Content uploaded by Takahiko Koyama
Author content
All content in this area was uploaded by Takahiko Koyama on Nov 17, 2018
Content may be subject to copyright.
Enhancing Next-Generation Sequencing-Guided Cancer Care Through
Cognitive Computing
NIRALI M. PATEL,
a,b,†
VANESSA V. MICHELINI,
f,†
JEFF M. SNELL,
a,c
SAIANAND BALU,
a
ALAN P. HOYLE,
a
JOEL S. PARKER,
a,c
MICHELE C. HAYWARD,
a
DAVID A. EBERHARD,
a,b
ASHLEY H. SALAZAR,
a
PATRICK MCNEILLIE,
g
JIA XU,
g
CLAUDIA S. HUETTNER,
g
TAKAHIKO KOYAMA,
h
FILIPPO UTRO,
h
KAHN RHRISSORRAKRAI,
h
RAQUEL NOREL,
h
ERHAN BILAL,
h
AJAY ROYYURU,
h
LAXMI PARIDA,
h
H. SHELTON EARP,
a,d
JUNEKO E. GRILLEY-OLSON,
a,d
D. NEIL HAYES,
a,d
STEPHEN J. HARVEY,
i
NORMAN E. SHARPLESS,
a,c,d
WILLIAM Y. KIM
a,c,d,e
a
Lineberger Comprehensive Cancer Center,
b
Department of Pathology and Laboratory Medicine,
c
Department of Genetics,
d
Department of
Medicine, and
e
Department of Urology, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA;
f
IBM Watson Health,
Boca Raton, Florida, USA;
g
IBM Watson Health, Cambridge, Massachusetts, USA;
h
IBM Research, Yorktown Heights, New York, USA;
i
IBM
Watson Health, Herndon, Virginia, USA
†
Contributed equally
Disclosures of potential conflicts of interest may be found at the end of this article.
Key Words. Genomics •High-throughput nucleotide sequencing •Artificial intelligence •Precision medicine
ABSTRACT
Background. Using next-generation sequencing (NGS) to guide
cancer therapy has created challenges in analyzing and report-
ing large volumes of genomic data to patients and caregivers.
Specifically, providing current, accurate information on newly
approved therapies and open clinical trials requires consider-
able manual curation performed mainly by human “molecular
tumor boards” (MTBs). The purpose of this study was to deter-
mine the utility of cognitive computing as performed by Wat-
son for Genomics (WfG) compared with a human MTB.
Materials and Methods. One thousand eighteen patient cases
that previously underwent targeted exon sequencing at the
University of North Carolina (UNC) and subsequent analysis
by the UNCseq informatics pipeline and the UNC MTB
between November 7, 2011, and May 12, 2015, were
analyzed with WfG, a cognitive computing technology for
genomic analysis.
Results. UsingaWfG-curatedactionablegenelist,weidentified
additional genomic events of potential significance (not discov-
ered by traditional MTB curation) in 323 (32%) patients. The
majority of these additional genomic events were considered
actionable based upon their ability to qualify patients for
biomarker-selected clinical trials. Indeed, the opening of a rele-
vant clinical trial within 1 month prior to WfG analysis provided
the rationale for identification of a new actionable event in
nearly a quarter of the 323 patients. This automated analysis
took <3 minutes per case.
Conclusion. These results demonstrate that the interpretation
and actionability of somatic NGS results are evolving too rapidly
to rely solely on human curation. Molecular tumor boards
empowered by cognitive computing could potentially improve
patient care by providing a rapid, comprehensive approach for
data analysis and consideration of up-to-date availability of
clinical tr ials. The Oncologist 2017;22:1–7
Implications for Practice: The results of this study demonstrate that the interpretation and actionability of somatic next-generation
sequencing results are evolving too rapidly to rely solely on human curation. Molecular tumor boards empowered by cognitive
computing can significantly improve patient care by providing a fast, cost-effective, and comprehensive approach for data analysis
in the delivery of precision medicine. Patients and physicians who are considering enrollment in clinical trials may benefit from the
support of such tools applied to genomic data.
