MOTIVATION: Prediction of Compound-Protein Interactions (CPI) in bacteria is crucial to advance various pharmaceutical and chemical engineering fields, including biocatalysis, drug discovery, and industrial processing. However, current CPI models cannot be applied for bacterial CPI prediction due to the lack of curated negative interaction samples. RESULTS: We propose a novel Positive-Unlabeled (PU) learning framework, named BIN-PU, to address this limitation. BIN-PU generates pseudo positive and negative labels from known positive interaction data, enabling effective training of deep learning models for CPI prediction. We also propose a weighted positive loss function that weights to truly positive samples. We have validated BIN-PU coupled with multiple CPI backbone models, comparing the performance with the existing PU models using bacterial cytochrome P450 (CYP) data. Extensive experiments demonstrate the superiority of BIN-PU over the benchmark models in predicting CPIs with only truly positive samples. Furthermore, we have validated BIN-PU on additional bacterial proteins obtained from literature review, human CYP datasets, and uncurated data for its reproducibility. We have also validated the CPI prediction for the uncurated CYP data with biological and biophysical experiments. BIN-PU represents a significant advancement in CPI prediction for bacterial proteins, opening new possibilities for improving predictive models in related biological interaction tasks. AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/datax-lab/CYP.

The rapid growth of uncharacterized enzymes and their functional diversity urge accurate and trustworthy computational functional annotation tools. However, current state-of-the-art models lack trustworthiness on the prediction of the multilabel classification problem with thousands of classes. Here, we demonstrate that a novel evidential deep learning model (named ECPICK) makes trustworthy predictions of enzyme commission (EC) numbers with data-driven domain-relevant evidence, which results in significantly enhanced predictive power and the capability to discover potential new motif sites. ECPICK learns complex sequential patterns of amino acids and their hierarchical structures from 20 million enzyme data. ECPICK identifies significant amino acids that contribute to the prediction without multiple sequence alignment. Our intensive assessment showed not only outstanding enhancement of predictive performance on the largest databases of Uniprot, Protein Data Bank (PDB) and Kyoto Encyclopedia of Genes and Genomes (KEGG), but also a capability to discover new motif sites in microorganisms. ECPICK is a reliable EC number prediction tool to identify protein functions of an increasing number of uncharacterized enzymes.

BACKGROUND: Compound-protein interaction prediction is necessary to investigate health regulatory functions and promotes drug discovery. Machine learning is becoming increasingly important in bioinformatics for applications such as analyzing protein-related data to achieve successful solutions. Modeling the properties and functions of proteins is important but challenging, especially when dealing with predictions of the sequence type. RESULT: We propose a method to model compounds and proteins for compound-protein interaction prediction. A graph neural network is used to represent the compounds, and a convolutional layer extended with a bidirectional recurrent neural network framework, Long Short-Term Memory, and Gate Recurrent unit is used for protein sequence vectorization. The convolutional layer captures regulatory protein functions, while the recurrent layer captures long-term dependencies between protein functions, thus improving the accuracy of interaction prediction with compounds. A database of 7000 sets of annotated compound protein interaction, containing 1000 base length proteins is taken into consideration for the implementation. The results indicate that the proposed model performs effectively and can yield satisfactory accuracy regarding compound protein interaction prediction. CONCLUSION: The performance of GCRNN is based on the classification accordiong to a binary class of interactions between proteins and compounds The architectural design of GCRNN model comes with the integration of the Bi-Recurrent layer on top of CNN to learn dependencies of motifs on protein sequences and improve the accuracy of the predictions.