The MC team designed a platform for IFIS wherein users can use keywords or journal titles to search and browse the FSTA database of trusted journals, all of which have passed IFIS’ rigorous journal assessment policy. Further, users can narrow down the results by filtering by the criteria that matter to them, such as open access options and Impact Factor.

Utilizing Molecular Connections’ robust state-of-the-art deep learning algorithms, the team developed the only journal finder tool designed especially for researchers in the sciences of food and health. The heuristics related to the journals recommended also contributes to the suggestion; including, but not limited to journal quality metrics, publisher, and accessibility.

The team incorporated various contextual vectorizations/representations such as word and sentence embedding in conjugation; custom inserted generalized layers across the model; bi-directional transformers are used as an attempt to construct and learn dependency grammars; and a Siamese encoder-decoder is used in conjugation with a BERT: a deep bi-directional transformer to handle large corpus and ensure that it works efficiently with live inputs.

To ensure optimum performance, the team also employed few techniques such as Quantization and Approximate Nearest Neighbours (ANN) search.