INTRODUCTION
Next-generation sequencing (NGS) has emerged as an afford-
able and reproducible means to query patients’ tumors for
somatic genetic anomalies [1, 2]. The optimal utilization of NGS
is fundamental to the promise of “precision medicine,” yet the
results of even targeted-capture NGS are highly complex,
returning a variety of somatic events in hundreds of analyzed
genes. The majority of such events have no known relevance
to the treatment of patients with cancer, and even for
Correspondence: William Y. Kim, M.D., or Norman E. Sharpless, M.D., Lineberger Comprehensive Cancer Center, University of North Carolina, CB#
7295, Chapel Hill, North Carolina 27599-7295, USA. Telephone: 919-966-4765; e-mail: william_kim@med.unc.edu or nes@med.unc.edu Received
April 18, 2017; accepted for publication October 6, 2017. http://dx.doi.org/10.1634/theoncologist.2017-0170
The Oncologist 2017;22:1–7 www.TheOncologist.com
O
cAlphaMed Press 2017
Cancer Diagnostics and Molecular Pathology
Published Ahead of Print on November 20, 2017 as 10.1634/theoncologist.2017-0170.
by guest on November 16, 2018http://theoncologist.alphamedpress.org/Downloaded from
well-understood driver events (e.g., BRAF V600E), the combina-
torial significance of other mutations is poorly understood.
Tumors may also possess a large degree of intratumor hetero-
geneity [3], adding further complexity to the analysis.
In order to handle somatic NGS data, many institutions
have created a “molecular tumor board” (MTB) made up of
physicians and biomedical scientists to analyze the results of
NGS and make recommendations. MTBs in turn rely on an
“actionable gene list” of specific genetic events that should be
considered of clinical significance. Mutations on this list can
guide therapy (e.g., BRAF mutations in melanoma), provide
prognostic information (e.g., FLT3 mutations in acute myeloge-
nous leukemia), or be of diagnostic utility (e.g., EWS-FLI translo-
cations in a poorly differentiated pediatric sarcoma). At
present, the state of our clinical knowledge regarding the
actionability of genetic events evolves and grows sporadically,
largely through the reporting of new clinical results in a variety
of scientific venues. As thousands of new cancer-relevant publi-
cations are produced daily, staying abreast of new clinical infor-
mation in oncology is extremely challenging and differs from
institution to institution.
In 2015, there were more than 2.5 million scholarly articles
published, with more than 150,000 directly related to cancer, a
volume of literature that is growing at an estimated rate of
6.7% per year over the past decade [3]. At the time of submis-
sion of this article, a total number of 61 targeted inhibitors are
approved for the treatment of a few conditions. There are
more than 650 targeted therapies in development, with thou-
sands of clinical trials in progress. In order to be used by current
computer systems, relevant data from these articles and clinical
trials, which are written in a free-text format (unstructured
data), need to be extracted, cleaned, translated to canonical
forms, validated, and formatted in structured tables and data-
bases. In many cases, this process is done manually by subject
matter experts who must read the free text and transpose the
information into a structured format. However, with such rapid
growth of new data, this is both expensive and not a practical,
scalable approach.
MATERIALS AND METHODS
Targeted Exon Sequencing
Targeted exon sequencing was conducted after institutional
review board (IRB) approval through the UNCseq (University of
North Carolina, Chapel Hill, NC, http://www2.cscc.unc.edu/
unchreg/UNCseq) pipeline, as previously described [4, 5]. In
brief, sequencing data are routed through an automated pipe-
line. This workflow uses paired tumor and normal libraries to
detect somatic mutations, large and small indels, structural var-
iants, and copy number aberrations. Raw sequences are aligned
using the Burrows-Wheeler Aligner (BWA)-mem algorithm and
refined using our Assembly Based ReAlignment (ABRA [6]) pro-
cess. Our UNCeqR [7] algorithm, combined with Strelka [8],
then provides sensitive detection of somatic variants.
UNCseq Actionability
Genes were defined as “actionable” by the University of North
Carolina (UNC) MTB if they met criteria that placed them in
Tier 1 (variant targeted by commercially available drug that is
approved to treat this specific genetic variation), Tier 2A
(variant potentially treatable by commercially available tar-
geted drug, but the drug is not indicated for this use), or Tier
2B (variant is potentially treatable by targeted drug that is in
clinical trials) [1].
All variants of unknown significance (VUS) are evaluated by
the UNC MTB and, based upon characteristics of the VUS and a
search of the published literature, are considered for return
into the medical record. Not all VUSs are returned to the medi-
cal record.
