subject matter. In addition, those skilled in the art
will understand and appreciate that the method 400 could
alternatively be represented as a series of interrelated states via
a state diagram or events.
[0088] At 402, the processing device may generate a biological
context representation 200 of a set of drug compounds. The
biological context representation 200 may include a first data
structure having a first format (e.g., a knowledge graph). The
biological context representation 200 may include, for each drug
compound of the set of drug compounds, one or more relationships
between or among, without limitation, (i) physical properties data
202, (ii) peptide activity data 204, (iii) microbe data 206, (iv)
antimicrobial compound data 208, (v) clinical outcome data 210,
(vi) evidence-based guidelines 212, (vii) disease association data
214, (viii) pathway data 216, (ix), compound data 218, (x) gene
interaction data 220, (xi) antimicrobial compound data, (xii)
pro-neuroplasticity data 224, or some combination thereof.
[0089] At 404, the processing device may translate, by the
artificial intelligence engine 140, the first data structure having
the first format to a second data structure having a second format.
The translating may include converting the first data structure
having the first format (e.g., knowledge graph) to the second data
structure having the second format (e.g., vector) according to a
specific set of rules executed by the artificial intelligence
engine 140. In some embodiments, the translating may be performed
by one or more of the machine learning models 132. For example, a
recurrent neural network may perform at least a portion of the
translating.
[0090] The translating may include obtaining a higher-dimensional
vector and compressing the higher-dimensional vector into a
lower-dimensional vector (e.g., two-dimensional, three-dimensional,
four-dimensional), referred to as an embedding herein. In some
embodiments, one or more embeddings may be created from the first
data structure having the first format. There may be any suitable
number of dimensions of the embeddings. When used for classifying
candidate drug compounds, the number of dimensions may be selected
based on a desired performance to process the embeddings. The
lower-dimensional vector may have at least one fewer dimension than
the higher-dimensional vector.
[0091] At 406, the processing device may generate, based on the
second data structure having the second format, a set of candidate
drug compounds. In some embodiments, the generating may be
performed by one or more of the machine learning models 132. For
example, a generative adversarial network may perform the
generating of the set of candidate drug compounds. In some
embodiments, the set of candidate drug compounds may be associated
with design spaces pertaining to antimicrobial, anti-cancer,
anti-biofilm, or the like. A biofilm may include any syntrophic
consortium of microorganisms in which cells stick to each other and
often also to a surface. These adherent cells may become embedded
within an extracellular matrix that is composed of extracellular
polymeric substances (EPS). Cancer may refer to a disease caused or
correlated with an uncontrolled division of abnormal cells in a
part of the body.
[0092] At 408, the processing device may classify a candidate drug
compound from the set of candidate drug compounds as a selected
candidate drug compound. In some embodiments, the classifying may
be performed by one or more of the machine learning models 132. For
example, a classifier trained using supervised or unsupervised
learning may perform the classifying. In some embodiments, the
classifier may use clustering techniques to rank and classify the
selected candidate drug compound.
[0093] In some embodiments, the processing device may generate a
set of views including a representation of a design space. The
design space may be antimicrobial. The processing device may cause
the set of views to be presented on a computing device (e.g.,
computing device 102). The representation of the design space may
pertain to, without limitation, (i) antimicrobial activity, (ii)
immunomodulatory activity, (iii) neuromodulatory activity, (iv)
cytotoxic activity, or some combination thereof. Each view of the
set of views may present an optimized sequence representing the
selected candidate drug compound.
[0094] The optimized sequence in each view may be generated using
any suitable optimization technique. The optimization technique may
include maximizing or minimizing an objective function by
systematically selecting input values from a domain of values and
computing the value using the objective function. The domain of
values may include a subset of values from a Euclidean space. The
subset of values may satisfy one or more constraints, equalities,
and/or inequalities. A value that minimizes or maximizes the
objective function may be referred to as an optimal solution.
