Angel Janevski
`Chief Data Scientist at MediQuire
`Greater New York City Area
`Information Technology and Services
`
`Current
`Previous
`
`MediQuire
`MediQuire, Medidata Solutions, Philips Research
`
`500+
`connections
`
`View Angel Janevski’s full profile.
`It's free!
`
`Your colleagues, classmates, and 500 million other professionals are on LinkedIn.
`
`View Angel’s Full Profile
`
`View Angel’s Full ProfileView Angel’s Full Profile
`
`Experience
`
`MediQuire
`2 years 9 months
`Chief Data Scientist
`MediQuire
`January 2017 – Present • 2 years
`Greater New York City Area
`
`Vice President of Analytics
`MediQuire
`April 2016 – January 2017 • 10 months
`New York, New York
`
`Senior Data Scientist, Project & Technical Lead
`Medidata Solutions
`May 2013 – March 2016 • 2 years 11 months
`Greater New York City Area
`Guide clinical trials planning and execution with data: Transform clinical and
`operational data into organized and actionable content
`
`Philips Research
`14 years 4 months
`Senior Member Research Staff & Project Leader
`Philips Research
`January 2004 – May 2013 • 9 years 5 months
`Greater New York City Area
`Clinical bioinformatics: Project lead, designer and key contributor for two
`generations of a Clinical Decision Support/Predictive analytics platform
`(PAPAyA) for analysis, management and delivery of high-throughput molecular
`profiling data to clinicians; Diagnostic patterns discovery and biological
`processes modeling based on high-throughput molecular profiling and clinical
`data
`
`Sign in
`
`Join now
`
`People Also Viewed
`
`Boris Zlochevsky
`Senior Data Architect at UnitedHealth
`Group / Optum
`
`Tristan Spoor
`Senior Data Scientist at Optum,
`Advanced Analytics Lab
`
`NAVJOT K.
`Network Claims Analyst at Zelis
`Healthcare
`
`Lauren Blasch
`Senior Data Engineer at MediQuire
`
`Dante Rankart
`Vice President of Sales at MediQuire
`
`John Porawski
`CTO at MediQuire
`
`Aanal Patel
`Principal Data Scientist, Enterprise
`Data Science at Express Scripts
`
`Robbie Pottharst
`COO at Cityblock Health
`
`Trevor Murphy
`Data Scientist
`
`Emily Chen
`CEO at MediQuire
`
`Public profile badge
`
`Include this LinkedIn profile on other websites
`
`Angel Janevski
`Chief Data Scientist at
`MediQuire
`
`MediQuire
`
`View profile
`
`View profile badges
`
`View profile badgesView profile badges
`
`Search by name
`
`Over 500 million professionals are already on
`LinkedIn. Find who you know.
`
`First Name
`Example: Jeff Weiner
`
`Last Name
`
`
`
`Page 1 of 12
`
`Implicit Exhibit 2079
`Sonos v. Implicit, IPR2018-0766, -0767
`
`