Watson for Genomics
Upon sequence completion by UNCseq, the following informa-
tion was uploaded to Watson for Genomics (WfG): (a) tumor
type, (b) a list of variants as a variant calling file (.vcf), and (c)
gene level copy number alterations as a log 2 ratio of tumor to
UNCseq
MTB
UNCseq
informatics pipeline
WfG
UNCseq MTB
actionable genes
Variants
Copy number alterations
WfG
actionable genes
Figure 1. Study outline. Sequencing data from 1,018 cases were run
through the UNCseq informatics pipeline to generate lists of variants
and copy number alterations. Genomic profiles for each patient
were reviewed at the UNCseq MTB and, based on the genomic
alteration and its presence on the list of actionable genes previously
determined by the UNCseq Clinical Committee for Genomic
Research, were deemed actionable. For each patient, WfG was pro-
vided information on the type of cancer and the full list of variants
and copy number alterations that had been detected by the UNCseq
informatics pipeline to derive its list of actionable genomic events.
Abbreviations: MTB, molecular tumor board; UNC, University of
North Carolina; WfG, Watson for Genomics.
2Enhancing Cancer Care Through Cognitive Computing
O
cAlphaMed Press 2017
Published Ahead of Print on November 20, 2017 as 10.1634/theoncologist.2017-0170.
by guest on November 16, 2018http://theoncologist.alphamedpress.org/Downloaded from
normal. After the above information was uploaded, the follow-
ing steps were executed by WfG for each gene with a variant or
copy number alteration (supplemental online Fig. 1):
1. Molecular Profile Analysis (MPA).Evidence from functional
studies and protein structure, combined with programming
logic, was used to classify variants into five categories: patho-
genic, likely pathogenic, benign, likely benign, and VUS. Benign
and likely benign mutations were removed from the report.
2. Actionable alterations analysis.Once the alterations were
categorized by the MPA, WfG assigned a gene as actionable
if (a) the variant was pathogenic or likely pathogenic, (b)
the variant was directly targetable or part of a pathway that
was targetable based on evidence from the literature, and
(c) a U.S. Food and Drug Administration-approved or investi-
gational target therapy was available.
3. Drug analysis.In this step, potential therapeutic options
were associated with actionable mutations. Note that only
clinical trials actively recruiting were considered during this
step. Analysis of resistance was also performed during this
step. WfG uses levels of evidence (Table 2) for the gene, var-
iant, cancer type, and drug association.
4. Report.A report was generated by WfG showing the var-
iants (pathogenic, likely pathogenic, and VUS) alongside
potential targeted drugs. An example of the user interface
is shown in supplemental online Figure 1.
The supplemental online Methods provides further details
on WfG natural language processing (NLP) techniques and liter-
ature extraction. Supplemental online Figure 1 outlines the
workflow for Watson for Genomics Analysis, representing the
four steps described above.
RESULTS
Several cancer centers have started using cognitive computing
systems [9], yet few data exist on the validity of these
approaches or their promise to deliver personalized medicine
to patients. Cognitive computing is a form of artificial intelli-
gence (AI) that relies on machine learning, NLP, and other data
analysis technologies to understand and draw patterns from
massive volumes of disparate data. Cognitive computing
approaches such as WfG rely on computerized models to simu-
late aspects of human thought. In particular, using state-of-the-
art machine learning, NLP, and cognitive insights, WfG is well
suited to ingest, organize, aggregate, and extract relevant
insights from large volumes of rapidly emerging clinical data.
Although cognitive systems can ingest new information in real
time, WfG uses an offline process that consists of extraction,
validation, and testing before the insights are incorporated into
real-time analysis (supplemental online Fig. 1). Importantly,
WfG can learn new information and analyze data at a rate that
far exceeds manual curation and analysis [10].
In order to compare the effectiveness of the WfG cognitive
computing engine with human-only MTBs at identifying treat-
ment options for patients, we retrospectively examined 1,018
consecutive cases from UNC that had undergone targeted DNA
sequencing (supplemental online Table 1) of matched tumor
and normal tissue and subsequent analysis by the UNCseq
informatics pipeline and the UNC MTB between November 7,
2011, and May 12, 2015 (Fig. 1). Baseline genomic characteris-
tics of the 1,018 patients demonstrated that the relative muta-
tional burden of different tumor types appeared to be in
keeping with the relative mutational burden previously
reported across TCGA tumors (e.g., melanoma, lung, and blad-
der cancers had the highest mutational burden; Fig. 2A and
supplemental online Table 2) [11]. A mean of 37% of protein-
altering mutations was considered actionable as defined by the
UNC MTB (Fig. 2B).
