Variant Viewer | Streamlit
Variant viewer dashboard to browse annotated variant calling result for ACMG variant classification
Highly motivated individual with a deep interest in leveraging artificial intelligence for precision medicine. My focus lies in applying bioinformatics & AI/ML techniques to analyze biological problems and next-generation sequencing (NGS) data.
My skillset combines technical expertise with hands on wet lab experience. I’m proficient in common AI/ML frameworks and possess a strong understanding of NGS data processing pipelines, variant calling, and functional genomics analysis. Additionally, I have a solid foundation in molecular biology techniques, cell culture, and in vitro drug assays.
I’m driven by the transformative potential of AI in the realm of precision medicine. I believe the synergy of deep learning and NGS data holds the key to unlocking novel diseases diagnoses and treatment strategies.
β€ Data: WGS, WES, RNA-Seq, targeted resequencing, 16S/shotgun microbiome
β€ Database: GEO, TCGA, PCAWG, COSMIC, dbSNP, gnomAD, ClinVar, OncoKB, CCLE, LINCS, SILVA, Greengenes etc.
β€ Analysis: biological data mining, biomarkers discovery, molecular subtyping, survival analysis, differential abundance analysis, network inference etc.
β€ Pipeline: GATK, DRAGEN, QIIME2/PICRUSt, kneadData/MetaPhlAn/HUMAnN
β€ Experience in variant interpretation using ACGS, ACMG, AMP guidelines
β€ Lanuages: Python, R, Shell, SQL
β€ Frameworks: Django, Flask, Streamlit, HTML, Bootstrap, JavaScript, SQL, C++
β€ Platform: Linux, Mac, Windows, AWS and GCP
Data wrangling, model training (scikit-learn), data visualisation (matplotlib, seaborn, ggplot), database managment (SQL)
NGS, PCR (PCR, qPCR, dPCR), cloning, immunostaining (IF/ICC/IHC), western blotting, flow cytometry
Clinical Validation (CAP, ISO)
Cell lines, Organoids, Mouse Xenograft
Variant viewer dashboard to browse annotated variant calling result for ACMG variant classification
Deep learning framework to predict response towards sequential application of anti-cancer drugs
Using shallow neural network layer (embedding) to infer gene-gene/sample relationship from gene expression data
A python package that simulates cancer chemoresistance dynamics based on a stochastic model. tags: