U.S. patent application number 14/871616 was filed with the patent office on 2016-09-22 for pharmaceutical/life science technology evaluation and scoring.
The applicant listed for this patent is DR/DECISION RESOURCES, LLC. Invention is credited to David GREENWALD, Brigham B. HYDE.
Application Number | 20160275112 14/871616 |
Document ID | / |
Family ID | 48467659 |
Filed Date | 2016-09-22 |
United States Patent
Application |
20160275112 |
Kind Code |
A1 |
HYDE; Brigham B. ; et
al. |
September 22, 2016 |
Pharmaceutical/Life Science Technology Evaluation And Scoring
Abstract
A method for evaluating and/or scoring pharmaceutical/life
science technology is provided. The method includes importing data
of a publication; transforming the data into a structured schema;
ingesting the structured schema to determine a context of the data
and draw associations between the data and a plurality of profiles;
and generating a score based on the associations between the raw
data and the profiles. The method may also include generating
meta-data based on the determined context of the data and/or one or
more quantitative metrics having a temporal component based on the
ingested data. Related apparatus, systems, techniques and articles
are also described.
Inventors: |
HYDE; Brigham B.; (Boston,
MA) ; GREENWALD; David; (East Boston, MA) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
DR/DECISION RESOURCES, LLC |
Burlington |
MA |
US |
|
|
Family ID: |
48467659 |
Appl. No.: |
14/871616 |
Filed: |
September 30, 2015 |
Related U.S. Patent Documents
|
|
|
|
|
|
Application
Number |
Filing Date |
Patent Number |
|
|
14275163 |
May 12, 2014 |
|
|
|
14871616 |
|
|
|
|
13688101 |
Nov 28, 2012 |
8725552 |
|
|
14275163 |
|
|
|
|
61564020 |
Nov 28, 2011 |
|
|
|
Current U.S.
Class: |
1/1 |
Current CPC
Class: |
G06Q 30/0204 20130101;
G06Q 10/10 20130101; G06F 16/3344 20190101; G06Q 30/02 20130101;
G06F 16/24578 20190101; G06F 16/212 20190101 |
International
Class: |
G06F 17/30 20060101
G06F017/30 |
Claims
1. A computer-implemented method, comprising: importing data of a
publication; transforming the data into a structured schema;
ingesting the structured schema to determine a context of the data
and draw associations between the data and a plurality of profiles;
and generating a score based on the associations between the raw
data and the profiles; wherein the at least one of the above is
performed on at least one processor.
Description
CROSS-REFERENCE TO RELATED APPLICATION
[0001] This application is a continuation of and hereby claims
priority under 35 U.S.C. .sctn.120 to U.S. patent application Ser.
No. 14/275,163, filed May 12, 2014 and entitled,
"PHARMACEUTICAL/LIFE SCIENCE TECHNOLOGY EVALUATION AND SCORING",
which in turn is a continuation of U.S. patent application Ser. No.
13/688,101 filed Nov. 28, 2012 and entitled, "PHARMACEUTICAL/LIFE
SCIENCE TECHNOLOGY EVALUATION AND SCORING," which in turn claims
priority under 35 U.S.C. .sctn.119 to U.S. Provisional Application
No. 61/564,020, filed on Nov. 28, 2011, the contents of each
application being expressly incorporated herein by reference in
their entirety.
TECHNICAL FIELD
[0002] This disclosure relates generally to data analysis and in
particular, to assembling, aggregating, and interpreting multiple
complex data sources to generate strategic intelligence and
business solutions in different topics including, for example,
biologic, genetic, biopharmaceutical, and medical topics.
BACKGROUND
[0003] Pharmaceutical innovation relies on a continuum of
scientific and medical information that aims to address the cause,
treat the symptoms, and improve the outcome of diseases. The
pharmaceutical industry currently relies on the capacity of the
involved stakeholders to evaluate an opportunity, raise the
necessary capital, and develop a potential therapy. Assets are
commonly purchased and sold at various stages of their life cycle.
This has resulted in a diverse marketplace driven by transactions
at all stages of drug development--from pre-clinical and discovery
through phase III clinical trials.
[0004] Transaction decision-making is made based on a number of
criteria that aim to maximize the commercial value and future
potential of an asset. This is a challenging process, limited by
two primary factors: (1) overwhelming depth, breadth, and
complexity of scientific information, and (2) a scarcity of
accurate and relevant market data.
[0005] Thus, there is a need to provide methods and systems for
assembling, aggregating, and interpreting multiple complex data
sources to generate strategic intelligence and business solutions
in different topics.
SUMMARY
[0006] In accordance with the present subject matter, a method for
evaluating and/or scoring a technology is provided. The method may
include: importing data of a publication; transforming the data
into a structured schema; ingesting the structured schema to
determine a context of the data and draw associations between the
data and a plurality of profiles; and generating a score based on
the associations between the raw data and the profiles.
[0007] In some embodiments, the method may also include generating
meta-data based on the determined context of the data and/or
generating one or more quantitative metrics having a temporal
component based on the ingested data.
[0008] In some embodiments of the present subject matter, the
method may include assigning a weight to at least one of the
profiles, and may also include adjusting the weight.
[0009] In some embodiments, the method may also include measuring a
confidence in at least one of the associations by calculating a
number of times the at least one of the associations has been
associated with previous data. This may further include elevating a
weighting of the at least one of the associations when the at least
one of the associations has been associated with previous data.
[0010] In some embodiments, the method includes displaying the
score to a user through a user interface.
[0011] In some embodiments of the present subject matter, the
method includes checking the data against a plurality of predefined
key words.
[0012] Articles of manufacture are also described that comprise
computer executable instructions permanently stored on
non-transitory computer readable media, which, when executed by a
computer, causes the computer to perform operations herein.
Similarly, computer systems are also described that may include a
processor and a memory coupled to the processor. The memory may
temporarily or permanently store one or more programs that cause
the processor to perform one or more of the operations described
herein. In addition, operations specified by methods can be
implemented by one or more data processors either within a single
computing system or distributed among two or more computing
systems.
[0013] The subject matter described herein provides many
advantages. For example, by assembling, aggregating, and
interpreting multiple complex data sources, strategic intelligence
and business solutions in different topics can be provided. By
generating "Scores" (e.g. ranking) that assess the value and
multi-attribute components of various entities such as (for
example) drugs (e.g. molecules), companies, genes, people,
diseases, and research topics, these quantitative measures may be
leveraged, for example, to aid in decision making on investment
and/or identify trends for users. The provided systems and methods
may be leveraged in a multitude of contexts factorially created by
the array of entities being defined. For example, the present
subject matter may be used to ask questions of people in a disease,
drugs and genes, research topics and companies, etc. This creates
value for users in all realms, including for example, life science,
from basic to clinical science, as well as within the business
context of biopharmaceuticals, life science tools, diagnostics, and
patient care.
[0014] The details of one or more variations of the subject matter
described herein are set forth in the accompanying drawings and the
description below. Other features and advantages of the subject
matter described herein will be apparent from the description and
drawings, and from the claims.
DESCRIPTION OF DRAWINGS
[0015] FIG. 1 is an illustration of the overall architecture in
accordance with an embodiment of the present subject matter;
[0016] FIGS. 2A and 2B are process flow diagrams illustrating the
data and process steps of an embodiment of the present subject
matter;
[0017] FIG. 3 is a graphical illustration showing data
transformation and association of an embodiment;
[0018] FIG. 4 is a process flow diagram of a scoring process in
accordance with an embodiment of the present subject matter;
[0019] FIG. 5 is a process flow diagram of a search process in
accordance with an embodiment of the present subject matter;
[0020] FIG. 6 shows an example of a search and view provided by an
embodiment of the present subject matter; and
[0021] FIG. 7 is a diagram showing an example of a computing system
in which the present subject matter can be implemented.
