Elucidata Polly AI Biomedical Data and Target Discovery

Elucidata is an AI and biomedical data company with offices in Cambridge (Boston) and San Francisco in the US and in New Delhi and Bengaluru in India. It addresses a core bottleneck in drug discovery: omics, assay and clinical data sit in inconsistent formats, so research teams spend more time cleaning data than testing hypotheses.

Its Polly platform ingests a company's proprietary data together with public biomedical evidence, harmonises it with ontology-backed metadata into a unified data model, and links genes, diseases, drugs and pathways in a knowledge graph. Modules include a curation engine, Atlas multi-modal data sets, Polly Xtract for turning documents into structured data, and Co-Scientist agents that run discovery workflows in natural language and score drug targets. Customers are pharmaceutical and biotech R&D teams.

• Data harmonisation: maps measurements and metadata into a unified, ontology-backed data model.
• Curation engine: configurable pipelines that turn omics, assay and clinical data into ML-ready resources.
• Atlas: harmonised multi-modal biomedical data collections.
• Knowledge graph: links genes, diseases, drugs and pathways in one queryable graph.
• Polly Xtract: converts unstructured documents into structured, analysis-ready data.
• Co-Scientist: agents that run discovery workflows and rank drug targets across 14 dimensions.

Vietnamese genomics institutes and biobanks can harmonise sequencing and clinical data into AI-ready assets for research partnerships. Biotech start-ups can use curated public datasets to prioritise drug targets with a small team. Pharmaceutical R&D centres can extract structured data from study reports and literature.

Provides a catalogue of about 1.5 million ML-ready datasets and processes over 35 TB of molecular data a month. The company reports LLM-powered harmonisation that is about 10 times faster than manual curation. Case studies cite about 80% faster gene target identification and validation and about US$3 million saved by using curated public data. Deployment can be cloud, on-premise or hybrid.

Pharmaceutical R&D is moving toward AI-driven target discovery, which depends on clean, connected biomedical data. Biobanks and hospitals in Asia are turning their samples into AI-ready data products for global partners. Vietnam's investment in genomics and precision medicine creates data that research institutes will need to harmonise before it can support drug discovery.

Offices in Cambridge (MA), San Francisco, New Delhi and Bengaluru; co-founder and CEO Abhishek Jha. Raised a US$16 million Series A in 2022 led by Eight Roads Ventures with F-Prime Capital. Partnered with Sapien Biosciences (2025) and Axio BioPharma (2026). Former Evotec CEO Werner Lanthaler joined the board in 2025.