913
Views
1
CrossRef citations to date
0
Altmetric
RESEARCH ARTICLES

Proteomics based drug repositioning applied to improve in vitro fertilization implantation: an artificial intelligence model

, , , , , , & ORCID Icon show all
Pages 281-297 | Received 31 Aug 2020, Accepted 25 Apr 2021, Published online: 14 Jun 2021

Figures & data

Table 1. EI molecular characterization

Table 2. List of the key proteins in successful EI identified by the mathematical models

Figure 1. Visual representation of the physiological motives involved in EI. Proteins reported to be associated with each of the motives (according to scientific bibliography) are indicated

Figure 1. Visual representation of the physiological motives involved in EI. Proteins reported to be associated with each of the motives (according to scientific bibliography) are indicated

Figure 2. Steps followed to generate mathematical models of EI. First, proteins with a known role in EI (namely protein effectors) were determined by literature search. An exhaustive protein network was grown around these proteins incorporating information from several scientific databases. The protein network was then trained with functional information in humans and two types of mathematical models were generated, one mimicking successful EI and another simulating unsuccessful EI after IVF (this one trained with endometrial fluid-proteomics data from women collected immediately before embryo transfer in IVF cycles, linked to a known pregnancy outcome (pregnant or non‐pregnant). The analyses of these models through two different mathematical approaches (triggering analysis and model reversion analysis) allowed the identification of key proteins in successful EI

Figure 2. Steps followed to generate mathematical models of EI. First, proteins with a known role in EI (namely protein effectors) were determined by literature search. An exhaustive protein network was grown around these proteins incorporating information from several scientific databases. The protein network was then trained with functional information in humans and two types of mathematical models were generated, one mimicking successful EI and another simulating unsuccessful EI after IVF (this one trained with endometrial fluid-proteomics data from women collected immediately before embryo transfer in IVF cycles, linked to a known pregnancy outcome (pregnant or non‐pregnant). The analyses of these models through two different mathematical approaches (triggering analysis and model reversion analysis) allowed the identification of key proteins in successful EI

Figure 3. Scheme of the repositioning analysis and the criteria used to filter the candidate drugs

Figure 3. Scheme of the repositioning analysis and the criteria used to filter the candidate drugs

Table 3. List of repositioned candidates

Supplemental material

Supplemental Material

Download MS Word (26.4 KB)

Reprints and Corporate Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

To request a reprint or corporate permissions for this article, please click on the relevant link below:

Academic Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

Obtain permissions instantly via Rightslink by clicking on the button below:

If you are unable to obtain permissions via Rightslink, please complete and submit this Permissions form. For more information, please visit our Permissions help page.