`

`Sign in
`
`Join now
`
`Learn new skills with online courses
`
`Machine Learning and AI
`Foundations: Clustering
`and Association
`Viewers: 6166
`
`Everyday Statistics, with
`Eddie Davila
`Viewers: 5083
`
`Neural Networks and
`Convolutional Neural
`Networks Essential
`Training
`Viewers: 10141
`
`View all online courses
`
`  
`
`Member Research Staff
`Philips Research
`February 1999 – December 2003 • 4 years 11 months
`Greater New York City Area
`Consumer information management/Content augmentation: Architecture design,
`specification and implementation of a content processing, augmentation and
`delivery. Prototypes featured by Philips on prominent trade shows and
`numerous technology events. (jointly in part w/IBM T. J. Watson Lab)
`
`Research Assistant/Fellow
`University of Kentucky
`August 1997 – January 1999 • 1 year 6 months
`Lexington, Kentucky Area
`Rule-based information extraction: Designed and implemented a software
`framework based on a full document-processing pipeline that intelligently
`navigates any Web content and deploys information extraction rules plug-ins.
`
`Research Internship
`Philips Research
`May 1998 – August 1998 • 4 months
`Greater New York City Area
`Implementation of Wireless Transport Layer Security (WTLS) layer of the
`Wireless Application Protocol (WAP) stack with a GUI test environment.
`
`Software Engineer & Project Leader
`Asseco South Eastern Europe (Pexim Macedonia)
`November 1994 – August 1997 • 2 years 10 months
`Macedonia
`Software design and development focusing on complete front- and back-end
`office in banking solutions as well as the National Post Office
`
`System Administrator, Programmer, Content
`Publishing House M
`February 1993 – November 1994 • 1 year 10 months
`Macedonia
`
`Education
`
`Columbia University in the City of New York
`Engineer’s Degree, Computer Science
`2000 – 2003
`Post-MS Professional Degree in Computer Science
`Advisor: Kenneth A. Ross; Title: "Querying Faceted Databases"
`
`Master’s Degree, Computer Science
`1997 – 1999
`Advisor: Victor Marek; Title: "UniversityIE: Information Extraction From University Web Pages"
`
`Ss. Cyril and Methodius University
`Bachelor’s Degree, Computer Science
`1988 – 1994
`
`Page 2 of 12
`
`Implicit Exhibit 2079
`Sonos v. Implicit, IPR2018-0766, -0767
`
`

`

`Sign in
`
`Join now
`
`Rade Jovcevski Korcagin
`High School, Mathematics-Informatics
`1983 – 1987
`
`Volunteer Experience
`
`Mentor
`FIRST
`September 2011 – May 2013 • 1 year 9 months Education
`
`Mentor
`iMentor
`September 2005 – June 2006 • 10 months Children
`Mentoring high-school students
`
`Tutor
`East Harlem Tutorial Program
`January 2005 – June 2006 • 1 year 6 months Education
`
`Skills & Endorsements
`
`Join LinkedIn to see Angel’s skills, endorsements, and
`full profile
`
`Join now
`
`Macedonian
`Native or bilingual proficiency
`
`Languages
`
`English
`Full professional proficiency
`
`Serbian
`Native or bilingual proficiency
`
`Patents
`
`Medical analysis system 
`United States 9,858,392
`Issued January 2018
`The present invention relates to effective diagnosis of patients and assisting clinicians in treatment
`planning. In particular, invention provides a medical analysis system that enables refinement of
`molecular classification. The system provides a molecular profiling solution that will allow improved
`diagnosis, prognosis, response prediction to provide the right chemotherapy, and follow-up to
`monitor for cancer recurrence.
`Inventors:
`Angel Janevski, Nevenka Dimitrova, Sitharthan Kamalakaran, Yasser alSafadi, Anca Bukur,
`Jasper Van Leeuwen, Vinay Varadan
`
`Clinical workstation integrating medical imaging and biopsy data and
`methods using same 
`United States 9,798,856
`Issued October 2017
`
`Page 3 of 12
`
`Implicit Exhibit 2079
`Sonos v. Implicit, IPR2018-0766, -0767
`
`