Certain values in the subset may result in a gradient of the
objective function being zero. Those certain values may be at
stationary points, where a first derivative at those points with
respect to time (dt) is zero. The gradient may refer to a
scalar-valued differentiable function (e.g., objective function) of
several variables, where a point p is a vector whose components are
the partial derivatives of the objective function. If the gradient
is not a zero vector at a certain point p, then a direction of the
gradient is the direction of fastest increase of the objective
function at the certain point p.
[0095] Gradients may be used in gradient descent, which refers to a
first-order iterative optimization algorithm for finding the local
minimum of an objective function. To find the local minimum,
gradient descent may proceed by performing operations proportional
to the negative of the gradient of the objective function at a
current point. In some embodiments, the optimized sequence may be
found for a candidate drug compound performing gradient descent in
the design space. Additionally, gradient ascent, which is the
algorithm opposite to gradient descent, may determine a local
maximum of the objective function at various points in the design
space.
[0096] The views generated may include a topographical heatmap,
itself including indicators for the least activity at points in the
design space and the most activity at points in the design space.
The indicator associated with the most activity may represent a
local maximum obtained using gradient ascent. The indicator
associated with the least activity may represent a local minimum
obtained using gradient descent. The optimal sequence may be
generated by navigating points between the local minima and local
maxima. The optimized sequence may be overlaid on the indicators
ranging from at least one least active property to an at least one
most active property.
[0097] In some embodiments, the processing device may cause the
selected candidate drug compound to be formulated. In some
embodiments, the processing device may cause the selected candidate
drug compound to be created, manufactured, developed, synthesized,
or the like. For example, the artificial intelligence engine 140
may control one or more pumps, mixers, heaters, and reaction
chambers to synthesis a desired candidate drug sequence in an
automated flow process. The synthesis may be controlled in the
reaction chamber via one or more parameters, such as solvents,
temperature, pressure, and the like. In some embodiments, the
processing device may cause the selected candidate drug compound to
be presented on a computing device (e.g., computing device 102).
The selected candidate drug compound may include one or more active
ingredients (e.g., chemicals) at a specified amount.
[0098] FIGS. 5A-5D provide illustrations of generating a first data
structure including a biological context representation 200 of a
plurality of drug compound devices according to certain embodiments
of this disclosure. The first data format may include a knowledge
graph. The biological context representation 200 may capture an
entire biological context by integrating every known association or
relationship for each drug compound into a comprehensive knowledge
graph.
[0099] FIG. 5A presents the biological context representation 200
including biomedical and domain knowledge on peptide activity,
microbes, antimicrobial compounds, clinical outcomes, and any
relevant information depicted in FIG. 2. A table 500 may include
rows representing various categories (A, B, C, D, and E) pertaining
to a biological context for each drug compound and columns
representing sub-categories (1, 2, 3, 4, and 5). For example, the
table includes subcategories for category A: A1 2D fingerprints, A2
3D fingerprints, A3 Scaffolds, A4 Struct. Keys, A5 Physicochem./B:
B1 Mech. Of act., B2 Metab. Genes, B3 Crystals, B4 Binding, B5 HTS
bioassays/C: C1 S. mol. Roles, C2 S. mol. Path., C3 Signal. Path.,
C4 Biol. Proc., C5 Interactome/D: D1 Transcript, D2 Can. Cell
lines, D3 Ch. Genetics, D4 Morphology, D5 Cell bioassays/E: E1
Therap. Areas, E2 Indications, E3 Side effects, E4 Dis. &
Toxicol., E5 Drug-drug inter.
[0100] Charts 502, 504, and 506 represent characteristics for each
subcategory. The characteristics for chart 502 include the size of
molecules, for chart 504 the complexity of variables, and for 506
the correlation with mechanism of action. Another chart 508 may
represent the various characteristics of the subcategories using an
indicator (such as a range of colors from 0 to 1) to express the
values of the characteristics in relation to each other.
