FAQ (Frequently Asked Questions)
All you need to know, to use the platform

Accounts & Settings

Researchers are completely free of charge, only companies that choose to sponsor the platform or use the tool for internal R&D will have to pay, in that case, contact us.

If you lost your credentials, please go to the login page, click on “Forgot password?” and follow the procedure.

To avoid misuse of the platform you are limited to 30 recommendations per day and 100 recommendations per month.
If you need more please contact info@theprophetai.com

If you are planning to use Generecommender intensively and you may need more recommendations, please, contact us, and we can find the best way to support you.


The answer is yes. You can find them under the Main tab in “Your saved searches”. Additionally, previous searches can be edited.

There is no restriction on the number of genes that can be inputted. However, as a general guideline, it is advisable to include more than five inputs to prevent overly generic recommendations. By incorporating a larger number of inputs, you can enhance the specificity and relevance of the generated recommendations.

You have the option to export a comprehensive report in PPTX format that includes all the relevant details. This report can provide a detailed overview of the analysis, recommendations, and other pertinent information. Additionally, you can also export a list of the predicted genes in XLSX format, which allows for easy access and further analysis of the recommended genes.

TheGenerecommender platform, developed by TheProphetAI, does not manufacture or sell biological products. The links to commercial products on the platform are provided by sponsors from your country who have supported the service. While there is no obligation to make purchases from these sponsors, it is important to note that they have financially contributed to the provision of this free service.

When conducting new searches, you have the option to select from three distinct algorithms. Among them, DeepProphet2, a deep neural network designed for biomedical purposes, stands out as the most advanced and high-performing option. However, we have retained the older algorithms to ensure continuity and accommodate users who may prefer or rely on them.

During the training phase, the algorithm’s parameters are adjusted systematically through a trial and error process to achieve optimal results. This process can be time-consuming, often spanning several hours or even days in certain cases. However, once the algorithm has been trained, the recommendation process becomes remarkably fast, involving a series of straightforward mathematical operations.

We appreciate your offer to explore sponsorship opportunities. If there is a specific area of interest where you believe a partnership could be mutually beneficial, please contact us. We can then discuss the possibility of scheduling a meeting to delve into the specific benefits and opportunities in more depth.

The enrichment process involves evaluating the probability (p-value) that genes within a specific set are associated with a particular pathway or disease. This analysis takes into account the p-values for each pathway or disease, which are then adjusted to correct for multiple testing. This adjustment ensures that the statistical significance of the associations is appropriately accounted for, considering the number of comparisons made during the enrichment analysis.

The Algoritm

A branch of computer science, artificial intelligence is concerned with the development of software capable of simulating human intelligence. As with human brains, intelligence refers to their ability to learn from mistakes and correct themselves.

Deep learning is a subset of Artificial Intelligence that develops machine learning algorithms that have multiple layers, hence the name. As each layer learns a specific characteristic of the data, the software can perform harder tasks.

There is no doubt that it can. By scanning all scientific papers, the platform could uncover hidden knowledge already present in literature but ignored by humans, and with this broader perspective, new connections could be made. Artificial intelligen

Undoubtedly, the platform has the capability to achieve this. Through the comprehensive scanning of scientific papers, it has the potential to reveal concealed knowledge that already exists in literature but has been overlooked by humans. By adopting a broader perspective, new connections can be established. Artificial intelligence in the field of life science has the potential to elevate knowledge to unprecedented heights and greatly aid in research. Would you like to explore the correlation between new genes and a specific pathology? Give it a shot!

In order to train the algorithm, all the freely available scientific papers on Pubmed (about 7 million) are processed and used.

Regrettably, that is not the case. The neural network operates within a 64-dimensional space, where each dimension holds a fragment of information necessary for the algorithm to comprehend and differentiate genes. However, this representation is not easily interpretable by humans. The best approach is to rely on the suggested genes and initiate the process of gathering information about them. In all likelihood, you will uncover intriguing insights related to genes that you did not anticipate.

Currently, only human genes are considered by the neural network, but other species may be added in the future. Please let us know if you have any requests at info@theprophetai.com.

They were tested using gene sets for pathways and diseases. Each time a gene was left out and the remaining input was given, we tested if the algorithm could predict, in its first recommendations, which gene was missing. During training, the algorithm does not know the gene sets, so if it can complete them, then it has learned an accurate representation of genes. The performance in this kind of analysis was astonishingly good, reaching an AUC of 0.9, read our paper for more information. [DOI]