`

`Sign in
`
`Join now
`
`An imaging visualization workstation (30) includes a graphical display device (32) and an electronic
`data processor, and is configured to perform a method including: spatially registering a biopsy
`sample extracted from a medical subject with a medical image (12) of the medical subject;
`combining the medical image with a graphical representation of information (20, 22) generated from
`the biopsy sample to generate a combined image in which the graphical representation is spatially
`delineated based on the spatial registration of the biopsy sample; and displaying the combined
`image on the graphical display device of the imaging visualization workstation. A method comprises
`extracting a biopsy sample spatial sample from a medical subject, processing the biopsy sample to
`generate biopsy information, acquiring a medical image of the subject, spatially registering the
`biopsy sample with the medical image, and displaying the medical image modified to include an
`annotation generated from the biopsy information.
`Inventors:
`Angel Janevski, Nilanjana Banerjee, Sitharthan Kamalakaran, Vinay Varadan, Nevenka Dimitrova
`
`System and Method for Contextualized Tracking of the Progress of a
`Clinical Study 
`United States
`Filed February 2016
`An improved system for tracking the progress of a clinical study includes a classifier generator, a
`classifier application subsystem, a study stage annotation subsystem, a progress status models
`generator, an aggregation module, and a progress status evaluation subsystem. The classifier
`generator automatically generates clinical data element classifiers by evaluating clinical data
`containers and clinical study stage attributes across clinical studies; the classifier application
`subsystem applies the clinical data element classifiers to classify clinical data elements into pre-
`determined categories; the study stage annotation subsystem uses the clinical data element
`classifiers and the classified clinical data elements to determine clinical study stages; the progress
`status models generator generates at least one progress status model based on the clinical study
`stages, the aggregation module selects and aggregates the classified clinical data elements and
`clinical study stages; and the progress status evaluation subsystem computes the state of at least
`one progress status model. The progress status evaluation subsystem generates at least one
`progress status of the clinical study by using the clinical data element classifiers and clinical data to
`compare contextualized study properties of one or more associated clinical study stages. An
`improved method for tracking the progress of a clinical study is also described and claimed.
`Inventors: Angel Janevski, Mladen Laudanovic
`
`Compositions and methods for micro-RNA expression profiling of
`colorectal cancer 
`United States 9,074,206
`Issued July 2015
`The present invention relates compositions and methods for microRNA (miRNA) expression
`profiling of colorectal cancer. In particular, the invention relates to a diagnostic kit of molecular
`markers for identifying one or more mammalian target cells exhibiting or having a predisposition to
`develop colorectal cancer, the kit comprising a plurality of nucleic acid molecules, each nucleic acid
`molecule encoding a miRNA sequence, wherein one or more of the plurality of nucleic acid
`molecules are differentially expressed in the target cells and in one or more control cells, and
`wherein the one or more differentially expressed nucleic acid molecules together represent a nucleic
`acid expression signature that is indicative for the presence of or the predisposition to develop
`colorectal cancer. The invention further relates to corresponding methods using such nucleic acid
`expression signatures for identifying one or more mammalian target cells exhibiting or having a
`predisposition to develop colorectal cancer as well as for preventing or treating such a condition.
`Finally, the invention is directed to a pharmaceutical composition for the prevention and/or treatment
`of colorectal cancer.
`Inventors:
`Ying Wu, Hongguang Zhu, Jian Li, PhD, Liang Xu, Wim Verhaegh, Yiping Ren, Angel Janevski,
`Vinay Varadan, Zhaoyong Li, Nevenka Dimitrova
`
`Device and method for comparing molecular signatures 
`United States 8,924,232
`Issued December 2014
`Inventors: Yasser alSafadi, Nilanjana Banerjee, Vinay Varadan, Angel Janevski
`
`System and Method for Monitoring Clinical Trial Progress 
`United States 20160085943
`Issued September 2014
`A method for monitoring clinical trial progress includes calculating progress curves for clinical trial
`states. Calculating a progress curve includes assigning values to events for a datapoint in the
`clinical trial, generating or building pairs of values for each consecutive sequence of the events,
`summing up the values of pairs of events corresponding to a state change, and determining a state
`for the datapoint based on the sum of the values. Monitoring clinical trial progress then includes
`
`Page 4 of 12
`
`Implicit Exhibit 2079
`Sonos v. Implicit, IPR2018-0766, -0767
`
`