DETAILED DESCRIPTION
[0022] FIG. 1 is an illustration of the overall architecture of an
embodiment of the present subject matter (which may be referred
hereafter as the "Innovation Engine"). The architecture may include
three general levels. The foundation of the Innovation Engine is a
model, which may include Ingest Engine 130 and Download Curate
Engine 140.
[0023] Interfacing with the model is a controller (e.g. implemented
on a server), which may include Service Bus 105, Scoring Engine
110, and Search Index Data Store 120. Service Bus 105 is in
communication with Score Engine 110 and Search Index Data Store
120, and may be configured to handle multiple data connectors (e.g.
for ingest) and search work flows.
[0024] The controller also interfaces with a user interface (e.g.
via a client) to display data to the user on request. As can be
seen, the users interface also communicates with Service Bus 105 of
the controller. In some embodiments, the user interface can
communicate with the controller over the internet or other
services, using, for example, HTTP, REST, XML, SOAP, or any
combination of protocols and languages. This may be done, for
example, by passing objects between the client and the server to
handle search queries and chart requests. The user interface may
include one or more user views such as views 151 and 152 as shown,
and may be configured to provide graphical illustration(s) of data
and search functionality.
[0025] In some embodiments, the architecture is configured to be
data scalable and capable of supporting multiple products. This may
be achieved by configuring the architecture to be data agnostic by
using connectors to enable structured and unstructured data to
build on existing system. The architecture may also be configured
to provide workflow flexibility to enable database interaction. For
example, in some embodiments, the scoring workflow can be carried
out in parallel or through query functions. This way, a new product
can be provided by providing a new user interface and a new query
workflow, and the architecture is thus scalable to multiple
products.
[0026] The present subject matter may be utilized in many different
fields and topics. For example, decisions regarding drug
development are complex and rely on multiple variables and factors.
Successful commercial biopharmaceutical development may require
patent protection in order to justify the capital risk associated
with development. The patent application database therefore serves
as a base layer for drugs in development. However, underlying any
patent application is the basic medical science, which is the main
driver of innovation. The decision to target a particular mechanism
of action for a disease may be based on the scientific literature
and publically available data. Many of the underlying scientific
trends precede novel patentable material, if not overtly then
through inference. Transactions are ultimately influenced by the
current perception of the scientific evidence, the interpretation
of scientific trends by scientists and business partners, deal
factors such as the interaction with the commercial entity, and
market potential.
[0027] FIGS. 2A and 2B are process flow diagrams illustrating the
data flow and process steps in accordance with one embodiment of
the present subject matter. As shown in FIG. 2A, the Download
Curate Engine 140 imports (e.g. downloads) at 201 raw data from one
or more sources. These sources may include one or more sources of
relevant data to be analyzed, including for example, National
Library of Medicine PubMed, United States Patent and Trademark
Office (USPTO), National Institutes of Health (NIH), Clinical
Trails, Swiss Gene Prot database, Online Mendelian Inheritance in
Man (OMIM), Kyoto Encyclopedia of Genes and Genomes (KEGG)
Database, the US Food and Drug Administration database of Approved
Drug Products with Therapeutic Equivalence (a.k.a. Orange Book),
historical transaction information, molecule target association
list, disease list and sub categorization, and conference abstract
lists. In some embodiments, the raw data is imported daily.
[0028] At 251, the raw data are transformed by Ingest Engine 130
for ingest to a schema by taking the raw data and converting it
from its original format into a structure that can be interpreted
by a downstream logic. A schema is a generalized architecture of
document contents, which enables the system to break a larger piece
of text into subsections. In some embodiments, the schema is
utilized by targeted extraction of ontologies and selective
targeting of queries. For example, breaking the text of a press
release into subsections in order to ask specific questions of the
first paragraph as opposed to the second. The value of this
approach in concert with ontologic and natural language driven
queries is that it applies domain specific knowledge of the
construction of the language within these documents to enable
accurate extraction of information that is very difficult (if not
impossible) to accomplish simply by keyword searching.
[0029] One component of the Innovation system is the use of natural
language and controlled vocabulary phrases used to identify key
concepts in scientific, medical, clinical and business literature.
In some embodiments, these phrases are grouped by key concepts to
identify stage of development of pharmaceutical assets. This
detection of experimental concepts and stages of development uses
expert knowledge of drug development and life science research
combined with text extraction and mapping. This approach is unique
because the detection of key natural language concepts is designed
to detect concepts specifically important to the value of a drug
asset. This differs principally from typical natural language
approaches which look for common terms and require no expert
know-how in fields of life science and or biopharma.
[0030] Using text-mining and natural language processing, Ingest
Engine 130 mines and processes the text to add meta-data to
incoming data streams (i.e. schemas) that apply a context and/or
describe "what it's about." Ingest Engine 130 also ingest the
instance of the schema transform (or parse) each document (with
Entity Extraction) into fields. In some embodiments, this is done
using XML workflows/connectors.
[0031] Ingest Engine 130 also performs an association process,
which is important to determining and automating the association of
(e.g.) drugs, diseases, genes, companies, people, and research
topics. This process today is largely manual or wrought with false
positives and negatives when done through keyword association. In
some embodiments, Ingest Engine 130 applies weighting to specific
sources of association (e.g. mentions in a press release outweigh
mentions in a PubMed document), normalizes to commonly mentioned
entities (e.g. cancer is often mentioned with many things, but may
only be truly associated with a subset), and adds a contextual
basis (e.g. a given person may only be associated with a drug in a
basic animal testing sense as opposed to a financing and
fundraising sense). This context is important to defining
appropriate associations. In some embodiments, this process is
utilized to automate the process of profile building for, e.g., a
given drug or company in the Innovation Engine. In some
embodiments, data transformation and association 251 is run daily.
In some embodiments, this is run when new data is imported.
[0032] In some embodiments, one or more of the following features
may be extracted for each type of publication.
[0033] For PubMed: Metadata from the publication record; Journal
name; Title; Abstract; Listed Keywords; All author's names; Authors
order; Specifically first 2 author and last three authors;
Institution referenced; Department; Institution/commercial entity;
City; Pubmed ID; Publication Date; Day; Month; Year; EPUB Date;
DOI; NME; Calculated fields; Gene/protein name in title;
Gene/protein name in abstract; Disease in title; Disease in
abstract; Molecule name in abstract; Molecule name in Title; Tissue
referenced in abstract; Tissue Referenced Title; Presence or
absence of specific "key words" in abstract; Presence or absence of
"Relay Key Words" in title; Alchemy Identified terms; and
State.
[0034] For conference abstracts: Conference name; Gene/protein name
in title; Gene/protein name in abstract; Disease in title; Disease
in abstract; Molecule name in abstract; Molecule name in Title;
Tissue referenced in abstract; Tissue Referenced Title; Presence or
absence of "Relay key words" in abstract; Presence or absence of
"Relay Key Words" in title; Listed Keywords; Alchemy Identified
terms; All author's names; Authors order; Specifically first 2
author and last three authors; Institution referenced; Department;
Institution/commercial entity; City; State,
[0035] For Intellectual Property: Patent Number; Date of issuance;
Inventors names; Inventor affiliation; Inventor location; Assignee;
Assignee location; Filing date; PCT filing date; Application
number; PCT number; PCT PUB date; PCT PUB no.; Foreign application
countries; Foreign application dates; Patents cited; Numbers;
Dates; Inventors; Foreign patents cited; Number; Country; Dates;
Examiner; Attorney, agent or firm; Number of claims; Gene/protein
name in title; Gene/protein name in abstract; Disease in title;
Disease in abstract; Molecule name in abstract; Molecule name in
Title; Tissue referenced in abstract; Tissue Referenced Title;
Presence or absence of specific "keywords" in abstract; Presence or
absence of specific keywords in title; Listed Keywords; Alchemy
Identified terms in title; Alchemy Identified terms in the
Abstract; Chemical Nomenclature Term in Title; Chemical
nomenclature term in Abstract; Gene/protein name in Claims; Number
of times; Number of claims present; Gene/protein name in
description; Disease in claims; Number of times; Number of claims
present; Disease in Description; Molecule name in claims; Number of
times; Number of claims present; Molecule name in Description;
Tissue referenced in Claims; Number of times; Number of claims
present; Tissue Referenced Description; Presence or absence of
"Relay key words" in claims; Number of times; Number of claims
present; Presence or absence of specific keywords in Description;
Alchemy Identified terms in Claims; Alchemy Identified terms in the
Description; Chemical Nomenclature Term in Claims; Chemical
nomenclature term in Description;
[0036] For Chemistry and Physical Properties: Molecular weight; Log
D; Log P; Number of stereogenic centers; Number of heteroatoms;
Number of hydrogen bond donors; Number of hydrogen bond acceptors;
Aqueous solubility (mg/mL at different pH's); Number of steps in
synthesis; Crystallinity; Polymorphism; Melting point;
Stability--solid state, thermal, hydrolytic, photo, stereoisomeric;
Salt forms.
