Minkyung Baek (University of Washington)

'They have shown that this is not some im­pos­si­ble thing': Aca­d­e­m­ic lab copies Google’s big bi­o­log­i­cal break­through

When Demis Has­s­abis, CEO of Google’s AI out­fit Deep­Mind, an­nounced last year that they had cracked one of the tough­est puz­zles in bi­ol­o­gy — suc­cess­ful­ly pre­dict­ing a pro­tein’s shape from its amino acid se­quence — Minkyung Baek watched with a cu­ri­ous mix­ture of dread and ex­cite­ment.

“It felt like I just lost my job,” said Baek, a post­doc at the Uni­ver­si­ty of Wash­ing­ton’s In­sti­tute for Pro­tein De­sign.

Baek had spent the last three years try­ing to do the ex­act same thing, work­ing with what for years had been the lead­ing pro­tein de­sign tech­nol­o­gy at the lead­ing pro­tein de­sign lab. Now Deep­Mind had ful­ly eclipsed her. She felt the sci­en­tif­ic com­mu­ni­ty’s ex­cite­ment, even as she pon­dered her pro­fes­sion­al fu­ture.

Deep­Mind’s break­through, though, had a caveat: The com­pa­ny hadn’t ac­tu­al­ly shown how they cracked the puz­zle, nor had they made their head­line-grab­bing soft­ware avail­able to any re­searchers out­side of Google’s dis­parate of­fices. Baek won­dered if she could, with the few bread­crumbs Google left, re­con­struct Deep­Mind’s soft­ware and dis­trib­ute it to the world.

On Thurs­day, she showed she could. Baek and her team at UW’s Bak­er lab de­tailed ma­chine learn­ing soft­ware in Sci­ence that was al­most — al­beit not quite — as pow­er­ful as Deep­Mind in pre­dict­ing a pro­tein’s struc­ture from its se­quence, and demon­strat­ed how it could be de­ployed to probe ques­tions in­tri­cate­ly linked to un­der­stand­ing dis­ease and de­sign­ing new drugs. They have made the tool, known as RoseTTaFold, avail­able on GitHub, where UW claims it has al­ready been down­loaded by over 140 re­search teams.

John Moult

“If you want­ed to be neg­a­tive about it, you could say they’re play­ing catch-up and got re­sults that were not quite as good,” said John Moult, a com­pu­ta­tion­al bi­ol­o­gist at the Uni­ver­si­ty of Mary­land who in 1994 launched the an­nu­al chal­lenge where Deep­Mind de­buted their re­sults. “I think the more pos­i­tive and prop­er way of look­ing at it is that they have done it near­ly as well and they have al­ready pro­vid­ed a serv­er, which works at least in a cou­ple of times. And they have done a full re­lease of their code.

“They have shown that this is not some im­pos­si­ble thing for oth­er peo­ple to achieve,” Moult added.

The pa­per came out the same time Na­ture pub­lished the de­tailed meth­ods be­hind Deep­Mind’s work — a co­in­ci­dence the folks at the Bak­er lab chalk up to their de­ci­sion to re­lease the preprint and open source soft­ware last month. Has­s­abis’ team sim­i­lar­ly promised to make their soft­ware pub­lic, al­though they have not pro­vid­ed a sim­i­lar serv­er to Baek’s.

The two ap­proach­es are broad­ly sim­i­lar on a high lev­el, said Baek, re­ly­ing on broad datasets of known pro­tein se­quences and struc­tures and sim­i­lar­i­ties be­tween co-evolved pro­teins. But they dif­fer vast­ly in how they tech­ni­cal­ly car­ry out their vi­sion.

Col­lec­tive­ly, they give re­searchers two so­lu­tions to a decades-old prob­lem and of­fer im­prove­ments over the orig­i­nal re­sults re­leased last year, in­clud­ing the abil­i­ty to pre­dict struc­ture in min­utes or hours, rather than days.

A pro­tein’s func­tion is de­ter­mined by its struc­ture, but for decades the on­ly way to de­ter­mine that struc­ture was through a va­ri­ety of imag­ing tech­niques, such as X-ray crys­tal­log­ra­phy, that could be lengthy or dif­fi­cult and didn’t pro­duce ac­cu­rate de­pic­tions for every pro­tein. Al­though those tech­niques have im­proved over time, the po­ten­tial to pre­dict a a struc­ture from its se­quence alone — known as the fold­ing prob­lem — con­tin­ued to be a holy grail.

