Dyno sketch­es tens of thou­sands of vi­able next-gen AAV cap­sids with the help of ma­chine learn­ing — pa­per

Since its launch in May 2020, Dyno Ther­a­peu­tics has tout­ed its plat­form’s po­ten­tial to dis­cov­er vi­able vari­a­tions of cur­rent-gen AAVs with no­tice­able lim­i­ta­tions in terms of pa­tient safe­ty and ef­fi­ca­cy. Now, ac­cord­ing to a new study, Dyno has used its neur­al net­work to out­line tens of thou­sands of vari­ants that could add weight to its mis­sion to build a bet­ter cap­sid.

In a study meant to de­ter­mine how many vi­able vari­ants of the AAV2 cap­sid it could de­sign with the aid of ma­chine learn­ing, Dyno sketched out more than 100,000 virus­es that could be used to car­ry gene ther­a­pies, ac­cord­ing to a new pa­per pub­lished in Na­ture Biotech­nol­o­gy.

Us­ing a neur­al net­work to de­sign se­lec­tive­ly mu­tat­ed sites on a 28-amino acid chain, re­searchers at Dyno iden­ti­fied 110,689 vi­able vari­ants of the AAV2 cap­sid — a suc­cess rate of more than half of all vari­a­tions the biotech’s ma­chine learn­ing plat­form came up with as part of the ex­per­i­ment.

Sam Sinai

How did Dyno’s tech ac­com­plish that feat with lim­it­ed in­struc­tion­al da­ta? Ac­cord­ing to co-founder Sam Sinai, Dyno’s team worked smarter and not hard­er with the da­ta sets avail­able, se­lec­tive­ly in­putting — and some­times omit­ting — da­ta to cre­ate a bet­ter pre­dic­tion on less in­for­ma­tion.

“We looked at how dif­fer­ent ways at look­ing at the same da­ta — or even ig­nor­ing da­ta that we had — can help cer­tain ma­chine learn­ing mod­els in their abil­i­ty to mod­el the space that we are try­ing to go in­to,” Sinai told End­points News. “This is a huge ad­van­tage, re­mov­ing the bur­den of ex­pen­sive ex­per­i­ments from the lab­o­ra­to­ry to the com­put­er.”

The re­sult was a rich va­ri­ety of AAV vari­ants that could of­fer the need­ed di­ver­si­ty to tack­le Dyno’s sig­na­ture chal­lenge — work­ing around pa­tients’ nat­ur­al im­mu­ni­ty to spe­cif­ic AAV serotypes due to pri­or ex­po­sure. Paired with oth­er re­search in­to how to de­sign a cap­sid to bet­ter tar­get spe­cif­ic tis­sues, Sinai ar­gued his team is piec­ing to­geth­er a po­ten­tial road map for the fu­ture of AAV-based gene ther­a­pies.

The ex­per­i­ment has a side ben­e­fit, Sinai said, as one of the biggest ex­per­i­ments ever un­der­tak­en to dra­mat­i­cal­ly re­work the shape of a pro­tein. The high rates of suc­cess in find­ing vi­able vari­a­tions is just the cher­ry on top.

“The study it­self is one of the largest de­signs of any pro­teins to date with ma­chine learn­ing in terms of band­width and in terms of how much change we have in­duced in this pro­tein,” he said. “In that sense it’s very ex­cit­ing. When we start­ed this study in 2017, we didn’t know we could change the pro­tein as much as we did. One of the ex­cit­ing re­sults of this study is that we could.”

With the high suc­cess in map­ping AAV2, Sinai said Dyno is al­so fo­cus­ing on ad­di­tion­al serotypes, in­clud­ing AAV9 — the tech be­hind No­var­tis’ Zol­gens­ma. The team’s com­pu­ta­tion­al pow­er should work the same way across all wild serotypes, Sinai said, which could churn out mil­lions of unique vi­able vari­ants down the road.

So far, some big-name play­ers in phar­ma are tak­ing a bet on Dyno’s grow­ing po­ten­tial, with the Roche/Genen­tech group just re­cent­ly pledg­ing up to $1.8 bil­lion to the team’s hunt for a bet­ter cap­sid. As part of the deal signed in Oc­to­ber, Dyno went to work with the Spark team at Roche build­ing bet­ter mod­els of pro­to­type AAV vec­tors and look­ing to over­come some of the bar­ri­ers that have kept the ther­a­py’s po­ten­tial cor­ralled to a lim­it­ed set of or­gans.

The Roche deal came on the heels of sim­i­lar deals with Sarep­ta and No­var­tis, both of which looked to har­ness the com­pu­ta­tion­al pow­er be­hind Dyno’s de­signs.

The DCT-OS: A Tech­nol­o­gy-first Op­er­at­ing Sys­tem - En­abling Clin­i­cal Tri­als

As technology-enabled clinical research becomes the new normal, an integrated decentralized clinical trial operating system can ensure quality, deliver consistency and improve the patient experience.

The increasing availability of COVID-19 vaccines has many of us looking forward to a time when everyday things return to a state of normal. Schools and teachers are returning to classrooms, offices and small businesses are reopening, and there’s a palpable sense of optimism that the often-awkward adjustments we’ve all made personally and professionally in the last year are behind us, never to return. In the world of clinical research, however, some pandemic-necessitated adjustments are proving to be more than emergency stopgap measures to ensure trial continuity — and numerous decentralized clinical trial (DCT) tools and methodologies employed within the last year are likely here to stay as part of biopharma’s new normal.

