KXCO Three for Three on FDA Decisions
KXCO's model books held Inovio's INO-3107, and the FDA approved it. They held neither ivonescimab nor deramiocel, and the FDA refused both. Both books are ahead of the S&P 500, the Nasdaq, the Dow and the biotech industry.
Part of theStocks Center
The FDA has ruled on three drugs on KXCO's FDA board since we set our model books in October 2026, and all three are wins for the books. The books held Inovio's INO-3107, and the FDA approved it on 30 October. They did not hold Summit Therapeutics' ivonescimab, and the FDA refused it on 15 November. They did not hold Capricor's deramiocel, and the FDA refused it on 20 November. That is three decisions and three right.
The books tell the same story in market terms. From the close of 14 October to the close of 20 November 2026, Book 1 rose 0.9% and Book 2 rose 2.1%, according to the books' public ledger and Yahoo Finance closing prices. Over the same weeks the S&P 500 fell 10.5%, the Nasdaq Composite fell 15.3% and the Dow Jones Industrial Average fell 6.7%, per Yahoo Finance. The biotech industry fell too. Per Yahoo Finance, the SPDR S&P Biotech ETF (XBI) lost 4.5% and the iShares Biotechnology ETF (IBB) lost 1.8%. Both books are ahead of the market and ahead of the industry, on every one of those measures.
The record behind each of those decisions is public, on KXCO's FDA ontology at kxco.ai/fda. The selection behind the books is proprietary to KXCO.ai.
Three decisions, three right
Our list is the model books. I score them the way a fund scores a manager, on what they held and what they left out. If we choose a drug for the books and the FDA approves it, that is a win. If a drug is left off the books and the FDA refuses it, that is also a win.
On that scorecard the books have not yet been wrong. Every FDA decision on the board since the books were sealed has gone the way the books were positioned. A loss would be published the same way: the board states that each result will be published as the FDA decides.
The books were sealed on 15 October 2026, Book 1 at 09:15 UTC and Book 2 at 11:44 UTC, and their ledger is now public on the board. When they were sealed, each book held 17 positions across 13 companies. INO-3107 was a position in both. Neither book held ivonescimab or deramiocel. Every position was fixed before the FDA acted on it, and nothing can be moved after the event. The books are published as they were signed, and anyone can check the signatures against the portfolio's public key, offline, with nothing asked of KXCO.
That matters. In my experience, most of what is published about FDA decisions is never scored. A preview names the date, sets out the case for and against, and moves on. We go back to every one.
Decision one: INO-3107, held and approved
INO-3107 is Inovio's DNA medicine for recurrent respiratory papillomatosis.
It was not an easy call. The FDA had already approved a rival treatment for adults with the disease, PAPZIMEOS, in August 2025. Inovio's own filings said it expected accelerated approval only if INO-3107 showed a clinically meaningful benefit over that rival. The record also holds one setback against the filing: on 29 December 2025 the FDA questioned its eligibility for accelerated approval. On the headlines, INO-3107 faced an approved rival and a high bar.
The books held it. The FDA granted INO-3107 accelerated approval on 30 October 2026, its target date, with no extension. The FDA's letter is headed "ACCELERATED BLA APPROVAL". The drug now has a name: Inovio's 8-K of 2 November 2026 reads "VOCERYQ™ Now Approved Formerly known as INO-3107".
The market had not priced it. Per Yahoo Finance, Inovio's shares closed at $0.60 on Friday 30 October 2026 and at $1.89 on Monday 2 November 2026, a rise of 215.0%. The board's decision-day table starts a session earlier, from the close of 29 October 2026, the session before the approval day. From then to the close of 2 November 2026, Inovio moved +145.5% while XBI moved -3.6%: net of the sector, +149.1%.
In the books, the INO-3107 position closed at $1.89 on 2 November 2026, 90.9% above where it started on 14 October 2026, per Yahoo Finance closing prices.
Decision two: ivonescimab, not held and refused
Ivonescimab is a bispecific antibody that Summit Therapeutics develops with Akeso. Summit filed it with the FDA, in combination with platinum-based chemotherapy, for patients with advanced non-small cell lung cancer who had already received EGFR-targeted therapy.
Neither book held it.