We next asked WfG to perform an independent analysis of
these 1,018 patients (Fig. 1). All 1,018 cases were analyzed by
WfG in November 2015. For each patient, WfG was provided
information on the type of cancer and the full list of variants
Number of protein-alterin
g
mutations
Sarcoma
Other
Thyroid
Hematologic
Upper GI
Kidney
Brain
Ovarian/peritoneal
Cervical
Breast
GI
Lymphoma
Head and neck
Uterus
Bladder
Lung
Melanoma
Number of mutations
0 5 10 15
Actionable
Total mutations
AB
Sarcoma
Other
Thyroid
Hematologic
Upper GI
Kidney
Brain
Ovarian/peritoneal
Cervical
Breast
GI
Lymphoma
Head and neck
Uterus
Bladder
Lung
Melanoma
0 102030405060
Figure 2. Mutational and actionable mutation burden by tumor type. (A): Median (dark line), interquartile range (box), and range
(whiskers) of protein-altering mutations by cancer type. (B): Number of actionable mutations (blue bar) as determined by the University
of North Carolina Molecular Tumor Board by cancer type.
Abbreviation: GI, gastrointestinal.
Patel, Michelini, Snell et al. 3
www.TheOncologist.com
O
cAlphaMed Press AlphaMed
Published Ahead of Print on November 20, 2017 as 10.1634/theoncologist.2017-0170.
by guest on November 16, 2018http://theoncologist.alphamedpress.org/Downloaded from
Additional mutations
Figure 4. Additional actionable mutations identified by WfG and not by the University of North Carolina Molecular Tumor Board (MTB),
categorized by tumor type. Tumor types are plotted on the y-axis and number of mutations are plotted on the x-axis. The solid circles rep-
resent the mean number of mutations identified by WfG and not by the MTB for each subtype, and the whiskers show the minimum and
maximum.
Abbreviations: GI, gastrointestinal; WfG,Watson for Genomics.
UNCseq pts
(1,018)
UNCseq pts
Actionable gene
(703)
UNCseq pts
No actionable gene
(315)
WfG
Actionable gene
(231)
WfG
Actionable gene
(96)
WfG
Actionable gene
(327)
WfG-identified actionable
gene approved by CCGR
(323)
Potential to change therapy (47)
No evidence of disease (145)
Lost to follow-up (29)
Withdrew from study (4)
Deceased (98)
AB
CDE
Figure 3. Sankey diagram of the flow of the UNCseq molecular tumor board (MTB) and WfG comparison. Of the 1,018 patients previously ana-
lyzed by the University of North Carolina (UNC) MTB, 703 were determined to have alterations in genes that met the UNC MTB definition of
actionability (A) and 315 did not (B).The WfG analysis suggested that an additional eight genes not previously defined as actionable should be
added to the actionable gene list. (C): Mutations in these eight genes were found in 231 and 96 patients out of the 703 and 315 patients with
actionable mutations and no actionable mutations, respectively. (D): Of the eight newly identified WfG genes, seven passed the criteria for
actionability as determined by the UNC CCGR. Mutations in at least one of these seven genes were found in 323 patients. (E): Re-examination
of these 323 patients revealed that while 47 had potential to change therapy, the majority of patients did not have the potential to change
therapy for several reasons (no evidence of disease, n5145; lost to follow-up, n529; withdrew from study, n54; and deceased, n598).
Abbreviations: CCGR, Clinical Committee for Genomic Research; pts, patients; WfG, Watson for Genomics.
4Enhancing Cancer Care Through Cognitive Computing
O
cAlphaMed Press 2017
Published Ahead of Print on November 20, 2017 as 10.1634/theoncologist.2017-0170.
by guest on November 16, 2018http://theoncologist.alphamedpress.org/Downloaded from
and copy number alterations that had been detected by the
UNCseq informatics pipeline (for details, see the Materials
and Methods section). The WfG analysis took approximately 3
minutes per case in this study. Of these 1,018 cases, the
human-only MTB had previously requested validation of
actionable variants in 703 of the patients (Fig. 3).These results
were reported to the treating physician and included in the
patient record in accordance with the IRB-approved UNCseq
protocol (LCCC1108/IRB #11–1115). In its independent analy-
sis of these 1,018 patients, WfG also categorized as actionable
the entirety of the human-only MTB-defined actionable var-
iants in all 1,018 cases. This result shows that WfG is able to
identify all reportable genetic events found by an MTB using
standard practices, including a human-curated actionable
gene list.
