Pichai Raman
Computational Biology | Machine Learning | Drug Discovery
About Me
I am an accomplished and versatile bioinformatics leader with over 20 years of experience at the intersection of computational biology, artificial intelligence, and machine learning. My expertise spans cancer informatics, biomarker development, gene therapy, and the design of scalable genomic workflows to drive scientific discovery and therapeutic innovation.
Throughout my career, I've consistently advanced drug discovery pipelines from concept through development by integrating diverse data types—including RNA-Seq, WES/WGS, single-cell, ATAC-Seq, ChIP-Seq, proteomics, and functional screens—with cutting-edge analytics. I bring deep technical fluency in machine learning, omics integration, cheminformatics, and visualization of large-scale biological data, supported by a strong foundation in statistics.
Career Highlights
- 15+ years' experience leveraging cloud platforms (AWS, GCP, Azure) to design and deploy scalable genomic workflows across transcriptomics, metabolomics, epigenomics, and other omics data types
- 10+ years building and leading cross-functional high performing teams of up to a dozen individuals in machine learning, computational analysis, and bioinformatics engineering
- Over 50+ publications in high impact factor peer-reviewed journals across Precision Oncology, Bioinformatics, Immunogenomics, and Translational science
- Led target discovery efforts in a multi-institutional collaboration (Pediatric Cancer Dream Team / Stand Up to Cancer), identifying GPC2 as a key neuroblastoma target that advanced to clinical trials
- Played a key role in the original Cancer Cell Line Encyclopedia (CCLE) project and leveraged the data to identify the target and mechanism of action of Englerin A
- Contributed to groundbreaking research on mechanisms of resistance to CD19-targeted CAR T-cell therapy, identifying alternative splicing and acquired mutations in CD19 as key factors enabling immune evasion in leukemia
- Senior author on the development of a robust transcriptome-based classifier for medulloblastoma subtyping, achieving over 97% accuracy across independent datasets and enabling reliable classification of retrospective and prospective RNA-based data
Experience
Incyte
Senior Director, Computational Biology
Leading a computational biology team driving data-driven discovery and translational insights across the drug development pipeline. Overseeing both preclinical target identification and clinical biomarker strategies to accelerate therapeutic development.
- Managing and mentoring a team of 6 computational biologists, setting strategic direction and ensuring high-impact delivery
- Leading computational efforts for target identification, prioritization, and mechanistic assessment in preclinical programs
- Designing and executing translational biomarker strategies to support clinical trials and patient stratification
Cadent
Senior Director, Data Science
Led the Data Science function delivering large-scale identity and audience intelligence solutions, translating complex data into actionable insights for clients and customers.
- Directed teams processing 200+ billion data points daily using Google Cloud Platform and BigQuery to power real-time analytics and decisioning
- Oversaw development and productionization of dozens of machine learning models, optimizing tradeoffs between predictive accuracy and audience reach to meet diverse business and customer objectives
Spark Therapeutics
Director, Computational Biology & Machine Learning
Led the Computational Biology and Machine Learning team in support of research and technical development projects including:
- NGS Product Characterization: Oversaw next-generation sequencing (NGS) automated workflow for the characterization of vectors and plasmids, ensuring drug product quality
- Computational Biology Support: Provided pivotal support for research initiatives with single-cell and bulk NGS, imaging analysis, and advanced analytical techniques for target identification and candidate selection
- Machine Learning Capability Development: Led the development and implementation of cutting-edge deep learning and machine learning strategies to optimize upstream and downstream technical development and enhance discovery platforms within the gene therapy landscape
GSK
Oncology Data Strategy & Design Director
Defining the data strategy and developing workflows and endpoints to support Oncology research and clinical activities and projects, while leading a matrixed team across functions to ensure alignment and execution. Key initiatives listed below:
- Oncology Workflows: Spearheaded the development of scalable workflows and tools for translational oncology team to enhance biomarker analytics. Championed strategic AI/ML initiatives to streamline oncology drug discovery, integrating cheminformatics and predictive analytics.
- Data Frameworks: Led strategic initiatives to optimize data management and design frameworks, significantly improving the efficiency of oncology research.
Children's Hospital of Philadelphia
Supervisory Bioinformatics Scientist / Director of Scientific and Analytic Services
Developed and led an interdisciplinary team of bioinformatic analysts, data scientists, and engineers to deliver strategic informatics solutions and support scientific programs and projects in the pediatric cancer space. Team remit and activities included the following:
- PedcBioPortal: Headed effort to collaborate with MSKCC, DFCI, and Princess Margeret and build a pediatric focused cBioPortal for use by the pediatric cancer community (https://pedcbioportal.org/).
