├── ReadMe.md ├── academicJobNotes.md ├── conferences ├── 2016 │ ├── JSM2016.md │ ├── SCGen16Tweets │ │ ├── scgen16.Rmd │ │ └── scgen16.html │ ├── SCGen2016.md │ └── WSDS2016.md ├── 2017 │ ├── BioC2017.md │ ├── JSM2017.md │ └── scWorkshopAscona2017.md ├── 2018 │ └── JSM2018.md └── 2019-jsm.md ├── figures └── permissionSettings.png └── teachers_pet-GitHubClassroom.md /ReadMe.md: -------------------------------------------------------------------------------- 1 | # classroomNotes 2 | 3 | This is Github repo containing notes all things academic. 4 | 5 | * [General Advice on an Academic Career Path](https://github.com/stephaniehicks/classroomNotes/blob/master/academicJobNotes.md) 6 | * [Using git/GitHub in the Classroom](https://github.com/stephaniehicks/classroomNotes/blob/master/teachers_pet-GitHubClassroom.md) -------------------------------------------------------------------------------- /academicJobNotes.md: -------------------------------------------------------------------------------- 1 | # General Advice on an Academic Career Path 2 | 3 | ![Female Academic Minions](http://3.bp.blogspot.com/-5rGlRTQ0OVw/VO8l6YWBMlI/AAAAAAAADto/HMgCCGEvPvM/s1600/minions.png) 4 | 5 | This document contains resources and notes that I've gathered about following an academic career path (from being a graduate student and postdoctoral fellow to faculty). I should preface this by stating this advice is geared towards an applied statistics/genomics field, but I think most of it applies to a broader set of fields. Pull requests and comments are welcomed! 6 | 7 | ## Advice for Graduate Students 8 | 9 | * [Tips for PhD students and early-career researchers](http://www.opiniomics.org/tips-for-phd-students-and-early-career-researchers/) by Opiniomics 10 | * [General advice for Graduate Students](https://sites.google.com/site/adviceforgraduatestudents/) 11 | * [Grad students in (bio)stats - do a postdoc!](http://simplystatistics.tumblr.com/post/14929329755/grad-students-in-biostatistics-do-a-postdoc) by Simply Statistics 12 | * [Leek guide to sharing data with a statistician](https://github.com/jtleek/datasharing) by Jeff Leek 13 | 14 | #### Why do a postdoc? 15 | 16 | 17 | 18 | #### Applying for a postdoc 19 | 20 | * 20 percent of your applications should be to to advertised positions and 80 percent should be cold emails to people who you are interested in working with (i.e. leaders in your field). It's OK to email them directly (even if you've never met before). 21 | * The reason is because advertised positions are usually for projects that have already been funded and the principal investigator (PI) needs someone to complete the work. If that specific work interests you, awesome! If not (or if you have another project in mind), definitely email the individuals you do want to work with and propose your idea. If they have funding and you are a good fit for their lab/group, then they will want to hire you. They may be able to find the funding. If they don't have funding, but they think you are a good candidate, they might put you in touch with a colleague of theirs who would be interested in hiring a postdoc. 22 | * Read about the faculty's interests and if you have ideas, be sure to propose ideas on projects that you would like to work on and how it relates to the faculty's interests. 23 | * If you answering an advertised position, submit those materials. If you are sending a cold email, send an updated copy of your CV and a cover letter explicitly stating why you are a good fit for their lab/group. 24 | 25 | 26 | ## Advice for Postdocs 27 | 28 | * [Managing your postdoc year(s): avoid these mistakes](http://theprofessorisin.com/2014/09/12/managing-your-postdoc-years-a-guest-post/) by The Professor Is In 29 | * [Leek guide to reading papers](https://github.com/jtleek/readingpapers) by Jeff Leek 30 | * [How to stand out in academic scientific research](http://www.opiniomics.org/how-to-stand-out-in-academic-scientific-research/) by Opiniomics 31 | 32 | 33 | ## Applying for faculty positions 34 | 35 | * [Advice for students on the academic job market](http://simplystatistics.org/2013/12/04/advice-for-stats-students-on-the-academic-job-market-2/) by Simply Statistics 36 | * [Tips for a job search](https://hopstat.wordpress.com/2016/10/05/tips-for-job-search/) by John Muschelli 37 | 38 | #### The application package 39 | 40 | The application package should contain (at a minimum): 41 | 42 | * A cover letter. What is unique about your interest in the department? 43 | * Your CV. Should contain the list of references (approximately 3-5). 44 | * A research statement. I have found the length varies significantly from field to field (anywhere from 1-15 pages). Generally though it should contain your past and current research interests and future research plans. e.g. What's your plan for your lab (2-3 projects) for the next 3-5 years? Write a good story. What's hot in your field? What are key limitations in your field? How does it complement existing expertise of faculty in the department? 45 | * A teaching statement. Again this varies from field to field and what type of position it is. If the position is mostly focused on research, then a 1 page teaching statement is sufficient. If the position is mostly teaching, then this should be significantly longer. 46 | * Prepare 3-5 reference letters to be emailed (or mailed via snail mail sometimes) directly to the department. 47 | 48 | #### Cover letters and CVs 49 | 50 | * [Academic Cover Letters for Statistical Science Faculty Positions](http://drsherrirose.com/academic-cover-letters-for-statistical-science-faculty-positions) by Sherri Rose 51 | * [Academic CVs for Statistical Science Faculty Positions](http://drsherrirose.com/academic-cvs-for-statistical-science-faculty-positions) by Sherri Rose 52 | 53 | #### Research and teaching statements 54 | 55 | * [Graham Coop, Jeff Leek, et al.](https://github.com/cooplab/statements/tree/master/statements): example research and teaching statements 56 | * [The Dreaded Teaching Statement: Eight Pitfalls](http://theprofessorisin.com/2016/09/12/thedreadedteachingstatement/) by The Professor Is In 57 | 58 | #### Interviews 59 | 60 | If your application was well-received and you get an offer to interview, CONGRATULATIONS! You made it through the first round! Here is a brief summary of what you should expect next. 61 | 62 | * [Preparing for tenure track job interviews](http://simplystatistics.org/2014/01/07/preparing-for-tenure-track-job-interviews-2/) by Simply Statistics 63 | * [Tips for faculty job interviews](http://mathbionerd.blogspot.com/2014/03/tips-for-job-interviews.html) by mathbionerd 64 | 65 | #### 1st interview 66 | 67 | * It is typically 1-2 days long. You will have many, many 15-30 mins meetings with faculty. This will be exhausting and exhilarating at the same time. Ask for water and to take breaks periodically if needed. Read up on the faculty by reviewing their profiles online. 68 | * You will have meetings with junior and senior faculty. Ask the junior faculty if the expectations of promotion were clearly explained to them? Do they get annual feedback on what to improve/focus on in the promotion evaluation? Ask the senior faculty if/how they mentor junior faculty in the promotion process? 69 | * You will typically give a one hour talk summarizing your research thus far and discussing your future research plans. This is where you want to shine! You want to show that you are the best candidate for the position. Practice your talk in front of different audiences (e.g. members of your lab, your family, your friends, your cat, your dog, your hamster, whatever works for you). 70 | * If this is mostly a teaching position, you may be asked to teach a class on a specific topic proposed by the hiring committee. If this is mostly a research position, you may be asked to give a [chalk talk](https://en.wikipedia.org/wiki/Chalk_talk). The chalk talk may or may not include slides (be sure to ask the department). 71 | * You will probably be given the opportunity to meet with students over a lunch or coffee break. Be prepared to ask questions about how the students view the faculty. What are things the students like or don't like about the department. This can be very insightful. 72 | * There will be at least one meeting scheduled with the department head/chair. Come prepared with any questions that you still have. 73 | * You will probably go out to dinner with a set of faculty (who may be on the hiring committee). At dinner definitely be yourself. These are potential colleagues of yours. You want to know that you can get along with them and they want to know if they can get along with you. 74 | 75 | **A few interview killers**: lack of enthusiasm, inability to interact well with the faculty, do not fit the vision or direction, do not have the specific background or teaching experience, lack of original or clear research plan. 76 | 77 | **Two most important parts to keep in mind**: An impressive CV or set of publications lands you the job interview, but an impressive job talk lands you the job offer. 78 | 79 | 80 | #### 2nd interview 81 | 82 | * If the first interview was successful, an offer is made. Then comes the second interview, which is an opportunity to explore more of the town you would be moving to. The department may even offer to connect you with a relator to show you around the town. 83 | * You can meet with faculty that you may have not had the chance to meet on the first interview. You can also ask to meet with faculty outside of the department (e.g. potential collaborators). 84 | 85 | 86 | #### Preparing for faculty interviews 87 | 88 | * Keep your CV up-to-date and accurate. No gaps. Get in touch with references sooner rather than later. 89 | * Research the department: what kind of support is available for young investigators? (e.g. small grants? local opportunities)? 90 | * What are the disciplinary backgrounds of the faculty? Specific expertise? 91 | * Do you know anyone there? If so, email them to find out more information about the department. 92 | * Be prepared to explain what you've done up until now (PhD, postdoc? did you take time off? your most recent work?) 93 | * Be prepared to explain what motivates you. Have a good sense of what your ideal job is. 94 | * Figure out the system for academic rank at the institution or university. For example, most people at the Harvard institutions start out as instructors (not as assistant professors). Read about the promotion metrics online if available. 95 | * Look at the publications of lab/group members 1-2 years ahead of you and see where the bar is set. 96 | 97 | #### During the faculty interview 98 | 99 | Things you may be asked: 100 | 101 | * "How come you only have 1 journal manuscript?". e.g. maybe the project was given to you as a graduate student or the project didn't really work out in the long run. If so, it is important to state what you learned from the project or how you moved forward. 102 | * "What are your key values that motivate your science?" 103 | * "Who are your biggest competitors in your area of research?" 104 | * "What specifically attracted you to our department?" e.g. pioneering department, many department resources, etc. 105 | * "What are the most important qualities of faculty in our department?" 106 | * "Tell me about your experience in teaching. What would you like to teach?" You could talk about how you've taught in a classroom and mentored PhD students. Give examples of the types of subjects. 107 | * "How would you see your career progressing over the next 3-5 years?" State research focus. State funding goals (e.g. R01). 108 | * "What are your weaknesses technically? How can you bolster those weaknesses?" e.g. you may have an inability to let go of a project that won't succeed, etc. 109 | * "Are there any technical skills you want to build up and enhance you effectiveness and funding capability?" 110 | * "How you would handle mentoring (e.g. undergraduates, graduate students)?" For example, for postdocs, it may be important to you to build a relationship, define the goals of the lab and let the postdoc innovate & gain a sense of being command of project to promote independence. 111 | 112 | Things you may want to ask: 113 | 114 | * Are you happy? What is the departmental/institutional outlook on a work/life balance? Are there opportunities for building a life or family? Is there a gender mix in the faculty? Are there resources for helping young families? How much time do you spend on research versus other things (e.g. teaching, service to the department and/or university)? 115 | * What is the percentage of my salary that I'm expected to cover? How many years am I given at the beginning to ramp up before that starts? 116 | * Ask about protected time. Can you go to another institution to learn new technique/method? 117 | * Explicitly ask about the promotion process and tenure criteria. What are the metrics for promotion (e.g. a certain number of publications? teaching reviews? etc). Do you need an R01 grant to be promoted? If you want to take time off for maternity or paternity leave, how does this affect the tenure process? What's the turnover rate at the institution? 118 | * How well funded are the faculty? What is the percent of faculty funded by an R01? 119 | * Are there opportunities for mentorship from senior faculty (a formal or an informal mechanism)? Are senior faculty willing to help review grants and/or manuscripts? Are there opportunities for co-mentorship between faculty members of graduate students and postdocs? 120 | * Where do you see department going in the next 3-5 years? What are your plans for other recruitment? 