In addition to identifying reportable events already con-
veyed by the UNC MTB, WfG detected actionable variants in
323 (32%) of cases across a spectrum of tumor types (Fig. 4)
that were not reported by the UNC MTB (Fig. 4 and supplemen-
tal online Table 3). These events reflected eight genes that
were deemed actionable by WfG but not the human MTB at
the time of the reanalysis (Table 1). Importantly, even at the
time of the WfG analysis, these eight genes were still not on
the UNC MTB list of actionable genes, suggesting that our dis-
parate results were not merely reflecting the retrospective
nature of this study. Seven of the eight genes met the UNCseq
program’s own definition of actionability (e.g., being part of
entry criteria for a biomarker selected clinical trial; see the
Materials and Methods section), but were not identified by the
human-curated actionable gene list. These seven genes were
subsequently approved by the UNC Clinical Committee for
Genomic Research (CCGR). This left 323 patients with WfG-
identified actionable mutations that met the UNCseq definition
of actionability. The majority of newly actionable events discov-
ered by WfG were based on recent publications or newly
opened clinical trials for patients harboring inactivating events
of ARID1A,FBXW7,andATR (with or without concomitant
mutations of ATM;Table1).Ofthe323patientswithnewly
identified events, 283 (88%) patients were made potentially eli-
gible for enrollment in a biomarker-selected clinical trial that
had not been identified by the MTB. In particular, several of the
relevant clinical trials had opened and begun enrollment within
weeks of the WfG analysis (e.g., NCT02576444 for AIRD1A
mutant cancers). These observations suggest that staying
abreast of enrolling clinical trials is a particular challenge for
human-curated MTBs, and this problem is likely to worsen
as larger numbers of genotype-driven studies are opened
nationally.
As the WfG analysis was performed retrospectively on
selected patients, new findings were not relevant to the major-
ity of patients analyzed. In most cases, patients were not candi-
dates for further therapy for a variety of reasons (e.g.,
deceased, n598; no evidence of disease, n5145). Despite
the historical nature of the analysis, the MTB determined that
the results of the WfG analysis were of value in 47 patients
with active disease potentially needing further therapy. In
these cases, the NGS results were confirmed by a standard-of-
care, Clinical Laboratory Improvement Amendments-approved
assay in accord with the UNCseq guidelines, and then included
in the patient’s medical records and reported to the treating
physicians. To our knowledge, no patient with a WfG-identified
potentialtherapywentontobeenrolledinaclinicaltrial.
Table 1. Description of actionable findings in 283 patients identified by WfG missing in MTB recommendations
Gene n
CCGR
before
CCGR
after
WfG-identified
therapy
Clinical
trial Ph.
Rec.
agent
Ref.
(PMID)
APC 57 Not actionable Beta-catenin inhibitor Y II PRI-724 26396911
ARID1A 176 Not actionable PARPi Y II AZD2881 26069190
ATR 82 Not actionable PARPi Y I/Ib AZD6378 26517239
BRIP1 9 Not actionable PARPi Y II BMN 673 23881923
CDKN2B 13 Not Not CDK4/6i Y III Palbociclib 20354191
FBXW7 45 Not actionable mTORi N N/A N/A 24360397
MITF 3 Not actionable BRAFi N N/A N/A 24265153
RAD50 20 Not actionable Irinotecan 1Chk1/2i N N/A N/A 24934408
Abbreviations: CCGR, UNC Clinical Committee for Genomic Research; MTB, molecular tumor board; N, no; N/A, not applicable; Ph., clinical trial
phase; PMID, PubMed identifier; Rec. agent, recommended agent; Ref., reference; WfG, Watson for Genomics; Y, yes.
Table 2. Levels of evidence used by Watson for Genomics
Level Description
1 FDA-approved drug in this cancer type and biomarker
2A Standard of care biomarker predictive of response to an FDA-approved drug in this indication
2B Standard of care biomarker predictive of response to an FDA-approved drug in a different indication
3A Compelling clinical evidence supports the biomarker as being predictive of response to a drug in this indication
3B Compelling clinical evidence supports the biomarker as being predictive of response to a drug in a different indication
4 Compelling biological evidence supports the biomarker as being predictive of response to a drug
R1 Standard of care biomarker predictive of resistance to an FDA-approved drug in this indication
Abbreviation: FDA, U.S. Food and Drug Administration.