`

`calculating a second progress curve for another clinical trial state and comparing the delay between
`points of the progress curves. A system for monitoring clinical trial progress is also described.
`Inventors: Glen de Vries, Mladen Laudanovic, Angel Janevski
`
`Sign in
`
`Join now
`
`Method of determining a reliability indicator for signatures obtained from
`clinical data and use of the reliability indicator for favoring one signature
`over the other
`United States 8,762,072
`Issued June 2014
`Inventors: Angel Janevski, Nilanjana Banerjee, Yasser alSafadi, Vinay Varadan
`
`Method and system for retrieving information about television programs
`United States 8,453,189
`Issued May 2013
`Inventors: Angel Janevski, Lalitha Agnihotri
`
`Method and system for providing complementary information for a video
`program
`United States 7,934,233
`Issued April 2011
`Inventors:
`Angel Janevski, Johanna Maria Bont, Nevenka Dimitrova, Andreas Henricus Elisabeth Lamers,
`Dongge Li, Lira Nikolovska, John Zimmerman
`
`Implementation of mandatory segments in multimedia content
`United States 7,292,773
`Issued November 2007
`Inventors: Angel Janevski
`
`Precipitation/dissolution of stored programs and segments
`United States 7,457,811
`Issued June 2002
`Inventors: Angel Janevski, Nevenka Dimitrova, Lalitha Agnihotri
`
`System and method for providing videomarks for a video program
`United States 6,988,245
`Issued June 2002
`Inventors: Angel Janevski
`
`Graphic user interface having touch detectability
`United States 6,988,247
`Issued June 2002
`Inventors: Angel Janevski
`
`Apparatus and method for synchronizing presentation from bit streams
`based on their content
`
`United States 7,269,3387,269
`Issued December 2001
`Inventors: Angel Janevski
`
`Image extraction from video content
`United States 7,590,333
`Issued October 2001
`Inventors: Angel Janevski
`
`Page 5 of 12
`
`Implicit Exhibit 2079
`Sonos v. Implicit, IPR2018-0766, -0767
`
`

`

`Sign in
`
`Join now
`
`Adaptive picture-in-picture
`United States 6,697,123
`Issued March 2001
`Inventors: Angel Janevski, Nevenka Dimitrova
`
`Smart picture-in-picture
`United States 6,697,124
`Issued March 2001
`Inventors: Angel Janevski, Nevenka Dimitrova
`
`System and Method For Real Time Clinical Questions Presentation and
`Management 
`United States
`Filed June 2013
`In a clinical decision support method, outputs of computer-implemented analytical modules are
`computed for a patient. Information is displayed for the patient pertaining to a clinical question
`comprising outputs computed for the patient of analytical modules associated with the clinical
`question. The analytical modules may include modules configured to perform in silico
`genetic/genomic tests using genetic/genome sequencing (whole genome, whole exome, whole
`transcriptome, targeted gene panels, etc) or microarray data. A clinical question-module matrix (CQ-
`M matrix) may be generated for the patient associating clinical questions with analytical modules,
`and the method may further include populating the clinical questions with outputs computed for the
`patient of the analytical modules associated with the clinical questions by the CQ-M matrix. Such
`populating advantageously re-uses outputs computed for the patient when an analytical module is
`associated with two or more different clinical questions by the CQ-M matrix. This system empowers
`the clinician to focus on the clinical aspects of patient management while allowing the data
`complexities of patient genomic data interpretation to be handled by the clinical decision support
`system.
`Inventors:
`Angel Janevski, Sitharthan Kamalakaran, Nilanjana Banerjee, Vinay Varadan, Nevenka Dimitrova,
`Mine Danisman Tasar
`
`Integrated access to and interation with multiplicity of clinical data analytic
`modules 
`United States
`Filed January 2011
`A state machine (22) stores a current state (30) comprising a clinical context defined by available
`patient-related information relating to a medical patient, and identifies one or more available
`analytical tools of a set of analytical tools (24) that are applicable to the current state. A graphical
`user interface module (16) receives a user selection of an available analytical tool. The state
`machine loads patient-related information (40) to the user-selected available analytical tool
`(24.sub.sel) and invokes the user-selected available analytical tool to operate on the loaded patient-
`related information to generate additional patient-related information relating to the medical patient
`and/or graphical patient-related content relating to the medical patient. The state machine
`transitions from the current state (30) to a next state (30') and/or invokes the graphical user
`interface module to display the graphical patient related content.
`Inventors:
`Angel Janevski, Sitharthan Kamalakaran, Christian Reichelt, Nilanjana Banerjee, Vinay Varadan,
`Nevenka Dimitrova
`
`Biomarkers based on sets of molecular signatures 
`United States
`Filed May 2009
`A method (10) for forming novel signatures of biological data is provided. The method comprises
`ranking features based on a trend value, which is created based on multiple signatures identified by
`a pattern discovery method. Furthermore, a device (30) and a computer program product (40),
`performing the steps according to the method (10) is provided. Uses of the method, for statistically
`analyzing clinical data, designing assays based on multiple molecular signatures and interpreting
`assays based on multiple molecular signatures are also provided.
`Inventors: Angel Janevski, Vinay Varadan, Nilanjana Banerjee
`
`Publications
`
`Page 6 of 12
`
`Implicit Exhibit 2079
`Sonos v. Implicit, IPR2018-0766, -0767
`
`