121 | * How many graduate students does the department have? Are there training grants for students? (see NIH reporter) How are the graduate students funded? If you want to work with a student, do you need to cover tuition and/or stipend? 122 | * How are connections made? How are research collaborations formed within and outside of the department? 123 | * The chair makes a lot of decisions. Get a sense of what the chair's academic values are. 124 | * How are the computational resources funded? Are they provided to you at no cost? Is there an annual cost of your lab? Is there is cost per person in your group? How much? 125 | 126 | Other important things to keep in mind: 127 | 128 | * Treat department secretaries/receptionists respectfully! They are your friend and there to help make the interview process as painless as possible. They also can express enthusiasm for particular candidates if asked. 129 | * Be enthusiastic. Body language is important. Confidence in yourself as a candidate is important. If you suffer from Imposter Syndrome, read up before the interview on books like [Lean In](http://leanin.org/book/) or read more about it [in #4 of my blogpost here](http://statisticalrecipes.blogspot.com/2014/05/inaugural-women-in-statistics-2014.html). 130 | * Be specific in your goals. Verbalize why you want this job. Be direct and honest. 131 | * Keep in mind that the faculty you are scheduled meet with has either (1) never read your CV (most likely) or (2) quickly scanned your CV 10 minutes before the meeting (if you're lucky). Be prepared to succinctly summarize your work and research interests in a way that is relevant to the department/university that you are interviewing at. Also, there will be the 1-2 people who have spent some serious time looking at your CV and will ask some **very insightful** questions. 132 | * Do not ask about salary and/or negotiate salary, space, etc on the first interview. Do your due diligence and figure a ball park estimate for the salary of the type of job you are interested in. 133 | * Do not knock your present or past employer. 134 | 135 | #### The offer letter 136 | 137 | * [Tips for academic startup: what is negotiable?](http://mathbionerd.blogspot.com/2014/03/academic-startup-what-is-negotiable.html) by mathbionerd 138 | * [Startup Suggestions tweets](https://storify.com/mwilsonsayres/start-up-suggestions-startupwishlist) by mathbionerd 139 | 140 | Key things to look for in the offer letter: 141 | 142 | * Salary (is it 12-months or 9-months? Is some summer salary included?), money equipment / supplies, support for graduate students or lab space, teaching load during 1st year and subsequent years, admin support, discretionary/startup funds, money to help relocate, starting date (this last one is typically flexible at research-focused positions and less flexible in teaching-focused positions)? 143 | * It's best to have a competing offer when negotiating. Talk to friends and mentors. Figure out what is "reasonable". What do you need for success? Find out if there is lab space, salary for graduate students, start up funding? 144 | * If you negotiate something over the phone or in person, be sure to get everything in writing before your sign the offer letter. 145 | * Keep in mind, you **can** and **should** ask for things that you truly believe will help you start out on the right foot. You may not get everything you asked for, but if you logically explain your reasoning behind each item, that usually goes a long way in getting some of the items. 146 | * Keep in mind, you can ask for just about anything (within reason). For example, a parking spot (if they are hard to come by), a spot in the daycare on campus for your child, supplemental housing support (if you are moving to a city with expensive housing), proximity of lab space to office, etc. 147 | 148 | 149 | ## Advice for Faculty 150 | 151 | * [Prepping for Class](http://mathbionerd.blogspot.com/2014/10/prepping-for-class.html) by mathbionerd 152 | * [Things to avoid as a new faculty member](https://kbroman.wordpress.com/2013/12/05/things-to-avoid-as-a-new-faculty-member/) by Karl Broman 153 | * [Ten lessons I wish I had been taught](http://alumni.media.mit.edu/~cahn/life/gian-carlo-rota-10-lessons.html) by Gian-Carlo Rota 154 | * [Leek guide to give talks](https://github.com/jtleek/talkguide) by Jeff Leek 155 | * [The Awesomest 7-Year Postdoc or: How I Learned to Stop Worrying and Love the Tenure-Track Faculty Life](https://blogs.scientificamerican.com/guest-blog/the-awesomest-7-year-postdoc-or-how-i-learned-to-stop-worrying-and-love-the-tenure-track-faculty-life/) by Radhika Nagpal: "Seven things I did during my first seven years at Harvard. Or, how I loved being a tenure-track faculty member, by deliberately trying not to be one." (1) I decided that this is a 7-year postdoc. (2) I stopped taking advice. (3) I created a "feelgood" email folder. (4) I work fixed hours and in fixed amounts. (5) I try to be the best "whole" person I can. (6) found real friends. (7) I have fun "now". 156 | * [Documenting and Evaluating Data Science Contributions in Academic Promotion in Departments of Statistics and Biostatistics](http://biorxiv.org/content/early/2017/01/25/103093) by Lance Waller 157 | 158 | For what it's worth, here is some specific advice that I've gotten: 159 | 160 | * Learn how to say **no** to almost everything people ask you to do and **yes** to specific things that will specifically advance your career and research goals. The majority of things you will be asked to do is extra or extracurricular with regards to your promotion. Therefore make sure to think carefully about what you commit to. 161 | * Find a sponsor. Someone to advocate for you, nominate you for awards and promote your work to colleagues. 162 | * When you are deciding whether or not to work with a potential collaborator, check out their publication list to assess what kind of productivity you should expect. 163 | * Get copies of successful grants. Ask people not in your field to review your grant because these are the types of people who will review your grant (i.e. avoid jargon and use simple enough language). 164 | 165 | 166 | #### Examples of NSF Biosketch 167 | 168 | * [Titus Brown](https://github.com/ctb/resume/blob/master/NSF%20BioSketch.pdf) 169 | 170 | ## Podcasts 171 | 172 | * [The Effort Report](http://effortreport.libsyn.com) - Podcasts about what it's like to have an academic career by Roger Peng [@rdpeng](https://twitter.com/rdpeng) and Elizabeth Matsui [@eliza68](https://twitter.com/eliza68). 173 | 174 | 175 | ## Sources for academic job listings 176 | 177 | * [Statistics Jobs (posted at UF)](http://www.stat.ufl.edu/jobs/) 178 | * [Statistics Jobs (posted at UW)](https://www.stat.washington.edu/jobs/) 179 | * [academickeys.com](http://academickeys.com) 180 | 181 | 182 | -------------------------------------------------------------------------------- /conferences/2016/JSM2016.md: -------------------------------------------------------------------------------- 1 | # Notes on talks for the Joint Statistical Meetings (JSM) 2016 2 | 3 | * [JSM Online Program](https://www.amstat.org/meetings/jsm/2016/onlineprogram/index.cfm) 4 | * A pdf of the [JSM Program can be found here](https://www.amstat.org/meetings/jsm/2016/pdfs/JSM2016-ProgramBook.pdf) 5 | * Follow [#JSM2016 tweets here](https://twitter.com/search?q=%23jsm2016&src=typd) 6 | * There is even a [JSM 2016 app](https://www.amstat.org/meetings/jsm/2016/jsmapp.cfm) that you can download 7 | * [Links to slides]](https://github.com/kbroman/JSM2016slides) from JSM 2016 from Karl Broman's GitHub repo 8 | 9 | ## My agenda 10 | 11 | These are the sessions I'm interested in attending. I know there a lot listed in the same time slots, but I'm hoping to catch a few talks in different ones. The numbers at the beginning list the session number. If anyone is interested, my talk is on Tues 2-3:50pm in [Session 405 titled Statistical Challenges in the Analysis of Single-Cell RNA-Seq Data](https://www.amstat.org/meetings/jsm/2016/onlineprogram/ActivityDetails.cfm?SessionID=212483) 12 | 13 | #### Sunday 14 | 15 | 2-3:50pm 16 | 17 | * 2 - Novel Statistical Methods in Imaging (Invited) 18 | * 2:05pm - From Statistical Visual Modeling and Computing to Communicative Learning ([Tianfu Wu](http://www.stat.ucla.edu/~tianfu.wu/), UCLA but soon NCSU) 19 | * "dark learning" = want to go beyond deep learning to understand the social meaning in images 20 | * Visual [Turning Test](https://en.wikipedia.org/wiki/Turing_test) in images - you can ask, answer and test story-like questions 21 | * Classical assumption for tracking is to use [Hidden Markov Models](https://en.wikipedia.org/wiki/Hidden_Markov_model) and [Particle Filtering](https://projecteuclid.org/euclid.ss/1280841735) (tries to integrates out previous state to predict current state). Big challenges: high-dimensional space and in-homogenous state spaces. 22 | * 2:30pm - Nonparametric Spatio-Temporal Analysis of Neuroimaging Data ([Nathaniel Helwig](http://users.stat.umn.edu/~helwig/), U of Minnesota) 23 | * [Bilinear model](https://www.quora.com/What-are-some-examples-of-bilinear-models) - e.g. PCA, factor analysis, ICA. Across the rows is the temporal relationship. Across the columns is the spatial relationship. Here PCA "scores" are the temporal components and "loadings" are the spatial components. 24 | * Major caveats (can rotate model without changing fit). **Rotational indeterminacy problem** = pick any orthogonal rotation matrix. we can define a new rotation. To solve in practice, people assume this bilinear model form and assume the columns (or rows) are independent. Tensor 25 | * Models for three-way data. Argues these are under utilized models (i.e. multi-mode, multi-linear) 26 | * The Covariation Chart by Raymond Cattell (1952) - first illustration of a three-way array 27 | * Tucker's three-way factor analysis model (1966) - assumes a cube of data is composed of a smaller cube 28 | * Parafac (parallel factors) - popular in chemistry. No rotational indeterminacy problem (yay!) 29 | * Tensor models with smoothness constraints. Can analyze variation across time, space and samples. Suggests using the parafac model, but uses a smoothed component function across the ith time point and jth spatial point. 30 | * e.g. B-splines basis, smooth splines, second-order difference penalty. (All adds big computational costs due as does sample size) 31 | * [bigsplines R pkg](https://cran.r-project.org/web/packages/bigsplines/index.html) = Smoothing Splines for Large Samples 32 | * 2:55pm - Bayesian Feature Screening for Big Neuroimaging Data via Massively Parallel Computing ([Jian Kang](http://www-personal.umich.edu/~jiankang/), U of Michigan) 33 | * **structural imaging** (measures brain structures or shows contrasts between brain tissues e.g. MRI) vs **functional imaging** (measures neural activity and makes inference on the brain function) 34 | * Data: [Autism brain imaging data exchange (ABIDE)](http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4162310/) - Goal is to develop a biomarker using neuro-imaging data to predict risk of disease. Biomarker used is the Voxel-wise fALFF value (captures local brain activity). Total of 1112 individuals (~500 cases, ~500 controls). Data from individual captured includes 175K voxels in 116 ROIs (regions of interest). 35 | * Models: "Scalar-on-Image Regression". Discussed many variable selection methods and "ultra-high dimensional [variable screening](http://www.stat.ncsu.edu/people/bloomfield/courses/st430-514/slides/MandS-ch06-sec01-04.pdf)" methods. Author extends models to a bayesian framework for the Posterior Mean Screening. 36 | * 2:50pm - Joint Analysis of Brain Imaging Data and Genetics Data ([Wenxuan Zhong](http://www.stat.uga.edu/people/wenxuan-zhong), U of Georgia) 37 | * 6 - Open Source Statistical Software for Data Science (Invited) 38 | * 2:05pm - Software Engineering for Data Science ([Skipper Seabold](https://twitter.com/jseabold), Civis' Analytics) [[Slides](https://speakerdeck.com/jseabold/having-an-impact-as-a-modern-statistician)] 39 | * 2:25pm - The Python Data Science Stack ([Jake VanderPlas](http://staff.washington.edu/jakevdp/), U of Washington) [[Slides](https://speakerdeck.com/jakevdp/pythons-data-science-stack-jsm-2016)] 40 | * 2:45pm - Flexibility and Speed: Can We Have Both? ([Douglas Bates](https://www.stat.wisc.edu/~bates/), U of Wisconsin) 41 | * [lme4](http://r-forge.r-project.org/projects/lme4/) - Linear, generalized linear and nonlinear mixed models in R 42 | * 3:05pm - If You Can't Beat 'Em ([Dirk Eddelbuettel](http://dirk.eddelbuettel.com), Ketchum Trading/Debian & R Projects) 43 | * 3:25pm - Grammars and Structures for Computing with Data (Michael Kane, Yale University) [[Slides](http://slides.com/michaelkane/deck-17#/)] 44 | * 10 - Statistical Methods in Integrative Genomics (Invited) 45 | * 26 - Distinguishing Between Statistics Education for Undergraduate and Graduate Nonstatistics Major Students (Topic-Contributed) 46 | * 33 - Efficient Methods for Structured Large Genomics Data (Contributed) 47 | * 3:20pm - Bayesian Large-Scale Multiple Regression with Summary Statistics from Genome-Wide Association Studies (Xiang Zhu, U of Chicago) [[Slides](http://www.stat.uchicago.edu/%7Exiangzhu/JSM_20160731.pdf) 48 | 49 | 4-5:50pm 50 | 51 | * 45 - Introductory Overview Lecture: Spatio-Temporal Data Analysis (Invited) 52 | * 47 - Making the Most of R Tools (Invited) 53 | * 4:05pm- Thinking with Data Using R and RStudio: Powerful Idioms for Analysts ([Nicholas Horton](https://www.amherst.edu/people/facstaff/nhorton), Amherst College) [[Slides](https://github.com/Amherst-Statistics/JSM2016-thinkwithR)] 54 | * 4:35pm - Transform Your Work Flow and Deliverables with Shiny and R Markdown ([Garrett Grolemund](https://twitter.com/statgarrett), Rstudio) 55 | * [RStudio Cheatsheets](https://www.rstudio.com/resources/cheatsheets/) - RMarkdown, IDE, Shiny, Data Viz, Package Development, Data Wrangling, Base R, Advanced R 56 | * [htmlwidgets](http://www.htmlwidgets.org) - Use JavaScript data visualization libraries in R (i.e. plots). Embed widgets in RMarkdown documents and Shiny web applications. 