[0101] FIG. 5B illustrates a different representation 520 of
characteristics for several subcategories (e.g., A1, B1, C5, D1,
and E3) across different subject matter areas (e.g., neurology and
psychiatry, infectious disease, gastroenterology, cardiology,
ophthalmology, oncology, endocrinology, pulmonary, rheumatology,
and malignant hematology.). Accordingly, the representation 520
provides an even more granular representation of the biological
context representation 200 than does the chart 508. Flowchart 530
represents the process for generating candidate drugs as described
further herein.
[0102] FIG. 5C illustrates a knowledge graph 540 representing the
biological context representation 200. The knowledge graph 540 may
refer to a cognitive map. In particular, the knowledge graph 540
represents a graph traversed by the AI engine 140, when generating
candidate drug compounds having desired levels of certain types of
activity in a design space. Individual nodes in the knowledge graph
540 represent a health artifact (health-related information) or
relationship (predicate) gleaned and curated from numerous data
sources. Further, the knowledge represented in the knowledge graph
540 may be improved over time as the machine learning models
discover new associations, correlations, and/or relationships. The
nodes and relationships may form logical structures that represent
knowledge (e.g., Genes Participates Pathways). FIG. 5D illustrates
another representation of the knowledge graph 540 that more clearly
identifies all the various relationships among the nodes.
[0103] FIG. 6 illustrates example operations of a method 600 for
translating the first data structure of FIGS. 5A-5B a second data
structure according to certain embodiments of this disclosure.
Method 600 includes operations performed by processors of a
computing device (e.g., any component of FIG. 1, such as server 128
executing the artificial intelligence engine 140). In some
embodiments, one or more operations of the method 600 are
implemented in computer instructions that are stored on a memory
device and executed by a processing device. The method 600 may be
performed in the same or a similar manner as described above in
regards to method 400. The operations of the method 600 may be
performed in some combination with any of the operations of any of
the methods described herein.
[0104] The method 600 may include operation 404 from the
previously-described method 400 depicted in FIG. 4. For example, at
404 in the method 600, the processing device may translate, by the
artificial intelligence engine 140, the first data structure having
the first format (e.g., knowledge graph) to the second data
structure having the second format (e.g., vector). The method 600
in FIG. 6 includes operations 602 and 604.
[0105] At 602, the processing device may obtain a higher
dimensional vector from the biological context representation 200.
This process is further illustrated in FIG. 7.
[0106] At 604, the processing device may compress the
higher-dimensional vector to a lower dimensional-vector. The
compressing may be performed by a first machine learning model 132
trained to perform deep auto-encoding via a recurrent neural
network configured to output the lower-dimensional vector.
[0107] At 606, the processing device may train the first machine
learning model 132 by using a second machine learning model 132 to
recreate the first data structure having the first format. The
second machine learning model 132 is trained to perform a decoding
operation to recreate the first data structure having the first
format. The decoding operation may be performed on the second data
structure having the second data format (e.g., two-dimensional
vector).
[0108] FIG. 7 provides illustrations of translating the first data
structure of FIGS. 5A-5B to the second data structure according to
certain embodiments of this disclosure. Aggregated biological data
may be difficult to model and format correctly for an AI engine to
process. Aspects of the present disclosure overcome the hurdle of
modeling and formatting the aggregated biological data to enable
the AI engine 140 to generate candidate drug compounds accurately
and efficiently.
[0109] As depicted, a higher-dimensional vector 700 may be obtained
from the biological context representation 200. Using a recurrent
neural network performing autoencoding, the higher-dimensional
vector is compressed to a lower-dimensional vector 702. The
recurrent neural network performing autoencoding is trained using
another machine learning model 132 that recreates the
higher-dimensional vector 704. If the other machine learning model
132 is unable to recreate higher-dimensional vector 704 from the
lower-dimensional vector 702, then the other machine learning model
132 provides feedback to the recurrent neural network performing
autoencoding in order to update its weights, biases, or any
suitable parameters.
[0110] FIGS. 8A-8C provide illustrations of views of a selected
candidate drug compound according to certain embodiments of this
disclosure. As depicted, FIG. 8A illustrates a view 800 including
antimicrobial activity, FIG. 8B illustrates a view 802 including
immunomodulatory activity, and FIG. 8C illustrates a view 804
including cytotoxic activity. Each view presents a topographical
heatmap where one axis is for sequence parameter y and the other
axis is for sequence parameter x. Each view includes an indicator
ranging from a least active property to a most active property.
Further each view includes an optimized sequence 806 for a selected
candidate drug compound classified by the classifier (machine
learning model 132). These views may be presented to the user on a
computing device 102. Further, the selected candidate drug compound
806 may be formulated, generated, created, manufactured, developed,
and/or tested.
[0111] FIG. 9 illustrates example operations of a method 900 for
presenting a view including a selected candidate drug compound
according to certain embodiments of this disclosure. Method 900
includes operations performed by processors of a computing device
(e.g., any component of FIG. 1, such as computing device 102). In
some embodiments, one or more operations of the method 1000 are
implemented in computer instructions that are stored on a memory
device and executed by a processing device. The method 1000 may be
performed in the same or a similar manner as described above in
regards to method 400. The operations of the method 1000 may be
performed in some combination with any of the operations of any of
the methods described herein.
[0112] At 902, the processing device may receive, from the
artificial intelligence engine 140, a candidate drug compound
generated by the artificial intelligence engine 140.
[0113] At 904, the processing device may generate a view including
the candidate drug compound overlaid on a representation of a
design space. The view may present a topographical heatmap of the
representation of the design space. The topographical heatmap may
include the candidate drug compound overlaid on indicators ranging
from an at least one least active property to an at least one most
active property.
[0114] At 906, the processing device may present the view on a
display screen of a computing device (e.g., computing device
102).
[0115] FIG. 10A illustrates example operations of a method 1000 for
using causal inference during the generation of candidate drug
compounds according to certain embodiments of this disclosure.
Method 1000 includes operations performed by processors of a
computing device (e.g., any component of FIG. 1, such as server 128
executing the artificial intelligence engine 140). In some
embodiments, one or more operations of the method 1000 are
implemented in computer instructions that are stored on a memory
device and executed by a processing device. The method 1000 may be
performed in the same or a similar manner as described above in
regards to method 400. The operations of the method 1000 may be
performed in some combination with any of the operations of any of
the methods described herein.
[0116] At 1002, the processing device may perform one or more
modifications pertaining to the biological context representation
200, the second data structure having the second format, or some
combination thereof.
[0117] At 1004, the processing device may use causal inference to
determine whether the one or more modifications provide one or more
desired performance results. In some embodiments, using causal
inference may further include using 1006 counterfactuals to
calculate alternative scenarios based on past actions, occurrences,
results, regressions, regression analyses, correlations, or some
combination thereof. The term "calculate" may be used
interchangeably with any of the following terms: simulate, emulate,
determine, generate, formulate, execute, and/or obtain. A
counterfactual may refer to determining whether the desired
performance still results if something does not occur during the
calculation. For example, in a scenario, a person may improve their
health after taking a medication. The counterfactual may be used in
causal inference to calculate an alternative scenario to see
whether the person's health improved without taking the medication.
If the person's health still improved without taking the medication
it may be inferred that the medication did not cause the health of
the person to improve. However, if the person's health did not
improve without taking the medication, it may be inferred that the
medication is correlated with causing the health of the person to
improve. There may, however, be other factors involved in
conjunction with taking the medication that actually cause the
health of the person to improve.
[0118] FIG. 10B illustrates another example of operations of method
1050 for using causal inference during the generation of candidate
drug compounds according to certain embodiments of this disclosure.
