Yiannis Kiachopoulos and Artur Saudabayev, co-founders of Causaly

Lon­don AI up­start, which counts No­var­tis as a cus­tomer, can teach your com­put­er to read

When Ama­zon de­vel­oped a ma­chine-learn­ing tool to make its re­cruit­ment process more ef­fi­cient — the man-made sys­tem ab­sorbed the gen­der-bias of its hu­man mak­ers, and the project was abort­ed. In the field of bio­phar­ma­ceu­ti­cals, the way re­searchers train their ma­chine learn­ing al­go­rithms can skew the out­come of pre­dic­tions. But be­fore those pre­dic­tions can be made, the en­gine must learn to read to make sense of ex­plo­sive vol­ume of knowl­edge out there.

That is what Lon­don-based Causaly has set out to do, and has raised $4.8 mil­lion as it works on re­fin­ing its tech­nol­o­gy, co-founder Yian­nis Ki­a­chopou­los told End­points News in an in­ter­view.

The key is­sue is find­ing ev­i­dence in the first place be­cause 90% to 95% of search re­sults are noise, he said. “The prob­lem that we’re solv­ing is find­ing the ev­i­dence in the first place. The read­ing part and the judg­ment part is still up to the hu­man.”

Mil­lions of bio­med­ical ar­ti­cles have been pub­lished so far, and thou­sands are added each month. The tiny 11-per­son start­up Causaly, which is work­ing with No­var­tis and a host of oth­er bio­phar­ma­ceu­ti­cal com­pa­nies, has de­vel­oped ar­ti­fi­cial in­tel­li­gence tech­nol­o­gy that process­es lan­guage from this avalanche of pub­lished bio­med­ical da­ta — and is de­signed to ex­tract causal re­la­tion­ships the way hu­mans can — ex­cept faster and more ef­fi­cient­ly.

The tech­nol­o­gy is de­signed to iso­late rel­e­vant da­ta and make it vi­su­al­ly ac­ces­si­ble and that’s what sci­en­tists want, Ki­a­chopou­los said. “Our users are specif­i­cal­ly ask­ing us not to make these judg­ments for them…and that’s how we see our­selves as aug­ment­ing hu­mans and not kind of re­plac­ing judg­ments or any­thing like that, that gets more prob­lem­at­ic.”

Users are giv­en the op­tion of us­ing fil­ters, for in­stance, they can iso­late da­ta that em­anates on­ly from ran­dom­ized clin­i­cal tri­als or from jour­nals with a de­fined ‘im­pact fac­tor’ or ar­ti­cles that have been pub­lished dur­ing a spe­cif­ic time pe­ri­od. The plat­form is not judg­ing whether that ev­i­dence is cred­i­ble, he said. “We leave the judg­ment to the hu­man, but we give the hu­man the tools to make the judg­ment in a bet­ter way.”

There is an­oth­er lay­er of bias en­trenched in da­ta — and that is lin­guis­tic bias. Nei­ther Causaly’s tech­nol­o­gy nor hu­mans can ful­ly elim­i­nate that be­cause cul­tur­al con­texts play a key role in the way da­ta is processed and ar­tic­u­lat­ed, he added.

Causaly raised $1 mil­lion in seed fund­ing last year, and this in­jec­tion of se­ries A cap­i­tal was led by Pen­tech and EBRD Ven­ture Cap­i­tal, with par­tic­i­pa­tion from ex­ist­ing in­vestors, in­clud­ing Marathon Ven­ture Cap­i­tal.

It is hard­ly the first AI com­pa­ny at­tempt­ing to as­sist de­ci­sion-mak­ers in the fields of phar­ma­ceu­ti­cals and health care to ag­gre­gate and syn­the­size in­for­ma­tion. A grow­ing list of star­tups in­clud­ing Am­plion, Biore­late, Da­ta4Cure, Ev­id Sci­ence, Inno­plexus, In­ve­ni­AI, Lin­gua­mat­ics, Meta, Plex Re­search, Quer­tle, Re­search­ably and nfer­ence are all work­ing on ways to help sci­en­tists and re­searchers di­gest and make in­fer­ences from the del­uge of bi­o­log­i­cal da­ta on of­fer to­day.