`

`Sign in
`
`Join now
`
`Brief-exposure to preoperative bevacizumab reveals a TGF-β signature
`predictive of response in HER2-negative breast cancers (PMID: 26284485) 
`International Journal of Cancer
`August 2015
`
`n order to best define biomarkers of response, and to shed insight on mechanism of action of
`certain clinically important agents for early breast cancer, we used a brief-exposure paradigm in the
`preoperative setting to study transcriptional changes in patient tumors that occur with one dose of
`therapy prior to combination chemotherapy. Tumor biopsies from breast cancer patients enrolled in
`two preoperative clinical trials were obtained at baseline and after one dose of bevacizumab (HER2-
`negative), trastuzumab (HER2-positive) or nab-paclitaxel, followed by treatment with combination
`chemo-biologic therapy. RNA-Sequencing based PAM50 subtyping at baseline of 46 HER2-negative
`patients revealed a strong association between the basal-like subtype and pathologic complete
`response (pCR) to chemotherapy plus bevacizumab (p≤0.0027), but did not provide sufficient
`specificity to predict response. However, a single dose of bevacizumab resulted in down-regulation
`of a well-characterized TGF-β activity signature in every single breast tumor that achieved pCR
`(p≤0.004). The TGF-β signature was confirmed to be a tumor-specific read-out of the canonical
`TGF-β pathway using pSMAD2 (p≤0.04), with predictive power unique to brief-exposure to
`bevacizumab (p≤0.016), but not trastuzumab or nab-paclitaxel. Down-regulation of TGF-β activity
`was associated with reduction in tumor hypoxia by transcription and protein levels, suggesting
`therapy-induced disruption of an autocrine-loop between tumor stroma and malignant cells.
`Modulation of the TGF-β pathway upon brief-exposure to bevacizumab may provide an early
`functional readout of pCR to preoperative anti-angiogenic therapy in HER2-negative breast cancer,
`thus providing additional avenues for exploration in both preclinical and clinical settings with these
`agents.
`Authors:
`Vinay Varadan, Sitharthan Kamalakaran, Hannah Gilmore, Nilanjana Banerjee, Angel Janevski,
`Kristy L.S. Miskimen, Nicole Williams, Ajay Basavanhalli, Anant Madabhushi, Nevenka Dimitrova,
`Lyndsay Harris
`
`Translating next generation sequencing to practice: Opportunities and
`necessary steps (PMID: 23769412) 
`Molecular oncology
`May 2013
`
`Abstract: Next-generation sequencing (NGS) approaches for measuring RNA and DNA benefit from
`greatly increased sensitivity, dynamic range and detection of novel transcripts. These technologies
`are rapidly becoming the standard for molecular assays and represent huge potential value to the
`practice of oncology. However, many challenges exist in the transition of these technologies from
`research application to clinical practice. This review discusses the value of NGS in detecting
`mutations, copy number changes and RNA quantification and their applications in oncology, the
`challenges for adoption and the relevant steps that are needed for translating this potential to
`routine practice.
`
`Highlights:
`•Next Generation sequencing (NGS) enables measurement of clinically relevant mutations, DNA
`copy number and gene expression.
`•We review diagnostic, prognostic and therapy selection applications of NGS for different types of
`cancer.
`•We discuss technology challenges that need to be overcome for implementing NGS into
`widespread clinical use.
`•We discuss education, regulatory framework, storage, privacy and confidentiality of genomic data
`to enable adoption.
`Authors:
`Angel Janevski, Sitharthan Kamalakaran, Vinay Varadan, Nilanjana Banerjee, David Tuck,
`Dick McCombie, Nevenka Dimitrova, Lyndsay Harris
`
`Effective normalization for copy number variation detection from whole
`genome sequencing (PMID: 23134596) 
`BMC Genomics
`October 2012
`
`Background: There have been a number of tools to infer copy number variation in the genome.
`These tools, while validated, also include a number of parameters that are configurable to genome
`data being analyzed. These algorithms allow for normalization to account for individual and
`population-specific effects on individual genome CNV estimates but the impact of these changes on
`the estimated CNVs is not well characterized. We evaluate in detail the effect of normalization
`methodologies in two CNV algorithms FREEC and CNV-seq using whole genome sequencing data
`from 8 individuals spanning four populations.
`Methods: We apply FREEC and CNV-seq to a sequencing data set consisting of 8 genomes. We
`use multiple configurations corresponding to different read-count normalization methodologies in
`FREEC, and statistically characterize the concordance of the CNV calls between FREEC
`configurations and the analogous output from CNV-seq. The normalization methodologies evaluated
`in FREEC are: GC content, mappability and control genome. We further stratify the concordance
`analysis within genic, non-genic, and a collection of validated variant regions.
`Results: The GC content normalization methodology generates the highest number of altered copy
`number regions. Both mappability and control genome normalization reduce the total number and
`
`Page 7 of 12
`
`Implicit Exhibit 2079
`Sonos v. Implicit, IPR2018-0766, -0767
`
`