[0037] For Existing Drug Candidates: Imported list;
Target/mechanism; Chemical name; Marketing name; Development name;
Associated Commercial entity.
[0038] For Orange Book: Active Ingredient; Dosage Form Route;
Concentration; Proprietary name; Commercial applicant; Therapeutic
equivalence; Application number; Approval date; Patent expiration;
Drug substance claim; Drug product claim.
[0039] For Clinical Trial Information: Gene/protein name in title;
Gene/protein name in purpose; Disease in title; Disease in purpose;
Molecule name in purpose; Molecule name in Title; Tissue referenced
in Purpose; Tissue Referenced Title; Presence or absence of "Relay
keywords" in Purpose; Presence or absence of "Relay Keywords" in
title; Listed MESH terms; Alchemy Identified terms in title;
Alchemy Identified terms in the Purpose; Chemical Nomenclature Term
in Title; Chemical nomenclature term in Purpose; CTG identifier;
Sponsor; First received; Last updated; Condition; Intervention;
Phase; Study Type; Study design; Primary outcomes; Secondary
outcomes; Estimated enrollment; Start Date; Estimated completion
date; Number of arms; Inclusion criteria; Exclusion criteria;
Locations; Investigators; Study sponsor; Publications; Author;
Journal; Date; Title; Pubmed ID.
[0040] For NIH Grant Database: Primary investigator; PI email;
Title; Awardee organization; Project number; City; State; Study
Section; Project start date; Project end date; Administering
institution; Total funding; Year; Funding per year; Project terms;
Pub med ID of associated publications; Associated clinical trial
identifier; Associated patent number; Gene/protein name in title;
Gene/protein name in abstract; Gene/protein name in Keyword list;
Disease in title; Disease in abstract; Disease in Keyword list;
Molecule name in abstract; Molecule name in Title; Molecule name in
Keyword list; Tissue referenced in abstract; Tissue Referenced
Title; Tissue referenced in keyword list; Presence or absence of
specific key words in abstract; Presence or absence of specific Key
Words in title; Presence or absence of specific keywords in keyword
list; Alchemy Identified terms in title; Alchemy identified terms
in abstract.
[0041] In some embodiments of the present subject matter,
structured database profiles 230 are generated and maintained
within the Innovation Engine. For example, attributes associated
with biopharmaceutical assets may be assigned to different
categories. In some embodiments, the categories (or profiles) may
include one or more of: [0042] 1. Molecule. [0043] 2. Compound.
[0044] 3. Gene (e.g. the associated gene/mechanism). [0045] 4.
Disease (e.g. disease area or therapeutic market opportunity).
[0046] 5. Personnel (e.g. the people involved). [0047] 6.
University/Commercial Entity (e.g. the associated commercial
entities). [0048] 7. Intellectual Property (e.g. patents/patent
applications).
[0049] Decisions regarding asset development may take into account
one or more of these factors. In some embodiments, as new
information enters the system, it is automatically incorporated
within their profiles.
[0050] As an example, FIG. 3 is a graphical illustration showing
the Data Transformation and Association 251. As shown, Publication
A is imported from a source (e.g. as raw data). Publication A
includes various information, including Gene X 311, Investigator A
312, Disease Y 313, Institution Z 314, and Compound D 315. By
performing the data transformation and association process
discussed above, Ingest Engine 130 generates Publication A
Associated Data 320, which includes Gene X Profile 321,
Investigator A Profile 322, Disease Y Profile 323, Institution Z
Profile 324, and Compound D Profile 325. In some embodiments,
Ingest Engine 130 may be configured to query this data to assess
the quality of association. Examples of such queries include "Has
this gene been previously associated with this disease?" 351; "Has
this investigator been previously associated with this disease?"
352; "Has this institution been previously associated with this
disease?" 353; and "Has this compound been previously associated
with this disease?" 354.
[0051] In some embodiments, the Innovation Engine maintains a
dynamic database of experiments and milestones, e.g. as a drug
(e.g. molecule) continues its iterative process of development to
track its progress. By anticipating the logical progression of drug
development, the Innovation Engine provides a framework for which
to benchmark commercial drug development. In addition, by following
scientific trends through grants issued, publications, patents, and
people, the nuance of "discovery" can be projected and trends can
be identified at early stages. To this end, at 253, Scoring Engine
110 may be configured to specifically identify and predict
scientific trends by assigning a "Score" to, for example, each
molecule, key opinion leader, commercial entity, and/or disease
pathway. In some embodiments, the Score may be a numerical value
representing the likelihood that the market will favor assets
associated with an entity.
[0052] FIG. 4 is a process flow diagram of scoring in accordance
with an embodiment of the present subject matter. In this
embodiment, the scoring includes four general steps (Tiers
1-4).
[0053] Tier 4 includes variable calculation and counting. This may
include counting the context specific occurrence of a variable
(e.g. Entity Raw Count 401, Entity Count Norm 402, Entity 2.times.2
403, and the number of other variables: >500 Other Variables
404). For example, a drug has been mentioned 3 times with positive
news about clinical trial results in breast cancer. This generates
a count which can be manipulated by, e.g., normalization, or binary
filter to produce additional variables. These variables can be
normalized to an aspect of the entities mentioned, e.g. to the
company, drug, disease, or by phase.
[0054] Tier 3 includes generating trend data such as, e.g.,
Publication Rate 411, Grant Rate 412, Development Stage 413, and
>40 Other Variables 414. For example, the 3 mentions of positive
data in clinical trials (referenced above) represent 5% of all
positive mentions of clinical trial data in breast cancer, or the
growth in mentions over the last 3 years is the third highest of
all breast cancer drugs.
[0055] Tier 2 includes sequence variables that have a temporal
component. For example, by assembling the variables of Tiers 4 and
3 for a given drug and analyze them on a temporal basis, both in
terms of how they compare to other breast cancer drugs, but also
how the different variables relate to each other temporally. This
may include weighting through machine learning against other drugs
with positive outcomes, and creating additional variables related
to sequence of events.
[0056] Tier 1 includes variables such as, e.g. Investigator 431,
Therapeutic Advancement 432, and Scientific Evidence 433. These
variables roll up to become primary variables for evaluation of
Scoring (e.g. Compound Score) of a given therapeutic. In some
embodiments, this score is calculated daily, and/or recalculates as
time advances and as new information enters the system.
[0057] In some embodiments, one or more of the following variables
may be used: The following are the specific variables considered by
Scoring Engine 110:
Categories:
[0058] Stage of Development; [0059] Scientific Relevance; [0060]
Therapeutic Relevance; [0061] Intellectual Property Protection;
[0062] Inventor Profile; and [0063] Commercial Entity/Institutional
Profile.
