A Proposed Artificial Neural Network based Approach for Molecules Bitter Prediction

15 Nov 2023  ·  Huynh Quoc Anh Bui, Trong Hop Do, Thanh Binh Nguyen ·

In recent years, the development of Artificial Intelligence (AI) has offered the possibility to tackle many interdisciplinary problems, and the field of chemistry is not an exception. Drug analysis is crucial in drug discovery, playing an important role in human life. However, this task encounters many difficulties due to the wide range of computational chemistry methods. Drug analysis also involves a massive amount of work, including determining taste. Thus, applying deep learning to predict a molecule's bitterness is inevitable to accelerate innovation in drug analysis by reducing the time spent. This paper proposes an artificial neural network (ANN) based approach (EC-ANN) for the molecule's bitter prediction. Our approach took the SMILE (Simplified molecular-input line-entry system) string of a molecule as the input data for the prediction, and the 256-bit ECFP descriptor is the input vector for our network. It showed impressive results compared to state-of-the-art, with a higher performance on two out of three test sets according to the experiences on three popular test sets: Phyto-Dictionary, Unimi, and Bitter-new set [1]. For the Phyto-Dictionary test set, our model recorded 0.95 and 0.983 in F1-score and AUPR, respectively, depicted as the highest score in F1-score. For the Unimi test set, our model achieved 0.88 in F1-score and 0.88 in AUPR, which is roughly 12.3% higher than the peak of previous models [1, 2, 3, 4, 5].

PDF Abstract
No code implementations yet. Submit your code now

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here