Computational identification of 4-carboxyglutamate sites to supplement physiological studies using deep learning

Protein feature engineering framework for AMPylation site prediction

AMPylation is a biologically significant yet understudied post-translational modification where an adenosine monophosphate (AMP) group is added to Tyrosine and Threonine residues primarily. While recent work has illuminated the prevalence and functional impacts of AMPylation, experimental identification of AMPylation sites remains challenging. Computational prediction techniques provide a faster alternative approach. The predictive performance of machine learning models is highly dependent on the features used to represent the raw amino acid sequences. In this work, we introduce a novel feature extraction pipeline to encode the key properties relevant to AMPylation site prediction. We utilize a recently published dataset of curated AMPylation sites to develop our feature generation framework. We demonstrate the utility of our extracted features by training various machine learning classifiers, on various numerical representations of the raw sequences extracted with the help of our framework. Tenfold cross-validation is used to evaluate the model's capability to distinguish between AMPylated and non-AMPylated sites. The top-performing set of features extracted achieved MCC score of 0.58, Accuracy of 0.8, AUC-ROC of 0.85 and F1 score of 0.73. Further, we elucidate the behaviour of the model on the set of features consisting of monogram and bigram counts for various representations using SHapley Additive exPlanations.

Pentacyclic triterpene-amino acid derivatives induced apoptosis and autophagy in tumor cells, affected the JNK and PI3K/AKT/mTOR pathway

A series of pentacyclic triterpene-amino acid derivatives were synthesized and tested for anti-proliferative activity. The results showed that most of the target compounds had good anti-proliferative activity. 2c did not contain protecting groups and hydrochloride, had excellent cytotoxicity, so it had been selected for further study in the mechanism of action in T24 cells. The data from transcriptome sequencing indicated that 2c was found to be closely related to apoptosis and autophagy. Observation of fluorescence staining and analysis from flow cytometry demonstrated that 2c induced apoptosis and cause cell cycle arrest in S/G2 phase in T24 cells. Molecular mechanism studies exhibited that 2c induced apoptosis in the intrinsic and extrinsic pathways. 2c also induced cellular autophagy in T24 cells. Results from Western Blotting showed that 2c could activate JNK pathway and inhibit PI3K/AKT/mTOR pathway. In conclusion, 2c was deserved further investigation in the field of anti-tumor.

Stmol: A component for building interactive molecular visualizations within streamlit web-applications

Streamlit is an open-source Python coding framework for building web-applications or "web-apps" and is now being used by researchers to share large data sets from published studies and other resources. Here we present Stmol, an easy-to-use component for rendering interactive 3D molecular visualizations of protein and ligand structures within Streamlit web-apps. Stmol can render protein and ligand structures with just a few lines of Python code by utilizing popular visualization libraries, currently Py3DMol and Speck. On the user-end, Stmol does not require expertise to interactively navigate. On the developer-end, Stmol can be easily integrated within structural bioinformatic and cheminformatic pipelines to provide a simple means for user-end researchers to advance biological studies and drug discovery efforts. In this paper, we highlight a few examples of how Stmol has already been utilized by scientific communities to share interactive molecular visualizations of protein and ligand structures from known open databases. We hope Stmol will be used by researchers to build additional open-sourced web-apps to benefit current and future generations of scientists.