[0064] Sub-Categories: [0065] Clinical Stage; [0066] Experimental
Stage; [0067] Transactional Stage; [0068] Gene/Mechanism Score;
[0069] Alignment with Current Indication Standards; [0070]
Therapeutic Criteria; [0071] Intellectual Property Score; [0072]
Inventor/Investigator Score; [0073] University Score; [0074]
Commercial Entity Score; and [0075] Commercial History.
Variables Measured:
[0076] Development Stage: [0077] In vitro efficacy; [0078] In vitro
toxicity; [0079] in vitro binding assay; [0080] in vitro dose
escalation study; [0081] Mouse efficacy; [0082] Mouse toxicity;
[0083] Mouse dosing; [0084] Rat efficacy; [0085] Rat toxicity;
[0086] Rat dosing; [0087] Disease specific In vivo model; [0088]
Oral dosing in vivo; [0089] Licensed at least once; [0090] Acquired
as part of an M&A transaction; [0091] Genetic Knock Out (KO)
Animal published; [0092] Genetic population study published; [0093]
in vitro genetic study published; [0094] Cell line KO published;
[0095] Number Clinical Trial; Gene; [0096] Number of Clinical
trials; molecule; [0097] Funding history from NIH, NSF, DoD; [0098]
Funding from Disease Foundations; [0099] Capital investment from
Angel investors; [0100] Capital investment from Venture Capital
investors; and [0101] Matching of known attributes to therapeutic
criteria (oral, vs IV etc).
[0102] Preclinical Pharmacokinetics (PK): [0103] Absorption--CACO-2
permeability; [0104] Cmax; [0105] Route of absorption; [0106]
Distribution (Vss); [0107] Route of elimination/clearance; [0108]
Route of metabolism; [0109] Hepatocyte or microsome
stability/metabolism; [0110] Cyp inhibition--5 isoforms; [0111] Cyp
induction--5 isoforms; [0112] Known metabolites, metabolite ID;
[0113] Clearance; [0114] Bioavailability; [0115] CNS penetration;
[0116] Dose-related exposure, proportionality, linearity; [0117]
Half-life (% F); and [0118] Plasma protein binding.
[0119] Preclinical Safety/Toxicology: [0120] In-vitro [0121] hERG
1050; [0122] AMES genetic tox; [0123] CHO chromosomal aberration;
[0124] Selectivity panel, ligand profile; and [0125] Cellular
LD50,LD90. [0126] In-vivo [0127] Micronucleus; [0128]
Cardiovascular function, QT Prolongation; [0129] Respiratory
function; [0130] CNS function--Irwin Test; [0131] Renal function;
[0132] Hepatic function; [0133] GI transit; [0134] Maximum
tolerated dose (MTD); [0135] NOAEL; [0136] Therapeutic Index:
EC50/LD50; and [0137] Dose/exposure relationship.
[0138] Preclinical Pharmacology, PD and Efficacy: [0139] In-vitro
[0140] Enzymatic IC50, IC90; and [0141] Cellular EC50, EC90. [0142]
In-vivo [0143] Animal disease models, ED50; and [0144]
Dose-response relationship.
[0145] IND-Enabling Studies: [0146] Single does and dose-ranging
study (rat and/or dog); [0147] Acute toxicology (rat and/or dog);
[0148] 14 or 28-day toxicology (rat and/or dog); [0149] Acute
toxicology (monkey); [0150] 14 or 28-day toxicology (monkey);
[0151] Rat/Rabbit teratology; and [0152] CV function in Telemetered
dogs or monkeys.
[0153] Patent Characteristics: [0154] Term of Protection 20-18
years; [0155] Term of Protection 17-15 years; [0156] Term of
Protection 12-15 years; [0157] Term of protection 10-12 years;
[0158] Term of protection 8-10 years; [0159] Term of protection 4-8
years; [0160] Term of protection 0-3 years; [0161] 0-5 divisionals
and continuations; [0162] <5 divisionals and continuations;
[0163] Disease prevalence in geographic region of coverage; [0164]
Relative strength of Intellectual Property Protection law in region
of patent; [0165] Total number of issued claims; [0166] claims less
than 15 words; [0167] claims considered novel and broad based on
Relay Keywords approach; [0168] patents cited as prior art; [0169]
1st 5 claims are over 20 words; [0170] Ratio of issued to filed
claims from application; [0171] outside counsel law firm ranking;
[0172] composition of matter protection; [0173] method patent;
[0174] market size of covered indications; [0175] Prior art score,
# of patents; [0176] Assignee score company vs. university vs.
individual; and [0177] International freedom to operate score.
[0178] Investigator and Institution: [0179] Number of patents and
growth rate; [0180] Number of patents issued vs. filed; [0181]
Total number of patents; [0182] Number of research grants; [0183]
Number of training grants; [0184] Number of fellowship grants;
[0185] Number of other awards; [0186] Number of R&D contracts;
[0187] Number of invention disclosures; [0188] Options and
licenses, growth; [0189] Number of start up companies, growth,
success; [0190] Licensing income; [0191] Sponsored research income;
and [0192] Intellectual capital; # of PhD's, MD's, faculty, Size of
endowment.
[0193] Scientific Factors: [0194] Overall publication rank of gene;
[0195] Frequency and prominence of scientific review articles as
measured by impact factor and citation index; [0196] Genetic
evidence; [0197] In vivo evidence; [0198] Xenograph animal models;
[0199] Survival curves; [0200] Chromatin Immunoprecipitation;
[0201] Protein binding characterization; [0202] Genome Wide
Association Studies (GWAS); [0203] MicroArray data; [0204] Western
blot verification in vitro; [0205] Western blot verification in
vivo; [0206] Cell binding assay; [0207] In vivo efficacy; [0208] In
vivo rescue experiments; [0209] Single nucleotide polymorphism
(SNP) identification; [0210] High throughput screening; and [0211]
Lead candidate identification.
[0212] In some embodiments, the Compound Score (CS) is generated
as:
CS=(.alpha.+.beta.+.chi.))+((.delta.+.epsilon.+.phi.+.gamma.+.eta.)+()+(-
.phi.+.kappa.+.lamda.+.mu.+.nu.+o+.pi.+.theta.+.rho.)+(.sigma.+.tau.+.upsi-
lon.+.omega.+.omega.+.xi.+.psi.+.zeta.)
Wherein:
TABLE-US-00001 [0213] Stage of Development: .alpha. Phase Score: 10
points for Phase 2 and above; 5 points for phase 1; 1 point for
IND; 0 points for Preclinical .beta. Experimental Stage: in vitro
efficacy, if Y + 3; in vitro toxicity, if Y + 3; in vitro binding
assay, if Y + 3; in vitro dose escalation study, if Y + 3; Mouse
efficacy, if Y + 5; Mouse toxicity, if Y + 5; Mouse dosing + 5; Rat
efficacy, if Y + 5; Rat dosing + 5; Disease specific In Vivo model;
Oral dosing in vivo, if Y + 5 .chi. Transactional stage: Licensened
at Least once, if Y + 3; acquired as part of an M&A
transaction, if Y + 3; Scientific Relevance: .delta. Publication
Trent: (genetic KO published, if Y + 5; Genetic population study
published, if Y + 5; in vitro genetic study published, if Y + 5 . .
.) .epsilon. Clinical Trial Trend .phi. NIH Grant Trend .gamma.