57 | * 51 - Media and Statistics (Invited) 58 | * 4:05pm - Causal Inferences from Observational Studies: Fracking, Earthquakes, and Oklahoma (Howard Wainer, NBME) 59 | * 4:25pm - It's Not What We Say, It's Not What They Hear, It's What They Say They Heard ([Barry Nussbaum](http://magazine.amstat.org/blog/2012/02/01/nussbaum/), EPA, [ASA President-Elect 2016](http://magazine.amstat.org/blog/2015/07/01/2015electionresults/)) 60 | * 4:45pm - Bad Statistics, Bad Reporting, Bad Impact on Patients: The Story of the PACE Trial ([Julie Rehmeyer](http://julierehmeyer.com), Discover Magazine) [[Slides](http://www.slideshare.net/JulieRehmeyer/bad-statistics-bad-reporting-bad-impact-on-patients-the-story-of-the-pace-trial)] 61 | * [PACE Trial](http://www.wolfson.qmul.ac.uk/current-projects/pace-trial/) = deeply flawed [trial on chronic fatigue syndrome (CFS) published in The Lancet in 2011](http://www.thelancet.com/journals/lancet/article/PIIS0140-6736(11)60096-2/abstract). Impacts public health recommendations world-wide. 62 | * Results from trial states psychotherapy and exercise can help with CFS. Turns out it had flawed definition of what is an "improvement" (i.e. you could actually get worse and be defined as "better"). 63 | * 5:05pm - Can Statisticians Enlist the Media to Successfully Change Policy? ([Don Berry](http://faculty.mdanderson.org/Donald_Berry/), MD Anderson) 64 | * 56 - Extraordinary Impact of Statistics (Invited) 65 | * 4:05pm - A Short History of Statistical Ideas (David Siegmund, Stanford U) 66 | * 4:30pm - Cutting-Edge Research in Modern Statistical Sciences: Modern Tools and Impact in Data Science ([Heike Hofmann](http://hofmann.public.iastate.edu), ISU) 67 | * 4:55pm - Women in Statistics: Past, Present, and Future (Sally Morton, U of Pittsburgh) 68 | * 5:20pm - Disc ([Xiao-Li Meng](http://statistics.fas.harvard.edu/people/xiao-li-meng), Harvard) 69 | * 61 - Modeling Multivariate Count Data: Multivariate Extensions and Generalizations of Standard Count Distributions (Topic-Contributed) 70 | * 74 - Estimation and Learning in Graphical Models (Contributed) 71 | * 4:35pm - An Exposition on the Propriety of Restricted Boltzmann Machines ([Andee Kaplan](http://andeekaplan.com), ISU) [[Slides](http://andeekaplan.com/rbm/presentations/jsm2016/)] 72 | * 78 - For the Love of the Game: Applicatsions of Statistics in Sports (Contributed) 73 | * 4:20pm - Estimating NCAA Football Coaches' Abilities: An Application of Item Response Theory (Brandon LeBeau, U of Iowa) [[Slides](http://educate-r.org/2016/07/31/jsm2016.html)] 74 | * 81 - Clustering Methods (Contributed) 75 | 76 | #### Monday 77 | 78 | 8:30-10:20am 79 | 80 | * 96 - Introductory Overview Lecture: Causal Inference (Invited) 81 | * 106 - Applied Data Visualization in Industry and Journalism (Invited) 82 | * 8:35am - Linked Brushing in R (Hadley Wickham, Rice U) 83 | * [modelr](https://github.com/hadley/modelr) - helper functions for modeling data 84 | * 8:55am - Creating Data Visualization Tools at Facebook (Andreas Gros, Facebook) 85 | * 9:15pm - Cocktail Party Horror Stories About Data Vis for Clients (Lynn Cherny, Ghostweather R&D) 86 | * [Data Vis Consulting: Advice for Newbies](http://blogger.ghostweather.com/2013/11/data-vis-consulting-advice-for-newbies.html) 87 | * 9:35pm - Visualizing the News at Five ThirtyEight (Andrei Scheinkman, FiveThirtyEight.com) 88 | * 9:55pm - Teaching Data Visualization to 100k Data Scientists: Lessons from Evidence-Based Data Analysis ([Jeffrey Leek](http://jtleek.com), Johns Hopkins SPH) [[Slides](http://www.slideshare.net/jtleek/data-science-as-a-science) 89 | * 111 - Recent Statistical Developments in Cancer Research (Topic-Contributed) 90 | * 8:35am - Normalization for Single-Cell RNA-Seq ([Christina Kendziorski](https://www.biostat.wisc.edu/~kendzior/), U of Wisconsin) 91 | * scnorm = Performs quantile polynomial regression within groups of genes (genes are grouped via K-means with distance depending on gene-specific expression level). Not published yet. 92 | * Models expression as a function of sequencing depth within each group of genes. Assessed FC bias in simulations 93 | * Idea: If you plot sequencing depth vs median expression (of non-zeros), the slope is different for different levels of expression (in groups of genes with high and low expression) 94 | * 8:55am - Statistical Issues in Single-Cell Analysis for Cancer Research ([Omar De La Cruz Cabrera](http://epbiwww.case.edu/index.php/people/faculty/129-delacruzcabrera), Case Western) 95 | * 116 - What's Wrong with P-Value? (Topic-Contributed) 96 | * 118 - Challenges in Metagenomic Data Analysis: Reproducibility and Interpretability of Inferences on Microbial Community Composition and Dynamics (Topic-Contributed) 97 | * 125 - Statistical Methods for Functional Data (Contributed) 98 | * 127 - R Tools for Statistical Computing (Contributed) 99 | * 9:50am - Broom: An R Package for Converting Statistical Modeling Objects Into Tidy Data Frames ([David Robinson](http://varianceexplained.org), Stack Overflow) 100 | 101 | 10:30am-12:20pm 102 | 103 | * 141 - Some New Perspectives in Statistical Analysis with Incomplete Data (Invited) 104 | * 142 - The Extraordinary Impacts of Statistics in Genomics and Genetics (Invited) 105 | * 10:35am - Latent Variable Methods for the Analysis of Genomic Data ([John Storey](http://www.genomine.org), Princeton) [[Slides](http://genomine.org/talks/jsm_2016.pdf)] 106 | * [jackstraw](http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4325543/) - Identify genomic variables that are statistically significantly associated with any subset or linear combination of PCs 107 | * 11:00am - Overcoming Bias and Batch Effects in RNAseq Data ([Michael Love](http://mikelove.github.io), [Rafael A. Irizarry](http://rafalab.dfci.harvard.edu), DFCI) 108 | * [alpine](https://github.com/mikelove/alpine) - Modeling and correcting fragment sequence bias for RNA-seq 109 | * 11:25am - Testing High-Dimensional Differential Matrices, with Applications to Detecting Schizophrenia Genes ([Kathryn Roeder](http://www.stat.cmu.edu/~roeder/), Carnegie Mellon U) 110 | * 11:50am - Graph-Restricted Mixture Models ([Michael Newton](http://www.stat.wisc.edu/~newton/), U of Wisconsin) 111 | * 159 - Biostatistical Literacy: How Best to Teach Medical and Public Health Professionals What They Need to Know About Statistics (Topic-Contributed) 112 | * 169 - SPEED: Statistical Computing and Sports? (Contributed) 113 | 114 | 2-3:50pm 115 | 116 | * 222 - Tricks and Treats in Classification and Regression Trees (Invited) 117 | * 227 - Statistical Foundations of Data Privacy (Invited) 118 | * 242 - Methods for Genetics and Genomics Data (Contributed) 119 | 120 | 4:45-6:15pm 121 | 122 | * 272 - ASA President's Invited Address (Invited) 123 | * [Joe Palca](http://www.npr.org/people/2101004/joe-palca), NPR - Science and News: A Marriage of Convenience 124 | 125 | #### Tuesday 126 | 127 | 8:30-10:20am 128 | 129 | * 280 - Introductory Overview Lecture: Data Science 130 | * 285 - New Advances in Statistical Genetics for Large-Scale Genomic Data (Invited) 131 | * 286 - Women in Statistics: Past, Present, Future (Invited) 132 | * 302 - Advanced Statistical Methods for High- Dimensional Microbiome Data Analysis (Topic-Contributed) 133 | * 318 - Novel Approaches for Metagenomic, Phylogenetic, and Epigenetic Analysis (Contributed) 134 | * 325 - Late-Breaking Session II: Data Journalism and Statistical Expertise: An Urgent Need for Writers, Bloggers, and Journalists to Be Statistically Savvy (Invited) 135 | 136 | 10:30am-12:20pm 137 | 138 | * 327 - Statistics in Personalized Medicine (Invited) 139 | * 332 - Doing More with Data in and Outside the Undergraduate Classroom (Invited) 140 | * 339 - Big Data Challenges and Statistical Advances in Functional Genomics (Topic-Contributed) 141 | * 334 - Novel Missing Data Imputation Methods (Topic-Contributed) 142 | * 356 - Methods for Next-Generation Sequencing Data (Contributed) 143 | * 357 - Advances in Statistical Genetics and Genomics (Contributed) 144 | 145 | 2-3:50pm 146 | 147 | * 403 - New Methods for Detecting Sparse and Weak Effects in Genetic/Genomic Data (Invited) 148 | * 405 - Statistical Challenges in the Analysis of Single-Cell RNA-Seq Data (Invited) 149 | * 2:05pm - [MAST](https://github.com/RGLab/MAST): A Novel Statistical Framework for Assessing Transcriptional Changes and Characterizing Heterogeneity in Single-Cell RNA-Seq Data ([Andrew McDavid](https://github.com/amcdavid), Fred Hutch/U Rochester) 150 | * Cellular detection rate may reflect the size of the cell (see [Padovan-Merhar et al. (2015)](http://www.ncbi.nlm.nih.gov/pubmed/25866248)) - McDavid is waiting experimental data to confirm this 151 | * 2:30pm - [Yoav Gilad](http://giladlab.uchicago.edu) - [Batch effects and the effective design of single-cell gene expression studies](http://biorxiv.org/content/early/2016/07/08/062919) 152 | * Conversion efficiency from reads to molecules is affected by individual and technical C1 batch; goes against the idea of using UMIs as the absolute measurement of gene expression 153 | * 2:55pm - Learning the 'Metadata' of the Cell: Inferring Cellular Phenotypes with Single-Cell Genomics ([Rahul Satija](http://www.satijalab.org), NY Genome Center) 154 | * [seurat](http://www.satijalab.org/seurat.html) - [Spatial reconstruction of single-cell gene expression data](http://www.nature.com/nbt/journal/v33/n5/full/nbt.3192.html) 155 | * 3:20pm - [On the Widespread and Critical Impact of Systematic Bias and Batch Effects in Single-Cell RNA-Seq Data](http://biorxiv.org/content/early/2015/12/27/025528) ([Stephanie Hicks](http://www.stephaniehicks.com), DFCI/Harvard) 156 | * 406 - Recent Advances in High-Dimensional Statistics and Computational Method (Invited) 157 | * 407 - Interactive Visualizations and Web Applications for Analytics (Invited) 158 | * 2:35pm - Composable Linked Interactive Visualizations in R with Htmlwidgets and Shiny (Joseph Cheng, RStudio) 159 | * [crosstalk](https://github.com/rstudio/crosstalk) - R pkg for interactive web graphs. Define in R, deploy in Javascript. 160 | * 3:05pm - Interactive and Dynamic Web-Based Graphics for Data Analysis (Carson Sievert, ISU) [[Slides](http://cpsievert.github.io/talks/20160802/)] 161 | * 3:20pm - HTML Widgets: Interactive Visualizations from R Made Easy! (Yihui Xie, RStudio) [[Slides](https://dl.dropboxusercontent.com/u/15335397/slides/2016-htmlwidgets-JSM-Yihui-Xie.html#(1))] 162 | * 418 - Biometrics Section Student Paper Award Session 2 163 | * 3:25pm - ScDD: A Statistical Approach for Identifying Differential Distributions in Single-Cell RNA-Seq Experiments (Keegan Korthauer, DFCI) [[Slides](http://bcb.dfci.harvard.edu/%7Ekeegan/talks/JSM_2016_Korthauer_Session_418.pdf)] 164 | * 434 - Statistical Modeling of RNA-Seq Data (Contributed) 165 | * 2:20pm - [TSCAN](https://www.bioconductor.org/packages/release/bioc/html/TSCAN.html): Pseudo-Time Reconstruction and Evaluation in Single-Cell RNA-Seq Analysis (Zhicheng Ji and [Hongkai Ji](http://www.biostat.jhsph.edu/~hji/), JHU) 166 | 167 | In the afternoon 168 | 169 | * 454 - Deming Lecture 170 | * President's address (8-9:30pm) 171 | 172 | #### Wednesday 173 | 174 | 8:30-10:20am 175 | 176 | * 465 - Data Science for Health Policy: A Broad Tent (Invited) 177 | * 471 - New Statistical Methods for the Analysis of High-Dimensional Biomarkers (Invited) 178 | * 475 - Reproducibility in Statistics and Data Science (Invited) 179 | * 8:35am - Reproducibility for All and Our Love/Hate Relationship with Spreadsheets ([Jenny Bryan](http://www.stat.ubc.ca/~jenny/), U of British Columbia) [[Slides](https://github.com/jennybc/2016-06_spreadsheets#readme)] 180 | * [googlesheets](https://cran.r-project.org/web/packages/googlesheets/vignettes/basic-usage.html) 181 | * 8:55am - Steps Toward Reproducible Research ([Karl Broman](http://kbroman.org), U of Wisconsin) [[Slides](https://www.biostat.wisc.edu/~kbroman/presentations/repro_research_JSM2016_withnotes.pdf)] 182 | * 9:15am - Enough with Trickle-Down Reproducibility: Scientists, Open is Gate! Scientists, Tear Down is Wall! ([Karthik Ram](http://karthik.io), UC Berkeley) [[Slides](http://inundata.org/talks/jsm2016/#/)] 183 | * 9:35am - Integrating Reproducibility into the Undergraduate Statistics Curriculum ([Mine Cetinkaya-Rundel](http://www2.stat.duke.edu/~mc301/), Duke) [[Slides](https://github.com/mine-cetinkaya-rundel/2016-08-03-reproducible-undergrad-stats)] 184 | * 9:55am - Disc: [Yihui Xie](http://yihui.name/en/), RStudio 185 | * 499 - Statistical Learning Approaches to Biological Inference Problems (Contributed) 186 | * 501 - Analysis of Gene Expression, Genomics, and Next-Generation Sequencing Dat (Contributed) 187 | 188 | 10:30am-12:20pm 189 | 190 | * 509 - Social Networks as the Unit of Observation (Invited) 191 | * 511 - Statistical Methods for Analyzing Microbiome Data (Invited) 192 | * 10:35am - Bayesian Variable Selection Models for Microbiome Data Integration (Duncan Wadsworth, Rice/Microsoft) 193 | * 11:00am - Statistical Methods for Integrating the Phylogenetic Tree in Microbiome Data Analysis (Jun Chen, Mayo Clinic) 194 | * 11:25am - Kernel