Patel, Michelini, Snell et al. 5
www.TheOncologist.com
O
cAlphaMed Press AlphaMed
Published Ahead of Print on November 20, 2017 as 10.1634/theoncologist.2017-0170.
by guest on November 16, 2018http://theoncologist.alphamedpress.org/Downloaded from
DISCUSSION
In this work, we employed Watson for Genomics, a cognitive
computing approach with sophisticated NLP, to extract relevant
information from unstructured data and to identify actionable
insights in patients enrolled in a clinical sequencing program.
Through ingestion of thousands of cancer-relevant publications
and analysis of ongoing clinical trials, WfG was able to identify
the same actionable events reported by the human-only MTB.
In addition, WfG identified new actionable events in more than
a quarter of the patients in this study. The majority of these
genetic events met criteria for enrollment in clinical trials, but a
minority also potentially predicted response to off-label therapy
and/or provided clinically meaningful prognostic information.
One reasonable response to this analysis is that a human
MTB can be infrequently informed by a cognitive computing
approach. For example, one might infer that a WfG analysis
could be run once on an institution’s actionable gene list and
then further human-only use would be adequate. This view,
however, misunderstands the fact that knowledge in this field is
rapidly evolving, with new publications and clinical trials chang-
ing the pathologic significance of a given genetic event on a near
daily basis. Therefore, the actionable gene list is never “finished,”
but instead requires real-time updating, which is a task to which
humans are poorly suited. Additionally, the evolving nature of a
given gene’s clinical utility provides an additional problem: a
given patient may not have actionable events at the time of ini-
tial diagnosis, but certain mutations may later become action-
able as research in the biomedical space progresses and
additional clinical trials become available. Therefore, reanalysis
of a tumor’s somatic mutations would seem prudent using
recent publication and trials information, but frequent reanalysis
of multiple patients would further increase the burden on over-
stretched MTBs. Therefore, the ability of a cognitive tool like
WfG increases the scalability of somatic tumor sequencing and
subsequent analysis of mutations for precision medicine.
Cognitive computational systems have shown promise in
other areas of medicine. For example, they have been success-
fully used to augment physicians’ ability to detect spinal lesions
in patient magnetic resonance images [12]. Medical cognitive
applications have also been found to be efficient for surgical
phase recognition and image processing for tumor progression
mappings [13]. In the arena of drug repurposing and drug target
identification, pilot studies have suggested that cognitive com-
puting can accelerate identification of novel drug targets [14].
Despite the power of cognitive computing approaches in these
other areas, however, to date their penetration into genomic
analysis has been limited. One reason for this has been frag-
mentation of medical data (i.e., the storage of data that cannot
be shared in multiple different formats across disparate plat-
forms); therefore, the large datasets required to train cognitive
computing approaches have not been available. This problem is
being directly addressed with several laudable data aggregation
efforts in both public and private settings (e.g., the American
Society of Clinical Oncology’s CancerLinQ and the American
Association for Cancer Research’s Project Genomics Evidence
Neoplasia Information Exchange). In this work, we were able to
identify a large amount of data (from http://www.ncbi.nlm.nih.
gov/pubmed and https://clinicaltrials.gov/, etc.) for an analysis
well suited to cognitive computing providing a highly useful
function for care of patients with cancer.
CONCLUSION
Although it is clear that cognitive computing will not substitute
for the ability of trained physicians and biomedical scientists to
interact with patients and to interpret clinical data, we have
reached a juncture at which many of the tasks related to cancer
care require a real-time analysis of large, continuously main-
tained datasets. Humans are poorly suited to tasks such as a
comprehensive analysis of the enormous amount of new clini-
cal information generated on a daily basis, and the present
study shows that a cognitive computing approach such as WfG
can enhance care for a significant fraction of patients.
Our study suggests that cognitive computing can expand
the treatment options for patients with cancer. However, the
majority of the 323 patients that WfG identified as having
actionable alterations were reclassified because an alteration in
the gene allowed them to be considered for enrollment in a
biomarker-selected clinical trial. We realize that these genes
have yet to demonstrate their capability as predictive bio-
markers of response to the proposed therapy and that while
patients may value the comprehensive nature of WfG, one
downside of the exhaustive nature of WfG may be the presen-
tation of too many options. Moreover, we recognize that the
mere identification of actionable and targetable genomic
events does not necessarily translate into patient benefit [15].