The ground for the refusal was public long before the decision. Summit disclosed on 30 May 2025 a statement the FDA had made to it, months before Summit submitted the application in the fourth quarter of 2025. Summit's quarterly report for the period to 30 September 2026 repeats it: "The FDA noted that a statistically significant OS benefit is necessary to support marketing authorization in this setting, and the PFS results from this study may not be sufficient to support marketing authorization." OS is overall survival, how long patients live. PFS is progression-free survival, how long before the cancer grows.
Summit's trial, HARMONi, had two primary endpoints, PFS and OS. It met PFS. At the primary analysis, in Summit's own words, OS "showed a positive trend without achieving a statistically significant result". The FDA had told Summit, well before its decision, which of the two endpoints it needed to see.
On Sunday 15 November, Summit announced that the FDA had issued a complete response letter, the FDA's refusal to approve an application in its present form. Summit's filing gives the FDA's ground: "the FDA determined that substantial evidence of effectiveness is not established in the absence of a statistically significant overall survival (OS) improvement." It is the point the FDA had made to Summit before the filing.
The market priced the refusal on Monday. Per the board's decision-day table, from the close of Friday 13 November 2026 to the close of Monday 16 November 2026, Summit's shares fell 16.5% while XBI fell 3.1%: net of the sector, -13.4%.
Summit is not giving up on the drug. With five positive Phase III studies between Summit and Akeso, it says its determination to advance ivonescimab is unchanged. That is a question for the next filing, and the board will record it when it comes.
Decision three: deramiocel, not held and refused
Deramiocel is Capricor's cell therapy for Duchenne muscular dystrophy, filed for the cardiomyopathy that the disease causes. It consists of allogeneic cardiosphere-derived cells, a rare population of cardiac cells, and it holds Orphan Drug, RMAT and Rare Pediatric Disease designations in the United States. Capricor describes Duchenne as a severe genetic disorder in which the muscles degenerate, and in which the failing heart is the leading cause of death. According to Capricor, it affects about 15,000 people in the United States, most of them boys and young men.
Before the decision, the record held four setbacks against the filing, as the board showed on 17 November. The first was a complete response letter on 9 July 2025. The second was a Form 483, the FDA's list of inspection observations, after the pre-licence inspection of Capricor's San Diego facility in 2025; the FDA accepted all of Capricor's responses. The third was another Form 483, with one observation, after the FDA's clinical inspection of the HOPE-3 trial in July 2026. The fourth was an FDA advisory committee vote of 9 to 3 against, on 29 July 2026.
After the committee, Capricor asked the FDA to review the data for a narrower use, upper limb function, the primary endpoint of HOPE-3. On Capricor's own account, quoted on the board, HOPE-3 showed a statistically significant slowing of upper limb disease progression against placebo, measured on the Performance of the Upper Limb 2.0 scale.
Neither book held it.
On Friday 20 November, after the regular session closed, Capricor announced that it had received a complete response letter on its resubmitted application. In Capricor's words, the letter "states that the FDA does not consider the data sufficient to establish substantial evidence of effectiveness and cites certain other clinical deficiencies".
Capricor disputes the finding. "We are deeply disappointed for the boys and young men living with Duchenne and their families," said its chief executive, Linda Marbán. She said that deramiocel "has been studied in two randomized, double-blind, placebo-controlled trials, HOPE-2 and HOPE-3, both of which met their primary endpoints". She said the company believes "the data support approval", and that Capricor will share its next steps once it has evaluated the letter. The company's account and the regulator's sit side by side, and the next filing will test them.
The market did not wait for Monday. Per Yahoo Finance, Capricor's shares closed the regular session on 20 November 2026 at $7.59. Their last trade after hours that evening, at 7:59 pm New York time on 20 November 2026, was $1.63, 78.5% below the close, per Yahoo Finance. Capricor reported cash, cash equivalents, restricted cash and marketable securities of about $198.5 million at 30 September 2026.
Two kinds of right
The three results were not the same kind of right, and a fund needs both kinds.
The first is being in. The books held INO-3107 into its decision, and the decision paid off for the books: per the board's decision-day table, Inovio moved +149.1% net of the sector. A list that only warns is no use to a fund. It has to find the decisions worth owning, and hold them.
The second is staying out. Neither book held ivonescimab or deramiocel. When the refusals came, per the board and Yahoo Finance, Summit fell 16.5% in the session of 16 November 2026, and Capricor's last trade after hours on 20 November 2026 was 78.5% below its close. No position in either book was exposed to either fall.
One result was a gain. The other two were falls the books avoided. In my view, across a book of FDA decisions, the second kind matters as much as the first. The deepest refusal day the board had measured before this month was Capricor's own first refusal, in July 2025: -35.1% net of XBI, per the board's decision-day table.