`

`Sign in
`
`Join now
`
`length of copy number regions. Mappability normalization yields Jaccard indices in the 0.07 - 0.3
`range, whereas using a control genome normalization yields Jaccard index values around 0.4 with
`normalization based on GC content. The most critical impact of using mappability as a normalization
`factor is substantial reduction of deletion CNV calls. The output of another method based on control
`genome normalization, CNV-seq, resulted in comparable CNV call profiles, and substantial
`agreement in variable gene and CNV region calls.
`Authors:
`Angel Janevski, Vinay Varadan, Sitharthan Kamalakaran, Nilanjana Banerjee, Nevenka Dimitrova
`
`A microRNA panel to discriminate carcinomas from high-grade
`intraepithelial neoplasms in colonoscopy biopsy tissue (PMID: 22535378) 
`Gut
`April 2012
`
`Objective It is a challenge to differentiate invasive carcinomas from high-grade intraepithelial
`neoplasms in colonoscopy biopsy tissues. In this study, microRNA profiles were evaluated in the
`transformation of colorectal carcinogenesis to discover new molecular markers for identifying a
`carcinoma in colonoscopy biopsy tissues where the presence of stromal invasion cells is not
`detectable by microscopic analysis.
`
`Methods The expression of 723 human microRNAs was measured in laser capture microdissected
`epithelial tumours from 133 snap-frozen surgical colorectal specimens. Three well-known
`classification algorithms were used to derive candidate biomarkers for discriminating carcinomas
`from adenomas. Quantitative reverse-transcriptase PCR was then used to validate the candidates in
`an independent cohort of macrodissected formalin-fixed paraffin-embedded colorectal tissue
`samples from 91 surgical resections. The biomarkers were applied to differentiate carcinomas from
`high-grade intraepithelial neoplasms in 58 colonoscopy biopsy tissue samples with stromal invasion
`cells undetectable by microscopy.
`
`Results One classifier of 14 microRNAs was identified with a prediction accuracy of 94.1% for
`discriminating carcinomas from adenomas. In formalin-fixed paraffin-embedded surgical tissue
`samples, a combination of miR-375, miR-424 and miR-92a yielded an accuracy of 94%
`(AUC=0.968) in discriminating carcinomas from adenomas. This combination has been applied to
`differentiate carcinomas from high-grade intraepithelial neoplasms in colonoscopy biopsy tissues
`with an accuracy of 89% (AUC=0.918).
`
`Conclusions This study has found a microRNA panel that accurately discriminates carcinomas from
`high-grade intraepithelial neoplasms in colonoscopy biopsy tissues. This microRNA panel has
