Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2311.09260

A Proposed Artificial Neural Network based Approach for Molecules Bitter Prediction

Huynh Quoc Anh Bui·Trong Hop Do·Thanh Binh Nguyen
View original source ↗Read source document ↗Export metadata ↓

Abstract

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].

Explore related subjects

q-bio.BM

Keep this discovery

BibTeXRIS

Huynh Quoc Anh Bui, Trong Hop Do, Thanh Binh Nguyen. 2023-11-15. A Proposed Artificial Neural Network based Approach for Molecules Bitter Prediction. https://arxiv.org/abs/2311.09260

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Sequence-Informed Geometric Evaluation of RNA 3D Structures

Computational RNA structure pipelines generate many candidate conformations for the same sequence. Reliable evaluation therefore requires more than recognising plausible geometry, it requires determining whether that geometry is compatible with the sequence. We introduce SIRGE, a sequence-informed geometric evaluator that conditions structural representations on nucleotide embeddings from a pretrained RNA language model. Early results show that SIRGE outperforms established evaluators in Kendall--$\tau$ alignment, Top-1 selection, and Top-3 ranking. Controlled comparisons further show that sequence conditioning corrects errors made by an otherwise matched geometric model and improves target-level rank structure. These findings provide initial evidence that pretrained sequence representations supply ranking information that complements geometric reasoning.

q-bio.BM↗
arXiv2026

PocketVE: Stable and Property-Guided Structure-Based Drug Design with Variance-Exploding Diffusion

Protein-conditioned 3D molecule generation is a central challenge in structure-based drug design, requiring a balance between pocket compatibility, molecular properties, and physical geometry. We propose \textbf{PocketVE}, a protein-pocket-conditioned variance-exploding (VE) diffusion framework that couples stable coordinate denoising with inference-time property guidance. Specifically, PocketVE combines an EDM-style training and sampling setup for 3D denoising, classifier-free guidance for multi-property steering without external property classifiers, and adaptive protein perturbation as a training-time pocket regularizer. Evaluated on CrossDocked2020 under the GenBench3D protocol, PocketVE improves Valid$_{3\text{D}}$ from 58.6 to 80.6 and reduces strain energy from 457.4 to 127.9 relative to its TAGMol architectural baseline, while retaining competitive docking and molecular-property scores under moderate guidance. A guidance-scale study shows that moderate guidance gives a favorable balance between target-related objectives and geometric quality, whereas stronger guidance can degrade geometry and distributional fidelity. Pocket-permutation and PoseCheck diagnostics further support pocket-specific spatial compatibility with reduced steric conflicts. Overall, the results suggest that geometric stability and inference-time property guidance should be considered as coupled design objectives.

q-bio.BM↗
arXiv2026

Predicting directional flexibility in proteins

Predicting protein dynamics is a long-standing problem in computational structural biology. Often, protein function critically depends on local directed motions, such as hinge movements, catalytic loop rearrangements and domain reorientations, which can be characterized by directional flexibility and correlated structural motions of the protein backbone. While Molecular Dynamics (MD) simulations provide an established but often prohibitively expensive approach, recent deep generative models aim to reduce this cost by directly predicting conformational ensembles, emulating MD. However, due to their large size and the need to generate several states until the derived dynamical properties converge, these models remain expensive. In this work, we propose BackFlip-2: a fast SE(3)-equivariant graph neural network trained to directly predict dynamical descriptors, such as directional backbone flexibility and pairwise dynamic correlations, from an equilibrium structure. In a series of experiments, we show that our model matches the accuracy of substantially larger ensemble generation models while being orders of magnitude faster, and demonstrate that the proposed equivariant architecture is especially well-suited for capturing anisotropic motions in proteins. BackFlip-2 model weights, training and inference code are available at https://github.com/graeter-group/backflip.

q-bio.BM↗