Conference Abstract Trend .eta. Commercial Trend Therapeutic
Matching of known attributes to therapeutic criteria (oral vs IV,
etc.) Relevance: IP Score: .phi. Points for 5-8 years, (5 points
for 3-5 years, -5 points for 0-3 years) + (10 .kappa. points for
0-5 divisional and continuations or 20 points for <5 .lamda.
divisional and continuations). Note: Weighting variable dependent
.mu. upon indication(s), average length of clinical trials for
specific indication, .nu. previous licensing trends based covers
>40% market) + Relative strength .omicron. of Intellectual
Property Protection law (5 points if top 10.sup.th percentile of
.pi. CDI, 4 points if 10-25.sup.th percentile, 3 points if
25-50.sup.th percentile, -5 points .theta. if 50-100.sup.th
percentile) Less than 15 words) + (2 points if 1.sup.st claim
considered novel and broad based on bag of words approach) + (1
point if more than 25 patents cited as prior art and 1.sup.st 5
claims are over 20 words) + (1 point if ratio of issued to filed
claims >7). Outside Counsel from top 50.sup.th percentile law
firm) + (8 points if internal counsel) + (2 points if top 25.sup.th
percentile attorney, 1 point if top 50.sup.th percentile attorney)
Type of patent: 12 points if composition of matter protection, 8
points if method patent as determined by bag of words approach Sum
of market size of covered indications > $600M, then 8 points; if
sum of market size of covered indications > $400M, then 6
points; if sum of market isze of covered indications > $200M,
then 4 points Prior Art Score: 5 points if <5 patents; 4 points
if <10 patents; 3 points if <20 patents; 2 points if <40
patents; 2 points if <60 patents; 1 point if >60 patents.
Assignee Score: 5 points if from top 25.sup.th percentile
commercial entity; 3 points if from top 50.sup.th percentile
commercial entity; 3 points if from top 10.sup.th percentile
academic entity. .rho. International Freedom to Operate Score: 20
points if positive Commercial .sigma. NIH Awards: Total number,
number of research grants, number of Entity/Institution training
grants, number of fellowship grants, number of other awards, Score:
number of R&D Contracts. .tau. Number of invention disclosures
.upsilon. US Patents: new applications, growth year over year,
total filed, total issued .omega. Foreign patents: new
applications, growth year over year, total filed, total issued
.omega. Options/licenses concluded .xi. Number of start-up
companies .psi. Income: licensing income, sponsored research income
.zeta. Intellectual capital: # Ph.Ds, # MDs, size of endowment,
total # faculty
[0214] In some embodiments, the Score is generated to correspond to
a relative value to a drug asset based on its likelihood of a
transactional event in the following twelve months. This may be
important for three main reasons: (1) it provides a measurable
outcome; (2) it solves the issue of "market value;" and (3) it
gives a relative value metric to assets.
[0215] As shown in FIG. 2A at 252, machine learning may be applied
to determine weighting of score, e.g., when the attributes and
subvariables of a given drug have been calculated and these
attributes are then compared quantitatively to the attributes of
drugs that historically have achieved success through value
creation events. For example, when analyzing phase 2 diabetes
drugs, all the drugs that have either been licensed, achieved
clinical success, advanced phase, or received additional funding
can be analyzed. Regression may be applied to the variables and
attributes of these historical drugs to determine which ones have
the highest influence on outcome. Based on these calculations, the
Innovation Engine assigns the variables and attributes with the
highest influence with more weight in calculating new Scores.
[0216] While the use of the Innovation Engine in biopharma drug
development/business development has been provided as an example,
uses in other areas, such as medical devices, chemical, physical,
and energy technology development are also possible. For example,
additional data sources may be imported to develop separate
products (e.g. with different weightings, sub-Scores and Compound
Scores, etc.) for different vertical markets, and the approach of
the present subject matter may be applicable in those settings as
well.
[0217] As discussed above, the Innovation Engine may include a data
transformation step 251 involving drawing associations between data
sources within the profiles (e.g. Molecule, Compound,
Gene/Mechanism, Disease, Personnel, University/Commercial Entity,
and Intellectual Property as discussed above). For example, once a
publication or patent becomes associated with a profile, all
associated data becomes a part of that profile. In some
embodiments, one or more associative rules are run upon database
updates daily.
[0218] In one example, publication title and abstract are searched
for the presence of the
gene/disease/molecule/investigator/institution or its synonym(s).
If an association is found, the Pubmed ID, data, and record are
added to the gene/mechanism profile.
[0219] The Innovation Engine may also include measuring the
confidence in an association through triangulation of existing
profiles, once the association is drawn. For example, if an
investigator recorded from a publications author list has been
previously associated with the disease, gene, and/or molecule found
in that same publication, the publication receives a higher
"confidence" or "quality" score. In some embodiments, associations
of higher confidence receive elevated weighting when considering
profile ranking.
[0220] To determine the relevant development information associated
with a given molecule or disease mechanism in an automated fashion,
in some embodiments, the Innovation Engine utilizes a list of
keywords which draw further inference about the meaning of an
imported piece of data. For example, if a publication contains gene
X, molecule Y, and the word "inhibit", "inhibition" and/or
"inhibitor," that publication is recorded as a publication that my
describe inhibition of gene X by molecule Y. Similarly, it may be
recorded that molecule Y may be an inhibitor of gene X. Confidence
in these types of associations may be built in the same way that
other associations are built. This information may be considered
when ranking molecules.
[0221] In order to answer the question "what molecule is most
likely to be acquired next?" the attributes of a molecule may be
considered when valuing and acquiring an asset. The components may
include one or more categories including, for example: [0222] 1.
Stage of development: this may include, for example, clinical
stage, experimental stage, and transactional stage. In some
embodiments, a sub-score is generated accordingly (e.g. between 0
to 25). [0223] 2. Relevance of asset to therapeutic opportunity:
this may include, for example, matching of current treatment
standards, and/or therapeutic criteria. In some embodiments, a
sub-score, for example, in the range of 0 to 12.5 is generated.
[0224] 3. Scientific relevance/importance: this may include, for
example, the gene/mechanism. In some embodiments, a sub-score may
be generated based on a search criteria, which may be, for example,
in the range of 25 to -25. [0225] 4. Intellectual property
protection: this may include, for example, patents and/or patent
applications. In some embodiments, a sub-score, for example, in the
range of 12.5 to -100 may be generated. [0226] 5. Profile of
inventor: this may include, for example, a sub-score of the
investigator based on search criteria. In some embodiments, the
sub-score has a range of, for example, 12.5 to 0. [0227] 6. Profile
of commercial entity/institution: this may include, for example, a
sub-score of the commercial entity/institution based on search
criteria and/or commercial history. In some embodiments, the
sub-score has a range of, for example, 12.5 to 0.
[0228] At 253, one or more sub-scores discussed above may be
generated, and based on relevance, may be added to generate one or
more Compound Scores (or simply Scores) 220.
[0229] As an example, the Innovation Engine may provide one or more
Scores that include one or more components including, for
example:
[0230] 1. Disease Subcategory: Diseases can fall into therapeutic
categories (e.g. cancer), and more specifically indications (e.g.
prostate cancer). The Score for a particular drug molecule or key
opinion leader may be calculated differently for both therapeutic
categories as well as specific indications. For example, Professor
Y at University X might have a Score of 95/100 for lung cancer, but
only a Score of 45/100 for breast cancer. This determination may be
based on the specific research that he/she conducts, and how it
relates to the market trends for each indication. For example,
scientific publications have suggested that RNAi would be best
suited for an easily accessible and immune-privileged organ such as
the eye. Accordingly, the Innovation Engine may be configured to
assign an investigator working on developing RNAi technologies for
the liver with a lower relative Score than an investigator working
on RNAi for eye disease.
[0231] 2. Risk of Stage of Development: Risk of commercial
development is inherently tied to the stage of development of the
drug molecule. The earlier the stage of development, the greater
the risk. This is particularly the case in pre-clinical drug
development, where there are many `shades of grey` when describing
the stage of development of a molecule (in vitro, in vivo,
toxicology, etc.). Just as the risk of technology may be impacted
by the most advanced phase of development, the Innovation Engine
may also be configured to take into account the current stage of
the individual molecule when calculating the Score.
[0232] 3. Scientific Factors: There are scientific factors such as
toxicology, pharmacodynamics, and pharmacokinetic data that may
impact the probability of successful drug development and
licensing. Much of this data may be included in patent abstracts,
publication abstracts, and other data sources that may be imported
into the Innovation Engine. The Engine may include one or more
additional proxies, such as, for example, the prestige of the
publication, which can be measured by factors such as journal
impact factors, and quantity/quality of citations.
