Current Project:
Generative Model for Antibody Sequence for Library Built

Currently work as Research Scientist II, Bioinformatics in Charles River Laboratory. Therefore I'm unable to provide further details at this moment.

Simulations of Molecule Interactions

Molecule Simulation

Docking

Screening

Since 2021 summer, I’m working as AI intern in InterX Inc Research group focusing on molecule interactions between proteins and ligands to bring out the novel candidate. I wrote functions for GROMACS (molecular dynamics package designed for simulations of proteins, lipids, and nucleic acids) database extraction and molecules alignment to prepare the data used in simulation.

Related Project:

Accurate determination of solvation free energies of neutral organic compounds from first principles.(Link, Acknowledgements)

Publications:

Neural Network Corrections to a Molecular Force Field Capture Nuclear Quantum Effects in Calculations of Liquid Thermodynamic Properties (In Progress)

Protein Kinetics: ABC Transporter

Key Words:
Protein Kinetics
Pharmacokinetics
ABC transportation
Protein Purification

From 2020 summer till 2022, I study the mechanism of ABC transporter which may reveal the new drug delivery system. Using LC/MS, Anisotropy, FPLC, ATP Assay.

(Image Source: the publication mentioned below)

Publication:

Chen, Y.C., Yang, J. (2022, April). Mechanisms of Substrate Selectivity and Transport by a Bacterial Methionine ABC Importer. American Society for Biochemistry and Molecular Biology, Philadelphia, NY.

Disease Identification

Key Words:
Computer Vision
Medical Imaging

RPN/RCNN

The overview of the proposed MP3D FPN: MP3D ResNet extracts context enhanced 3D features and converts them to 2D ones with a group transform module (GTM). These context enhanced 2D features are then fed into the FPN neck and the RPN/RCNN head for further 2D lesion detection.

The MP3D FPN is pre-trained on Microsoft COCO object detection dataset

(Image Source: the publication mentioned below)

Publication:

Zhang, S., Xu, J., Chen, Y. C., Ma, J., Li, Z., Wang, Y., & Yu, Y. (2020, October). Revisiting 3D context modeling with supervised pre-training for universal lesion detection in CT slices. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 542-551). Springer, Cham (Link)

Related Project:

  1. Annotation-free training approach to pathological classification (sample Code)

  2. Cross-view Correspondence Reasoning based on Bipartite Graph Convolutional Network for Mammogram Mass Detection (Link, Acknowledgements)

NGS Data Analysis

Key Words:
Proteomics

sgRNA-seq

These are some practicing projects based on different types of NGS datasets. They are implementation of publications and workshops to explore R in visualization since it’s more like a statistical task(not much machine learning).

  1. Proteomics (sample Code)

  2. Single cell RNA sequencing (sample Code)