Method 1050 includes operations performed by processors of a
computing device (e.g., any component of FIG. 1, such as server 128
executing the artificial intelligence engine 140). In some
embodiments, one or more operations of the method 1050 are
implemented in computer instructions that are stored on a memory
device and executed by a processing device. The method 1050 may be
performed in the same or a similar manner as described above in
regards to method 400. The operations of the method 1050 may be
performed in some combination with any of the operations of any of
the methods described herein.
[0119] At 1052, the processing device may generate a set of
candidate drug compounds by performing a modification using causal
inference based on a counterfactual. For example, the
counterfactual may include removing an ingredient from a sequence
of ingredients to determine whether a candidate drug compound
provides the same level and/or type of activity it previously
provided when the ingredient was included in the sequence. If the
same level and/or type of activity is still provided after
application of the counterfactual (e.g., removal of the
ingredient), then the processing device may use causal inference to
determine that the ingredient is not correlated with the level
and/or type of activity. If the same level and/or type of activity
is not present after application of the counterfactual (e.g.,
removal of the ingredient), then the processing device may use
causal inference to determine that the ingredient is correlated
with the level and/or type of activity.
[0120] At 1054, the processing device may classify a candidate dug
compound from the set of candidate drug compounds as a selected
candidate drug compound, as previously described herein.
[0121] FIG. 11 illustrates example computer system 1100 which can
perform any one or more of the methods described herein, in
accordance with one or more aspects of the present disclosure. In
one example, computer system 1100 may correspond to the computing
device 102 (e.g., user computing device), one or more servers 128
of the cloud-based computing system 116, the training engine 130,
or any suitable component of FIG. 1. The computer system 1100 may
be capable of executing application 118 and/or the one or more
machine learning models 132 of FIG. 1. The computer system may be
connected (e.g., networked) to other computer systems in a LAN, an
intranet, an extranet, or the Internet. The computer system may
operate in the capacity of a server in a client-server network
environment. The computer system may be a personal computer (PC), a
tablet computer, a wearable (e.g., wristband), a set-top box (STB),
a personal Digital Assistant (PDA), a mobile phone, a camera, a
video camera, or any device capable of executing a set of
instructions (sequential or otherwise) that specify actions to be
taken by that device. Further, while only a single computer system
is illustrated, the term "computer" shall also be taken to include
any collection of computers that individually or jointly execute a
set (or multiple sets) of instructions to perform any one or more
of the methods discussed herein.
[0122] The computer system 1100 includes a processing device 1102,
a main memory 1104 (e.g., read-only memory (ROM), flash memory,
solid state drives (SSDs), dynamic random access memory (DRAM) such
as synchronous DRAM (SDRAM)), a static memory 1106 (e.g., flash
memory, solid state drives (SSDs), static random access memory
(SRAM)), and a data storage device 1108, which communicate with
each other via a bus 1110.
[0123] Processing device 1102 represents one or more
general-purpose processing devices such as a microprocessor,
central processing unit, or the like. More particularly, the
processing device 1102 may be a complex instruction set computing
(CISC) microprocessor, reduced instruction set computing (RISC)
microprocessor, very long instruction word (VLIW) microprocessor,
or a processor implementing other instruction sets or processors
implementing a combination of instruction sets. The processing
device 1102 may also be one or more special-purpose processing
devices such as an application specific integrated circuit (ASIC),
a system on a chip, a field programmable gate array (FPGA), a
digital signal processor (DSP), network processor, or the like. The
processing device 1102 is configured to execute instructions for
performing any of the operations and steps discussed herein.