[0233] 4. Importance of Intellectual Property: Intellectual
property, as mentioned previously, can play a quintessential factor
in deciding which drugs to license/acquire for commercialization.
There are many factors that can influence the strength of
biomedical intellectual property, such as the term protection
remaining, the breadth of claims granted and indications listed,
among other factors.
[0234] 5. Importance of University/Commercial Entity: Drug
development decisions are not only made by examining scientific
data. There are socially driven factors that influence the
decision-making process that are subtler, and are inherently more
subjective than objective. The reputation of particular
Universities for having a successful track record of innovative
science and efficient technology transfer are factors that
influence this variable. In some embodiments, the Innovation Engine
incorporates quantitative metrics to calculate the impact of such
factors.
[0235] 6. Importance of People and Relationships: Associated with
the importance of the reputation of the University/Commercial
Entity are the personal relationships between, for example,
scientists, investors, and/or business people. In some embodiments,
the Innovation Engine examines one or more of the co-authorship of
scientific publication, co-inventors on patents, venture capital
and angel financings, and other relationships to quantify the
social network (e.g. of scientists) in a quantitative manner. In
some embodiments, this aspect directly impacts the scores for
commercial entities, Universities, and/or researchers/key opinion
leaders.
[0236] In some embodiments, the Innovation Engine provides a score
having a range that is determined by one or more of, for example,
the therapeutic category, indication, mechanism(s), and phase of
development. In some embodiments, the Score is normalized to 100,
and can vary depending on the above variables, and evolves with
market trends.
[0237] In some embodiments, the Innovation Engine builds the Score
over time. For example, the Score for a particular drug molecule
may increase/decrease as, for example, additional validation from
experiments become available, and/or as the marketplace evolves and
additional licensing transactions are made. This continuous
feedback may adjust the Score positively and/or negatively. For
example, if a drug molecule reports an adverse side effect in phase
I clinical trials, the Score will be negatively impacted.
Conversely, if licensing trends reveal a trend towards stem cell
therapies for a particular indication, drug molecules utilizing
such a technology would be favorably impacted.
[0238] In some embodiments, a "perfect" score essentially
represents the highest likelihood that the biopharma industry will
act in a particular direction. A "perfect" score for a particular
indication and phase of development is achieved when all relevant
scientific experiments have been conducted and published in
peer-reviewed scientific journals. Market forces such as terms of
intellectual property protection, capital investment and licensing
trends support the technology in a statistically significant
manner.
[0239] In some embodiments, the distribution of weighting factors
that influence the Score may be determined by rigorous historical
analysis of drug development trends, clinical trial results, and
licensing/merger & acquisitions data. As new data continuously
becomes available through the data sources the popular the
Innovation Engine database, the weighting of specific factors may
be adjusted at 252 to accurately reflect the current trends in drug
development.
[0240] In some embodiments, the Innovation Engine includes an
internal quality assurance alert system which automatically
notifies a user when significant changes occur to Scores for, for
example, molecules, key opinion leaders, genes/mechanisms,
diseases, Universities, and Commercial Entities. This system allows
the user to monitor developments as they occur, and also enable
proactive quality assurance checks to be made. In some embodiments,
the system includes identifying of statistical outliers, and makes
this information available for quality control measures to be
taken.
[0241] There are many factors that simultaneously impact the
probability of a transaction occurring. The specific factors may
vary based on, for example, indication and phase of development,
and may be determined through the machine learning approach.
[0242] Referring now to FIG. 2B, the Innovation Engine may provide
a user interface 210 through which the user may access the Scores
220 and other data (e.g. the original data sources and other data
provided by the Innovation Engine). This may be done by generating
and sending a user query 211 to the controller, processing the user
query 211, and generating and sending a ranked profile list
returned by the search query 221.
[0243] FIG. 5 shows an example of a process flow provided by the
Innovation Engine to enable the user to search and receive
analytical data. In this example, the user can select one of
several categories to search by 501, which in this case, is Disease
502. The Innovation Engine then returns at 503 a list of drugs
which are associated with the Disease, and provides multiple
options. The options include, for example, options to explore
high-level custom categories 510, which enable the user to search
with a broad focus 530, for example, by profiles 531, topics 532,
and/or sources 533. The options may also include, for example,
options to explore data by individual drug 520. This may allow the
user to search using a narrow focus 540, for example, by drug
summary 541, drug profiles 542, and/or documents 543. The
Innovation Engine may be configured to allow the user to switch
between broad focus 530 and narrow focus 540 at any time, as well
as narrow down by each of the options 531-533 and 541-543. Based on
the user selected options (e.g. criteria), the Innovation Engine
delivers, for example, chart data, export data, and/or share data
550 to the user.
[0244] FIG. 6 shows an example of a search and view provided by the
Innovation Engine. Here, the user has selected PubMed as the data
source 601, Multiple Sclerosis as the Disease 602, and Alpha4-Beta1
Integrin as the Target 603. Based on these search criteria, the
Innovation Engine displays a graphical illustration 604 of the
associated data.
[0245] In some embodiments, the user may access the Innovation
Engine at their desktop (e.g. a Personal Computer, terminal,
tablet, etc.) on a continuous basis to stay abreast of scientific
and market developments in their respective fields of interest. By
providing a series of dashboards, which may be customizable, users
will be able to monitor clinical trial developments, publication
trends, funding awards, and market dynamics on a real-time
basis.
[0246] The users may interact with the dashboards as well. In some
embodiments, the Innovation Engine utilizes one or more
visualization tools, such as (e.g.) Google widgets and SPOTFIRE
TIBCO to provide a dynamic and hands on experience for business
development and licensing professionals to explore complex data
sets, and gather insights that would not normally be available.
This may be done, for example, by examining the historical trend
analysis of a Score for a particular indication. For example, the
user interface may be configured to allow the user to visualize the
overall trend, and associated events that have impacted the Score
for each mechanism of action.
[0247] In some embodiments, the user interface may include
graphical representations including various levers and dials that
will allow the user to influence the weighting of the Score for a
given search. In some embodiments, the user may customize how the
Score is calculated on a broad scale without revealing the actual
calculation(s) that go into the Score. For example, a user may be
concerned with the strength of Intellectual Property for a given
search, specifically the mention of an indication(s) in the claims,
and the term of protection. The user in this case may at the same
time not be particularly concerned with the publication record of
the molecule, and may choose to decrease this weighting aspect of
the Score.
[0248] In some embodiments, visualization of the Score over time
may be displayed to the user using a temporal line graph that shows
annotations of events that impact the Score. By allowing users to
view how the score changes over time as well as the events
associated with the change, users will gain an appreciation for the
components (e.g. the sub-scores) of the Score without knowing the
precise weighting and components. Additionally, the interface may
be configured to provide a natural history of the historical
development trends associated with the search criteria.
EXAMPLE
[0249] The following case study, which is based on real events, is
provided as an example to illustrate how the event of the purchase
of Company S assets by Company R could be predicted by the Score,
and what happens when, for example, a paper P is published and how
it impacts the scoring system in accordance with some embodiments
of the present subject matter.
[0250] The paper P references multiple profiles within the
Innovation Engine database: [0251] Compound--Compound R and Company
S's compound R-like small molecule activators; [0252]
Gene/Mechanism--GeneX1, GeneX2, GeneX3, Disease: Type 2 Diabetes;
[0253] People (Major)--Dr. X, Dr. Y, and Dr. Z; [0254] Commercial
entities/Institutions--Company S, University T, and Medical School
M.
[0255] When paper P was published (in 2007), all of these profiles
would have been established for several years. Here is how the
Score for the compound (Company S's compounds) and mechanism/gene
(GeneX1) would have evolved in the Innovation Engine database.
