Venter hires Google machine learning expert to build Translate for genomics

J. Craig Venter

Over the past year, the worlds of Google ($GOOG) and J. Craig Venter have converged, with the search giant's startup Calico and Baseline Study sharing goals with the genomic pioneer's Human Longevity. And now Venter has gone to Mountain View to make his latest hire, nabbing Franz Och to build a Google Translate for genomics.

Och has spent the past decade applying his machine learning skills to improving Google Translate, the tool that hundreds of millions of people use to understand text in more than 80 languages. Google Translate works by comparing a trove of previously translated materials--including United Nations documents and Harry Potter novels--to learn how to write a phrase in English, French and tens of other languages. When a user asks Google to translate a phrase, it uses this knowledge to suggest an answer.

Venter thinks genomics faces similar challenges and set out to hire the person who led the Google Translate program. "The 6 billion letters of the genome represent one of the biggest translation issues ever. We need to use machine learning to find associations between genes that mere mortals can't find from staring at the data. It's too complex," Venter told U-T San Diego. Och could be the first of many Silicon Valley hires for Human Longevity, with Venter planning to build a computer science team in the area instead of trying to persuade people to relocate down the coast to San Diego.

The raid on Silicon Valley comes as Google continues to move into life sciences. Calico and Baseline Study both overlap with the goals of Human Longevity, but Venter thinks they are operating at different scales. "[Baseline Study is] a baby step, a much smaller version of what we are doing," he told MIT Technology Review.

- read U-T San Diego's article
- check out Technology Review's Q&A
- here's Xconomy's take
- view Slate's Google Translate feature
- and the press release

Special Report: 2012's 25 most influential people in biopharma - J. Craig Venter

Suggested Articles

St. Jude, Microsoft and DNAnexus have created a data-sharing and analysis platform to help accelerate pediatric cancer research.

The new solution aims to streamline the incorporation of human genomic data into clinical trial designs.

The $58 million financing round represents biopharma industry's growing interest in genomics data.