Skip to content
View shajoezhu's full-sized avatar
Magic beans are real, it's called coffee!
Magic beans are real, it's called coffee!

Highlights

  • Pro

Organizations

@Roche @mcveanlab @ga4gh @scrm @hybridLambda @luntergroup @bigdatapractice2017 @DEploid-dev

Block or report shajoezhu

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
shajoezhu/README.md

Hi there 👋

I am a lead statistical programming analyst and lead software engineer at Roche. My daily job involves a wide range of data analysis activities in the pharmaceutical industry and developing software packages to support other data scientists at Roche.

Before joining Roche, I was a Senior Data Scientist working on Clinical AI using NHS patient records. I also worked as a research associate at the Oxford Big Data Institute and Wellcome Centre for Human Genetics, where my job mainly focused on malaria parasite genomes and statistical genomic research using a lot of coalescent theory. On the side, I also worked as a research consultant at the BGI, where I contributed and developed methods for data storage using DNA.

I love programming! Check out some of the open source tools at this page.

朱砂于2006年新西兰坎特伯雷大学破格录取直接升入大学二年级,在校成绩优异突出(全校前15%),连续在2008,2009获得数学统计系奖学金。本科毕业后留校直博,连续三年获得坎大一等博士学奖学金,于2013年取得统计博士学位,同年荣获由中国国家留学基金委颁发的国家优秀自费留学生奖(新西兰两位获奖者之一),并且被牛津大学录用并开展博士后科研工作, 立志于基因组溯祖模型的研究,在人类种群分布以及恶性疟疾疟原虫分型的运用。先后发表17篇学术论文,其中一作文章10篇,通讯作者文章4篇。公开发表16个开源软件包和软件库,支持多种编程语言下载。并多次受邀在国际学术会议和论坛发言,尤其是在2019年1月,作为牛津大学的五位学生代表之一在新加坡参加了全球科学家峰会,并向多位诺贝尔奖,菲尔兹奖,千年科技奖获奖者交流学习。在牛津大数据研究所博后期间,被深圳华大基因公司特聘为海外专家顾问,联合开发DNA存储技术,指导并研发代码转录及压缩的算法和软件,并发表3篇学术论文(其中一篇被Nature Computational Science接收)。2019年,加入人工智能制药公司Sensyne Health, 作为“血液抗凝剂对心力衰竭患者的益处研究”技术项目负责人,设计并使用生存分析来检验假设。研究结果在股东大会和伦敦交易所展示。自2020年加入罗氏制药,先后在三个产品研发团队担任技术带头人, 主要成果包括

  1. 通过软件开发,填补了数据处理软件的空缺,并拓展运用在14个课题中,实现了数据处理的一致性,并减少了十倍的软件维护工作量。
  2. 通过云计算改善程序流程构架,运行时间从4小时缩短到半小时,显著提高了团队工作效率。
  3. 特发性肺纤维化与生物标志物的专利申请书。
  4. 2021年评选罗氏产品部的最高奖项“卓越突破奖”,带领的高级软件团队在180个团队参选评比中,为14个获奖团队之一。
  5. 2025年评选罗氏中国“啄木鸟计划”创新优胜奖,通过使用多个AI软件平台,把翻译和校对工作周期从六周降为一周,大大提升了效率和质量。

Pinned Loading

  1. DEploid-dev/DEploid DEploid-dev/DEploid Public

    dEploid is designed for deconvoluting mixed genomes with unknown proportions. Traditional ‘phasing’ programs are limited to diploid organisms. Our method modifies Li and Stephen’s algorithm with Ma…

    C++ 21 10

  2. scrm/scrm scrm/scrm Public

    A coalescent simulator for genome-scale sequences

    C++ 44 6

  3. luntergroup/smcsmc luntergroup/smcsmc Public

    Demographic inference from whole genomes

    C++ 13 4

  4. ntpz870817/Chamaeleo ntpz870817/Chamaeleo Public

    BGI DNA Storage Kit

    Python 44 9

  5. insightsengineering/tern insightsengineering/tern Public

    Table, Listings, and Graphs (TLG) library for common outputs used in clinical trials

    R 94 29

  6. insightsengineering/autoslider.core insightsengineering/autoslider.core Public

    autoslideR core

    R 7 2