Out to ‘re­think the drug de­sign process,’ AI star Daphne Koller is cre­at­ing a new ma­chine learn­ing ven­ture at in­sitro with some heavy­weight back­ers

Daphne Koller has been busy.

Just two months since the high pro­file AI ex­pert ex­it­ed Google’s an­ti-ag­ing biotech Cal­i­co Labs, where she was chief com­put­ing of­fi­cer, Koller has gath­ered a group of mar­quee in­vestors to back a tech up­start — in­sitro — with plans to de­vel­op a ma­chine learn­ing plat­form equipped with cus­tom-built datasets to cre­ate a new and far more ef­fi­cient ap­proach to drug dis­cov­ery and de­vel­op­ment.

AI cir­cles have been buzzing with spec­u­la­tion and queries about what the for­mer Stan­ford pro­fes­sor planned to do af­ter ex­it­ing Cal­i­co, where she had been de­vel­op­ing com­pu­ta­tion­al meth­ods for an­a­lyz­ing bi­o­log­i­cal da­ta sets. She an­swered at least some of those ques­tions with a blog post late Tues­day that spelled out her com­mit­ment to “in­vest heav­i­ly” in cre­at­ing new datasets that can ac­cel­er­ate the use of ma­chine learn­ing in bio­phar­ma.

Koller has some high rollers back­ing the start­up, in­clud­ing some ven­ture groups well known for block­buster fundrais­ing and a yen for trans­for­ma­tion­al ven­tures. They are: Arch Ven­ture Part­ners, Fore­site Cap­i­tal, a16z, GV (for­mer­ly Google Ven­tures) and Third Rock.

In­sitro, she says, will “col­lect and use a range of very large da­ta sets to train ML mod­els that will help ad­dress key prob­lems in the drug dis­cov­ery and de­vel­op­ment process. To en­able the ma­chine learn­ing, we will use high-qual­i­ty da­ta that has al­ready been col­lect­ed, but we will al­so in­vest heav­i­ly in the cre­ation of our own datasets us­ing high through­put ex­per­i­men­tal ap­proach­es, datasets that are de­signed ex­plic­it­ly with ma­chine learn­ing in mind from the very start. The ML mod­els that are de­vel­oped will then help guide sub­se­quent ex­per­i­ments, pro­vid­ing a tight, closed loop in­te­gra­tion of in sil­i­co and in vit­ro meth­ods (an in­sitro par­a­digm).”

Ac­cord­ing to Koller, the low hang­ing fruit in drug dis­cov­ery has been picked. Reach­ing high­er, go­ing for much bet­ter drugs, will re­quire “a dif­fer­ent ap­proach to drug de­vel­op­ment.” Spend­ing bil­lions to de­vel­op new drugs — and then pass­ing the cost to pa­tients — is not sus­tain­able.

In launch­ing in­sitro with a group of hy­per con­nect­ed back­ers, Koller is in­stant­ly mak­ing her­self a top play­er in a field that has Big Phar­ma’s rapt at­ten­tion. Stream­lin­ing R&D and im­prov­ing the odds of suc­cess find­ing high im­pact ther­a­pies are con­sid­ered keys to longterm prof­itabil­i­ty. But now the fo­cus is on which out­fits can ac­tu­al­ly de­liv­er.

There will be plen­ty of peo­ple watch­ing to see if Koller and the team she’s now re­cruit­ing can per­form. And she knows it won’t be easy. She writes:

There is a lot of hype to­day around ma­chine learn­ing, with hy­per­bol­ic promis­es that it will mag­i­cal­ly solve all of hu­mankind’s prob­lems (and dire warn­ings that it will lead to the de­struc­tion of hu­mankind). We at in­sitro don’t ex­pect ML to be the so­lu­tion to all of the prob­lems in drug de­vel­op­ment, nor to be the mag­ic bul­let that helps find a treat­ment for every dis­ease. How­ev­er, we do be­lieve that the time is right to re­think the drug de­sign process us­ing a dif­fer­ent and more mod­ern toolk­it, in the hope that a new par­a­digm may help us cure more peo­ple, soon­er, and at a much low­er cost.