Results of the SHIVA trial question whether off-label use of
molecularly targeted agents does benefit patients [16], and this
topic remains debated in the medical literature [15, 17]. None-
theless, we remain in the early days of NGS-guided cancer care
and believe that the road to improved patient outcomes likely
lies in an iterative process that needs to be instituted between
MTB-recommended therapies and patient outcomes as well as
the availability of potent and effective therapies [1].
ACKNOWLEDGMENTS
We thank the members of the UNCseq team and the Line-
berger Bioinformatics Core for expertise and data analysis and
Arrow Genomics, LLC, for help with manuscript preparation.
Partial results of this study have previously been presented as
part of the CBS 60 Minutes segment on artificial intelligence.
This work was supported by the NC University Cancer Research
Fund and grant funding from NIH U10-CA181009 (D.N.H.) and
NIH R01-CA202053 (W.Y.K.).
AUTHOR CONTRIBUTIONS
Conception/design: Vanessa V. Michelini, David A. Eberhard, Patrick McNeillie,
Filippo Utro, Raquel Norel, Ajay Royyuru, H. Shelton Earp, Juneko E. Grilley-
Olson, D. Neil Hayes, Stephen J. Harvey, Norman E. Sharpless, William Y. Kim
Provision of study material or patients: Juneko E. Grilley-Olson, D. Neil Hayes,
Norman E. Sharpless, William Y. Kim
Collection and/or assembly of data: Nirali Patel, Vanessa V. Michelini, Saianand
Balu, Alan P. Hoyle, Joel S. Parker, Michele C. Hayward, David A. Eberhard,
Ashley H. Salazar, Patrick McNeillie, Raquel Norel, Erhan Bilal, D. Neil Hayes,
William Y. Kim
Data analysis and interpretation: Nirali Patel, Vanessa V. Michelini, David A.
Eberhard, Patrick McNeillie, Jia Xu, Claudia S. Huettner, Takahiko Koyama,
Filippo Utro, Kahn Rhrissorrakrai, Laxmi Parida, D. Neil Hayes,William Y. Kim
Manuscript writing: Nirali Patel, Vanessa V. Michelini, Jeff M. Snell, Saianand
Balu, Alan P. Hoyle, Joel S. Parker, Michele C. Hayward, David A. Eberhard,
Ashley H. Salazar, Patrick McNeillie, Jia Xu, Claudia S. Huettner, Takahiko
Koyama, Filippo Utro, Kahn Rhrissorrakrai, Raquel Norel, Erhan Bilal, Ajay
Royyuru, Laxmi Parida, H. Shelton Earp, Juneko E. Grilley-Olson, D. Neil Hayes,
StephenJ. Harvey, Norman E. Sharpless, William Y. Kim
Final approval of manuscript: Nirali Patel, Vanessa V. Michelini, Jeff M. Snell,
Saianand Balu, Alan P. Hoyle, Joel S. Parker, Michele C. Hayward, David A.
Eberhard, Ashley H. Salazar, Patrick McNeillie, Jia Xu, Claudia S. Huettner,
6Enhancing Cancer Care Through Cognitive Computing
O
cAlphaMed Press 2017
Published Ahead of Print on November 20, 2017 as 10.1634/theoncologist.2017-0170.
by guest on November 16, 2018http://theoncologist.alphamedpress.org/Downloaded from
Takahiko Koyama, Filippo Utro, Kahn Rhrissorrakrai, Raquel Norel, Erhan Bilal,
Ajay Royyuru, Laxmi Parida, H. Shelton Earp, Juneko E. Grilley-Olson, D. Neil
Hayes,Stephen J. Harvey, Norman E. Sharpless,William Y. Kim
DISCLOSURES
Vanessa V. Michelini:IBM(E,OI);Patrick McNeillie: IBM (E, OI); Jia Xu:
IBM (E, OI); Claudia S. Huettner: IBM (E, OI); Takahiko Koyama: IBM
(E, OI); Filippo Utro:IBM(E,OI);Kahn Rhrissorrakrai:IBM(E,OI);
Raquel Norel: IBM (E, OI); Erhan Bilal: IBM (E, OI); Ajay Royyuru:IBM
(E, OI); Laxmi Parida: IBM (E, OI); H. Shelton Earp: FORTHCOMING;
Stephen J. Harvey: IBM (E, OI); Norman E. Sharpless:G1
Therapeutics, Unity Biotechnology, HealthSpan Diagnostics (C/A, IP,
SAB, OI), Pfizer (H); William Y. Kim: IBM (C/A). The other authors
indicated no financial relationships.