[0124] The computer system 1100 may further include a network
interface device 1112. The computer system 1100 also may include a
video display 1114 (e.g., a liquid crystal display (LCD), a
light-emitting diode (LED), an organic light-emitting diode (OLED),
a quantum LED, a cathode ray tube (CRT), a shadow mask CRT, an
aperture grille CRT, a monochrome CRT), one or more input devices
1116 (e.g., a keyboard and/or a mouse), and one or more speakers
1118 (e.g., a speaker). In one illustrative example, the video
display 1114 and the input device(s) 1116 may be combined into a
single component or device (e.g., an LCD touch screen).
[0125] The data storage device 1116 may include a computer-readable
medium 1120 on which the instructions 1122 embodying any one or
more of the methods, operations, or functions described herein is
stored. The instructions 1122 may also reside, completely or at
least partially, within the main memory 1104 and/or within the
processing device 1102 during execution thereof by the computer
system 1100. As such, the main memory 1104 and the processing
device 1102 also constitute computer-readable media. The
instructions 1122 may further be transmitted or received over a
network via the network interface device 1112.
[0126] While the computer-readable storage medium 1120 is shown in
the illustrative examples to be a single medium, the term
"computer-readable storage medium" should be taken to include a
single medium or multiple media (e.g., a centralized or distributed
database, and/or associated caches and servers) that store the one
or more sets of instructions. The term "computer-readable storage
medium" shall also be taken to include any medium that is capable
of storing, encoding or carrying a set of instructions for
execution by the machine and that cause the machine to perform any
one or more of the methodologies of the present disclosure. The
term "computer-readable storage medium" shall accordingly be taken
to include, but not be limited to, solid-state memories, optical
media, and magnetic media.
[0127] None of the description in this application should be read
as implying that any particular element, step, or function is an
essential element that must be included in the claim scope. The
scope of patented subject matter is defined only by the claims.
Moreover, none of the claims is intended to invoke 35 U.S.C. .sctn.
112(f) unless the exact words "means for" are followed by a
participle.
[0128] Consistent with the above disclosure, the examples of
systems and method enumerated in the following clauses are
specifically contemplated and are intended as a non-limiting set of
examples.
[0129] Clause 1. A method comprising: [0130] generating a
biological context representation of a plurality of drug compounds,
wherein the biological context representation comprises a first
data structure having a first format; [0131] translating, by an
artificial intelligence engine, the first data structure having the
first format to a second data structure having a second format;
[0132] generating, based on the second data structure having the
second format, a plurality of candidate drug compounds; and
classifying a candidate drug compound from the plurality of
candidate drug compounds as a selected candidate drug compound.
[0133] Clause 2. The method of any preceding clause, wherein the
biological context representation comprises, for each of the
plurality of drug compounds, one or more relationships between or
among: [0134] physical properties data, [0135] chemical data,
[0136] biological data, [0137] clinical outcome data, or [0138]
some combination thereof.
[0139] Clause 3. The method of any preceding clause, wherein the
translating the first data structure further comprises: [0140]
converting the first data structure having the first format to the
second data structure having the second format according to a
specific set of rules executed by the artificial intelligence
engine.
[0141] Clause 4. The method of any preceding clause, wherein
converting the biological context representation to the second data
structure having the second format further comprises: [0142]
obtaining a higher-dimensional vector from the biological context
representation; and [0143] compressing the higher-dimensional
vector to a lower-dimensional vector, wherein the compressing is
performed by a machine learning model trained to perform deep
auto-encoding via a recurrent neural network configured to output
the lower-dimensional vector.
[0144] Clause 5. The method of any preceding clause, further
comprising: [0145] training the machine learning model by using a
second machine learning model to recreate the higher-dimensional
vector, [0146] wherein the second machine learning model is trained
to perform a decoding operation to recreate the higher-dimensional
vector, wherein the decoding operation is performed on the
lower-dimensional vector.
[0147] Clause 6. The method of any preceding clause, wherein:
[0148] the translating is performed by a recurrent neural network,
[0149] the generating of the plurality of candidate drug compounds
is performed by a generative adversarial network, and [0150] the
classifying of the candidate drug compound is performed by a
classifier trained using supervised learning.
