I have developed lots of computational software packages.
Tools for simulating conventional and single-cell transcriptome sequencing readouts.
The Markov clustering algorithm is used to remove PCR artifacts in sequencing molecules labelled with single-UMI tags.
A comprehensive analysis platform that uses simulated or real sequencing data to improve molecular quantification algorithms.
PyPropel provides a Python interface to better pre-processing and post-processing protein data. pre-processing: interaction sites, protein datasets, protein features, etc. post-processing: statistics plot, evaluation, protein functional classes, etc.
PCSER is a computational tool for predicting protein corona stealth effects. It was built using the random forest machine learning approach.
ResimPy provides a scalable interface for users via Python to simulate massive reads of varying sequencing technologies, in order to avoid the time-consuming nature of experimental trials. Simulated reads can have the UMI- barcode- primer-, or spacer-featured composition.
TMKit is an open-source Python programming interface, which is modular, scalable, and specifically designed for processing transmembrane protein data. It enables users to perform database wrangling, engineer features at the mutational, domain, and topological levels, and visualise protein-protein interaction interfaces through its unique programming interface.
DeepdlncUD is used to predict the regulation types of small molecules on modulating lncRNA expression. This method is powered by 9 deep learning models.
Drutai is used to predict interactions between small molecule drugs and protein targets. This program has been made by using 12 leading deep learning frameworks.
DeepsmirUD is used to predict the regulation types of small molecules on modulating microRNA expression. This method is powered by 12 deep learning models.
DeepTMInter is a deep-learning-based approach for predicting interaction sites in transmembrane proteins. It was developed using stacked generalization ensembles of ultradeep residual neural networks.
DeepTMInter is a predictor for accurately predicting inter-helical residue contacts in transmembrane proteins.