David Bak­er

Baek’s lab, run by bio­chemist David Bak­er and fa­mous for its work in de­sign­ing pro­teins from scratch, had been lead­ing the race for years be­fore Deep­Mind leapfrogged them. See­ing the com­pa­ny’s progress, they adopt­ed more ma­chine learn­ing tech­niques to catch up.

In their pa­per, Baek showed a few of the ways wide­spread ac­cess to such tech­nol­o­gy could be used to build new drugs. They pre­dict­ed struc­tures for three class­es of pro­teins key to a range of dis­eases, in­clud­ing can­cer and de­men­tia, show­ing how rare mu­ta­tions could warp the pro­tein’s shape and re­veal­ing pos­si­ble open­ings to tar­get drugs.

“It’s not as good as Deep­Mind,” said Jin­bo Xu, a com­pu­ta­tion­al bi­ol­o­gist at the Uni­ver­si­ty of Chica­go. “But some of the struc­tures are very ac­cu­rate. It will be use­ful.”

Un­til Deep­Mind re­leas­es their open-source work, RoseTTaFold, Xu said, will be more help­ful to the field. They may not have long to wait, though.

Baek post­ed their pa­per as a preprint on June 15. Three days lat­er, Has­s­abis tweet­ed out a “brief up­date” on Deep­Mind’s pro­tein fold­ing soft­ware, say­ing that a full pa­per out­lin­ing their meth­ods was un­der re­view and that they would be pro­vid­ing the source code and “broad ac­cess” to the soft­ware to re­searchers. Xu said a serv­er for re­searchers to ac­cess Deep­Mind’s tech would be the ide­al tool.

Moult not­ed the Bak­er pa­per took their soft­ware to places that Deep­Mind didn’t. In ad­di­tion to pre­dict­ing the struc­ture of in­di­vid­ual pro­teins, they al­so pre­dict­ed how dif­fer­ent pro­teins come to­geth­er to form larg­er struc­tures, as they do to per­form man­i­fold bi­o­log­i­cal func­tions. Baek pre­dict­ed the dif­fer­ences be­tween two im­mune com­plex­es: one formed by IL-23 and one by IL-12. The re­sults could help drug de­vel­op­ers iden­ti­fy mol­e­cules that block one but not the oth­er, cre­at­ing more pre­cise drugs for au­toim­mune dis­eases.

Baek said her next big project is im­prov­ing the soft­ware’s abil­i­ty to pre­dict these in­ter­ac­tions.

IDC: Life Sci­ences Firms Must Em­brace Dig­i­tal Trans­for­ma­tion Now

Pre-pandemic, the life sciences industry had settled into a pattern. The average drug took 12 years and $2.9 billion to bring to market, and it was an acceptable mode of operations, according to Nimita Limaye, Research Vice President for Life Sciences R&D Strategy and Technology at IDC.

COVID-19 changed that, and served as a proof-of-concept for how technology can truly help life sciences companies succeed and grow, Limaye said. She recently spoke about industry trends at Egnyte’s Life Sciences Summit 2022. You should watch the entire session, free and on-demand, but here’s a brief recap of why she’s urging life sciences companies to embrace digital transformation.

Geoffrey Porges, new Schrödinger CFO

Long­time an­a­lyst Ge­of­frey Porges de­parts SVB to lead fi­nances at a drug dis­cov­ery shop

Geoffrey Porges has ended his two-decade run as a biotech analyst, as the former SVB Securities vice chair began as CFO of Schrödinger on Thursday.

The long-running analyst, who previously headed up vaccines marketing at Merck before the turn of the millennium, will lead the financial operations of the 700-employee company as Schrödinger broadens its focus from a drug discovery partner to also building out an in-house pipeline, with clinical trial No. 1 set to begin next quarter.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 148,400+ biopharma pros reading Endpoints daily — and it's free.

FDA ap­proves one of the prici­est new treat­ments of all time — blue­bird's gene ther­a­py for be­ta tha­lassemia

The FDA on Wednesday approved the first gene therapy for a chronic condition — bluebird bio’s new Zynteglo (beti-cel) as a potentially curative treatment for those with transfusion-dependent thalassemia.