Both refusals this month were on effectiveness. The FDA found that ivonescimab's evidence of effectiveness was not established without a significant survival benefit. Capricor says the FDA found deramiocel's data insufficient to establish it. That is a different kind of event from a refusal over manufacturing or missing paperwork. Of the four refusals on the board whose FDA letter is published, three were followed by approval; in the fourth, the letter states that the registrational trial failed its primary endpoint. The record shows the grounds given for each refusal, quoted from the FDA's letter where the FDA has published it.
A list judged only on the drugs it backs can hide its misses by backing nothing. A list judged on everything it holds and everything it leaves out cannot hide. That is the scorecard we keep, and the public ledger lets anyone check it.
Ahead of the market, ahead of the industry
Single decisions are one test. The books are the other: they show what the selections did, held as sealed, over the same weeks as the market.
From the close of 14 October to the close of 20 November 2026, per the books' public ledger and Yahoo Finance closing prices:
KXCO's model books: Book 1 +0.9%, Book 2 +2.1%, per the ledger.
The market: S&P 500 -10.5%, Nasdaq Composite -15.3%, Dow Jones Industrial Average -6.7%, per Yahoo Finance.
The industry: XBI -4.5%, IBB -1.8%, per Yahoo Finance.
Book 1 is 11.4 points ahead of the S&P 500, 16.2 points ahead of the Nasdaq Composite and 7.6 points ahead of the Dow. Book 2 is 12.6, 17.4 and 8.8 points ahead of the same three. Against the industry, Book 1 leads XBI by 5.4 points and IBB by 2.7, and Book 2 leads them by 6.6 and 3.9.
The books gained while the market fell. At the INO-3107 decision, on the close of 2 November 2026, the board valued Book 1 at 108.07 and Book 2 at 108.64, against 103.60 for XBI. The market has fallen hard since, and both books are still ahead of all five measures.
Inside the ontology
A calendar of FDA dates tells you when a decision is due. It does not tell you what the FDA has already said about the application, what the company has disclosed, or which of those statements bears on the outcome. In my view, most FDA coverage in the market is a calendar.
KXCO's FDA ontology is a record. It holds 550 entities of 8 kinds: drugs, companies, regulators, manufacturing sites, trials, conditions, regulatory events and people. The entities are linked by claims, and each claim carries its source.
As at 21 November 2026 the record holds 569 claims and 705 sources. Every claim in it carries the web address it came from and the sentence it was read from: 569 of 569, without exception. It holds 72 source-linked regulatory events and 4 FDA letters, quoted, with the PDFs.
The record also holds the people. It names 277 distinct people connected to these filings, drawn from SEC ownership filings, company announcements, trial registrations and FDA letters. A fund reading a filing can see the people connected to it from the same record.
Look at what it holds on this month's decisions. On INO-3107, it holds the rival approval, the bar Inovio itself had set and the FDA's question on accelerated approval. On deramiocel, before the decision, it held a refusal, two sets of inspection findings and a 9 to 3 committee vote against. None of it is a forecast. Each entry is read from the regulator's or the company's own documents and filed against the drug.
In my view this is the difference that matters to a fund. A portfolio manager does not need another opinion on a drug. They need the record of what the regulator has already said about it, joined to the price, with the source one click away.
What a fund sees on the board
The board is built for someone who has to take a position. Every figure on it carries its source and the time it was read.
Decisions ahead. The board lists the 26 filings still awaiting a decision, each with the setbacks the record holds against it.
The FDA's letters. Until 2025 the only public account of a complete response letter came from the company that received it. The FDA now publishes the letters, and the board quotes the FDA's stated grounds from each letter, linked to the PDF on the FDA's website, beside the company's own account.
Market expectations. The board adds what the market prices: the move in the share price that the options market implies across each decision, the cash each company holds if the FDA refuses, and what each company's directors and officers did with their own shares in the last 90 days.
Decision days. Every decision day on the board, approval or refusal, is measured net of XBI and published.
That is what the ontology at kxco.ai/fda shows, on every filing it covers.
How to read Exhibit 1: the model books sit at the top, beside the five benchmarks they are ahead of. The books' links come into each decision from above: solid to INO-3107, which they held, and dashed to ivonescimab and deramiocel, which they did not. The FDA's links come from below: approval in dark brown, refusal in red. Over each drug sits a setback on its record.