[0256] While Compound R itself has a profile in the database that
would show up as a GeneX1 activator according to the publication
and patent records, the actual Company S compounds that were sold
to Company R entered the database as a result of a 2005 patent
application. Based on that application, the Innovation Engine would
record that Company S owns a set of small molecule drugs targeted
at GeneX for use in a cadre of diseases including Type 2 Diabetes.
The list of gene targets that would be recorded include GeneX1,
GeneX2, GeneX3, and all the associated genes. This is important
because when the compound actually gets a name later, which can be
taken from press releases or future publications, it will be
associated back to the appropriate patent or set of patents. So
when the original patent application comes in, the Innovation
Engine creates a defector compound profile for all
compounds--target matches. In other words, based on what is in that
patent application, we know that company S may have compounds that
modulate human GeneX1, GeneX2, GeneX3, etc. The database would
therefore include all the compounds for company S based on this
patent, and the compound and their mechanism/gene targets would be
linked through the gene profile to a number of diseases,
researchers, institutions, etc., which would subsequently
contribute to that compound's Score at the time they enter the
database. Later on, in publications and press releases when the
name is identified, it will be added as synonym to the current
internal name, joining the profiles. Furthermore, company S had
originally licensed Dr. X's compound R derivative compounds from
Medical School M in 2004, these profiles would have already existed
and would have been synonymously linked when the new filings were
submitted.
[0257] It should be noted that while up-to-date and published list
of known compounds and their synonyms have been used to build the
basis for the system, the issue of how to enter new compounds is a
critical one. Because the Innovation Engine determines a predictive
score which may be based on the likelihood of a compound to be
licensed, this commercial event is dependent largely on a base of
intellectual property. In other words, without a patent there is
nothing to license. While compound profiles can exist without a
patent, driven largely by the mechanism/gene profile, and
publication/clinical history, the important compounds have a patent
for our purpose. Accordingly, in some embodiments, the Innovation
Engine preferably obtains new compound profiles from patent
applications. Furthermore, patent application are likely to link
the compound to an inventor/researcher, commercial
entity/institution, gene/mechanism, disease or all four profiles,
thus instantly allowing the Innovation Engine to generate a Score
(or rankable profile) for the compound within the database.
[0258] To see how the Score of a compound could evolve over time,
let's look back in time a bit more. In 1999, Dr. X (eventual
co-founder of company S) authored a paper with another researcher
Dr. G, which for the first time, mentions GeneX1 with human
disease. At that time, Dr. X was a post-doctoral fellow in Dr. G's
laboratory, and while an up and coming researcher, particularly in
the cell cycle and yeast field, it would have been Dr. G's
involvement that would be of importance. Dr. G was an established
researcher with a strong grant history (recorded in the Innovation
Engine system from the NIH database) who would have added to the
importance of this paper to GeneX1 in drug development. The initial
work focused around cell biology, and most cell biology related to
Cancer research focused on cell cycle, DNA damage, and senescence.
The translational aspects of this research were primary to Cancer.
Thus, the initial work would have improved the rank of GeneX1 as a
drug target within Oncology.
[0259] Between 2000 and 20001, a number of related publications and
patents, including a patent by Dr. G became available.
[0260] In 2002, Dr. G and other researchers received the first
R01's (major research grants from NIH--also captured by the
Innovation Engine) for GeneX1 and metabolism (metabolism would link
the grant and the mechanism to Diabetes in our database), and the
field essentially explodes from there. The number of grants,
patents, and publications increased dramatically in both number and
prestige between 2001 and 2004 for GeneX1 in metabolism and
diabetes. In 2003, Dr. X (now no longer working for Dr. G, and with
his own lab at Medical School M) authors a paper, which is
published by a prestigious journal, became the first one to
demonstrate the positive effects of GeneX1 activation in
metabolism, which he did with a group of Compound R-like compounds
he had paid to have generated. He subsequently patented those
compounds for activation of Gene1. All of this information was
attainable from the related patent application and would have
entered the Innovation Engine database as independent compounds
which are linked directly to Dr. X's investigator profile in the
database.
[0261] Over the following two years, 2003-2005, the number and
prestige of publications increased dramatically. The number of
grants for GeneX1 research expanded. The number of patents filed
with the USPTO expanded, including Company S's patents. GeneX1
abstracts presence at multiple conferences also expanded over the
period.
[0262] Company S was founded in 2004 by Dr. Y, and licensed the
original Dr. X compounds. All of this information was in press
releases from 2004, and would have been linked to the profiles of
company S, Dr. X, GeneX1, and Diabetes. At this stage sometime in
late 2004 and early 2005, the GeneX1 compounds would have begun to
be in the top-ranked quartile within pre-clinical Diabetes
compounds according to the Score. This position would have only
been enhanced by additional patent filings, grant funding, and the
publication of results linking GeneX1 to more established diabetes
disease pathways, and other dysfunctions (all of which the
Innovation Engine database would already be able to correlate based
on the data it pulls from the relational KEGG database). A number
of other publications ultimately led up to the 2007 paper P
sponsored by company S, but the evidence had continued to build in
multiple preclinical models of Diabetes that activation of GeneX1
could be a treatment. For company S, the paper represented the
first demonstration of in vivo efficacy for their compounds and
certainly contributed to the purchase of the company by company R
less than four months later.
[0263] Since the 2007 paper P, a controversy developed in the
literature surrounding GeneX1 activation by company S compounds and
the lead candidate showed lackluster results in early clinical
trials for diabetes. Both of these issues would have impacted the
compound's Score. However, company S has several compounds in
development and the literature has expanded. One of the key
findings is that other genes of the GeneX family may actually be
more important targets in Diabetes, and other diseases continue to
pursue GeneX targets. Specifically, Dr. G's own company has several
patents surrounding GeneX modulating compounds, and another company
in 2009 acquired an exclusive option to acquire Dr. G's company
after the company postponed an IPO during the economic
downturn.
[0264] Calculating the Score: As discussed above, the Score may
include one or more variables including, for example, (1) Stage of
Development, (2) Scientific Relevance, (3) Therapeutic Relevance,
(4) Intellectual Property, (5) Inventor Profile, and (6) Commercial
Entity Profile. Using the case study, here is how the Score would
be calculated, in accordance with an embodiment of the Innovation
Engine, at two different time periods: right after the paper P in
late 2007, and January 2005.
[0265] Stage of Development 2005--At this time, there are no GeneX1
compounds in the clinic for any indication. However, there are
several preclinical steps published, including use of the compounds
in a model, use of the compounds in vitro, use of the compounds
rescue of Knock Out (KO) animals, genetic KO Mouse, yeast, and c.
elegans, publications on the gene in key diabetic disease models
and relevant tissue models, and a significant background literature
on the core compound R including clinical studies. Furthermore, the
transactional stage of the compounds had begun to advance; patents
had been filed by more than one party, licenses had occurred,
start-up companies formed.
[0266] Stage of Development 2007--In additional to all studies
noted above, several other in vivo steps had been taken with the
compounds, more patents had been filed, more companies started,
more licenses executed.
[0267] Scientific Relevance 2005--By 2005, the importance of GeneX1
in Diabetes had begun to accelerate as noted by the number and
prestige of the publications, similarly the presence of the work in
abstracts for conferences, as well as the increasing number of
major NIH grants from the relevant funding agencies signified the
rising position of the gene/mechanism scientifically. However, at
that time the major areas of research focus in terms of Diabetes
treatments focused around other targets, and these targets remained
better classified in some cases and compounds targeting those genes
were considered to have more scientific relevance. Of note in late
2004, several publications emerged functionally linking the
function of GeneX1 and other genes. However, this was already
established in multiple signaling pathway databases (such as the
ones already imported into the database), this link would have
added to the value of GeneX1 programs.
