Case Studies Teaming up with a trailblazer to develop next-gen drug discovery

Edit This Case Study Record

	Teaming up with a trailblazer to develop next-gen drug discovery

Teaming up with a trailblazer to develop next-gen drug discovery

Technology Category	Analytics & Modeling - Machine Learning Application Infrastructure & Middleware - Data Exchange & Integration
Applicable Industries	Healthcare & Hospitals Pharmaceuticals
Applicable Functions	Product Research & Development Quality Assurance
Use Cases	Predictive Maintenance Predictive Quality Analytics
Services	Data Science Services
Challenge	Anagenex, a drug discovery company, is combining DNA encoded library (DEL) technology with machine learning (ML) to accelerate the traditionally time- and labor-intensive portion of drug discovery. However, they faced several challenges. Treating DNA sequencing readouts as an intermediary step to understanding the molecule of interest is an indirect use case, creating an additional layer of complexity. Each experiment can introduce batch effects that mask the biologically relevant effects and confuse the machine learning process. Anagenex needed a robust solution that could start tracking from the very first experiments and scale quickly as the company grows. Read More
About Customer	Anagenex is a drug discovery company that combines DNA encoded library (DEL) technology with machine learning (ML) to achieve their vision of finding a drug candidate for every disease cheaply and quickly. Their goal is to radically accelerate the traditionally time- and labor-intensive portion of drug discovery with a fast and powerful approach based on combinatorial chemistry, machine learning and rapid, large scale iteration. They’ve relied on Benchling from day one, capturing every intermediate data point to ensure that their computational systems get a complete picture of lab processes. The company is based in the Bay Area, CA and has between 1-10 employees. Read More
Solution	Anagenex chose Benchling to make sure they would have a digital lab solution that could keep up with its team’s fast pace and cutting edge science. Benchling allowed Anagenex to create a custom data schema in their Benchling Registry that mapped the parent-child relationships between DELs, the DNA tags identifying the building blocks of each DEL, and the pools each DEL was added to. This helped them decode DNA sequencing readouts. Anagenex also used templatized registration in Benchling to lower friction to data entry, keeping scientist compliance up and data records clean and complete. This standardized data entry sped up their ML workflows despite high volumes of data because no extra data cleaning was required. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Application Infrastructure & Middleware - Data Exchange & Integration

Applicable Industries

Healthcare & Hospitals

Pharmaceuticals

Applicable Functions

Product Research & Development

Quality Assurance

Use Cases

Predictive Maintenance

Predictive Quality Analytics

Services

Data Science Services

Challenge

Anagenex, a drug discovery company, is combining DNA encoded library (DEL) technology with machine learning (ML) to accelerate the traditionally time- and labor-intensive portion of drug discovery. However, they faced several challenges. Treating DNA sequencing readouts as an intermediary step to understanding the molecule of interest is an indirect use case, creating an additional layer of complexity. Each experiment can introduce batch effects that mask the biologically relevant effects and confuse the machine learning process. Anagenex needed a robust solution that could start tracking from the very first experiments and scale quickly as the company grows.

About Customer

Anagenex is a drug discovery company that combines DNA encoded library (DEL) technology with machine learning (ML) to achieve their vision of finding a drug candidate for every disease cheaply and quickly. Their goal is to radically accelerate the traditionally time- and labor-intensive portion of drug discovery with a fast and powerful approach based on combinatorial chemistry, machine learning and rapid, large scale iteration. They’ve relied on Benchling from day one, capturing every intermediate data point to ensure that their computational systems get a complete picture of lab processes. The company is based in the Bay Area, CA and has between 1-10 employees.

Solution

Anagenex chose Benchling to make sure they would have a digital lab solution that could keep up with its team’s fast pace and cutting edge science. Benchling allowed Anagenex to create a custom data schema in their Benchling Registry that mapped the parent-child relationships between DELs, the DNA tags identifying the building blocks of each DEL, and the pools each DEL was added to. This helped them decode DNA sequencing readouts. Anagenex also used templatized registration in Benchling to lower friction to data entry, keeping scientist compliance up and data records clean and complete. This standardized data entry sped up their ML workflows despite high volumes of data because no extra data cleaning was required.

Impact #1	Benchling helped connect bench and ML work together.
Impact #2	Anagenex was able to decrease time spent on data entry and cleanup by 50%.
Impact #3	Anagenex was able to establish a robust data infrastructure from the start, which is estimated to increase their speed by 200%.

Impact #1

Benchling helped connect bench and ML work together.

Impact #2

Anagenex was able to decrease time spent on data entry and cleanup by 50%.

Impact #3

Anagenex was able to establish a robust data infrastructure from the start, which is estimated to increase their speed by 200%.

Benefit #1	100% of scientists agree that Benchling has helped connect bench and ML work together.
Benefit #2	50% decrease in time spent on data entry and cleanup.
Benefit #3	200% estimated increase in speed due to starting with a robust data infrastructure.

Benefit #1

100% of scientists agree that Benchling has helped connect bench and ML work together.

Benefit #2

50% decrease in time spent on data entry and cleanup.

Benefit #3

200% estimated increase in speed due to starting with a robust data infrastructure.

Download PDF Version

Overview

Teaming up with a trailblazer to develop next-gen drug discovery

Operational Impact

Quantitative Benefit