Consulting biotech and pharma companies on R&D tt https://insilico-biosystems.com/. Example consulting projects:• Drug discovery project review and portfolio optimization, for a company working on multiple disease areas and modalities.• NGS data management, analysis, and integration of internal and external samples; Systematic mining and assessment of tumor-associated antigens as ADC targets, for a company focusing on Oncology.• Target and off-target safety assessment for preclinical projects and lifting clinical hold, for a biopharma on pediatric diseases.• Revised bioinformatics software and database for AI/ML analytics, for a biotech software company. • Advising VC firms and others on technology and portfolio evaluation and strategies of AI-driven and other biotech companies. • R&D IT and Informatics roadmap (joint with another consulting firm), for an early-stage biopharma.

Built new team and developed team strategy and goals. Led team on computational predictive and investigative assessment of targets and compounds in all J&J disease areas and modalities. Led innovation projects in building new computational infrastructure, knowledgebase and analytic tools. Led collaboration with internal and external partners and CROs. Participated in establishing frameworks and templates for drug discovery governance and project reviews.• Revamped toxicogenomics and multi-omics operation by aligning process flow, technology platform, data analysis and communication with project stages. Transformed it to drive impact on decision-making in stage transitions.• Established computational analysis workflow for a) siRNA modality from target transcript validation to IND submission, b) optimization of bi- and tri-specific antibody for maximizing on-tumor binding and minimizing off-target and off-tumor binding.• Built/Tested/Implemented toxicity AI/ML models for compound lead selection• Created Target Safety Assessment (TSA) workflows for all targets, addressing different needs among modalities and evolving needs with project stages. TSA became a required component in portfolio entry and pre-clinical candidate declaration of all drug discovery projects.• Instituted Off-Target Prediction & Identification (OTPI) and Off-Target Safety Assessment (OTSA) workflows for multiple modalities, significantly improved compound safety assessment in lead selection, issue resolution and regulatory filing.• Developed a collaborative framework across multiple departments to provide computational support for drug discovery projects throughout portfolio stages.• Coordinated on building new IT infrastructure for organization’s data management and computing needs in Amazon VPC.• Member of Rancho Single Cell Consortium and account owner of BioTuring licensing, working on co-development of software tools and data integration for single cell and spatial multi-omics analysis.

Established team G&Os. Led fund raising for joint projects. led team in building analytical tools and knowledge bases, to support drug discovery projects across therapeutic areas and modalities. Directed computational and R&D teams in defining business requirements and developing computational solutions. Analyzed/Mined various integrated data for pre-portfolio target discovery and individual drug discovery projects. Served as a member of the Site Leadership Team and as liaison to global Nonclinical Safety.• Expanded BodyMap project by generating new RNA-Seq data of nonclinical species and integrating internal and external disease data fro. BodyMap became an essential resource for target discovery and safety assessment of all drug discovery projects.• Integrated and mined public data of human postmortem brain data for neuroscience disease pathways and targets. Mined TCGA data for oncology biomarkers and targets. Both contributed to new projects in Neurosciences and Oncology TAs.• Developed computational workflow for phenotypical screening-based compound lead and target ID for immune diseases.• Analyzed various data in Immunology disease target/biomarker identification, disease classification, treatment response prediction. Developed in-vitro disease and assay models for screening IBD compounds.• Streamlined NGS and other big data exchange, data flow and user access. Improved efficiency and reduced costs by developing tiered data management infrastructure based on data volume, value, user access and regulatory requirements.Led migration of NGS data management and computing from in-house and SDSC to Amazon AWS.• Account owner for Omicsoft and Qiagen IPA licensing and co-development. Guided Omicsoft and Qiagen teams by defining software and data requirements for different user groups (research scientists and data scientists).

Built new team. Managed internal and external collaboration, licensing and outsourcing. Contributed to mission and strategies and identified opportunities for new organization. Built foundation for broad data catalog and integration.• Integrated Electronic Medical Records (EMR) and omics data in Immunology diseases. Mined data for biomarker identification, disease classification and progression prediction.• Led building J&J’s NGS infrastructure and analysis pipeline in the San Diego Supercomputer Center (SDSC).• Established collective mechanism for funding global resources by obtaining backing from multiple organizations for enterprise software licensing and internal and external data integration expansion.

Strategized and implemented team goals. Led internal infrastructure, knowledgebase, and analytic tools development for global R&D through collaboration across multifunctional teams. Led bioinformatics tool and database licensing. Represented R&D IT in external collaborations and consortia. Example informatics projects:• Established Janssen BodyMap: omics and genomics database for cells and organ tissues from human and nonclinical species under normal and disease conditions, with more than 10K internal and external studies.• Enhanced workflow for NGS data management and computing utilizing distributed in-house servers.• Improved system for HCI (High Content Imaging) profiling of compound library by cellular gene expression and morphology.• Migrated infrastructure from in-house to SDSC and Amazon Cloud.• Implemented LIMS for tracking and automation of Genomic Core operations.Managed data analytics efforts in cross-functional matrix teams for study design, data collection, systematic analysis and hypothesis generation / validation. Contributing to decision-making of advancing or discontinuing various drug discovery projects.• Identified biomarkers for diabetes risk, depression diagnosis, Remicade response in IBD patients, Ketamine response in social defeat animal and others.• Determined potential targets for Diabetes, Psoriasis, Mood Disorders and others.• Predicted new indications for compounds by analyzing phenotypic profiling data.• Forecasted disease comorbidity and progression by mining electronic medical records in CPRD and Optum databases.• Refined Tox signature gene panels by integrative analysis of toxicogenomics and literature data.

Led evaluation, design and implementation of global bioinformatics and other informatics solutions essential for drug discovery. Provided data analytics to R&D teams across therapeutic areas. Supported global bioinformatics community. Examples of internal software projects I led at enterprise level:• DNAchip: A system for study request fulfillment, LIMS, data management and analysis of in-house microarray operations.• Hydra: A system that downloads, extracts, transforms and integrates bioinformatics data from >80 external sources. Became the backbone of Janssen informatics systems for target identification and annotation.• Advanced Biological & Chemical Discovery (ABCD): A system for in-house compound bioactivity assays, having study design, assay request/approval, LIMS, Data integration/aggregation, and analysis modules.• ToxGen: Data management and analysis pipeline of rat liver gene expression data treated with compendium of toxic compounds, for identifying toxicity biomarkers and developing biomarker panel for toxicity prediction.Ran integrative analysis of biological and chemical data analysis in multiple databases, identifying new targets and tool compounds. Predicted target hits for new compounds. Contributed to discovery of Histamine H4 receptor (novel G-Protein Coupled Receptor (GPCR)) through bioinformatics analysis of mRNA sequences.