[0268] Scientific Relevance 2007--The GeneX family had taken off as
important players in metabolic disease with grant support and
publication rates expanding exponentially from 2004-2007, this
would have increased the scores of GeneX1 compounds, as well as the
scores of all GeneX targeting compounds. According to the weighting
of this embodiment, much of this relevance would have been
incorporated by 2005.
[0269] Therapeutic Relevance 2005--At this early stage there would
be only a few boxes checked for this component of the score. The
compound was oral which would be a positive for this indication,
and early studies had indicated disease prevention and
reversal.
[0270] Therapeutic Relevance 2007--Not a lot of changes since 2007,
the lack of pharmacology studies at this stage would be a slight
negative to the compound.
[0271] Intellectual Property 2005--The number of submissions, the
breadth of the claims, and the IP holders are all positives for the
IP support.
[0272] Intellectual Property 2007--Issuance of patents for company
S, completion of licensing deals, as well as a number of the
details of the 2007 patents which ensure breadth of claim are all
incremental positives for the compounds.
[0273] Inventor/Researcher Profile 2005--Dr. X, although young and
lacking strong funding history from the NIH, would still receive
relatively high marks for GeneX1 specifically. His affiliations at
a prestigious university benefit his Score (ranking). If he had a
compound for oncology, his score in GeneX1 would be higher due to
arguably equal levels in oncology and diabetes.
[0274] Inventor/Researcher Profile 2007--Dr. X's Score would be
improved not only because of the successful license of the
technology, but because of NIH grants, publications and title
promotion at his university.
[0275] Commercial Entity/Institution Profile 2005--Both Medical
School M and company S would be considered in this evaluation.
Medical School M is a prestigious institution, and therefore
positively impacts the translational/commercial attractiveness in
the marketplace. Company S would be scored as an emerging company,
however considered very well capitalized ($45 MM a round shortly
before this date). Additionally, Y's track record, the board
members, the advisory board, and their recent success would be
considered.
[0276] Commercial Entity/Institution Profile 2007--Somewhat
similar, however additional raises and IP would be considered.
[0277] In summary, in 2005, despite being preclinical the compounds
had achieved several hurdles adding value on both the IP,
Scientific Relevance, Stage of Development, Inventor, and Entity
aspects. Relative to other potential targets in diabetes, it would
be considered a relative newcomer, but a fast rising start (and
important factor in the Innovation Engine). The primary
advancements from there to 2007 involve further advancement in
stage of development, enhancement of scientific relevance, expanded
IP protection, and improved profile of Dr. X. It could be said that
company R would not have purchased the company without the in vivo
data, and or the final patent issuance, both of which were likely
important factors. However, a number of other factors clearly
contributed to the deal, and the fact that Dr. G's company
partnered with another company less than a year after validates the
broader approach.
[0278] As discussed above, the Innovation Engine creates
quantitative metrics for analyzing, predicting, and measuring
trends, which may be used in fields including: diagnostics markers,
life science tools, genetic tools and technologies, proteomic tools
and technologies, medical devices, surgical devices and
technologies, imaging tools and technologies, drug repositioning,
generic pharmaceuticals, antibody production, animal model
production, stem cell therapy, regulatory, pharmaceutical and
biological manufacturing, clinical trial design, intellectual
property strategy, human resources, nutraceuticals research,
healthcare policy, investment strategies (VC hedge angel), public
securities trading instruments, education, and bioinformatics.
Ingestion of additional data sources such as patient medical
records, insurer information, Medicare inpatient statistics, or
patient genetic information would enable the existing system to be
leveraged to analyze, predict, and measure trends in physician
performance, diagnosis and therapeutic decision trees, cost benefit
analysis of treatment, comparative effectiveness, reimbursement
trends, and cause of adverse events. The system can enable software
applications for use by physicians, hospitals, administrators,
policy makers, insurers, government officials, and patients. The
system and ontologies are also specifically designed to enable
production of consumer/patient driven application for interaction
with individual electronic medical records and background trends
and data.
[0279] Aspects of the subject matter described herein can be
embodied in systems, apparatus, methods, and/or articles depending
on the desired configuration. In particular, various
implementations of the subject matter described herein can be
realized in digital electronic circuitry, integrated circuitry,
specially designed application specific integrated circuits
(ASICs), computer hardware, firmware, software, and/or combinations
thereof These various implementations can include implementation in
one or more computer programs that are executable and/or
interpretable on a programmable system including at least one
programmable processor, which can be special or general purpose,
coupled to receive data and instructions from, and to transmit data
and instructions to, a storage system, at least one input device,
and at least one output device.
[0280] These computer programs, which can also be referred to
programs, software, software applications, applications,
components, or code, include machine instructions for a
programmable processor, and can be implemented in a high-level
procedural and/or object-oriented programming language, and/or in
assembly/machine language. As used herein, the term
"machine-readable medium" refers to any computer program product,
apparatus and/or device, such as for example magnetic discs,
optical disks, memory, and Programmable Logic Devices (PLDs), used
to provide machine instructions and/or data to a programmable
processor, including a machine-readable medium that receives
machine instructions as a machine-readable signal. The term
"machine-readable signal" refers to any signal used to provide
machine instructions and/or data to a programmable processor. The
machine-readable medium can store such machine instructions
non-transitorily, such as for example as would a non-transient
solid state memory or a magnetic hard drive or any equivalent
storage medium. The machine-readable medium can alternatively or
additionally store such machine instructions in a transient manner,
such as for example as would a processor cache or other random
access memory associated with one or more physical processor
cores.
[0281] To provide for interaction with a user, the subject matter
described herein can be implemented on a computer having a display
device, such as for example a cathode ray tube (CRT) or a liquid
crystal display (LCD) monitor for displaying information to the
user and a keyboard and a pointing device, such as for example a
mouse or a trackball, by which the user may provide input to the
computer. Other kinds of devices can be used to provide for
interaction with a user as well. For example, feedback provided to
the user can be any form of sensory feedback, such as for example
visual feedback, auditory feedback, or tactile feedback; and input
from the user may be received in any form, including, but not
limited to, acoustic, speech, or tactile input. Other possible
input devices include, but are not limited to, touch screens or
other touch-sensitive devices such as single or multi-point
resistive or capacitive trackpads, voice recognition hardware and
software, optical scanners, optical pointers, digital image capture
devices and associated interpretation software, and the like.
[0282] FIG. 7 is a diagram showing an example of a computing system
in which the present subject matter can be implemented. As shown,
the computing system includes a back-end component 710, such as for
example one or more data servers, or that includes a middleware
component, such as for example one or more application servers, or
that includes a front-end component 720, such as for example one or
more client computers having a graphical user interface or a Web
browser through which a user can interact with an implementation of
the subject matter described herein, or any combination of such
back-end, middleware, or front-end components. These components may
include one or more processors 711, 721, and memory 712, 722 (e.g.
computer readable medium for storing instructions). The computing
system may also include one or more data storage 741, 742. The
client and server are generally, but not exclusively, remote from
each other and typically interact through a communication network
730, although the components of the system can be interconnected by
any form or medium of digital data communication. Examples of
communication networks include, but are not limited to, a local
area network ("LAN"), a wide area network ("WAN"), and the
Internet. The relationship of client and server arises by virtue of
computer programs running on the respective computers and having a
client-server relationship to each other.
[0283] The implementations set forth in the foregoing description
do not represent all implementations consistent with the subject
matter described herein. Instead, they are merely some examples
consistent with aspects related to the described subject matter.
Although a few variations have been described in detail herein,
other modifications or additions are possible. In particular,
further features and/or variations can be provided in addition to
those set forth herein. For example, the implementations described
above can be directed to various combinations and sub-combinations
of the disclosed features and/or combinations and sub-combinations
of one or more features further to those disclosed herein. In
addition, the logic flows depicted in the accompanying figures
and/or described herein do not necessarily require the particular
order shown, or sequential order, to achieve desirable results. The
scope of the following claims may include other implementations or
embodiments.
* * * * *