- Cavatica: Working with Seven Bridges Genomics to develop a cloud platform for genomic analysis and collaboration (http://www.cavatica.org/).
- Kids First: Helped to design and create the Kids First genomic application, that houses pediatric cancer and birth-defect genomic and phenotypic data (https://kidsfirstdrc.org/portal/).
- Mechanisms of Compound Sensitivity: Collaborating with various pharmaceutical companies to determine mechanisms of sensitivity to certain cancer therapeutics.
- Target Discovery in Pediatric Cancer: Led target discovery aim in a multi-institution effort (Pediatric Cancer Dream Team / Stand Up to Cancer) dedicated to cancer immunotherapy by building scalable bioinformatics workflows.
Novartis
Scientific Technical Leader
Led computational biology initiatives to support early discovery and translational research through the integration of high-dimensional data, development of analysis platforms, and collaborative pipeline building. Focused on accelerating target identification, pathway analysis, and compound profiling across diverse therapeutic areas:
- GSEA Project: Developed application in Java (J2EE) to store, manage, and share gene sets. In addition implemented GSEA to use sets in analysis of microarray and other high-throughput data.
- Compound Set Enrichment: Implemented set enrichment type approach (Pipeline Pilot) to aid in reducing FP-rate of high throughput screens. Worked with other internal groups on determining best methods for clustering and grouping of compound data for use with this approach.
- Cancer Cell Line Encyclopedia: Worked as part of a collaborative team (Broad / NIBR) to develop a pipeline (R) to determine markers (genetic lesion / expression) of sensitivity to compounds across a set of cell lines.
- mTORC1 Project: Worked with Manning lab (HMS) to determine specific set of TSC regulated genes from microarray data and associated processes (Metacore). Analysis used to help elucidate biology around mTOR Complex 1.
- Early Target Discovery: Integrated various data types including copy number data, shRNA / siRNA data, expression data, mutation data from both tissue and cell line data and developed analysis file in Spotfire DXP for early target discovery purposes. Data sources included internal and public repositories such as the TCGA, GEO, and ArrayExpress. Metacore and IPA used additionally to determine relevant disease pathway links and connections to known oncogenes or disease markers.
Publications
| Year | Title | Authors | Journal | PMID |
|---|
Education
Drexel University
Ph.D. in Biomedical Engineering, Science & Health Systems
Philadelphia, PA
The Ohio State University
M.S. in Bioinformatics
Columbus, OH
University of Michigan
B.S. in Cell and Molecular Biology
Ann Arbor, MI
Research Interests
Genomic & Transcriptomic Analysis
Focused on the analysis and integration of genomic and transcriptomic data, including bulk, single-cell, and spatial modalities, to better understand disease mechanisms and therapeutic opportunities.
Cancer Biology
Deeply engaged in cancer biology, with particular emphasis on pediatric and adult neuro-oncology, tumor heterogeneity, and the tumor microenvironment.
Machine Learning in Biomedicine
Applying machine learning and deep learning approaches to large-scale biomedical datasets to enable predictive modeling, phenotype stratification, and discovery of novel biological insights.
Biomarker Development
Experienced in the identification and development of biomarkers to support both translational research and clinical decision-making across oncology and gene therapy programs.
Gene Therapy Analytics
Leading research and development efforts in gene therapy analytics, with a focus on next-generation sequencing-based characterization of vectors, plasmids, and drug products.
Functional Genomics
Conducting functional genomics studies using tools like shRNA, siRNA, and CRISPR screens to elucidate gene function, therapeutic targets, and resistance mechanisms.
Multi-omics Workflows
Developing robust, scalable workflows for multi-omics data processing and analysis, enabling reproducible and efficient bioinformatics operations across research and development.
Data Integration
Building and implementing platforms that integrate diverse omics data types to support target identification, candidate prioritization, and mechanistic exploration.
Data Visualization
Designing and deploying visualization tools and user interfaces to facilitate the exploration, interpretation, and reporting of high-dimensional scientific data.
Cheminformatics
Utilizing cheminformatics, compound profiling, and response modeling to link genomic features with drug sensitivity and optimize therapeutic strategies.
Knowledge Management
Developing and curating knowledge bases and annotation frameworks to support data-driven decision-making in target discovery and compound triaging.