Clinically Validated Pathology-based AI Prediction of Remdesivir-specific Post-treatment Rebound of SARS-CoV-2
Clinically Validated Pathology-based AI Prediction of Remdesivir-specific Post-treatment Rebound of SARS-CoV-2
SWITZERLAND, THURSDAY, 30 APRIL 2020 13:10 PM CET
INTRODUCTION
As the world’s first AI-biopharma company that has discovered and publicized the precise aetiology and pathology of COVID-191, we are committed to the non-profit dissemination of our COVID-19 discoveries and the public validation of our COVID-19 clinical predictions.
Although remdesivir was almost universally believed as the most promising curative treatment candidate for COVID-19 based on strong compassionate use data2 and in vitro data3 published in January 2020, we announced a contrarian pathology-based clinical prediction on 23 February 2020 that remdesivir would be an effective but non-curative treatment for severely ill COVID-19 patients and remdesivir would present the clinical risk of post-treatment viral rebound:
“Remdesivir, as a COVID-19 treatment currently in clinical trial, does not directly interfere with PI3K signalling in host cells. Remdesivir would have significant clinical benefit of in-treatment reduction of intracellular viral replication, but it would also induce latent infection of COVID-19 in host cells. Remdesivir would have significant clinical risk of out-of-treatment rebound of intracellular viral replication for moderately-to-severely symptomatic patients.”4
DATA VALIDATION
On 29 April 2020, the results of the world’s first clinical trial of remdesivir for severely ill COVID-19 patients, “Remdesivir in adults with severe COVID-19: a randomised, double-blind, placebo-controlled, multicentre trial”5, was published in the Lancet. This trial adopted a rigorously designed protocol with one of the strictest primary endpoints and participation criteria and analyzed the data collected from 236 severely ill patients in the intention-to-treat population.
As remdesivir’s mechanism of action is to inhibit RNA replicase without which SARS-CoV-2 cannot replicate in host cells, the efficacy of remdesivir as a treatment for COVID-19 largely depends on its efficacy on inhibiting viral load. Therefore, multiple-site specimens from all the 236 severely patients were collected on both in-treatment days (days 1, 3, 5, 7 and 10) and out-of-treatment days (days 14, 21 and 28) to evaluate remdesivir’s effect on viral load by quantitative PCR5:

Despite different sites of viral specimens as shown in Figure 35, the out-of-treatment viral load significantly rebounded compared with the placebo group on days 21 and 28, though the in-treatment viral load numerically reduced compared with the placebo group on days 5 and 7.

Despite different times of remdesivir treatments as shown in Figure S65, the out-of-treatment viral load significantly rebounded compared with the placebo group on days 21 and 28, though the in-treatment viral load numerically reduced compared with the placebo group on days 5 and 7.
Therefore, this human clinical trial data have robustly validated our contrarian prediction that post-treatment viral rebound is a remdesivir-specific clinical risk for severely ill COVID-19 patients no matter when to start the treatment and where to collect the specimen.
The clinical trial data further demonstrate that AI-based disease modelling and clinical predictions can deliver much better predictive power and explanatory power than conventional approaches for novel diseases with limited clinical data and short response timeframes.
UNBIASED TREATMENTS
As much as it is disappointing to see that remdesivir had exhibited the most potent antiviral efficacy in cell lines but failed to show clinically meaningful antiviral efficacy in human patients, it is alarming to know that the biased mechanism of action of remdesivir that targets only viral replication is a mismatch to the unbiased mechanism of action of SARS-CoV-2 that balances viral replication and viral spread, as we have predicted and published since 7 March 20206:
“SARS-CoV-2 is fundamentally different from all the other viruses that the world has hitherto known.”1
“Severe acute respiratory syndrome (SARS) coronavirus 2 (SARS-CoV-2) adopts a unique unbiased survival strategy of balancing viral replication with viral spread, in stark contrast to other viruses that typically trade off one against the other.”1
“In accordance with the unbiased survival strategy of SARS-CoV-2 that balances viral replication and viral spread, the effective treatment for COVID-19 must also be unbiased such that both viral replication and host immunomodulation are equally targeted. ”
Therefore, the rational discovery of unbiased COVID-19 treatments and vaccines that target the exact mechanisms of SARS-CoV-2 for both viral replication and host immunomodulation may be the only effective means to put an end to the COVID-19 pandemic.
To that end, Demiurge is also the world's first company that has discovered the complete set of unbiased prophylactic and therapeutic treatments for COVID-19:
- Irinotecan + etoposide as a specialized treatment for critically ill patients (ongoing phase 2 clinical trial NCT04356690).
- PI3K inhibitors as a curative treatment for moderately-to-severely ill patients (ongoing in vitro study).
- Non-S-viral-protein optimal target for a broad-spectrum vaccine for the healthy population (ongoing early-stage development).
REFERENCES
1. Lovetrue, B. The AI-Discovered Aetiology of COVID-19 and Rationale of the Irinotecan+Etoposide Combination Therapy for Critically Ill COVID-19 Patients. (2020). doi:10.20944/PREPRINTS202003.0341.V1
2. Holshue, M. L. et al. First case of 2019 novel coronavirus in the United States. N. Engl. J. Med. 382, 929–936 (2020).