Penalized Regression Models for Microbiome Data (Timothy Randolph, Fred Hutch) 195 | * 11:50am - Analysis of Composition of Microbiome with Structural Zeros (ANCOMSZ) (Shyamal Peddada, NIEHS) 196 | * 513 - Recent Advances in Functional Data Analysis (Invited) 197 | * 517 - Do Courts Appreciate the Power of Statistical Evidence? (Invited) 198 | * 533 - Modeling Confounders via Smoothing and Regularization Methods? The Case of Age-Period Cohort and Beyond (Topic-Contributed) 199 | 200 | 2-3:50pm 201 | 202 | * 579 - Challenges and Opportunities for Analysis of High-Dimensional and Big Data (Invited) 203 | * 580 - Statistical and Computational Advances in Microbiome and Metagenomic Studies (Invited) 204 | * 586 - Collaboration Among Academia, Industry, and Government, and the Role of ASA (Invited) 205 | * 587 - Resampling Methods for High-Dimensional Inference (Invited) 206 | * 593 - Batch Effects in Genomics Data (Topic-Contributed) 207 | * 3:05pm - Accounting for Sample Quality and Other Unwanted Effects in Single-Cell RNA-Seq Data ([Davide Risso](http://www.stat.berkeley.edu/~davide/Personal_Page/Home.html), UC Berkeley) [[Slides](http://rpubs.com/daviderisso/jsm2016)] 208 | * [scone](https://github.com/YosefLab/scone) 209 | 210 | #### Thursday 211 | 212 | 8:30-10:20am 213 | 214 | * 632 - Julia for Modern Statistical Computing (Invited) 215 | * 634 - Analysis, Storage, and Privacy for Big Data (Invited) 216 | * 649 - Clustering, Classification, and Dimension Reduction Techniques (Contributed) 217 | * 655 - New Advances in Clustering Algorithms (Contributed) 218 | * 656 - Hypothesis Testing for Correlation and Dependence (Contributed) 219 | 220 | 10:30am-12:20pm 221 | 222 | * 678 - Strategies for Developing Undergraduate Data Science Programs (Invited) 223 | * 686 - Statistics for Social Good (Topic-Contributed) 224 | * 691 - Modern Biosurveillance at the Edge of Online Social Media, Social Networks, and Nontraditional Big Data (Topic-Contributed) 225 | 226 | 227 | -------------------------------------------------------------------------------- /conferences/2016/SCGen16Tweets/scgen16.Rmd: -------------------------------------------------------------------------------- 1 | --- 2 | title: "Single Cell Genomics 2016 (#SCGen16)" 3 | output: html_document 4 | --- 5 | 6 | ```{r echo = FALSE, cache = FALSE} 7 | knitr::opts_chunk$set(cache = TRUE, message = FALSE) 8 | 9 | options(httr_oauth_cache = TRUE) 10 | ``` 11 | 12 | Here is a quick analysis of tweets from the [2016 Single Cell Genomics (SCG) Conference](https://coursesandconferences.wellcomegenomecampus.org/events/item.aspx?e=596) 13 | at the Wellcome Genome Campus, Hinxton, Cambridge, UK from Sept 14-16, 2016. Twitter hashtag [#SCGen16](https://twitter.com/search?f=tweets&vertical=default&q=%23SCGen16&src=typd). 14 | 15 | Using the `twitteR` R package, I scraped 1000 tweets from the conference. 16 | 17 | ```{r} 18 | library(httr) 19 | library(twitteR) 20 | library(tidyr) 21 | library(dplyr) 22 | library(stringr) 23 | 24 | setup_twitter_oauth(getOption("twitter_consumer_key"), 25 | getOption("twitter_consumer_secret"), 26 | getOption("twitter_access_token"), 27 | getOption("twitter_access_token_secret")) 28 | 29 | scgen16 <- searchTwitter("#SCGen16", n = 1000) 30 | ``` 31 | 32 | Even though I asked for 1000 tweets, it turns out as of September 21 2016, there were only 586 tweets (for the entire conference). I'm not sure why, but that seems like so few to me compared to some of the other conferences that I have recently attended. 33 | 34 | Next, I transformed there scrapped data into a data frame and removed the duplicated retweets. 35 | 36 | ```{r} 37 | scgen16_tweets <- bind_rows(lapply(scgen16, as.data.frame)) # Transform into a data frame 38 | scgen16_non_retweets <- scgen16_tweets %>% filter(!isRetweet) # Filter out retweets 39 | ``` 40 | 41 | ## Who tweeted the most? 42 | 43 | ```{r} 44 | scgen16_non_retweets %>% 45 | count(screenName, sort = TRUE) 46 | ``` 47 | 48 | ## How often were tweets retweeted? favorited? 49 | ```{r} 50 | library(ggplot2) 51 | ggplot(scgen16_non_retweets, aes(retweetCount)) + 52 | geom_histogram() + xlab("Number of Retweets") 53 | 54 | ggplot(scgen16_non_retweets, aes(favoriteCount)) + 55 | geom_histogram() + xlab("Number of Favorites") 56 | ``` 57 | 58 | 59 | Using the `unnest_tokens()` function in the tidytext package, I divided the 60 | text from the tweets into words as rows on a data frame with a text column. 61 | 62 | ```{r} 63 | library(tidytext) 64 | 65 | tweet_words <- scgen16_non_retweets %>% 66 | select(screenName, id, created, text) %>% 67 | unnest_tokens(word, text) %>% 68 | filter(!word %in% stop_words$word) 69 | 70 | tweet_words %>% head() 71 | ``` 72 | 73 | ## What were the top 50 most tweeted words in the conference? 74 | 75 | ```{r, fig.height= 10} 76 | reg <- "([^A-Za-z\\d#@']|'(?![A-Za-z\\d#@]))" 77 | tweet_words <- scgen16_non_retweets %>% 78 | select(id, statusSource, text, created) %>% 79 | mutate(text = str_replace_all(text, "https://t.co/[A-Za-z\\d]+|&", "")) %>% 80 | unnest_tokens(word, text, token = "regex", pattern = reg) %>% 81 | filter(!word %in% stop_words$word,str_detect(word, "[a-z]")) 82 | 83 | tweet_words %>% count(word, sort = TRUE) %>% top_n(50) %>% 84 | ggplot(aes(x = reorder(word, n), n)) + geom_bar(stat="identity") + 85 | coord_flip() + xlab("Tweeted words") + ylab("Frequency") 86 | 87 | ``` 88 | 89 | OK if we remove `#scgen16`. You see a lot of the two letter words (e.g. `st`) were the speakers (`st` = Sarah Teichmann, `jm` = John Marioni, etc). 90 | 91 | ```{r, fig.height= 8} 92 | tweet_words %>% count(word, sort = TRUE) %>% top_n(50) %>% 93 | filter(!(word == "#scgen16")) %>% 94 | ggplot(aes(x = reorder(word, n), n)) + geom_bar(stat="identity") + 95 | coord_flip() + xlab("Tweeted words") + ylab("Frequency") 96 | 97 | ``` 98 | 99 | 100 | #### Useful Resources 101 | 102 | * [httr quickstart guide](https://cran.r-project.org/web/packages/httr/vignettes/quickstart.html) 103 | * [apps.twitter.com](https://apps.twitter.com/): start a Twitter app here before using the twitteR package 104 | -------------------------------------------------------------------------------- /conferences/2016/SCGen2016.md: -------------------------------------------------------------------------------- 1 | # Notes on talks for the 2016 SCG Conference 2 | 3 | Notes and slides for the [2016 Single Cell Genomics (SCG) Conference](https://coursesandconferences.wellcomegenomecampus.org/events/item.aspx?e=596) 4 | at the Wellcome Genome Campus, Hinxton, Cambridge, UK from Sept 14-16, 2016. Here is a pdf of the 5 | [SCG Program](http://conf.hinxton.wellcome.ac.uk/advancedcourses/SSG16draftprogrammeFinal.pdf). 6 | Follow the twitter hashtag [#SCGen16](https://twitter.com/search?f=tweets&vertical=default&q=%23SCGen16&src=typd). 7 | I missed some of the talks, so pull requests are welcome to fill in gaps! or tweet me 8 | [@stephaniehicks](https://twitter.com/stephaniehicks). 9 | 10 | 11 | ## Wednesday, Sept 14 12 | 13 | ### Keynote Lecture 14 | 15 | - [Arnold Kriegstein](https://bms.ucsf.edu/directory/faculty/arnold-kriegstein-md-phd), Genomic insights into human cortical development, lissencephaly, and Zika microcephaly 16 | - Very interesting story on using scRNA-seq to study the zika virus and congenital microcephaly. Both cause malformations in the brain (but Zika also destroys already developed tissue). The AXL Zika receptor is expressed in radial glia cells (precursors for neuronal expansion in brain cortex) and can be used to predict where damage occurs in the brain. Showed blocking AXL prevents Zika entry into progenitor cells in developing brain. Pregnancy-safe compounds now being tested. 17 | 18 | ### Session 1: Neuroscience & Tissue Development 19 | 20 | **Chair**: [Rickard Sandberg](http://sandberg.cmb.ki.se) from [@karolinskainst](https://twitter.com/karolinskainst) 21 | 22 | - [Sten Linnarsson](http://linnarssonlab.org), [@slinnarsson](https://twitter.com/slinnarsson), Towards a census of mouse brain cell types 23 | - Example of [identifying neurons that control goosebumps](http://linnarssonlab.org/publications/2016/08/29/sympathetic/). On brain development, "differentiation speed affects how many intermediate types scRNAseq captures". Useful links to data and software available on lab website including [BackSPIN](https://github.com/linnarsson-lab/BackSPIN): biclustering algorithm based on sorting points into neighborhoods (SPIN), implemented in MATLAB and Python and described in [Zeisel et al. (2015)](http://science.sciencemag.org/content/347/6226/1138). 24 | 25 | - [Barbara Treutlein](http://www.treutleinlab.org), Reconstructing human organogenesis using single-cell RNA-seq 26 | - [Treutlein et al. 2016](http://www.nature.com/nature/journal/v534/n7607/full/nature18323.html) - reprogramming from fibroblast to neuron using scRNA-seq 27 | 28 | - [Maria Kasper](http://ki.se/en/people/markas), Plasticity and heterogeneity of skin cells in health and tissue repair 29 | - There are 25 (!!) different cell types in a single hair follicle 30 | 31 | - [Naomi Habib](http://zlab.mit.edu/team.html), Single nucleus RNA-Seq reveals dynamics of adult neurogenesis 32 | - Developed [sNuc-Seq and Div-Seq](http://science.sciencemag.org/content/353/6302/925.full) to investigate dynamic transcriptome of rare adult newborn neurons; introduced bi-SNE (biclustering on Stochastic Neighbor Embedding) 33 | - sNuc-Seq (single nuclei RNA-seq): skips dissociation step and can be done on aging tissue, and fresh/frozen tissue, allows you to obtain neurons. 34 | - Div-Seq (combines sNuc-Seq with pulse labeling of proliferating cells): labels all dividing cells in dynamic processes, no need for marker genes. 35 | 36 | - [Gray Camp](http://www.eva.mpg.de/genetics/staff.html), Human cerebral organoids recapitulate gene expression programs of fetal neocortex development 37 | - [used scRNA-seq to deconstruct fetal human neocortex & cerebral organoid development](http://www.pnas.org/content/112/51/15672.full). Used [SCDE](http://hms-dbmi.github.io/scde/) identify DE genes between chimp and human (candidates for human-specific function). 38 | 39 | - [Marta Rodriguez Orejuela](https://www.mdc-berlin.de/10179514/en/research/research_teams/systems_biology_of_gene_regulatory_elements/team), Characterization of adult neurogenic niches at single cell resolution 40 | 41 | 42 | 43 | ## Thursday, Sept 15 44 | 45 | ### Session 2: Chromatin Structure and Organization 46 | 47 | **Chair**: [Ido Amit](https://www.weizmann.ac.il/immunology/AmitLab/front) from [@WeizmannScience](https://twitter.com/WeizmannScience) 48 | 49 | - [Amos Tanay](http://compgenomics.weizmann.ac.il/tanay/), Single cell dynamics of clonal memory 50 | - [MARS-Seq](http://science.sciencemag.org/content/343/6172/776.abstract) - Based on CEL-Seq technology, but automates processing of cells into 384-well plates and incorporates index sorting up to 10 markers (especially useful for immune cells) 51 | 52 | - [Will Greenleaf](http://greenleaf.stanford.edu/index.html), [@WJGreenleaf](https://twitter.com/wjgreenleaf), ATAC-ing regulatory variation in single cells 53 | - Starts out with both [Waddington's](https://en.wikipedia.org/wiki/C._H._Waddington) Classical Epigenetic Landscape images - [concept of an epigenetic landscape as a visual metaphor](http://www.cell.com/cell/pdf/S0092-8674(07)00186-9.pdf) for the cell (represented by the ball), which can take specific trajectories, leading to different outcomes or cell fates 54 | - discussed [ATAC-seq](http://www.nature.com/nmeth/journal/v10/n12/full/nmeth.2688.html) (captures open chromatin sites e.g. nucleosomes, TF binding footprints, chromatin states) and [scATAC-Seq](http://www.nature.com/nature/journal/v523/n7561/fig_tab/nature14590_F1.html) using Fluidigm platform 55 | 56 | - [Stephen Clark](http://www.babraham.ac.uk/our-research/lymphocyte/geoffrey-butcher/members/65/stephen-clark), Chromatin accessibility, DNA methylation and gene expression from the same single-cell 57 | - Discussed how chromatin accessibility within genes correlates with expression. Used [scM&T-Seq](http://www.nature.com/nmeth/journal/v13/n3/fig_tab/nmeth.3728_SF1.html) (combines G&T-seq, Smart-Seq2 + scBS-seq) to sequence the methylome and transcriptome in single-cells. 58 | 59 | - [Ana Pombo](https://pombolab.wordpress.com), [@apombo1](https://twitter.com/apombo1), Genome Architecture Mapping, new approach to map chromatin contacts 60 | - Genome Architecture Mapping (GAM): approach to measuring 3-D chromatin topology in a nucleus (spatial information). Maps chromatin contacts using random cryosectioning (slices through a nucleus), extract DNA from sections to sequence, to quantify the frequency of locus co-segregation (currently 30-40 kb resolution) and calculate individual nuclear profiles (NPs). 61 | 62 | - [Peter Fraser](http://www.babraham.ac.uk/our-research/nuclear-dynamics/peter-fraser), [@Peter_Fraser1](https://twitter.com/peter_fraser1), Chromosome dynamics revealed by single cell HiC 63 | - Really cool example of using [single-cell Hi-C](http://www.nature.com/nature/journal/v502/n7469/full/nature12593.html) to investigate chromosomal conformations through stages of the cell cycle. Suggests that TADs may more reflect replication dynamics than transcription regulation. 