Mean­while the tra­di­tion­al, and large­ly free, search tools haven’t ex­act­ly be­come ob­so­lete. “When I talk to our cus­tomers, our biggest com­peti­tor is the sta­tus quo,” not­ed Ki­a­chopou­los. “And that is Google Schol­ar, PubMed.”

Novartis CEO Vas Narasimhan (via AP Images)

Go­ing 0-for-4 on a big PhI­II pro­gram, No­var­tis scraps their top asth­ma prospect and sig­nal big trou­ble for a lit­tle biotech

Novartis this morning reported that their asthma drug fevipiprant flunked two more Phase III studies, crushing their hopes in what had been a star H2 development program at the pharma giant.

Back in October Novartis buried the news that fevipiprant had failed the first 2 Phase III studies in their Q3 report, noting a lack of success in scoring an improvement in FEV1 among moderate patients. But the pharma giant immediately shifted focus to LUSTER 1 and 2 in moderate to severe patients, noting that they were the core studies needed for registration and a blockbuster future.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 67,600+ biopharma pros reading Endpoints daily — and it's free.

Amarin CEO John Thero discussing the company's plans for Vascepa, August 2019 — via Bloomberg

Amarin wins a block­buster ap­proval from the FDA. Now every­one can shift fo­cus to the patent

For all those people who could never quite believe that Amarin $AMRN would get an expanded label with blockbuster implications, the stress and anxiety on display right up to the last minute on Twitter can now end. But new, pressing questions will immediately surface now that the OK has come through.

On Friday afternoon, the FDA stamped its landmark approval on the industrial strength fish oil for reducing cardio risks for a large and well defined population of patients. The approval doesn’t give Amarin everything it wants in expanding its use, losing out on the primary prevention group, but it goes a long way to doing what the company needed to make a major splash. The approval was cited for patients with “elevated triglyceride levels (a type of fat in the blood) of 150 milligrams per deciliter or higher. Patients must also have either established cardiovascular disease or diabetes and two or more additional risk factors for cardiovascular disease.”

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 67,600+ biopharma pros reading Endpoints daily — and it's free.

Sarep­ta was stunned by the re­jec­tion of Vyondys 53. Now it's stun­ning every­one with a sur­prise ac­cel­er­at­ed ap­proval

Sarepta has a friend in the FDA after all. Four months after the agency determined that it would be wrong to give Sarepta an accelerated approval for their Duchenne MD drug golodirsen, regulators have executed a stunning about face and offered the biotech a quick green light in any case.

It was the agency that first put out the news late Thursday, announcing that Duchenne MD patients with a mutation amenable to exon 53 skipping will now have their first targeted treatment: Vyondys 53, or golodirsen. Having secured the OK via a dispute resolution mechanism, the biotech said the new drug has been priced on par with their only other marketed drug, Exondys 51 — which for an average patient costs about $300,000 per year, but since pricing is based on weight, that sticker price can even cross $1 million.

Sarepta shares $SRPT surged 23% after-market to $124.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 67,600+ biopharma pros reading Endpoints daily — and it's free.

Paul Biondi (File photo)

Paul Biondi's track record at Bris­tol-My­ers cov­ered bil­lions in deals of every shape and size. Here's the com­plete break­down

Paul Biondi was never afraid to bet big during his stint as business development chief at Bristol-Myers Squibb. And while the gambles didn’t all pay out, by any means, his roster of pacts illustrates the broad ambitions the pharma giant has had over the last 5 years — capped by the $74 billion Celgene buyout.

On Thursday, we learned that Biondi had exited the company. And Chris Dokomajilar at DealForma came up with the complete breakdown on every buyout, licensing pact and product purchase Bristol-Myers forged during his tenure in charge of the BD team at one of the busiest companies in biopharma.

Endpoints Premium

Premium subscription required

Unlock this article along with other benefits by subscribing to one of our paid plans.