3. Wang, M. et al. Remdesivir and chloroquine effectively inhibit the recently emerged novel coronavirus (2019-nCoV) in vitro. Cell Res. 30, 269–271 (2020).
4. Demiurge AI Discovers the Clinical Benefits and Risks of Remdesivir, Chloroquine, and PI3K inhibitors against 2019 Novel Coronavirus (COVID-19) - English. Available at: https://www.demiurge.technology/blog/demiurge-ai-discovers-the-clinical-benefits-and-risks-of-remdesivir. (Accessed: 30th April 2020)
5. Wang, Y. et al. Remdesivir in adults with severe COVID-19: a randomised, double-blind, placebo-controlled, multicentre trial. Lancet. (2020).
6. Demiurge AI Discovers the Complete Aetiology of COVID-19 and the Optimal Treatment Strategy for COVID-19 - English. Available at: https://www.demiurge.technology/blog/demiurge-ai-discovers-the-complete-aetiology-of-covid-19-and-the-optimal. (Accessed: 30th April 2020)
About Demiurge Technologies AG
Demiurge Technologies is a research-based AI-biopharmaceutical company that transforms publicly available life science data into precise disease models in areas with unmet medical needs. The company pioneers a self-correcting scientific approach that validates disease models with the accuracy of AI-based predictions of phase 3 clinical trial outcomes. The company also pioneers a self-sustaining business that commercializes disease models by accelerating the AI-based discovery and development of innovative medicines. Demiurge started in 2016 with headquarters in Switzerland.
AI has been an emerging powerful approach to deeper disease understanding and faster drug discovery, yet it must be put to the most rigorous test to prove its worth under public scrutiny. Demiurge has predicted the outcomes of more than 90 phase 3 clinical trials across multiple therapeutic areas and achieved more than 80% accuracy. Furthermore, we have been inviting the public to witness our future predictions of clinical trial outcomes on Twitter (@DemiurgeTech).
Therefore, we officially put forward AI-based discoveries of the complete aetiology and pathology of COVID-19 and the candidate treatments for COVID-19 as scientific hypotheses only and invite the world to validate their potential to solve the unprecedented global crisis posed by COVID-19.
Disclaimers
This material is intended for information purposes only and is provided without any warranty of any kind, either expressed or implied. These statements are not guarantees of future performance, condition or results. Figures and graphs in this presentation are for illustration only and may not match the actual scale. This presentation contains certain forward-looking statements. These forward-looking statements may be identified by words such as ‘predicts’, ‘believes’, ‘expects’, ‘anticipates’, ‘projects’, ‘intends’, ‘should’,‘seeks’, ‘estimates’, ‘future’ or similar expressions or by discussion of, among other things, strategy, goals, plans or intentions. Various factors may cause actual results to differ materially in the future from those reflected in forward-looking statements contained in this presentation, among others: 1 pricing and product initiatives of competitors; 2 legislative and regulatory developments and economic conditions; 3 delay or inability in obtaining regulatory approvals or bringing products to market; 4 fluctuations in currency exchange rates and general financial market conditions; 5 uncertainties in the discovery, development or marketing of new products or new uses of existing products, including without limitation negative results of clinical trials or research projects, unexpected side-effects of pipeline or marketed products; 6 increased government pricing pressures; 7 interruptions in production; 8 loss of or inability to obtain adequate protection for intellectual property rights; 9 litigation; 10 loss of key executives or other employees. Demiurge Technologies AG (“Demiurge”) undertakes no duty or obligation to publicly update or revise the forward-looking statements or other information contained in this presentation. You should not view information related to the past performance of Demiurge and its affiliates or information about the market, as indicative of future results, the achievement of which cannot be assured. While some information used in this document may have been obtained from various published and unpublished sources considered to be reliable, Demiurge neither guarantees its accuracy or completeness nor accepts liability for any direct or consequential losses arising from its use. Amounts and percentages may reflect rounding adjustments, and consequently totals may not appear to sum. None of the information in this presentation does, by itself, constitute an offering or an offering circular according to Article 652a of the Swiss Code of Obligations and is subject to change without notice. Any offer or solicitation with respect to any securities that may be issued by Demiurge will be made only by means of definitive offering memoranda or prospectus, which will be provided to prospective investors and will contain material information that is not set forth herein, including risk factors relating to any such investment. Before making an investment, you must obtain and carefully read all information needed to evaluate the investment, including, but not limited to the documents providing important disclosures regarding risks, fees and expenses. An investment in Demiurge may be volatile and can suffer from adverse or unexpected market moves or other adverse events. Investors may suffer the loss of their entire investment. An investment in Demiurge will be discrete from an investment in any funds or other investment programs managed by Demiurge and the results or performance of such other investment programs is not indicative of the results or performance that will be achieved by Demiurge or such investment programs.
Media Inquiry:
covid2019@demiurge.technology