The thumbs-up from the FDA follows a unanimous adcomm vote in June, with outside experts pointing to extraordinary efficacy, with 89% of subjects with TDT who received beti-cel having achieved transfusion independence.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 148,400+ biopharma pros reading Endpoints daily — and it's free.

James Sabry, Roche global head of pharma partnering

Roche, Genen­tech plunk down $60M up­front to part­ner with Chi­nese phar­ma on PRO­TAC-based prostate can­cer drug

Roche and Genentech are always on the hunt for deals, and on Thursday they found their newest partner.

The pair will team up with the Chinese pharma company Jemincare to push forward a new program for prostate cancer, the companies announced. Roche is ponying up $60 million upfront to get its hands on the candidate and promising up to $590 million in biobucks, plus royalties, down the line.

In return, Genentech will get a worldwide license to develop the program, known as JMKX002992, and bring it to market.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 148,400+ biopharma pros reading Endpoints daily — and it's free.

Andrew Hopkins, Exscientia CEO

Ex­sci­en­tia ter­mi­nates Bay­er pact half a year ear­ly, col­lect­ing small por­tion of €240M promised

Bayer and Exscientia are winding down their three-year collaboration, leaving the big German pharma to take the AI-designed compounds born out of the pact further.

London-based Exscientia revealed in its Q2 update that the partners have “mutually agreed to end” their collaboration, which kicked off in early 2020, after recently achieving a drug discovery milestone. In an SEC filing, Exscientia said it terminated the pact on May 30, about six months early.

Bayer's first DTC ad campaign for chronic kidney disease drug Kerendia spells out its benefits

Bay­er aims to sim­pli­fy the com­plex­i­ties of CKD with an ABC-themed ad cam­paign

Do you know the ABCs of CKD in T2D? Bayer’s first ad campaign for Kerendia tackles the complexity of chronic kidney disease with a play on the acronym (CKD) and its connection to type 2 diabetes (T2D).

Kerendia was approved last year as the first and only non-steroidal mineralocorticoid receptor antagonist to treat CKD in people with type 2 diabetes.

In the TV commercial launched this week, A is for awareness, B is for belief and C is for cardiovascular, explained in the ad as awareness of the connection between type 2 and kidney disease, belief that something can be done about it, and cardiovascular events that may be reduced with treatment.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 148,400+ biopharma pros reading Endpoints daily — and it's free.

James Mock, incoming CFO at Moderna

Mod­er­na taps new CFO from PerkinElmer af­ter for­mer one-day CFO oust­ed

When Moderna hired a new CFO last year,  it didn’t expect to see him gone after only one day. Today the biotech named his — likely much more vetted — replacement.

The mRNA company put out word early Wednesday that after the untimely departure of then brand-new CFO Jorge Gomez, it has now found a replacement in James Mock, the soon-to-be former CFO at diagnostics and analytics company PerkinElmer.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 148,400+ biopharma pros reading Endpoints daily — and it's free.

Etleva Kadilli, director of UNICEF’s supply division

GSK lands first-ever UNICEF con­tract for malar­ia vac­cine worth $170M

GSK has landed a new first from UNICEF the first-ever contract for malaria vaccines, worth up to $170 million for 18 million vaccine doses distributed over the next three years.

The vaccine, known as Mosquirix or RTS,S, won WHO’s backing last October after a controversial start, but UNICEF said these doses will potentially save thousands of lives every year.

“We hope this is just the beginning,” Etleva Kadilli, director of UNICEF’s supply division, said. “Continued innovation is needed to develop new and next-generation vaccines to increase available supply, and enable a healthier vaccine market. This is a giant step forward in our collective efforts to save children’s lives and reduce the burden of malaria as part of wider malaria prevention and control programmes.”

Joe Jonas (Photo by Anthony Behar/Sipa USA)(Sipa via AP Images)

So­lo Jonas broth­er car­ries Merz's new tune in Botox ri­val cam­paign

As the lyrics of his band’s 2019 pop-rock single suggest, Joe Jonas is only human — and that means even he gets frown lines. The 33-year-old singer-songwriter is Merz’s newest celebrity brand partner for its Botox rival Xeomin, as medical aesthetics brands target a younger audience.

Merz kicked off its “Beauty on Your Terms” campaign on Tuesday, featuring the Jonas brother in a video ad for its double-filtered anti-wrinkle injection Xeomin.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 148,400+ biopharma pros reading Endpoints daily — and it's free.