`considerable clinical value in the early diagnosis and optimal surgical decision-making of colorectal
`cancer.
`Authors:
`Angel Janevski, Nevenka Dimitrova, Vinay Varadan, Wim Verhaegh, Ying Wu,
`Winston Patrick Kuo, Jiaqiang Ren, Dennis Merkle, Nayima Bayaxi, Lei Wang, Shuyang Wang
`
`DNA methylation patterns in luminal breast cancers differ from non-luminal
`subtypes and can identify relapse risk independent of other clinical
`variables (PMID: 21169070) 
`Molecular Oncology
`February 2011
`
`The diversity of breast cancers reflects variations in underlying biology and affects the clinical
`implications for patients. Gene expression studies have identified five major subtypes– Luminal A,
`Luminal B, basal-like, ErbB2+ and Normal-Like. We set out to determine the role of DNA
`methylation in subtypes by performing genome-wide scans of CpG methylation in breast cancer
`samples with known expression-based subtypes. Unsupervised hierarchical clustering using a set of
`most varying loci clustered the tumors into a Luminal A majority (82%) cluster, Basal-like/ErbB2+
`majority (86%) cluster and a non-specific cluster with samples that were also inconclusive in their
`expression-based subtype correlations. Contributing methylation loci were both gene associated loci
`(30%) and non-gene associated (70%), suggesting subtype dependant genome-wide alterations in
`the methylation landscape. The methylation patterns of significant differentially methylated genes in
`luminal A tumors are similar to those identified in CD24 + luminal epithelial cells and the patterns in
`basal-like tumors similar to CD44 + breast progenitor cells. CpG islands in the HOXA cluster and
`other homeobox (IRX2, DLX2, NKX2-2) genes were significantly more methylated in Luminal A
`tumors. A significant number of genes (2853, p < 0.05) exhibited expression–methylation
`correlation, implying possible functional effects of methylation on gene expression. Furthermore,
`analysis of these tumors by using follow-up survival data identified differential methylation of islands
`proximal to genes involved in Cell Cycle and Proliferation (Ki-67, UBE2C, KIF2C, HDAC4),
`angiogenesis (VEGF, BTG1, KLF5), cell fate commitment (SPRY1, OLIG2, LHX2 and LHX5) as
`having prognostic value independent of subtypes and other clinical factors.
`Authors:
`Angel Janevski, Sitharthan Kamalakaran, Nilanjana Banerjee, Nevenka Dimitrova, Vinay Varadan,
`James Hicks, Michael Wigler, Anne-Lise Borresen-Daleemail, Bjorn Naume, Robert Lucito,
`Hege E. Giercksky Russnes
`
`PAPAyA: Applications in Oncology Decision Support
`AMIA
`
`Page 8 of 12
`
`Implicit Exhibit 2079
`Sonos v. Implicit, IPR2018-0766, -0767
`
`

