Kék bab.png


COVID-19 is one one of the most popular research subjects recently. In order to collect the most available relevant and accurate information about the coronavirus pandemic, one shall read and analyze enormous quantity of articles from many different sources. 

Forget the highlighters and use HTM-CoD!

HTM-CoD is the specially developed, Coronavirus pandemic – DIY module of the HUBSCIENCE Text Mining application.

It is a revolutionary unique tool to get instant access to any required relevant information from any unstructured text.

Spend less time on finding data, and more on using it!

The scientific researcher or even any interested person can search for information according to their specific field of interest. It can be simply collecting trustable information on the COVID-19 pandemic, but can be as deep as searching symptoms, healing methods, statistics about sickening rate or mortality in different countries or sub-regions, defense measures and procedures of different governments, scientific parameters or even diplomatic disputes on the responsibilities about the global pandemic.

CoD yellow csupa feher felirat.png

HTM-CoD is a special text mining application, especially developed for the COVID-19 pandemic subject by the team of HubScience experts.

The application uses a targeted, so called pandemic taxonomy, and automatically collects connections between words and terms.

The application works with such an enormous speed, that it saves a great amount of time and energy and most of all human working hours.

Provides structured results according to the researchers exact requirements in a very short period of time. It gives you the advantage

of being faster and more accurate.

Your workflow is highly efficient, simple to follow and

easy to execute!

1 icon.png
Vector Smart Object.png
1 kek.png

Simple in-browser uploading

Uploading files to your HubScience cloud storage is pretty easy and straightforward. You just upload the HTML, PDF, MEDLINE or PubMed format files from your device or simply drag’n’drop them to the Drop Zone screen.

You can upload files one-by-one or multiple at a time. While searching the internet, you can also upload the interesting articles, web contents to your HubScience project by a simple click using HubScience Uploader client.

Upload 1 árnyék.png
Upload queue 2 árnyék.png
2 icon.png
Vector Smart Object.png
2 kek.png

Highly effective reading support

HTM-CoD can productively support your reading habits. In case you want to enjoy the detailed reading, you can use our clear reading platform (the annotation panel).

While you are reading your articles, the system will collect further filtered web contents, useful information for deeper understanding. You can also order the system to preprocess all the required articles and contents. This function will speed up your reading and understanding.

pdf annotation 3 arnyek.png
pdf annotation 2 arnyek.png
pdf annotation 1 arnyek.png
Vector Smart Object.png
E D T A 3b kek.png

Faster data extraction and improved user experience

If you want to automate the reading process, you can try our automated solutions. You can process the selected or even full content of your document library fully automatically. Using the support of artificial intelligence specially developed for COVID-19 research, one can process any related text with the speed of 1 sec/page.

HTM-CoD recognizes different entities, facts, included their respective synonyms or abbreviations, furthermore relationships and assertions. Based on our pandemic taxonomy our solution classifies the specific terms into hierarchical concepts such as VIRUS, EPIDEMIC, CLINIC FEATURES, DISORDER, RESEARCH, BIOLOGICAL, and CHEMICAL MATERIALS.

HTM-CoD extracts and stores relationships between entities and presents the results in clear graphs.

The collection of numeric data is always a high priority. The great advantage of HTM-CoD, that during processing the text it automatically identifies and collects numeric data in connection with units and parameters.

Docs graph arnyek.png
Docs preannotate arnyek.png
7 icon.png
Vector Smart Object.png

Finding detailed & reliable information

Once extracted, these information are converted into a structured resource that can be easily further analysed, or presented directly using tables, charts, graphs, or a taxonomy assisted filtering tools via the HTM-CoD web interface, but that is not the only option. Users can choose to export the results so they can be further analysed with other analytical tools.

Information is only useful if it is reliable. HTM-CoD is capable of tracking every extracted information back to the original text fragment. The user can check the correct identification of the entities, or even can modify or create new entities. HTM-CoD is not a “black box” software: the user can clearly control the processing of every single information, and can track them back to the original source.

search table arnyek.png
Chart arnyek.png
big graph arnyek.png
small graph arnyek.png


We can expect the extreme growth in the quantity of scientific research materials on COVID-19. The base of the successful research is the deep knowledge and understanding of the related literature. In order to find detailed and trustable information within mass of content, researchers need the support of a dedicated tool.

Our extensive curation experience over the last 15 years in life science publications & patents has made us experts in extracting, classifying, indexing and working with complex information from diverse sources. These activities have allowed us to develop the expertise and technology to help with the extraction of information from unstructured regulatory text, scientific, economic, trade, or industrial content.