(C/A)Consulting/advisory relationship;(RF) Researchfunding; (E) Employment; (ET) Expert
testimony; (H) Honoraria received; (OI) Ownership interests; (IP)Intellectualproperty rights/
inventor/patentholder; (SAB)Scientific advisory board
REFERENCES
1. Hayes DN, Kim WY. The next steps in next-gen
sequencing of cancer genomes. J Clin Invest 2015;
125:462–468.
2. Garraway LA. Genomics-driven oncology:
Framework for an emerging paradigm. J Clin Oncol
2013;31:1806–1814.
3. National Science Board, National Science Foun-
dation. Science and Engineering Indicators 2014.
Available at http://www.nsf.gov/statistics/seind14/.
Accessed September 10, 2016.
4. JeckWR,ParkerJ,CarsonCCetal.Targetednext
generation sequencing identifies clinically actionable
mutations in patients with melanoma. Pigment Cell
Melanoma Res 2014;27:653–663.
5. Zhao X, Wang A, Walter V et al. Combined tar-
geted DNA sequencing in non-small cell lung cancer
(NSCLC) using UNCseq and NGScopy, and RNA
sequencing using UNCqeR for the detection of
genetic aberrations in NSCLC. PLoS ONE 2015;10:
e0129280.
6. Mose LE, Wilkerson MD, Hayes DN et al.
ABRA: Improved coding indel detection via
assembly-based realignment. Bioinformatics
2014;30:2813–2815.
7. Wilkerson MD, Cabanski CR, Sun W et al. Inte-
grated RNA and DNA sequencing improves mutation
detection in low purity tumors. Nucleic Acids Res
2014;42:e107.
8. Saunders CT, Wong WS, Swamy S et al. Strelka:
Accurate somatic small-variant calling from
sequenced tumor-normal sample pairs. Bioinfor-
matics 2012;28:1811–1817.
9. American Association for Cancer Research.
News in Brief: Oncologists partner with Watson on
genomics. Cancer Discov 2015;5:788.
10. Wrzeszczynski KO, Frank MO, Koyama T et al.
Comparing sequencing assays and human-machine
analyses in actionable genomics for glioblastoma.
Neurol Genet 2017;3:e164.
11. Kandoth C, McLellan MD, Vandin F et al. Muta-
tional landscape and significance across 12 major
cancer types. Nature 2013;502:333–339.
12. Ogiela L, Tadeusiewicz R, Ogiela MR. Cognitive
techniques in medical information systems. Comput
Biol Med 2008;38:501–507.
13. Philipp P, Maleshkova M, Katic D et al. Toward
cognitive pipelines of medical assistance algorithms.
Int J Comput Assist Radiol Surg 2016;11:1743–1753.
14. Chen Y, Elenee Argentinis JD, Weber G. IBM
Watson: How cognitive computing can be applied to
big data challenges in life sciences research. Clin
Ther 2016;38:688–701.
15. West HJ. No solid evidence, only hollow argu-
ment for universal tumor sequencing: Show me the
data. JAMA Oncol 2016;2:717–718.
16. Le Tourneau C, Delord JP, Gonc¸alves A et al.
Molecularly targeted therapy based on tumour
molecular profiling versus conventional therapy for
advanced cancer (SHIVA): A multicentre, open-label,
proof-of-concept, randomised, controlled phase 2
trial. Lancet Oncol 2015;16:1324–1334.
17. Subbiah V, Kurzrock R. Universal genomic test-
ing needed to win the war against cancer: Genomics
IS the diagnosis. JAMA Oncol 2016;2:719–720.
See http://www.TheOncologist.com for supplemental material available online.
Patel, Michelini, Snell et al. 7
www.TheOncologist.com
O
cAlphaMed Press AlphaMed
Published Ahead of Print on November 20, 2017 as 10.1634/theoncologist.2017-0170.
by guest on November 16, 2018http://theoncologist.alphamedpress.org/Downloaded from