64 | 65 | - [Amanda Ackerman](http://www.chop.edu/doctors/ackermann-amanda#.V9F6JmX_RGI), Single-cell ATAC-seq identifies epigenetic differences in human pancreatic islet cell subtypes from normal and diabetic donors 66 | - studies differences between [alpha and beta islet cells](http://www.molmetab.com/article/S2212-8778(16)00003-X/fulltext) using sc and bulk RNA-seq, ChIP-seq, BS-seq and ATAC-seq 67 | 68 | - [Jan-Philipp Mallm](https://malone.bioquant.uni-heidelberg.de/people/mallm/index-mallm.html), Dissecting Deregulated Enhancer Activity in Primary Leukemia Cells 69 | 70 | 71 | ### Session 3: Immunology and Cancer 72 | 73 | **Chair**: [John Marioni](http://www.ebi.ac.uk/research/marioni) from [@emblebi](https://twitter.com/emblebi) and [@CRUKresearch](https://twitter.com/crukresearch) 74 | 75 | - [Sarah Teichmann](http://www.teichlab.org), Understanding Cellular Heterogeneity 76 | - Discusses [sensitivity, specificity and accuracy of different scRNA-seq protocols](http://biorxiv.org/content/early/2016/09/08/073692) using ERCC spike-ins (work with [@vallens](https://twitter.com/vallens)). Found endogenous genes are more **efficiently** captured than ERCC spike-ins (counterintuitive, but pleasantly surprising). Freeze-thaw cycles decrease RNA content about 20% with each cycle. Protocols are overall very **accurate** (Pearson correlation of expected vs observed), but there are differences in **sensitivity** (especially for detecting lowly expressed genes ~1-10 molecules per cell) - you get a benefit of sequencing up to 1 million reads. 77 | - Uses [Gaussian process latent variable model](http://www.cell.com/cell-reports/fulltext/S2211-1247(15)01538-7) for dim reduction 78 | - Software include [GPfates](https://github.com/Teichlab/GPfates) (models transcriptional cell fates as mixtures of Gaussian Processes) and [TraCeR](http://www.nature.com/nmeth/journal/v13/n4/full/nmeth.3800.html) (reconstructs T-cell clonal relationships from scRNA-seq data 79 | - Advertises for [Single Cell Omics Keystone Symposia](http://keystonesymposia.org/17e3) in Stockholm May 26-30, 2017 80 | 81 | - [Ido Amit](https://www.weizmann.ac.il/immunology/AmitLab/front), Immunology in the age of single cell genomics 82 | - Combined CRISPR with [MARS-seq2](https://compgenomics.weizmann.ac.il/tanay/?page_id=672) (~10,000 cells/day, better barcoding, SNR, reproducibility and cost) for pooled index screening - based on gRNA libraries bearing RNA barcodes 83 | 84 | - [Timm Schroeder](https://www.bsse.ethz.ch/department/people/detail-person.html?persid=193443), Long-term single cell quantification: New tools for old questions 85 | - Argued that snapshots of single cells is not sufficient. Need time dimension to really understand what's happening biologically. Critical of pseudotime approaches (not as good as real time in some situations e.g. identifying cycles). Reaffirms the need for good methods software to analyze single cell data 86 | - [The Tracking Tool]((http://www.nature.com/nbt/journal/v34/n7/full/nbt.3626.html)) - for continuous single cell behavior quantification 87 | 88 | - [Fabian Theis](http://fabian.theis.name), Diffusion pseudotime identifies lineage choice and graded transitions in myeloid progenitors 89 | - Extracts pseudotemporal ordering and branch points from diffusion maps (examples from early blood development) 90 | - [Diffusion Pseudotime (DPT)](http://www.nature.com/nmeth/journal/vaop/ncurrent/full/nmeth.3971.html?WT.feed_name=subjects_genetics) software - to estimate order of differentiating cells according to DPT (measures transitions between cells using diffusion-like random walks) 91 | 92 | - [Bart Deplancke](http://deplanckelab.epfl.ch), [@BartDeplancke](https://twitter.com/bartdeplancke), Single-cell RNA-seq-based identification and characterisation of somatic stem cells in adipose tissue & beyond 93 | - [Automated Single-cell Analysis Pipeline (ASAP)](http://asap.epfl.ch) 94 | 95 | - [Matan Hofree](https://www.researchgate.net/profile/Matan_Hofree), Unbiased whole tissue analysis of the single cell transcriptional landscape of colon cancer 96 | 97 | - [Amir Giladi](http://www.weizmann.ac.il/lifesci/idcards/AmirGiladi0464.html), Transcriptional heterogeneity and lineage commitment in hematopoietic progenitors 98 | 99 | 100 | 101 | ## Friday, Sept 16 102 | 103 | ### Sesssion 4: Transcriptomics 104 | 105 | **Chair**: [Sten Linnarsson](http://linnarssonlab.org), [@slinnarsson](https://twitter.com/slinnarsson) 106 | 107 | - [Rickard Sandberg](http://sandberg.cmb.ki.se), Single-cell gene expression analyses of allelic transcription and regulation 108 | - Discussed chromosome-wide evidence of de novo paternal X chromosome inactivation in mouse embryos using scRNA-seq 109 | 110 | - [Allon Klein](http://klein.hms.harvard.edu), Population balance reconstruction of differentiation hierarchies in developing and adult tissues by single cell droplet RNA-Seq 111 | - Discussed [inDrop](http://www.cell.com/cell/abstract/S0092-8674(15)00500-0) (core facility now at 15-20K cells/hr, 80% of cells barcoded, >2K cell input, 7 cents/cell) 112 | - SPRING - software for visualizing and interacting with single cell data using a force-directed graph approach; publication coming soon. 113 | 114 | - [Arnau Sebé-Pedrós](https://compgenomics.weizmann.ac.il/tanay/?page_id=12), [@ArnauSebe](https://twitter.com/arnausebe), Early metazoan cell type evolution by single cell RNA-seq analysis 115 | 116 | - [Omid Faridani](https://www.researchgate.net/profile/Omid_Faridani2), Sequencing Small-RNA transcriptome of individual cells 117 | 118 | - [Alexander van Oudenaarden](http://www.hubrecht.eu/onderzoekers/van-oudenaarden-group/), Revealing novel cell types, cell-cell interactions, and cell lineages by single-cell sequencing 119 | - Used [single-cell strand-specific 5hmC sequencing to explore cell-to-cell variability and cell lineage reconstruction](http://www.nature.com/nbt/journal/v34/n8/full/nbt.3598.html) 120 | 121 | - [Stephanie Hicks](http://www.stephaniehicks.com), [@stephaniehicks](https://twitter.com/stephaniehicks), Towards progress in batch effects and biases single-cell RNA-Seq data [[Slides](https://speakerdeck.com/stephaniehicks/towards-progress-in-batch-effects-and-biases-in-single-cell-rna-seq-data)] 122 | - Pre-print of our [paper on bioRxiv](http://biorxiv.org/content/early/2015/12/27/025528) 123 | 124 | - [Marc Wadsworth](https://www.researchgate.net/profile/Marc_Wadsworth), Seq-Well: A Portable Single-Cell RNA-Seq Platform for Low-Input Clinical Samples 125 | - Seq-Well: the portable microarray well technology for scRNA-seq (combines microwell and bead-based approaches in a nanowell) - 10K cells/array 126 | 127 | - [Eshita Sharma](https://scholar.google.com/citations?user=xljyFDkAAAAJ&hl=en), Single cell preservation for RNAseq 128 | 129 | - [Marc Lynch](https://www.fluidigm.com/about/aboutfluidigm), Single-cell transcriptomics and functional analysis of single- cells 130 | 131 | - [Manuel Garber](http://garberlab.umassmed.edu), Dissection of T1 Diabetes progression using Single cell RNA sequencing of a RAT model 132 | - [End sequencing analysis toolkit (ESAT)](https://github.com/garber-lab/ESAT) 133 | 134 | 135 | ### Sesssion 5: Imaging and Modeling 136 | 137 | **Chair**: [Alexander van Oudenaarden](http://www.hubrecht.eu/onderzoekers/van-oudenaarden-group/) from [@_Hubrecht](https://twitter.com/_hubrecht?lang=en) 138 | 139 | - [Long Cai](http://singlecell.caltech.edu/cailab/), In situ transcription profiling in tissues by seqFISH 140 | - [SeqFISH](http://www.nature.com/nmeth/journal/v11/n4/full/nmeth.2892.html) ? multiplexed spatial transcriptomics 141 | - Clustered 15,000 imaged cells with 125 genes to identify many cell types (mapped back onto slice images) 142 | 143 | - [Heather Lee](http://www.babraham.ac.uk/our-research/epigenetics/olivia-casanueva/members/198/heather-lee), Dynamic and heterogeneous DNA methylation in pluripotent cells 144 | - uses [scBS-seq](http://go.nature.com/2ccGomv) to measure methylation 145 | 146 | - [Steffen Rulands](http://www.rulands.net), [@srulands](https://twitter.com/srulands), Dynamic and heterogeneous DNA methylation in pluripotent cells 147 | 148 | - [Jeffrey Moffitt](https://scholar.google.com/citations?user=U7eic7AAAAAJ&hl=en), High-throughput, spatially resolved, single-cell transcriptomics with MERFISH 149 | - [MERFISH](http://www.pnas.org/content/early/2016/09/07/1612826113): an image-based single cell transcriptomics method; now increased throughput for imaging many cells 150 | 151 | - [Jan Philipp Junker](https://scholar.google.com/citations?user=0tt8A_4AAAAJ), Massively parallel clonal analysis using CRISPR/Cas9 induced genetic scars 152 | 153 | - [John Marioni](http://www.ebi.ac.uk/research/marioni), Dissecting cell fate choice using single-cell genomics 154 | - [BASiCs](http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1004333) (Bayesian Analysis of Single-Cell Sequencing data): finds differentially expressed and differentially variable genes 155 | - Discussed how bulk RNA-seq normalization tools (e.g. DESeq, TMM) do not work well for scRNA-seq; points to new normalization method in [Bioconductor called scran](http://bioconductor.org/packages/release/bioc/html/scran.html) which calculates cell-specific normalization factors by pooling information across cells to avoid problems due to sparsity in scRNA-seq data 156 | - Discussed problems with spike-ins in practice; points to [Synthetic Spike-ins Controls (sequins)](http://www.nature.com/nmeth/journal/v13/n9/full/nmeth.3958.html) 157 | 158 | - [David van Dijk](https://sciencedavid.wordpress.com), MAGIC: A Diffusion based data imputation method reveals progressions and gene-gene interactions in breast cancer cells undergoing EMT 159 | - MAGIC: uses random walks/diffusion to generate low-dimension global manifold (data structure) based on local cell similarities; validates method by showing it recovers structure even after inducing a lot of sparsity 160 | 161 | - [Rom Shenhav](http://shalevlab.weizmann.ac.il/group-members/), Single-cell spatial reconstruction reveals global division of labor in the mammalian liver 162 | 163 | - [Petra Schwalie](https://scholar.google.com/citations?user=EMSKH8cAAAAJ&hl=en), Accurate identification of somatic stem cells using single-cell RNA-sequencing 164 | - Used LASSO logistic regression to to identify stem cells in adult mammalian tissue across 14 scRNA-seq adult somatic data sets (train (2/3), tested (1/3)) 165 | 166 | 167 | 168 | -------------------------------------------------------------------------------- /conferences/2016/WSDS2016.md: -------------------------------------------------------------------------------- 1 | # Notes on talks for 2016 WSDS Conference 2 | 3 | My notes and slides for the [2016 Women in Statistics and Data Science (WSDS) Conference](https://ww2.amstat.org/meetings/wsds/2016/index.cfm) 4 | at in Charlotte, North Carolina from Oct 20-22, 2016. Here is a link to the online 5 | [WSDS Program](https://ww2.amstat.org/meetings/wsds/2016/onlineprogram/index.cfm). 6 | Follow the twitter hashtag [#WSDS2016](https://twitter.com/search?q=%23WSDS2016&src=typd). 7 | Feel free to tweet me [@stephaniehicks](https://twitter.com/stephaniehicks). 8 | 9 | 10 | ## Thursday, Oct 20 11 | 12 | ### Session: The Postdoc Option: Career Impacts 13 | 14 | - Kassandra Fronczyk, Institute for Defense Analyses 15 | - Stephanie Hicks, Dana-Farber Cancer Institute/Harvard, [@stephaniehicks](https://twitter.com/stephaniehicks) 16 | - Yajuan Sophie Si, University of Wisconsin, [@sophiesiduke](https://twitter.com/sophiesiduke) 17 | 18 | I will write a blogpost soon about this topic. 19 | 20 | ### Session: Do You Hear What I Hear?: An Examination of Effective Communication 21 | 22 | - Erin Anika Wiley, Westat 23 | - Conducted a survey on presentations from statisticians. Found 5 key conclusions. 24 | 1. Listener engagement. 25 | Do: make it understandable. Address audience you have not what you want. Why does audience need to know this info? Not give theory background. For a mixer group, aim for the middle. Show how subject fits into their big picture. Make it enjoyable. Show enthusiasm. Enjoy real life stories and humor. Pay attention. Engage audience. Check for understanding along the way. Place yourself in audiences shoes. 26 | Don't: avoid text and formulas. Avoid unnecessary details. Don't go too fast. Watch for signs that audience isn't getting the message. It's not about the speaker, but about the message. 27 | 2. Tone of voice. 28 | Conversational tone: suggests peer to peer respect. vs Instructional tone: less risk of diminishing the importance of understanding. Conversational is best for the work place. 29 | 3. Good practices. 30 | **Who**: audience is important. **What**: all about the content especially for dealing with clients. **When**: structure time to keep audience engaged. **Where**: watch for signs of understanding. **Why**: make sure they get the info they need. **How**: if you think about any of the above, your presentation style is already effected. People hate jargon!!! 31 | 4. Relationships. Relationships with colleagues change over time and your communication with them will too. 32 | 5. Thoughts about email vs communication in person. 33 | - Pros: necessary and unavoidable. Can be read and referred back to. Enjoyable and pref for some. 34 | - Cons: can be too reliant. (e.g. email 3 doors down). Good for specifics but not broader discussions. Tone and intent cannot be determined. 35 | - Short emails are good. Bad grammar leaves negative impressions. Be responsible when using cc. 36 | 37 | 38 | ### Keynote Lecture: Consider your Legacy 39 | 40 | - Cynthia Z.F. Clark 41 | - Gave an inspirational talk discussing what her contributions have been in her personal and professional life. She reflected and summarized what she believed her legacy is which included: (1) family (spouse, 6 children and 18 (!!) grandchildren), (2) friends and colleagues, (3) associates she has mentored, (4) leadership of research and other improvements and contributions to US official statistics (started out teaching and ended up as a leader in statistical methods for agricultural data), (5) a strategic vision that leads her to inspiring different aspects of her life, (6) honesty and integrity in her efforts. 