How can AI accelerate the COVID-19 research?

Angeliki Andrianopoulou
published on February 12, 2020


In December 2019, a series of respiratory infection cases emerged in Wuhan City, China. After sequencing analysis, they have been attributed to a new betacoronavirus, called COVID-19 (previously reported as 2019-nCoV). Symptoms range from mild to severe and might appear even 14 days after exposure. Up to date, there are approximately 43,000 confirmed cases from 25 countries with more than 1,000 deaths and the World Health Organization (WHO) has declared the virus outbreak a public health emergency (1).

Beyond the suggested preventive measures, the current approach for treating the COVID-19 is based on the molecular pathway similarities with other betacoronaviruses, such as the Severe Acute Respiratory Syndrome-CoV (SARS-CoV) and the Middle East Respiratory Syndrome-CoV (MERS-CoV) (2). Researchers are currently investigating whether existing treatments are effective for the new coronavirus infection (3).

Given the severity of the situation, there is an urgency to find appropriate preventive strategies and identify novel targets for developing effective medications.

Machine-reading literature to map existing treatment options

The Causaly platform allows to obtain a high-level view of all pharmacological substances that have been previously reported in literature as potential treatment options for the betacoronavirus genus. Within seconds, the platform surfaces 131 substances that can be further investigated by previewing the machine-read articles (Image 1). Among the most prominent ones are Type I interferon, chloroquine and the antiviral drugs lopinavir and ribavirin, which have been characterized as potent inhibitors of the SARS-CoV and MERS-CoV spread (4, 5, 6, 7).

Image 1. Potential treatments for the betacoronavirus genus.

Understanding the disease mechanism

In addition to treatment options, Causaly AI allows users to find biomarker genes and potential molecular targets of a disease. In the case of the betacoronavirus genus, a total of 89 results are found (Image 2). At the top of the list, Transmembrane Serine Protease 2 (TMPRSS2) gene expression is shown to induce SARS spread. Taking a closer look at the underlying evidence, it has been reported that the TMPRSS2 might promote the SARS-CoV spread by activating the spike protein SARS S (8). Notably, it has been recently found that the COVID-19 also uses the cellular protease TMPRSS2 for entry into target cells (9).

Image 2. Genes related to the betacoronavirus genus.

Having identified a potential molecular pathway, we can then explore the pharmaceutical molecules that suppress the TMPRSS2 gene expression or inhibit TMPRSS2. The result set is comprised of 12 drug candidates that are currently used in a broad set of conditions (Image 3). Researchers might infer that these drug substances could also be considered as potential treatments for the COVID-19. Indeed, camostat, the serine protease inhibitor surfaced by Causaly, has been recently suggested by Hoffmann et al. as a drug candidate for the treatment of the COVID-19 (9).

Following the same rationale, Causaly allows to rapidly inspect similar relationships for all the other genes related to the CoV molecular signaling.

Image 3. TMPRSS2 protein and related pharmacologic substances.

Overall, Causaly’s AI platform enables the rapid identification of all previously reported drugs for the betacoronavirus genus and also uncovers relationships that would not be obvious by traditional literature review search. AI-assisted algorithms could be useful in exploring promising drug candidates and especially in such health emergency situations where researchers and health officials should act quickly and efficiently in order to provide appropriate treatments.

Causaly’s dataset has been provided to the Global Health Drug Discovery Institute (GHDDI) for supporting the COVID-19 research (10).

If you are a researcher or health official and you are interested in using Causaly for the COVID-19 research, contact us to request access.


  1. WHO:Novel Coronavirus(2019-nCoV) Situation Report – 21, retrieved from
  2. Huang, Chaolin, et al. "Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China." The Lancet (2020).
  3. Wang, Manli, et al. "Remdesivir and chloroquine effectively inhibit the recently emerged novel coronavirus (2019-nCoV) in vitro." Cell Research (2020): 1-3.
  4. Widagdo, W., et al. "Host determinants of MERS-CoV transmission and pathogenesis." Viruses 11.3 (2019): 280.
  5. Arabi, Yaseen M., et al. "Treatment of Middle East respiratory syndrome with a combination of lopinavir-ritonavir and interferon-β1b (MIRACLE trial): study protocol for a randomized controlled trial." Trials 19.1 (2018): 81.
  6. Vincent, Martin J., et al. "Chloroquine is a potent inhibitor of SARS coronavirus infection and spread." Virology journal 2.1 (2005): 69.
  7. Kawase, Miyuki, et al. "Simultaneous treatment of human bronchial epithelial cells with serine and cysteine protease inhibitors prevents severe acute respiratory syndrome coronavirus entry." Journal of virology 86.12 (2012): 6537-6545.
  8. Glowacka, Ilona, et al. "Evidence that TMPRSS2 activates the severe acute respiratory syndrome coronavirus spike protein for membrane fusion and reduces viral control by the humoral immune response." Journal of virology 85.9 (2011): 4122-4134.
  9. Hoffmann, Markus, et al. "The novel coronavirus 2019 (2019-nCoV) uses the SARS-coronavirus receptor ACE2 and the cellular protease TMPRSS2 for entry into target cells." bioRxiv (2020).
  10. Targeting 2019-nCoV: GHDDI Info Sharing Portal, retrieved from
Causaly vs PubMed®: 2x as many relevant articles identified by Causaly using the same data
use case

Causaly vs PubMed®: 2x as many relevant articles identified by Causaly using the same data

Causaly AI finds more relevant articles than PubMed alone, using its advanced machine-reading technology.

Target identification and validation using AI for literature-based insights: Causaly & Pierre Fabre Joint Webinar

Target identification and validation using AI for literature-based insights: Causaly & Pierre Fabre Joint Webinar

Causaly and Pierre Fabre joint webinar Causaly and Pierre Fabre co-hosted a joint webinar on the 28th of October, addressing how...

Full-text vs Abstract advantage: Causaly identifies 3x as many relevant articles by machine-reading the full-text

Full-text vs Abstract advantage: Causaly identifies 3x as many relevant articles by machine-reading the full-text

Causaly enables regulatory experts to reduce time spent scanning research literature, while at the same time increase the yield from full-text articles which typically are not selected due to unsuspecting abstracts.

Sign up for Causaly newsletter