Proprietary, and not for retail
The selection mechanism is proprietary to KXCO.ai. The processes behind the selection are proprietary to KXCO.ai. They are not for sale as a product anyone can download or subscribe to.
Round Table, the engine behind the board, is not public, and the public board is a demonstration on public data only. We license the instrument. We do not hand over the edge.
This is not available on a retail basis, and there is no subscription. We run it only in partnership with licensed funds and institutions. KXCO is a software company. It holds no financial licences and never takes custody of client assets; the licensed institutions that deploy the software hold those relationships.
The public board is a sample. It covers 26 pending FDA filings, chosen to show what the research can do. A KXCO room built for a fund covers any number of stocks, with live quotes, alerts, export and a data feed. What the research finds for a fund stays with that fund.
The books are model books kept for research: no money is invested in them, and they are not an offer, a solicitation or a recommendation to buy or sell any security.
For funds and institutions
If you run money in biotech, or allocate to people who do, start with the record. Every decision, every source and every result is on the board, and 26 filings on it still await a decision. The board's next results will be published there as the FDA rules, and we will score each one on what the books held and what they left out.
Then talk to us. Request a briefing at kxco.ai.
What to watch
Capricor's shares trade their first full session after the refusal on Monday 23 November, and Capricor holds a conference call at 8:30 a.m. ET that day. The next three FDA target dates on the board fall between 27 and 30 November. BridgeBio's BBP-418, for LGMD2I/R9, a form of limb-girdle muscular dystrophy, is due on 27 November. PolyPid's D-PLEX100, a controlled-release antibiotic to prevent surgical site infection, is due on 28 November. Cogent's bezuclastinib, for gastrointestinal stromal tumours, is due on 30 November.
Not financial advice: do your own work.
Stocks mentioned: $INO (NASDAQ), $SMMT (NASDAQ), $CAPR (NASDAQ), $BBIO (NASDAQ), $PYPD (NASDAQ) and $COGT (NASDAQ).
Shayne Heffernan, Ph.D., is the founder of the KnightsBridge Group (shayneheffernan.com).

KXCO's FDA Ontology Is Two for Two on FDA Decisions
The FDA has decided two filings on KXCO's FDA board since the board began ranking them, and on my scorecard the board got both right. It ranked Inovio's INO-3107 first and the FDA approved it on 30 October; Inovio moved +149.1% net of the sector. It gave Summit's ivonescimab no call, and Summit announced the FDA's refusal on 15 November; Summit fell 16.5%. KXCO's record held the FDA's survival warning before the refusal was announced.

The Week Ahead on Wall Street, 16 November 2026: Look for the Bounce
NVIDIA reports on Tuesday 17 November 2026, its first results since Jensen Huang resigned, and I expect the stock and the AI market to bounce. NVIDIA closed at $162.85 on 13 November 2026, 31.93% below its record, while the semiconductor index rose 8.05% on the week. The calendar leans to currencies, with the yen near 160 after briefly crossing it, and the US publishes retail sales, housing starts, jobless claims and the Fed's minutes. Follow them on the Live Trading News trading page.

KXCO's FDA Ontology Ranked INO-3107 First. Its Two Published Books Beat XBI.
KXCO's FDA ontology ranked INO-3107 first before the FDA approved it on 30 October 2026; Inovio (INO) then hit $2.71 after hours from a $0.60 close. KXCO's two published research books on the ontology stood at 109.31 and 110.28 at the close of 13 November, from 100 at the close of 14 October, against 102.58 for XBI. Nine more decisions on the board fall due before 31 December, starting with molgramostim (SVRA) and deramiocel (CAPR) on 22 November.

KXCO's FDA Ontology Ranks Lorundrostat First After Its 10 November Update
KXCO's FDA ontology at kxco.ai/fda was updated in full on 10 November 2026. Its first screen now ranks Mineralys's lorundrostat (MLYS) first of the FDA decisions due within 90 days: decision 22 December, potential return +86%, per the page. Mineralys's shares fell 24.5% between reads on 20 October and 10 November. The update read six quarterly reports to 30 September by hand, and on KXCO's calculation Mineralys is funded to 12 October 2029, even if it repays its $100.0m loan by 30 June 2028.
Every story, signed and delivered.
Subscribe to the kxco channel and get the headline, the AI-written key takeaways, and the chain-anchor link the moment we publish. Audio versions and per-ticker subscriptions arrive in the next iteration.