I’d queried Koller re­cent­ly af­ter hear­ing word about in­sitro. For now, she tells me in a mes­sage, her blog post goes about as deep in­to this as she wants to go right now. But more is com­ing.


Im­age: Daphne Koller. STAN­FORD

Tesla and SpaceX founder Elon Musk gestures to the audience after being recognized by President Trump following the successful launch of a Falcon 9 rocket at the Kennedy Space Center. (via Getty Images)

Tes­la chief Elon Musk teams up with Covid-19 play­er Cure­Vac to build 'R­NA mi­cro­fac­to­ries'

Elon Musk has joined the global tech crusade now underway to revolutionize vaccine manufacturing — now aimed at delivering billions of doses of a new mRNA vaccine to fight Covid-19. And he’s cutting right to the front.

In a late-night tweet Wednesday, the Tesla chief announced:

Tesla, as a side project, is building RNA microfactories for CureVac & possibly others.

That’s not a lot to go on. But the tweet comes a year after Tesla’s German division in Grohmann and CureVac filed a patent on a “bioreactor for RNA in vitro transcription, a method for RNA in vitro transcription, a module for transcribing DNA into RNA and an automated apparatus for RNA manufacturing.” CureVac, in the meantime, has discussed a variety of plans to build microfactories that can speed up the whole process for a global supply chain.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 84,700+ biopharma pros reading Endpoints daily — and it's free.

George Yancopoulos (Regeneron)

UP­DAT­ED: Re­gen­eron co-founder George Yan­copou­los of­fers a com­bat­ive de­fense of the po­lice at a high school com­mence­ment. It didn’t go well

Typically, the commencement speech at Yorktown Central School District in Westchester — like most high schools — is an opportunity to encourage students to face the future with confidence and hope. Regeneron president and co-founder George Yancopoulos, though, went a different route.

In a fiery speech, the outspoken billionaire defended the police against the “prejudice and bias against law enforcement” that has erupted around the country in street protests from coast to coast. And for many who attended the commencement, Yancopoulos struck the wrong note at the wrong time, especially when he combatively challenged someone for interrupting his speech with a honk for “another act of cowardness.”

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 84,700+ biopharma pros reading Endpoints daily — and it's free.

Elias Zerhouni (Photo by Vincent Isore/IP3/Getty Images)

Elias Zer­houni dis­cuss­es ‘am­a­teur hour’ in DC, the de­struc­tion of in­fec­tious dis­ease R&D and how we need to prep for the next time

Elias Zerhouni favors blunt talk, and in a recent discussion with NPR, the ex-Sanofi R&D and ex-NIH chief had some tough points to make regarding the pandemic response.

Rather than interpret them, I thought it would be best to provide snippets straight from the interview.

On the Trump administration response:

It was basically amateur hour. There is no central concept of operations for preparedness, for pandemics, period. This administration doesn’t want to or has no concept of what it takes to protect the American people and the world because it is codependent. You can’t close your borders and say, “OK, we’re going to be safe.” You’re not going to be able to do that in this world. So it’s a lack of vision, basically just a lack of understanding, of what it takes to protect the American people.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 84,700+ biopharma pros reading Endpoints daily — and it's free.

Douglas Love, Annexon CEO (Annexon)

IPO bound? A Bay Area biotech grabs a mega-round on the road to a piv­otal neu­rode­gen­er­a­tion pro­gram

South San Francisco-based Annexon has added $100 million to its cash reserves, along with a new roster of marquee investors backing their play on the classical complement pathway involved in neurodegeneration. And that may well fit the profile for an IPO — though right now everything seems to be working on that score.