42 | 43 | ## Friday, Oct 21 44 | 45 | ### Keynote Address: Know Your Power 46 | 47 | - Stacy Lindborg, Biogen 48 | - Shared 5 reflections/tips on having a successful career which can feel like challenging at times or like a roller coaster: (1) We cannot afford to simply be busy. Busy does not mean progress. Failure is OK. Women underestimate their value. Men tend to overestimate value. Focus. (2) Need to learn to be dance (flexible). (3) Need to communicate. Be kind to be people; be hard on problems. (4) Need to reflect. (5) Have to be accountable to your own growth. 49 | - She noted, "we love the things that we are good at." 50 | 51 | 52 | ### Session: Forging Your Path: Turns and Detours 53 | 54 | - Michelle Dunn, NIH, Turns and Detours: Navigating Your Career 55 | - Advice on your career path: Follow your passion. It may take you through a non-traditional career path, you may fail and your passions may change over time. Four things to set yourself up for success to find new opportunities: (1) Prepare yourself intellectually and gaining the expertise. 2) persevere, (3) build a network who are motivated for your mutual gain, (4) be open to new ideas and risks. 56 | 57 | - Donna LaLonde, ASA, It's Ok to Fail 58 | - Highly suggests having a set of trusted advisors to recognize when you need to move forward or help you think through the tough decisions. When you get stuck in life, DO something to move forward! 59 | 60 | - Nancy Flournoy, University of Missouri, Knowing When to Leave 61 | - Shared very honest and personal experiences of leaving jobs. If you are in a constrained position (personally, mentally, intellectually), you can either to choose to stay constrained or you can break out into the unknown (can be a very scary thought). Networking is hugely beneficial when looking for new positions. 62 | 63 | 64 | ### Session: Career and Kids: Some Pros and Cons on Timing 65 | 66 | - Scarlett Bellamy, University of Pennsylvania 67 | - Julie Legler, St. Olaf College 68 | - Mary Dupuis Sammel, University of Pennsylvania 69 | - Kimberly Sellers, Georgetown University 70 | - Jing Zhao, Merck 71 | 72 | 73 | ### Session: Past, Current, and Future: ASA Presidents' Perspectives 74 | 75 | Panel of Past, Present, and Future ASA Presidents 76 | 77 | - Lynne Billard, University of Georgia 78 | - Mary Ellen Bock, Purdue University. Discussed the importance of supporting non-white women in this field. 79 | - Nancy Geller, Office of Biostatistics Research. "I find it necessary to speak in groups when there are few women there." 80 | - Sally Morton, University of Pittsburgh, [@sallycmorton](https://twitter.com/sallycmorton). Says she worked very hard when she was young and then had to learn how to work efficiently when she had a family. Her career now is about helping other people's careers. 81 | - Jessica Utts, University of California, [@JessicaUtts](https://twitter.com/JessicaUtts). If she was 18 and could choose a different career, she says she would write historical novels and travel the world doing the research needed to write the novels. 82 | 83 | ### Session: Legal Perspectives for Women in Statistics 84 | 85 | - Mary W. Gray, American University, [@AmericanU](https://twitter.com/AmericanU) 86 | - Fascinating discussion on what US laws exist to protect women. Wear's a 3/4 euro pin to promote "equal pay for equal work" referring to the Equal Pay Act in 1963 and Title VII in 1964. 87 | 88 | 89 | ## Saturday, Oct 22 90 | 91 | ### Keynote Address: Big Data and Grand Challenges in the Federal Statistical Agencies Presented 92 | 93 | - Wendy L Martinez, Bureau of Labor Statistics, [@BLS_gov](https://twitter.com/BLS_gov) 94 | - Discussed "Big Data" in the context of the three V's (Laney, 2001) - Volume (size of n and p), Velocity (speed, real-time), Variety (complexity, disparate sources). At the Bureau of Labor Statistics, "big data" is called "Alternative data sources". She stressed the importance of analysis, statistics & data science vs just discussing "Big Data". 95 | - G.Press (Forbes) defines "Data Science" as "more of a discipline for dealing with big data than a specific technology". ASA cites (1) Database management, (2) statistics & machine learning (3) distributed parallel learning as "Data Science" 96 | - She discussed various training programs in data science (e.g. to a program at VT). Highlighting MOOCs, NIH Big Data to Knowledge (BD2K) program 97 | 98 | ### Session: Effective Leadership 99 | 100 | - Kim-Anh Do, MD Anderson 101 | - Jane Pendergast, Duke University 102 | - Nancy Reid, University of Toronto 103 | - Kathryn Roeder, Carnegie Mellon University. She says when you share credit it reflects well on you. Be tenacious. 104 | 105 | ### Keynote Address: A Holistic Approach to Interdisciplinary Research 106 | 107 | - Bin Yu, University of California, Berkeley 108 | - Has a people centric view of life and research (people are mysteries to unveil just like research). Grew up during the cultural revolution in China (1966-1976) where the universities stopped for 10 years. Had three PhD advisors: Lucien Le Cam, Terry Speed, Jorma Rissanen. She most appreciates intellectual diversity in collaboration and research 109 | 110 | -------------------------------------------------------------------------------- /conferences/2017/BioC2017.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stephaniehicks/classroomNotes/4345de3076378c46a35aa3eeeef6494332e0737c/conferences/2017/BioC2017.md -------------------------------------------------------------------------------- /conferences/2017/JSM2017.md: -------------------------------------------------------------------------------- 1 | # Notes on talks for the Joint Statistical Meetings (JSM) 2017 2 | 3 | * [JSM Online Program](https://ww2.amstat.org/meetings/jsm/2017/onlineprogram/MainSearchResults.cfm) 4 | * Follow [#JSM2017 tweets here](https://twitter.com/search?q=%23JSM2017&src=tyah) 5 | * There is even a [JSM 2017 app](https://ww2.amstat.org/meetings/jsm/2017/jsmapp.cfm) that you can download 6 | 7 | 8 | ## My agenda 9 | 10 | These are the sessions I'm interested in attending. I know there a lot listed in the same time slots, but I'm hoping to catch a few talks in different ones. The numbers at the beginning list the session number. If anyone is interested, my talk is on Tues 2-3:50pm in [Session 408 titled Methods for Single-Cell Genomic Analysis](https://ww2.amstat.org/meetings/jsm/2017/onlineprogram/ActivityDetails.cfm?SessionID=214369) 11 | 12 | #### Sunday 13 | 14 | 2-3:50pm 15 | 16 | * 8 - Statistics and the Reproducibility Crisis (Invited) 17 | * 2:05pm - The Tools for Reproducibility Exist; P-Values Aren't the Problem; It's Time for the Real Work of Data Science ([Jeffrey Leek](), JHSPH) 18 | * 2:30pm - P-Values: Variability, Reproducibility and Lessons from Multiple Testing ([Naomi Altman](), Penn State) 19 | * 2:55pm - Resolving the Reproducibility Crisis Using Bayesian Inference ([Andrew Gelman](), Columbia) 20 | * 12 - Bridging BFF (Bayesian/Fiducial/Frequentist) Inference in the Era of Data Science (Invited) 21 | * 2:05pm - BFF Inferences with Rs: Replications, Relevance and Robustness (Xiao-Li Meng, Harvard) 22 | * 2:30pm - The Use of Rejection Odds and Rejection Ratios in Testing Hypotheses (James Berger, Duke) 23 | * 2:55pm - New Perspectives of P-Value and C-Factor for Hypothesis Testing (Regina Y Liu, Rutgers) 24 | * 24 - Statistical Computing and Graphics Student Awards (Topic-Contributed) 25 | * 25 - Teaching Biostatistics Online: A Discussion and Debate of Problems and Solutions (Topic-Contributed Panel) 26 | 27 | 3:30-4:30 28 | 29 | * Spotlight Baltimore: Berger Cookies (CC-Halls A&B) 30 | 31 | 4-5:50pm 32 | 33 | * 47 - Challenges in the Integrative Analysis of Multiple Genomics Studies (Invited) 34 | * 4:05pm - Integrative Genetic Risk Prediction Using Nonparametric Empirical Bayes Classification (Sihai Dave Zhao, Illinois at Urbana-Champaign) 35 | * 4:30pm - Estimating Effect-Size Distribution from Summary-Level Statistics for Large Genome-Wide Association Studies (Yan Zhang, JHSPH) 36 | * 4:55pm - Selective Inference in Genomics (Chiara Sabatti, Stanford) 37 | * 54 - Enabling Reproducibility in Statistical Translations of Genomics Data for Biomedical Research (Invited) 38 | * 75 - Statistical Genomics in Cancer (Contributed) 39 | 40 | 6-8pm 41 | 42 | * [Women in Mathematics Society (WiMS) Networking Session](https://ww2.amstat.org/meetings/jsm/2017/onlineprogram/ActivityDetails.cfm?SessionID=214682) (H-Key Ballroom 7) 43 | 44 | 8:30-10:30pm 45 | 46 | * [JSM Opening Mixer](https://ww2.amstat.org/meetings/jsm/2017/onlineprogram/ActivityDetails.cfm?SessionID=214654) and [Poster Session](https://ww2.amstat.org/meetings/jsm/2017/onlineprogram/ActivityDetails.cfm?SessionID=214471) (CC-Halls A&B) 47 | 48 | 49 | #### Monday 50 | 51 | 8:30-10:20am 52 | 53 | * 90 - Late-Breaking Session I: National Governments, Coerced Narratives, Creative Language, and Alternative Facts (Invited Special Presentation) 54 | * 101 - Foundation for Big Data Analysis (Invited) 55 | * 104 - How Funding Agencies and Journals Are Encouraging Reproducible Research and the Role of Statisticians (Invited Panel) 56 | * 109 - Learning from External Covariates in High-Dimensional Genomic Data Analysis (Topic-Contributed) 57 | * 129 - Quantile and Nonparametric Regression Models (Contributed) 58 | * 131 - Predictive Modeling in Data Science (Contributed) 59 | 60 | 10-10:45am 61 | 62 | * Spotlight Baltimore: JSM Coffee House (CC-Halls A&B) 63 | 64 | 10:30am-12:20pm 65 | 66 | * 132 - Introductory Overview Lecture: Computer Age Statistical Inference (Invited) 67 | * 142 - Recent Statistical Advances in Single-Cell RNA-Seq Analysis (Invited) 68 | * 10:35am - SCnorm: a Quantile-Regression Based Approach for Robust Normalization of Single-Cell RNA-Seq Data (Christina Kendziorski, University of Wisconsin - Madison) 69 | * 11:00am - On the Widespread and Critical Impact of Systematic Bias and Batch Effects in Single-Cell RNA-Seq Data (Rafael Irizarry, Harvard SPH) 70 | * 11:25am - Statistical Methods for Assessing Transcriptional Changes and Characterizing Heterogeneity in Single-Cell RNA-Seq Data (Raphael Gottardo, Fred Hutch) 71 | * 11:50am - Global Spectral Clustering in Dynamic Gene Expression Networks (Kathryn Roeder, Carnegie Mellon) 72 | * 143 - Advancing Translational Research Using Novel Statistical Analyses for Complex and Omics Data (Invited) 73 | * 152 - Recent Development in Sufficient Dimension Reduction (Topic-Contributed) 74 | 75 | 12-1:30pm 76 | 77 | * Rice University, Department of Statistics Alumni Lunch 78 | 79 | 12:30-2:30pm 80 | 81 | * Caucus for Women in Statistics Roundtable Lunch 82 | 83 | 1:30-2:30pm 84 | 85 | * Spotlight Baltimore: Popcorn Break (CC-Halls A&B) 86 | 87 | 2-3:50pm 88 | 89 | * 200 - Introductory Overview Lecture: Data Science: A Collaboration of Statistics and Computer Science (Invited) 90 | * 201 - Essential Recent Papers in Stat (Invited) 91 | * 204 - Recent Development in Statistical Methods for Analyzing Big and Complex Neuroimaging Data (Invited) 92 | * 213 - Training Statisticians to Be Effective Instructors (Invited Panel) 93 | * 214 - Implicit Bias and the Profession of Statistics (Invited Panel) 94 | * 221 - Advanced Statistical Methods for Microbiome Data Analysis (Topic-Contributed) 95 | * 237 - Feature Selection and Statistical Learning in Genomics (Contributed) 96 | 97 | 3:30-4:30pm 98 | 99 | * Spotlight Baltimore: Baltimore Microbrew Tasting (CC-Halls A&B) 100 | 101 | 4-5:50pm 102 | 103 | * 254 - ASA President's Invited Speaker: Jo Craven McGinty, *The Wall Street Journal* 104 | 105 | 5:30-7:00pm 106 | 107 | * Section on Statistics in Genomics and Genetics Business Meeting (CC-306) 108 | 109 | 6-8:00pm 110 | 111 | * Sections on Statistical Computing and Graphics Mixer (H-Key Ballroom 1) 112 | 113 | 6:30-8:30pm 114 | 115 | * Caucus for Women in Statistics Reception and Business Meeting (H-Holiday Ballroom 1&2) 116 | * Harvard University Joint Biostatistics-Statistics JSM Reception (H-Key Ballroom 8) 117 | 118 | 8-9:30pm 119 | 120 | * 255 - IMS Presidential Address and Awards Ceremony: Jon A. Wellner, University of Washington 121 | 122 | 123 | #### Tuesday 124 | 125 | 8:30-10:20am 126 | 127 | * 263 - Introductory Overview Lecture: Network Data, Modeling, Analysis, and Applications (Invited) 128 | * 264 - Statistical Methods for Novel Imaging Technology (Invited) 129 | * 266 - Novel Approaches to First Statistics / Data Science Course (Invited) 130 | * 304 - Statistical Learning: Dimension Reduction (Contributed) 131 | 132 | 10-10:45am 133 | 134 | * Spotlight Baltimore: Get Your JSM Energy Fix (CC-Halls A&B) 135 | 136 | 10:30am-12:20pm 137 | 138 | * 305 - Late-Breaking Session II: Hindsight is 20/20 and for 2020: Lessons from 2016 Elections (Invited) 139 | * 308 - Essential Survival Tips for Junior Researchers (Invited) 140 | * 323 - Recent Methods and Tools in Analyzing Human Microbiome Data (Topic-Contributed) 141 | * 336 - Next- Generation Sequencing (Contributed) 142 | 143 | 12:30-2pm 144 | 145 | * ASA Committee on Women in Statistics Business Meeting (CC-335) 146 | 147 | 1:30-2:30pm 148 | 149 | * Spotlight Baltimore: Popcorn Break (CC-Halls A&B) 150 | 151 | 2-3:50pm 152 | 153 | * 375 - Negative Results: They're Essential! (Invited) 154 | * 378 - Statistics in Biosciences Special Invited Papers: Genomics, Metagenomics, and Imaging (Invited) 155 | * 380 - Recent Advances in High-Dimensional Statistics and Computational Methods (Invited) 156 | * 389 - The Essential Power of Interactive Graphics (Invited) 157 | * 395 - Recent Advances in Zero-Inflated Regression Models (Topic-Contributed) 158 | * 408 - Methods for Single-Cell Genomic Analysis (Contributed) 159 | 160 | 3:30-4:30pm 161 | 162 | * Spotlight Baltimore: Experience Maryland Wines (CC-Halls A&B) 163 | 164 | 4-5:50pm 165 | 166 | * 427 - Deming Lecture: Fritz Scheuren (CC-Hall D) 167 | 168 | 5-6pm 169 | 170 | * Section on Statistical Learning and Data Science Meeting (H-Ruth) 171 | 172 | 8-9:30pm 173 | 174 | * ASA President's Address and Founders & Fellows Recognition (CC-Hall D) 175 | 176 | 9:30-12am 177 | 178 | * JSM Dance Party (CC-Ballroom II) 179 | 180 | #### Wednesday 181 | 182 | 8:30-10:20am 183 | 184 | * 441 - The Key to Integrative Analysis for Precision Medicine: Statistics! (Invited) 185 | * 445 - Quantification, Association Testing, and Integration of Micriobiome (Invited) 186 | * 451 - Current Trends in Statistical Genomics: Finding Needle in a Haystack? (Topic-Contributed) 187 | * 460 - Clustering Methods for Big Data Problems (Topic-Contributed) 188 | * 465 - Biometrics and High-Dimensional Data (Contributed) 189 | 190 | 10-10:45am 191 | 192 | * Spotlight Baltimore: JSM Coffee House (CC-Halls A&B) 193 | 194 | 10:30am-12:20pm 195 | 196 | * 477 - Bayesian Methods for High-Dimensional Inference (Invited) 197 | * 479 - Statistical Analysis of Complex Imaging Data (Invited) 198 | * 480 - Modernizing the Undergraduate Statistics Curriculum (Invited) [slides](https://github.com/Amherst-Statistics/Modernizing-Undergrad-Stat-Curric) 199 | * 502 - Essential Skills for Communicating Statistics (Topic-Contributed Panel) 200 | * 513 - Gene Expression Analysis (Contributed) 201 | 202 | 2-3:50pm 203 | 204 | * 548 - The Evolution and Future Direction of Statistical Computing and Visualization (Invited) 205 | * 555 - Statistical Analysis of Epigenetics Data (Invited) 206 | * 562 - Success in Interdisciplinary Research (Invited) 207 | * 565 - Data Science in Statistical Genomics: Challenges and Solutions (Topic-Contributed) 208 | * 574 - Being Research Active in Teaching-Focused Colleges (Topic-Contributed Panel) 209 | * 587 - Recent Advances in Statistical Graphics (Contributed) 210 | 211 | 4-5:50pm 212 | 213 | * 590 - COPSS Awards and Fisher Lecture: Robert E. Kass (CC-Hall D) 214 | 215 | #### Thursday 216 | 217 | 8:30-10:20am 218 | 219 | * 599 - Creating Interactive Graphics (Invited) 220 | * 602 - Bridging the Gap Between Statistics and Other Data Sciences: Where's the Bridge? Where's the Gap? (Invited Panel) 221 | 222 | 10:30am-12:20pm 223 | 224 | * 654 - Teaching Introductory Statistics Using Simulation-Based Inference Methods (Topic-Contributed) 225 | 226 | 227 | -------------------------------------------------------------------------------- /conferences/2017/scWorkshopAscona2017.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stephaniehicks/classroomNotes/4345de3076378c46a35aa3eeeef6494332e0737c/conferences/2017/scWorkshopAscona2017.md -------------------------------------------------------------------------------- /conferences/2018/JSM2018.md: -------------------------------------------------------------------------------- 1 | # Notes on talks for the Joint Statistical Meetings (JSM) 2018 2 | 3 | * [JSM Online Program](http://ww2.amstat.org/meetings/jsm/2018/onlineprogram/index.cfm) 4 | * Follow [#JSM2018 tweets here](https://twitter.com/search?src=typd&q=%23jsm2018) 5 | 6 | ## My agenda 7 | 8 | These are the sessions I'm interested in attending. I know there a lot listed in the same time slots, but I'm hoping to catch a few talks in different ones. The numbers at the beginning list the session number. FWIW, I have organized a late-breaking session on [Addressing Sexual Misconduct in the Statistics Community](http://ww2.amstat.org/meetings/jsm/2018/onlineprogram/ActivityDetails.cfm?SessionID=215487) on Mon 2-3:50pm, Rafael Irizary is giving an invited talk on a paper I co-wrote detailing a [Guide to Teaching Data Science](http://ww2.amstat.org/meetings/jsm/2018/onlineprogram/ActivityDetails.cfm?SessionID=215246) on Wed 10:30-12:20pm, and I'm giving a talk on [Missing Data in Single-cell RNA-Sequencing](http://ww2.amstat.org/meetings/jsm/2018/onlineprogram/ActivityDetails.cfm?SessionID=215111) on Thurs 10:30-12:20pm. Rafa and I are also giving a professional development continuing education courses titled [Data Science for Statisticians](http://ww2.amstat.org/meetings/jsm/2018/onlineprogram/ActivityDetails.cfm?SessionID=215370) on Tues 1-5pm. 9 | 10 | 11 | #### Sunday 12 | 13 | 1-2:00pm 14 | 15 | * Spotlight Vancouver Kick-off (CC-West Hall B) 16 | 17 | 2-3:50pm 18 | * 2 - Introductory Overview Lecture: The Deep Learning Revolution (Invited) 19 | * 4 - Transparency, Reproducibility and Replicability in Work with Social and Economic Data (Invited) 20 | * 9 - Data Science Education - Successes and Challenges: Stories from the classroom and beyond (Invited) 21 | * 12 - Novel Statistical Methods for Analyzing Electronic Health Records and Biobank Data (Invited) 22 | * 16 - Big Data Detectives: Improving Human Health through Informing Policy (Invited) 23 | * 29 - SPEED: An Ensemble of Advances in Genomics and Genetics (Contributed Speed) 24 | * 39 - Topics in Clustering (Contributed) 25 | 26 | 3:30-4:30pm 27 | 28 | * Spotlight Vancouver: Tasty Vancouver Fruit Tartelettes (CC-West Hall B) 29 | 30 | 4-5:50pm 31 | 32 | * 42 - Introductory Overview Lecture: Examining What and How We Teach at All Levels: Key Ideas to Ensure the Progress and Relevance of Statistics (Invited) 33 | * 49 - Skills to Leverage and Gaps to Fill to Thrive in Data Science (Invited) 34 | * 50 - Which sessions should this go to? Text analytics to the rescue of conference committees (Invited) 35 | * 54 - The Good, the Bad, and the Ugly: The Future of Statistics and the Public (Invited) 36 | * 63 - Omics Data: Study Design, Power and Sample Size (Topic Contributed) 37 | * 74 - Challenges and Approaches to Teaching Statistics in the Health Sciences (Contributed) 38 | * 81 - New development in epigenome-wide association studies (Contributed) 39 | 40 | 5:05-5:50pm 41 | 42 | * 85 - SPEED: An Ensemble of Advances in Genomics and Genetics (Contributed Poster) 43 | 44 | 8-10pm 45 | 46 | * Dinner with Keegan Korthauer and Kieran Campbell 47 | 48 | 8:30-10:30pm 49 | 50 | * [JSM Opening Mixer](http://ww2.amstat.org/meetings/jsm/2018/onlineprogram/ActivityDetails.cfm?SessionID=216595) and [ePoster Session](http://ww2.amstat.org/meetings/jsm/2018/onlineprogram/ActivityDetails.cfm?SessionID=215612) 51 | 52 | 53 | #### Monday 54 | 55 | 8:30-10:20am 56 | 57 | * 99 - Single Cell Sequencing and Cancer Genomics (Invited) 58 | * 104 - Visualization and Reproducibility - Challenges and Best Practices (Invited) 59 | * 115 - Papers in Honor of Professor James R Thompson (1938-2017) (Topic Contributed) 60 | * 118 - SPEED: Teaching Statistics: Strategies and Applications (Contributed Speed) 61 | 62 | 10-10:45am 63 | 64 | * Spotlight Vancouver: Insider Tips (CC-West Hall B) 65 | * Spotlight Vancouver: JSM Coffee House (CC-West Hall B) 66 | 67 | 10:30am-12:20pm 68 | 69 | * 138 - Statistical Methods for Electronic Healthcare Data (Invited) 70 | * 139 - Competing Effectively: Hosting, Designing, and Participating in Kaggle-Style Competitions (Invited) 71 | * 141 - Recent Advances in High-Dimensional Bayesian Model Selection (Invited) 72 | * 142 - Metabolomics Data Analytics - the New Frontier in Precision Medicine (Invited) 73 | * 165 - SPEED: Environmetrics: Spatio-Temporal and Other Models (Contributed) 74 | * 167 - Statistical Computing and Statistical Graphics: Student Paper Award and Chambers Statistical Software Award (Contributed) 75 | * 178 - Statistical Methods for Analysis of Heterogeneous Tissue Samples in Bulk and Single-Cell Sequencing Data (Contributed) 76 | 77 | 12-1:30pm 78 | 79 | * Rice University, Department of Statistics Reception 80 | 81 | 12:30-2:00pm 82 | 83 | * ASA Committee on Women in Statistics Business Meeting 84 | 85 | 1:30-2:30pm 86 | 87 | * Spotlight Vancouver: Popcorn Break (CC-West Hall B) 88 | 89 | 2-3:50pm 90 | 91 | * 211 - Late Breaking Session: Addressing Sexual Misconduct in the Statistics Community (Invited Special Presentation) 92 | * 212 - An Emerging Ecosystem for Data Science/Statistics Education (Invited) 93 | * 214 - Academic Publication Is Dead, Long Live Academic Publication (Invited) 94 | 95 | 3:30-4:30pm 96 | 97 | * Spotlight Vancouver: Vancouver Microbrew Tasting 98 | 99 | 4-5:50pm 100 | 101 | * Section on Statistical Learning and Data Science Business Meeting (CC-East 18) 102 | * 261 - ASA President's Invited Address 103 | 104 | 5:30-7:00pm 105 | 106 | * Section on Statistics in Genomics and Genetics Business Meeting (F-Mackenzie II) 107 | 108 | 6-8:00pm 109 | 110 | * Sections on Statistical Computing and Graphics Mixer (CC-West 113) 111 | * Harvard University Joint Biostatistics-Statistics JSM Reception (M-Pinnacle II) 112 | * Section on Teaching of Statistics in the Health Sciences Business Meeting and Mixer (CC-East 7) 113 | 114 | 7-10:00pm 115 | 116 | * Caucus for Women in Statistics Reception and Business Meeting (F-Malaspina) 117 | 118 | 119 | #### Tuesday 120 | 121 | 8:30-10:20am 122 | 123 | * 271 - Introductory Overview Lecture: Reproducibility, Efficient Workflows, and Rich Environments (Invited) 124 | * 276 - Addressing Emerging Statistical Challenges in Microbiome Studies (Invited) 125 | * 285 - Advances in Dimension Reduction and Model Selection for Statistically Challenging Data (Topic Contributed) 126 | * 288 - Genomical Is the New Astronomical: Big Data Algorithms and Applications in Genomics (Topic Contributed) 127 | * 291 - Statistical Applications in Forensic Evidence (Topic Contributed) 128 | * 299 - SPEED: Recent Advances in Statistical Genomics and Genetics (Contributed) 129 | 130 | 10-10:45am 131 | 132 | * Spotlight Vancouver: Get Your JSM Energy Fix (CC-West Hall B) 133 | 134 | 10:30-11:15am 135 | 136 | * 366 - SPEED: Recent Advances in Statistical Genomics and Genetics (Contributed Poster) 137 | 138 | 10:30am-12:20pm 139 | 140 | * 316 - Late-Breaking Session: Statistical Issues in Application of Machine Learning to High Stakes Decisions (Invited) 141 | * 318 - Advances on the Analysis of Single-Cell Sequencing Data 142 | * 321 - Detecting Structural Change in Complex Data (Invited) 143 | * 328 - What Should Be the Role of Collaboration/Consulting for Applied Statistical Faculty Members in Academia: Rewards and Punishments (Invited Panel) 144 | * 353 - Data Science (Contributed) 145 | 146 | 12:30pm-2pm 147 | 148 | * SDSS Planning Meeting (F-Terrace Room) 149 | 150 | 1-5:00pm 151 | 152 | * Professional Development Continuing Education Course: Data Science for Statisticians (CC-East 11) 153 | 154 | 1:30-2:30pm 155 | 156 | * Spotlight Vancouver: Popcorn Break (CC-West Hall B) 157 | 158 | 2-3:50pm 159 | 160 | * 386 - Recent Developments in Integrating Multiple-Omics Data in Complex Diseases (Invited) 161 | * 389 - Improving Survey Data Quality with Machine Learning Techniques (Invited) 162 | * 390 - Accessing Resources from the Web in Data Analysis (Invited) 163 | * 397 - Statistical Learning for Epigenomics Data (Topic Contributed) 164 | * 403 - The Power of Podcast: Promoting Statistics and Data Science in the Age of Social Media (Topic Contributed) 165 | 166 | 3:30-4:30pm 167 | 168 | * Spotlight Vancouver: Experience BC Wines (CC-West Hall B) 169 | 170 | 4-5:50pm 171 | 172 | * 437 - Deming Lecture: John L. Eltinge, United States Census Bureau (CC-West Ballroom BC) 173 | 174 | 6:30-9:30pm 175 | 176 | * Dinner cruise 177 | 178 | 8-9:30pm 179 | 180 | * ASA President's Address and Founders and Fellows Recognition (CC-West Ballroom BC) 181 | 182 | 8:30pm-12am 183 | 184 | * JHU Mixer 185 | 186 | 9:30-12am 187 | 188 | * JSM Dance Party (CC-West Ballroom D) 189 | 190 | 191 | #### Wednesday 192 | 193 | 7:45-8:20am 194 | 195 | * Hubki meetup 196 | 197 | 8:30-10:20am 198 | 199 | * 448 - Introductory Overview Lecture: The Statistical and Data Revolution in the Social Sciences (Invited) 200 | * 449 - Recent Advances in Change-Point Detection and Segmentation (Invited) 201 | * 452 - Advancements in Complex Functional Data Analysis (Invited) 202 | * 456 - Introductory Lectures on Recent Advancements in Computational Statistics (Invited) 203 | * 459 - Impostor Syndrome (Invited) 204 | * 461 - Bugs, Bugs Everywhere - the Statistics Behind Our Microbiome (Topic Contributed) 205 | * 467 - Statistical Advances for Cancer Genomics and Immunogenomics - from Single-Cell to Correlated Population (Topic Contributed) 206 | * 471 - Innovative and Effective Teaching for Large-Enrollment Statistics and Data Science Courses (Topic Contributed) 207 | * 478 - Missing Data (Contributed) 208 | * 490 - Advances in Methods for the Accurate Measurement of High-Throughput Sequencing Data (Contributed) 209 | 210 | 10-10:45am 211 | 212 | * Spotlight Vancouver: JSM Coffee House (CC-West Hall B) 213 | 214 | 10:30am-12:20pm 215 | 216 | * 496 - Building a Computing Age #StatisticsCurriculum for Biomedical Scientists (Invited) 217 | * 502 - Choose Your Own Adventure: Next Steps in a Programming/Analysis Career (Invited) 218 | * 519 - So You Think You Want to Be a Department Chair? Rewards, Challenges, and Balance (Topic Contributed) 219 | * 535 - Contributed Poster Presentations: Section on Statistics in Genomics and Genetics (Contributed Poster) 220 | 221 | 2-3:50pm 222 | 223 | * 554 - Deep Learning and Statistical Modeling with Applications (Invited) 224 | * 555 - The State of Peer-Review