`

`2011
`Authors:
`Angel Janevski, Nilanjana Banerjee, Sitharthan Kamalakaran, Vinay Varadan, Nevenka Dimitrova
`
`Sign in
`
`Join now
`
`Pathway and network analysis probing epigenetic influences on
`chemosensitivity in ovarian cancer
`GENSIPS
`2010
`
`Ovarian cancer is the leading cause of death in gynecological cancers. Carboplatinum-based
`therapy is the standard treatment choice for ovarian cancer. However, a majority of the patients
`develop resistance to carboplatinum fairly rapidly hence there is a clinical need for early predictors
`of carboplatinum resistance. While there are a few indicative gene markers, they have poor
`sensitivity and specificity in predicting response accurately. It is essential that multiple high
`throughput molecular profiling modalities are integrated and investigated to provide a full picture of
`the ongoing processes. Here, we propose a methodology to identify central players in platinum
`resistance from a list of stratifying genes using a data-driven approach. We have used correlation of
`DNA methylation and gene expression data and applied network based features to identify the
`influence of DNA methylation on gene expression. This provides interpretive analysis and is
`complementary to the biological pathway-enrichment approaches. We suggest that our method,
`based on network structure properties, adds a useful layer to multi-modal evidence integration to
`focus on the key processes and interactions in resistance mechanisms.
`Authors:
`Nilanjana Banerjee, Angel Janevski, Sitharthan Kamalakaran, Vinay Varadan, Robert Lucito,
`Nevenka Dimitrova
`
`PAPAyA: a platform for breast cancer biomarker signature discovery,
`evaluation and assessment (PMID: 19761577) 
`BMC Bioinformatics
`September 2009
`
`Background: The decision environment for cancer care is becoming increasingly complex due to the
`discovery and development of novel genomic tests that offer information regarding therapy
`response, prognosis and monitoring, in addition to traditional histopathology. There is, therefore, a
`need for translational clinical tools based on molecular bioinformatics, particularly in current cancer
`care, that can acquire, analyze the data, and interpret and present information from multiple
`diagnostic modalities to help the clinician make effective decisions.
`
`Results: We present a platform for molecular signature discovery and clinical decision support that
`relies on genomic and epigenomic measurement modalities as well as clinical parameters such as
`histopathological results and survival information. Our Physician Accessible Preclinical Analytics
`Application (PAPAyA) integrates a powerful set of statistical and machine learning tools that
`leverage the connections among the different modalities. It is easily extendable and reconfigurable
`to support integration of existing research methods and tools into powerful data analysis and
`interpretation pipelines. A current configuration of PAPAyA with examples of its performance on
`breast cancer molecular profiles is used to present the platform in action.
`
`Conclusion: PAPAyA enables analysis of data from (pre)clinical studies, formulation of new clinical
`hypotheses, and facilitates clinical decision support by abstracting molecular profiles for clinicians.
`Authors:
`Angel Janevski, Sitharthan Kamalakaran, NIla Banerjee, Vinay Varadan, Nevenka Dimitrova
`
`Towards identification of thematic overlaps in gene sets
`GENSIPS
`2009
`
`Genomic signatures for disease prognosis are discovered by applying statistical methods on high-
`throughput data. Enrichment analysis of gene set annotations provide limited understanding of the
`biological processes. We use curated sets reflecting various biological processes implicated in
`cancer and the thematic clusters to describe and compare four breast cancer prognostic signatures.
`We demonstrate an effective and automated use of curated gene sets to identify thematic overlaps
`in gene sets based on their associated significant Gene Ontology terms. This method enabled us to
`compare four breast cancer prognostic signatures The differences in the thematic content suggest
`that the signatures while answering the issue of aggressiveness are capturing different sets of
`biological processes to achieve efficacy.
`Authors: Nilanjana Banerjee, Vinay Varadan, Sitharthan Kamalakaran, Angel Janevski
`
`A Genetic Algorithm Approach for Discovering Diagnostic Patterns in
`Molecular Measurement Data
`IEEE: Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)
`2005
`
`Page 9 of 12
`
`Implicit Exhibit 2079
`Sonos v. Implicit, IPR2018-0766, -0767
`
`

`

`Sign in
`
`Join now
`
`The objective of this work is the development of an algorithm that, after training, will be able to
`discriminate between disease classes in molecular data. The system proposed uses a genetic
`algorithm (GA) to achieve this discrimination. We apply our method to three publicly available data
`sets. Two of the data sets are based on microarray data that allow the simultaneous measurement
`of the expression levels of genes under different disease states. The third data set is based on
`serum proteomic pattern diagnostics of ovarian cancer using high-resolution mass spectrometry to
`extract a set of biomarker classifiers. We show how our methodology finds an abundance of
`different feature models, automatically selecting a subset of discriminatory features, whose
`classification accuracy is comparable to other approaches considered. This raises questions about
`how to choose among the many competing mode