Onno van de Stolpe, Galapagos CEO (Thierry Roge/Belga Mag/AFP via Getty Images)

Gala­pa­gos chops in­to their pipeline, drop­ping core fields and re­or­ga­niz­ing R&D as the BD team hunts for some­thing 'trans­for­ma­tive'

Just 5 months after Gilead gutted its rich partnership with Galapagos following a bitter setback at the FDA, the Belgian biotech is hunkering down and chopping the pipeline in an effort to conserve cash while their BD team pursues a mission to find a “transformative” deal for the company.

The filgotinib disaster didn’t warrant a mention as Galapagos laid out its Darwinian restructuring plans. Forced to make choices, the company is ditching its IPF molecule ’1205, while moving ahead with a Phase II IPF study for its chitinase inhibitor ’4617.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 104,800+ biopharma pros reading Endpoints daily — and it's free.

Stéphane Bancel, Getty

Mod­er­na CEO brush­es off US sup­port for IP waiv­er, eyes more than $19B in Covid-19 vac­cine sales in 2021

Moderna is definitively more concerned with keeping pace with Pfizer in the race to vaccinate the world against Covid-19 than it is with Wednesday’s decision from the Biden administration to back an intellectual property waiver that aims to increase vaccine supplies worldwide.

In its first quarter earnings call on Thursday, Moderna CEO Stéphane Bancel shrugged off any suggestion that the newly US-backed intellectual property waiver would impact his company’s vaccine or bottom line. Still, the company’s stock price fell by about 9% in early morning trading.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 104,800+ biopharma pros reading Endpoints daily — and it's free.

Angela Merkel (AP Photo/Michael Sohn)

Covid-19 roundup: Pfiz­er sub­mits vac­cine for full ap­proval; Merkel op­pos­es Biden pro­pos­al to sus­pend IP for vac­cines

Pfizer and BioNTech said Friday that they’ve submitted a biologics license application to the FDA for full approval of their mRNA vaccine for those over the age of 16.

How long it will take the FDA to decide on the BLA will be set once it’s been formally accepted by the agency.

Peter Marks, director of the FDA’s Center for Biologics Evaluation and Research, previously told Endpoints News that the review of the BLA should take between three and four months, but it may be even faster than that.

UP­DAT­ED: EMA safe­ty com­mit­tee seeks more in­fo on heart in­flam­ma­tion fol­low­ing Pfiz­er Covid-19 vac­cine

The European Medicines Agency’s safety committee said Friday that it’s aware of cases of inflammation of the heart muscle and inflammation of the membrane around the heart, mainly reported following vaccination with Pfizer’s Covid-19 vaccine, known in Europe as Comirnaty.

“There is no indication that these cases are due to the vaccine,” the EMA’s Pharmacovigilance Risk Assessment Committee said.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 104,800+ biopharma pros reading Endpoints daily — and it's free.

As­traZeneca caps PD-L1/CT­LA-4/chemo com­bo come­back with OS win. Is treme­li­mum­ab fi­nal­ly ready for ap­proval?

AstraZeneca’s closely-watched POSEIDON study continues to be the rare bright spot in its push for an in-house PD-L1/CTLA-4 combo.

Combining Imfinzi and tremelimumab with physicians’ choice of chemotherapy helped patients with stage IV non-small cell lung cancer live longer, the company reported — marking the first time the still-experimental tremelimumab has demonstrated an OS benefit.

For AstraZeneca and CEO Pascal Soriot, the positive readout — which is devoid of numbers — offers much-needed validation for the big bet they made on Imfinzi plus tremelimumab, after the PD-L1/CTLA-4 regimen failed multiple trials in head and neck cancer as well as lung cancer.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 104,800+ biopharma pros reading Endpoints daily — and it's free.

Ron DePinho (file photo)

A 'fly­over' biotech launch­es in Texas with four Ron De­Pin­ho-found­ed com­pa­nies un­der its belt

In his 13 years at Genzyme, Michael Wyzga noticed something about East Coast drugmakers. Execs would often jet from Boston or New York to San Francisco to find more assets, and completely miss the work being done in flyover states, like Texas or Wisconsin.

“If it doesn’t come out of MGH or MIT or Harvard, probably not that interesting,” he said of the mindset.

Now, he and some well-known industry players are looking to change that, and they’ve reeled in just over $38 million to do it.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 104,800+ biopharma pros reading Endpoints daily — and it's free.

An­oth­er failed tri­al for Or­p­hazyme's 'pipeline-in-a-pro­duc­t' leaves shad­ow on drug's fu­ture

The tumultuous ride for Orphazyme continued on Friday as the company announced that a pivotal trial for its lead drug arimoclomol failed yet again, this time in the treatment of ALS, seeding doubt in a drug that had recently been cleared by the FDA for priority review. The latest failure casts a darker shadow on the upcoming decision despite Orphazyme’s upbeat outlook.

In a statement, the Danish biotech announced that the drug did not meet its primary or secondary endpoints evaluating function and survival. But the company has not announced any data surrounding the failure, instead saying that it will publish the complete results later this year.

In­cyte ponies up $12M to set­tle char­i­ty foun­da­tion kick­back claims; US ex­er­cis­es op­tion for more dos­es of mon­key­pox vac­cine

One in a string of lawsuits targeting copay charity foundations, the DOJ has been hunting drugmaker Incyte for what prosecutors alleged was a kickback scheme to court patients. Now, Incyte is clearing its name.

Incyte will shell out $12.6 million to settle claims it funneled funds through a charity foundation to cover federal copays for patients taking its JAK inhibitor Jakafi, the DOJ said this week.