[0151] Clause 7. The method of any preceding clause, further
comprising: [0152] generating a plurality of views comprising a
representation of a design space; and [0153] causing the plurality
of views to be presented on a computing device, [0154] wherein the
representation pertains to: [0155] antimicrobial activity, [0156]
immunomodulatory activity, [0157] neuromodulatory activity, [0158]
cytotoxic activity, [0159] or some combination thereof.
[0160] Clause 8. The method of any preceding clause, wherein the
design space is antimicrobial.
[0161] Clause 9. The method of any preceding clause, wherein each
view of the plurality of views presents an optimized sequence
representing the selected candidate drug compound.
[0162] Clause 10. The method of any preceding clause, wherein each
view presents a topographical heatmap comprising the optimized
sequence overlaid on indicators ranging from an at least one least
active property to an at least one most active property.
[0163] Clause 11. The method of any preceding clause, further
comprising: [0164] performing one or more modifications pertaining
to the biological context representation, the second data structure
having the second format, or some combination thereof; and [0165]
using causal inference to determine whether the one or more
modifications provide one or more desired performance results.
[0166] Clause 12. The method of any preceding clause, wherein using
causal inference further comprises: [0167] using counterfactuals to
calculate alternative scenarios based on past actions, occurrences,
results, regressions, regression analyses, correlations, or some
combination thereof.
[0168] Clause 13. The method of any preceding clause, further
comprising: [0169] causing the selected candidate drug compound to
be formulated.
[0170] Clause 14. The method of any preceding clause, further
comprising: [0171] causing the selected candidate drug compound to
be created.
[0172] Clause 15. The method of any preceding clause, further
comprising: [0173] causing the selected candidate drug compound to
be presented on a computing device.
[0174] Clause 16. A tangible, non-transitory computer-readable
medium storing instructions that, when executed, cause a processing
device to: [0175] generate a biological context representation of a
plurality of drug compounds, wherein the biological context
representation comprises a first data structure having a first
format; [0176] translate the first data structure having the first
format to a second data structure having a second format; [0177]
generate, based on the second data structure having the second
format, a plurality of candidate drug compounds; and [0178]
classify a candidate drug compound from the plurality of candidate
drug compounds as a selected candidate drug compound.
[0179] Clause 17. The computer-readable medium of any preceding
clause, wherein the biological context representation comprises,
for each of the plurality of drug compounds, one or more
relationships between or among: [0180] physical properties data,
[0181] chemical data, [0182] biological data, [0183] clinical
outcome data, or [0184] some combination thereof.
[0185] Clause 18. The computer-readable medium of any preceding
clause, wherein translating the biological context representation
to the second data structure having the second format further
comprises: [0186] obtaining a higher-dimensional vector from the
biological context representation; and [0187] compressing the
higher-dimensional vector to a lower-dimensional vector, wherein
the compressing is performed by a machine learning model trained to
perform deep auto-encoding via a recurrent neural network
configured to output the lower-dimensional vector.
[0188] Clause 19. The computer-readable medium of any preceding
clause, wherein the processing device further: [0189] trains the
machine learning model by using a second machine learning model to
recreate the higher-dimensional vector, [0190] wherein the second
machine learning model is trained to perform a decoding operation
to recreate the higher-dimensional vector, wherein the decoding
operation is performed on the lower-dimensional vector.
[0191] Clause 20. The computer-readable medium of any preceding
clause, wherein: [0192] the translating is performed by a recurrent
neural network, [0193] the generating of the plurality of candidate
drug compounds is performed by a generative adversarial network,
and [0194] the classifying of the candidate drug compound is
performed by a classifier trained using supervised learning.
[0195] Clause 21. The computer-readable medium of any preceding
clause, wherein the processing device further: [0196] generates a
plurality of views comprising a representation of a design space,
[0197] wherein the representation pertains to: [0198] antimicrobial
activity, [0199] immunomodulatory activity, [0200] neuromodulatory
activity, [0201] cytotoxic activity, [0202] or some combination
thereof.
