We accelerate drug discovery by using machine learning to facilitate successful experiments. We’re backed by Google’s AI fund, Gradient Ventures, and built by life scientists for life scientists.

Founded 2015
51-200 employees
  • Information Systems
  • Analytics & Business Information
  • Headquarters address
    559 College St. Suite 201, Toronto, ON, M6G 1A9

    About half a million scientists spend over $3 billion a year buying research antibodies for experiments. They use these essential reagents to detect and quantify proteins.

    The Problem: Wasted Money, Wasted Time, and Delayed Drugs

    Selecting antibodies slows the velocity of research and drug development. There are over 6,000,000 commercial antibodies, and vendors can't predict how each one will work in specific experiments. Data on antibody use is buried in biomedical papers, vendor catalogs, and independent validation databases. In part because this data is hard to find,  up to 50% of selected antibodies don't work in experiments.

    This wastes resources and delays research projects. Our work with pharmaceutical companies  suggests each spends up to $1-3 million a year on commercial antibodies that do not work. Researchers also purchase unnecessary custom antibodies at $50,000 and 3-6 months to develop, spend days to select and weeks (sometimes months) to test and validate antibodies, and redundantly and unknowingly often validate  the same antibodies as colleagues within the same organization.

    The Solution: AI-Assisted Antibody Selection

    Data to solve this problem is buried in scientific publications. Technological advances now allow it to be decoded. This includes advances in machine learning to better interpret text and images, increases in processing power to perform this analysis at scale, and improvements in graph databases to map and extract insights from results.
    This has enabled huge benefits from AI-assisted antibody selection. These include reducing the hard cost of consumables up to $3 million per year, accelerating projects by selecting antibodies in 30 seconds versus 12 weeks, empowering organizational purpose by alleviating manual publication searches and restoring research time to scientists, and providing an immediate turnkey application of AI to increase organizational efficiency.

    BenchSci: The Leader in AI-Assisted Antibody Selection

    BenchSci is the leader in AI-assisted antibody selection. We collate the world’s largest collection of antibody-specific data; identify biological entities in their text and images with proprietary, antibody-specific machine learning models; map their relationships in a knowledge graph that incorporates bioinformatics databases and ontologies; and provide an intuitive interface to select antibodies by protein target, technique, and other experimental variables.

    As the emerging industry standard, BenchSci now powers AI-assisted antibody selection for more than 26,000 researchers at more than 2,000 academic institutions and 15 of the top 20 pharmaceutical companies.

    Tech stack

    React, Python, Elasticsearch, Neo4J, AWS Lambda, Google Cloud Platform, Spark


    Compensation and retirement

    Stock Options

    Health and wellness

    Health insurance
    Dental insurance
    Vision insurance
    On-site fitness center

    Vacation and time off

    Paid time off
    Paid holidays

    Personal development

    Tuition reimbursement
    Management training
    Job training
    Conferences reimbursement

    Values and quality of life

    Accessible via public transportation
    Bike parking
    Employee groups and committees
    Snacks and beverages
    Catered dinners
    Company activities
    Games and recreation
    BenchSci - Company Photo
    BenchSci - Company Photo
    BenchSci - Company Photo
    BenchSci - Company Photo
    BenchSci - Company Photo
    BenchSci - Company Photo
    BenchSci - Company Photo