Paul Biondi (File photo)

Bris­tol-My­er­s' strat­e­gy, BD chief Paul Bion­di ex­it­ed the com­pa­ny — just ahead of the $74B Cel­gene deal close

Paul Biondi, who orchestrated billions of dollars in deals for Bristol-Myers Squibb over the 5 years he’s run their business development team, has exited the company. Biondi left last month, according to a company spokesperson, in pursuit of another — unspecified — external opportunity.

After 17 years with Bristol-Myers Squibb, Paul Biondi, Head of Strategy and Business Development, decided to leave the company to pursue an external opportunity. The company wishes him well in his new endeavors. Bristol-Myers Squibb  is actively searching for Paul’s successor, and will make an announcement, as appropriate.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 67,600+ biopharma pros reading Endpoints daily — and it's free.

Arie Belldegrun at UKBIO 2019. Shai Dolev for Endpoints News

Kite Phar­ma's ex-CEO con­tra­dicts founder as CAR-T patent tri­al heats up, with con­flict­ing val­u­a­tions

Two days after Kite Pharma founder Arie Belldegrun told a federal courtroom that a meeting he had with a Memorial Sloan Kettering executive wasn’t about licensing their immunotherapy patent, Kite’s ex-CEO Aya Jakobovits said it was.

The admission came Tuesday during cross-examination in a patent infringement case that features two of the biggest cancer biotechs and some of the most well-known names in American medicine.

Jakobovits initially said she was not in attendance, didn’t know it was going to happen and didn’t know what took place, according to Law360. But then the plaintiff’s lawyer handed her a document – whose contents were not publicly revealed – and asked again if she learned after-the-fact that the meeting involved a potential patent license.

“Yes,” Jakobovits eventually said.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 67,600+ biopharma pros reading Endpoints daily — and it's free.

On the heels of promis­ing MCL da­ta, Kite hus­tles its 2nd CAR-T to the FDA as the next big race in the field draws to the fin­ish line

Three days after Gilead’s Kite subsidiary showed off stellar data on their number 2 CAR-T KTE-X19 at ASH, the executive team has pivoted straight to the FDA with a BLA filing and a shot at a near-term approval.

In a small, 74-patient Phase II trial reported out at the beginning of the week, investigators tracked a 93% response rate with two out of three mantle cell lymphoma patients experiencing a complete response.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 67,600+ biopharma pros reading Endpoints daily — and it's free.

What does $6.9B buy these days in on­col­o­gy R&D? As­traZeneca has a land­mark an­swer

Given the way the FDA has been whisking through new drug approvals months ahead of their PDUFA date, AstraZeneca and their partners Daiichi Sankyo may not have to wait until Q2 of next year to get a green light on trastuzumab deruxtecan (DS-8201).

The pharma giant this morning played their ace in the hole, showing off why they were willing to commit to a $6.9 billion deal — with $1.35 billion in a cash upfront — to partner on the drug.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 67,600+ biopharma pros reading Endpoints daily — and it's free.

Arie Belldegrun (Photo: Jeff Rumans for Endpoints News)

Ju­ry finds Gilead li­able for $585M and big roy­al­ties in Kite CAR-T patent case

A Kite deal that’s already become a burden on Gilead’s back just got heavier as a California jury has ruled Gilead must pay Bristol-Myers Squibb and Sloan Kettering $585 million plus a 27.6% royalty for patent infringement committed by its subsidiary. The ruling is almost certain to be appealed.

Kite Pharma — founded by Arie Belldegrun, now focused on a next-gen CAR-T company — has been facing a lawsuit since the day its first CAR–T therapy won approval in October, 2017. Juno Therapeutics and Sloan Kettering filed a complaint saying Kite had copied its technology. Gilead acquired Kite in June of that year for $11.9 billion.  Juno was acquired the following year by Celgene for $9 billion, before Celgene was acquired by Bristol-Myers Squibb in 2019.

Endpoints News

Keep reading Endpoints with a free subscription

Unlock this story instantly and join 67,600+ biopharma pros reading Endpoints daily — and it's free.