and Publication in Statistics and the Sciences (Invited) 225 | * 567 - Are We (Academia) Producing Leaders with Necessary Statistical Skills? (Invited Panel) 226 | * 595 - Recent Methods Development on RNA-Seq Data Analysis (Contributed) 227 | 228 | 4-5:50pm 229 | 230 | * 597 - COPSS Awards and Fisher Lecture: Susan Murphy, Harvard University (CC-West Ballroom BC) 231 | 232 | 6:15pm 233 | 234 | * Dinner with NewPI Slack members 235 | 236 | #### Thursday 237 | 238 | 8:30-10:20am 239 | 240 | * 603 - Statistical Inference for Precision Medicine and Subgroup Analysis (Invited) 241 | * 609 - Foundation or Backdrop? - the Role of Statisticians in Academic Data Science Initiatives (Invited Panel) 242 | 243 | 10:30am-12:20pm 244 | 245 | * 639 - Causal Inference Meets Statistical Learning with Complex Data (Invited) 246 | * 642 - Data Science for Social Good (Invited) 247 | * 647 - Current Federal Research on Improving Measurement of LGBT Populations (Invited) 248 | * 648 - Statistical Challenges in the Analysis of EHR Data (Invited) 249 | * 649 - The 'Ergonomics' of Statistics and Data Science (Invited) 250 | * 651 - Expanding the Tent: Undergraduate Majors in Data Science (Invited) 251 | * 654 - New Methodology Developments in Single Cell RNA-Seq (Topic Contributed) 252 | * 658 - Recent Statistical Advances in Genomic and Genetic Data Analysis (Topic Contributed) 253 | 254 | 255 | -------------------------------------------------------------------------------- /conferences/2019-jsm.md: -------------------------------------------------------------------------------- 1 | # Notes on talks for the Joint Statistical Meetings (JSM) 2019 2 | 3 | * [JSM Online Program](https://ww2.amstat.org/meetings/jsm/2019/onlineprogram/index.cfm) 4 | * Follow [#JSM2019 tweets here](https://twitter.com/hashtag/JSM2019) 5 | 6 | ## My agenda 7 | 8 | #### Sunday 9 | 10 | 7:30-8:30 11 | 12 | * Dinner plans 13 | 14 | 8:30-10:30pm 15 | 16 | * JSM Opening Mixer and ePoster Session (CC-Hall C) 17 | 18 | 19 | #### Monday 20 | 21 | 8:30-10:20am 22 | 23 | * 97 - Introductory Overview Lecture: Likelihood Principle (Invited) 24 | * 102 - Challenges and Developments in Microbiome Data Science (Invited) 25 | 26 | 9-9:45am 27 | 28 | * Spotlight Denver: Insider Tips 29 | 30 | 10-10:45am 31 | 32 | * Spotlight Denver: JSM Coffee House 33 | 34 | 10:30am-12:20pm 35 | 36 | * 152 - Making an Impact in Statistics Education: Waller Award Winner Perspectives (Invited) 37 | * 155 - Research Reproducibility for Precision Medicine: From Controlled Experiments to Real-World Evidence (Topic Contributed) 38 | * 183-194 Contributed Poster Presentations (CC-Hall C) 39 | 40 | 41 | 12-1:30pm 42 | 43 | * Rice University, Department of Statistics Reception (H-Capitol Ballroom 7) 44 | 45 | 12:30-2:00pm 46 | 47 | * ASA Committee on Women in Statistics Business Meeting 48 | 49 | 1:30-2:30pm 50 | 51 | * Spotlight Denver: Popcorn Break (CC-West Hall B) 52 | 53 | 2-3:50pm 54 | 55 | * 211 - Getting to the Slope of Enlightenment with EHR Data (Invited) 56 | * 217 - Computing Making Impact: The Best of JCGS (Invited) 57 | * 219 - Making an Impact in Statistics Education Through Innovation and Outreach (Invited) 58 | * 224 - Sexual Harassment and Assault -Confronting the Threat to Our Statistical Community (Invited) 59 | 60 | 3:30-4:30pm 61 | 62 | * Spotlight Denver: Denver Microbrew Tasting 63 | 64 | 4-5:50pm 65 | 66 | * Section on Statistical Learning and Data Science Business Meeting (CC-206) 67 | * 261 - ASA President's Invited Address 68 | 69 | 6-8:00pm 70 | 71 | * Section on Teaching of Statistics in the Health Sciences Mixer (H-Mineral Hall B) 72 | * Caucus for Women in Statistics Reception and Business Meeting (H-Centennial Ballroom C) 73 | 74 | 8-9:30pm 75 | 76 | * IMS Presidential Address and Awards Ceremony (Xiao-Li Meng) 77 | 78 | 79 | #### Tuesday 80 | 81 | 8:30-10:20am 82 | 83 | * 281 - When Statistical Methods Impact Policy (Invited) 84 | 85 | 9:25-10:10am 86 | 87 | * 310- Contributed Poster Presentations (CC-Hall C) 88 | 89 | 10-10:45am 90 | 91 | * Spotlight Denver: Get Your JSM Energy Fix 92 | 93 | 10:30am-12:20pm 94 | 95 | * 312 - Theory for Deep Neural Networks (Invited) 96 | * 314 - They Never Die: a Historical Overview of the Many Uses of Famous Historic Data Sets (Invited) 97 | * 351 - Statistical Methods for Single-Cell Genomics (Contributed) (CC-101) 98 | 99 | 12:30pm-2pm 100 | 101 | * SDSS Planning Meeting (H-Agate B) 102 | 103 | 1:30-2:30pm 104 | 105 | * Spotlight Denver: Popcorn Break 106 | 107 | 2-3:50pm 108 | 109 | * 374 - Statistics in Biosciences (SIB) Special Invited Session -Impacts of Statistics in Genomics and Imaging (Invited) 110 | * 387 - Florence Nightingale David Award (Invited) 111 | * 388 - Building Bridges for Data Science Education (Invited) 112 | * 400 - Changing the Statistics Community: Effective Strategies for Promoting an Inclusive and Equitable Culture for Women (Topic Contributed) 113 | * 401 - Why JavaScript? (Topic Contributed) 114 | 115 | 3:30-4:30pm 116 | 117 | * Spotlight Denver: Sample Denver Wines 118 | 119 | 4-5:50pm 120 | 121 | * 428 - Deming Lecture (CC-Four Seasons 2-4) 122 | 123 | 5-7pm 124 | 125 | * Dinner plans 126 | 127 | 5:30-7:00pm 128 | 129 | * Section on Statistics in Genomics and Genetics Business Meeting (CC-304) 130 | 131 | 6-8pm 132 | 133 | * Harvard University Joint Biostatistics-Statistics JSM Reception (H - Centennial Ballroom F) 134 | 135 | 8-9:30pm 136 | 137 | * ASA President's Address and Awards (CC-Four Seasons 2-4) 138 | 139 | 8-11pm 140 | 141 | * Johns Hopkis Mixer 142 | 143 | 9:30-12am 144 | 145 | * JSM Dance Party (H-Centennial Ballrooms D-E) 146 | -------------------------------------------------------------------------------- /figures/permissionSettings.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stephaniehicks/classroomNotes/4345de3076378c46a35aa3eeeef6494332e0737c/figures/permissionSettings.png -------------------------------------------------------------------------------- /teachers_pet-GitHubClassroom.md: -------------------------------------------------------------------------------- 1 | # Using GitHub in the Classroom 2 | 3 | GitHub offers private (and of course public) repositories for students to use in the classroom through its [education initiative](https://education.github.com). This give students hands-on experience with version control and writing code in an individual setting (e.g. homework assignments) or collaborative setting (e.g. final projects). If you would like your students to submit assignments using git/GitHub, this is a tutorial that walks you through the process of setting it up. 4 | 5 | Here, I'm demonstrating the ideas using the [GitHub Organization datasciencelabs-students](https://github.com/datasciencelabs-students), 6 | which was created for submitting homework assignments in the [Introduction to Data Science course](http://datasciencelabs.github.io/) at the Harvard School of Public Health. We followed the [GitHub Education Classroom guide](https://education.github.com/guide) for this. To create private repositories for each student for each homework assignment, we followed the [sandboxing setup](https://education.github.com/guide/sandboxing). 7 | 8 | For more information about [`teachers_pet`](http://www.rubydoc.info/gems/teachers_pet) 9 | 10 | # Setting up `teachers_pet` 11 | 12 | 1. Set up [two factor authentication on GitHub](https://help.github.com/articles/about-two-factor-authentication/) with your mobile device (e.g. google authenticator). You may have to [check the SSH key on GitHub matches SSH key on your computer](https://help.github.com/articles/generating-an-ssh-key/). 13 | 14 | 2. Create an [access token for command line](https://help.github.com/articles/creating-an-access-token-for-command-line-use/). Save this token immediately in `.bash_profile` and add a phone number as backup. 15 | 16 | 3. Install the [`specific_install` gem](https://github.com/rdp/specific_install) which allows you to install a gem from a GitHub repo or a URL. 17 | 18 | $ gem install specific_install 19 | 20 | 4. Install the `teachers_pet` gem from the [https://github.com/stephaniehicks/teachers_pet](https://github.com/stephaniehicks/teachers_pet). I merged branches from two repositories: (1) [`teachers_pet` on CS 109](https://github.com/cs109/teachers_pet.git) which allows you to push files to specific branches and (2) [the `delete-repos` branch on `teachers_pet` on GitHub Education repository](https://github.com/education/teachers_pet.git) which allows you to delete repositories after your class is complete. This allows you to recycle the quota of private repos. 21 | 22 | $ gem specific_install https://github.com/stephaniehicks/teachers_pet.git 23 | 24 | #### Potential problems 25 | 26 | If you are not able to push/pull after setting up 2FA authentication, read [http://olivierlacan.com/posts/why-is-git-https-not-working-on-github/](http://olivierlacan.com/posts/why-is-git-https-not-working-on-github/) and 27 | [https://help.github.com/articles/https-cloning-errors/](https://help.github.com/articles/https-cloning-errors/). 28 | 29 | For example, if you have enabled two-factor authentication, you must provide a personal access token instead of entering your password for HTTPS Git. 30 | 31 | 32 | # Running `teachers_pet` 33 | 34 | ## Settings in GitHub Organization 35 | 36 | After you have created your GitHub Organization (e.g. `datasciencelabs-students`), you must change the default repository permission (under Settings) to "None" (Members will only be able to clone and pull public repositories. To give a member additional access, you'll need to add them to teams or make them collaborators on individual repositories.). 37 | 38 | ![permission settings](figures/permissionSettings.png) 39 | 40 | This ensures as you add each member (or student) to the organization, they will only be able to see the repositories that you give them access to. 41 | 42 | ## Creating assignments 43 | 44 | When using the sandboxing setup, you will need to create the repositories for the students. 45 | For each assignment, use the `create_repos` action to create a repository for each student. 46 | The repositories are technically created per team, but if you use `create_student_teams` first, then there will be one team per student. Start with one student GitHub username per line in a file called `students.txt` in your working directory. This will create one team per student. This ensures that each student will only have access to the repositories in his/her "team" and not any other "teams". 47 | 48 | $ teachers_pet create_student_teams --students=students.txt --organization=datasciencelabs-students 49 | 50 | ## Add all students and TAs to datasciencelabs-students 51 | 52 | $ teachers_pet add_to_team --members=students.txt --organization=datasciencelabs-students 53 | 54 | You can also create an "Owners.txt" file with one TA GitHub username per line. This will create a team for all the TAs involved with your course. If you changed the the default repository permission settings to "None" as mentioned above, then you must manually change the organizational role of each TA or instructor that will be involved with the grading. 55 | 56 | $ teachers_pet add_to_team --members=Owners.txt --organization=datasciencelabs-students 57 | 58 | ## Create repos for them (default is private repos) 59 | 60 | $ teachers_pet create_repos --organization=datasciencelabs-students --repository=2016HW2 --students=students.txt 61 | 62 | This will create empty repositories for each student called `-2016HW2`. For every homework assignment, you will repeat this process and change the name of the repository. 63 | 64 | ![create private repos](https://raw.githubusercontent.com/datasciencelabs/2016/master/lectures/git-and-github/images/github.png) 65 | 66 | ## Pushing starter files 67 | 68 | When creating repositories for students, you will often want to include boilerplate files. After running `create_repos`, create a new git repository called `2016HW2` with the starter files (e.g. README.md, or homework problems, .gitignore, Makefiles, etc.). This repository can be a local clone from some remote repository or it can just a git repository on your local computer. Change into that directory and use the `push_files action` to place that starter files in the repositories for each student. This works by creating a Git remote for each student repository, and doing a git push to each one. (i.e. the command treats the student repos on github as remotes) 69 | 70 | $ cd 2016-HW2 71 | 72 | $ teachers_pet push_files --organization=datasciencelabs-students --repository=2016HW2 --students=../students.txt 73 | 74 | **Note**: You can push files to specific branches with the `--branch` argument. e.g. If you want to push files from a specific branch, change to that branch of the repository using `git checkout ` and then push from there. 75 | 76 | $ cd 2016-HW2 77 | 78 | $ teachers_pet push_files --organization=datasciencelabs-students --repository=2016HW2 --students=../students.txt --branch= 79 | 80 | ## Deleting repos 81 | 82 | At the end of your course, if you want to recycle the private repositories to be able to use them again in your next course, use the `delete_repos` command. **Warning**: There is no un-doing this step. Once you delete the private repositories, you cannot get them back. Only run this command after all your students have a chance to clone / copy their homework assignments, if they wish. 83 | 84 | $ teachers_pet delete_repos --organization=datasciencelabs-students --repository=2016HW2 --students=../students.txt 85 | 86 | --------------------------------------------------------------------------------