[0203] Clause 22. The computer-readable medium of any preceding
clause, wherein the processing device further: [0204] causes each
view of the plurality of views to be presented, wherein each such
view comprises an optimized sequence representing the selected
candidate drug compound, and [0205] causes each view of the
plurality of views to be presented, wherein each such view
comprises the optimized sequence overlaid on indicators ranging
from an at least one least active property to an at least one most
active property.
[0206] Clause 23. The computer-readable medium of any preceding
clause, wherein the processing device further: [0207] performs one
or more modifications pertaining to the biological context
representation, the second data structure having the second format,
or some combination thereof; and [0208] uses causal inference to
determine whether the one or more modifications provide a desired
performance result.
[0209] Clause 24. The computer-readable medium of any preceding
clause, wherein the processing device employs causal inference to
further: [0210] use counterfactuals to calculate alternative
scenarios based on past actions, occurrences, results, regressions,
regression analyses, correlations, or some combination thereof.
[0211] Clause 25. A system comprising: [0212] a memory device
storing instructions; and [0213] a processing device
communicatively coupled to the memory device, the processing device
executes the instructions to: [0214] generate a biological context
representation of a plurality of drug compounds, wherein the
biological context representation comprises a first data structure
having a first format; [0215] translate the first data structure
having the first format to a second data structure having a second
format; [0216] generate, based on the second data structure having
the second format, a plurality of candidate drug compounds; and
[0217] classify a candidate drug compound from the plurality of
candidate drug compounds as a selected candidate drug compound.
[0218] Clause 26. A computing device comprising: [0219] a display
screen; [0220] a memory device storing instructions; and [0221] a
processing device communicatively coupled to the memory device and
the display screen, the processing device executes the instructions
to: [0222] receive, from an artificial intelligence engine, a
candidate drug compound generated by the artificial intelligence
engine; [0223] generate a view comprising the candidate drug
compound overlaid on a representation of a design space, wherein
the view presents a topographical heatmap of the representation of
the design space, and the topographical heatmap includes the
candidate drug compound overlaid on indicators ranging from an at
least one least active property to an at least one most active
property; and [0224] present the view on the display screen.
[0225] Clause 27. A method comprising: [0226] generating a
biological context representation of a plurality of drug compounds,
wherein the biological context representation comprises a first
data structure having a first format; [0227] translating, by an
artificial intelligence engine, the first data structure having the
first format to a second data structure having a second format;
[0228] generating, based on the second data structure having the
second format, a plurality of candidate anti-biofilm compounds; and
[0229] classifying a candidate anti-biofilm compound from the
plurality of candidate anti-biofilm compounds as a selected
candidate anti-biofilm compound.
[0230] Clause 28. A method comprising: [0231] generating a
biological context representation of a plurality of drug compounds,
wherein the biological context representation comprises a first
data structure having a first format; [0232] translating, by an
artificial intelligence engine, the first data structure having the
first format to a second data structure having a second format;
[0233] generating, based on the second data structure having the
second format, a plurality of candidate anti-cancer compounds; and
[0234] classifying a candidate anti-cancer compound from the
plurality of candidate anti-cancer compounds as a selected
candidate anti-cancer compound.
[0235] Clause 29. A method comprising: [0236] generating a
biological context representation of a plurality of drug compounds,
wherein the biological context representation comprises a first
data structure having a first format; [0237] translating, by an
artificial intelligence engine, the first data structure having the
first format to a second data structure having a second format;
[0238] generating, based on the second data structure having the
second format, a plurality of candidate antimicrobial compounds;
and [0239] classifying a candidate antimicrobial compound from the
plurality of candidate antimicrobial compounds as a selected
candidate antimicrobial compound.
* * * * *