Research Informatics

Syngene’s integrated research informatics services for biotech and pharmaceutical companies help reduce the complexity of analyzing large sets of biological data. Our services that extend across the drug discovery pipeline include building data packages, pathway databases, and knowledge bases, as well as analysis of high-throughput data, predictive modeling, structural modeling, mechanistic toxicology, and systems biology.

Our services are accessible as standalone projects or as part of an integrated project that includes any of Syngene’s capabilities across discovery biology, chemistry, clinical development, and safety assessment.


Our highly experienced team of biologists, data scientists, and informaticians work seamlessly with clients, delivering high-quality research data through artificial intelligence-based solutions, data annotation and analysis services, and software platforms such as Strand NGS, Sarchitect suite, and virtual liver technologies.

Artificial intelligence

Syngene’s Artificial Intelligence (AI) solutions learn from historical data as well as from the genomics, proteomics, phenomics, and chemical data generated throughout the drug discovery phase. Through aiding clients with better decision-making capabilities, our solutions accelerate the drug discovery process and reduce the chances of last stage attrition of drug candidates at the clinical stage.

Our scientists have vast experience in the modeling and design of peptides, enzymes, antibodies, and antibody-drug conjugates using bioinformatics, structural informatics, and predictive analytics. We also provide services in the humanization, design, and optimization of antibodies.

Data annotation and analysis

Syngene’s Data Annotation and Analysis services help accelerate progress in early drug discovery, target identification and validation, and biomarker discovery. Our services include:

  • Data analysis and pathway annotation: Our experienced team analyzes high-throughput genomic data to understand significant differential gene expressions for a gene or disease of interest. We provide insight into gene expression signatures and the associated signaling pathways that have chances of being impacted in a given condition. Our team reviews published literature on pathways to create a precise and succinct pathway annotation and represent them as curated pathway figures.
  • Knowledge base curation: Our scientists create knowledge bases and annotated interaction networks in specific disease areas or organs of interest. These curated knowledge bases are used to overlay data from experiments, derive therapeutic hypothesis, generate a mechanism of action, and compare compounds based on their biological effects.
  • Clinical relevance of next-generation sequencing (NGS) data: Our scientists are experts in interpreting NGS data obtained from sequencing germline and somatic mutations in disease areas that include genetically defined diseases, cardiac disorders, and cancer, to provide better health care.

Software platforms

Syngene uses computing and data mining platforms, acquired from Strand Life Sciences, to provide customized solutions and services that help analyze systems biology, pharmacokinetic properties such as absorption, distribution, metabolism, excretion, and toxicity (ADMET), and drug metabolism and pharmacokinetics (DMPK). Our software platforms include:

  • StrandSysbio is an interactive modeling and simulation-based computing platform that enables scientists to develop dynamic models of biological systems with mathematical models, simulations of disease evolution, clinical protocols, and therapeutic regimens. It allows the analysis of a model in dynamic and steady-state mode, helps understand a model’s behavior, and enables the creation of a context-specific knowledgebase.
  • Sarchitect Designer is a computing platform that provides powerful algorithms to help cheminformaticians and data scientists build optimal models, assess confidence in model predictions, and study the domain applicability of a model. The platform allows the building of regression and classifier models using algorithms such as Bayesian methods, neural networks, decision trees and forests, and support vector machines among others. The platform provides powerful data visualization and structure exploration features such as similarity and substructure searches.
  • Sarchitect Miner is a computing platform that enables medicinal chemists and DMPK scientists to deploy pre-built and custom models, profile and score molecules, and perform in silico lead optimization. The platform is pre-packaged with seven ADME and four ADME-Tox models.