Eighteen months after Bain and their syndicate partners put up $75 million to fuel clinical work, Annexon is back at the trough. And this time they’re adding Redmile Group for the lead role, with supporting investments from these new arrivals: BlackRock, Deerfield Management Company, Eventide Asset Management, Farallon Capital Management, Janus Henderson Investors and Logos Capital.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 84,700+ biopharma pros reading Endpoints daily — and it's free.

Sec­ond death trig­gers hold on Astel­las' $3B gene ther­a­py biotech's lead pro­gram, rais­ing fresh con­cerns about AAV

Seven months after Astellas shelled out $3 billion to acquire the gene therapy player Audentes, the biotech company’s lead program has been put on hold following the death of 2 patients taking a high dose of their treatment. And there was another serious adverse event recorded in the study as well, with a total of 3 “older” patients in the study affected.

The incidents are derailing plans to file for a near-term approval, which had been expected right about now.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 84,700+ biopharma pros reading Endpoints daily — and it's free.

Look­ing for 'ex­ter­nal in­no­va­tion,' Boehringer In­gel­heim re­serves $500M+ for new Shang­hai hub

Now that Boehringer Ingelheim’s bet on contract manufacturing in China has paid off, the German drugmaker is anteing up more to get into the research game.

Boehringer has set aside $507.9 million (€451 million) for a new External Innovation Hub to be built in Shanghai over five years. The site will become one of its “strategic pillars” as the team strives to get 71 approvals — either for new products or indications — by 2030, said Felix Gutsche, president and CEO of Boehringer Ingelheim China.

Vas Narasimhan, Novartis CEO (Patrick Straub/​EPA-EFE/​Shutterstock)

No­var­tis pays $678M for kick­back scheme as Vas Narasimhan tries to dis­tance phar­ma gi­ant from shady be­hav­ior

Novartis has reached another large settlement to resolve misconduct allegations, agreeing to pay more than $678 million to settle claims that it had spent hundreds of millions of dollars on lavish dinners, so-called speaking fees and expensive alcohol “that were nothing more than bribes” to get doctors to prescribe Novartis medications.

The top-shelf alcohol and lavish meals included a $3,250 per person night at Nobu in Dallas, a $672-per person dinner at Washington DC’s Smith & Wollensky and a $314 per person meal at Sushi Roku in Pasadena, according to the Justice Department complaint. There were at least 7 trips to Hooters and fishing trips in Alaska and off the Florida coast. Each of these events were supposed to be “speaker programs” where doctors educated other doctors on a drug, but the DOJ alleged many were “bogus” wine-and-dine events where the drug was barely mentioned, if at all.  (“Nobody presented slides on the fishing trips,” the complaint says.)

No­vavax snags Ben Machielse for CMC and pro­motes a trio of staffers; Mar­ty Du­vall lands an­oth­er CEO post at On­copep­tides

Novavax has been making waves recently by securing a $384 million commitment from CEPI to cover R&D and manufacturing for its Covid-19 vaccine while also spending $167 million on a 150,000 square-foot facility. The Maryland biotech continues to shore up its leadership team as well, bringing in Ben Machielse as their EVP of CMC just a couple weeks after nabbing AstraZeneca vet Filip Dubrovsky as their new CMO. Machielse was president and CEO of Vtesse from 2014-17, and before that, he also spent more than 11 years at MedImmune and was EVP of operations for the back half of his tenure.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 84,700+ biopharma pros reading Endpoints daily — and it's free.

Dan Gold, MEI Pharma CEO

De­vel­op­ment part­ners at MEI, Helsinn dump a high-risk PhI­II AML study af­ter con­clud­ing it would fail sur­vival goal

Four years after Switzerland’s Helsinn put $25 million of cash on the table for an upfront and near-term milestone to take MEI Pharma’s drug pracinostat into a long-running Phase III trial for acute myeloid leukemia, the partners are walking away from a clinical pileup.

The drug — an HDAC inhibitor — failed to pass muster during a futility analysis, as researchers concluded that pracinostat combined with azacitidine wasn’t going to outperform the control group in the pivotal.