返回到 Statistics for Genomic Data Science

4.1

140 个评分

•

26 个审阅

An introduction to the statistics behind the most popular genomic data science projects. This is the sixth course in the Genomic Big Data Science Specialization from Johns Hopkins University....

创建者 ZM

•Jun 28, 2018

The professor is really enthusiasm, so I was really impreesed by him. And his teaching is brief, and I can learn key points through the lectures. Great course!

创建者 LR

•May 23, 2016

I have really enjoyed the course and I have learnt different concepts relevant for my current study.\n\nYurany

筛选依据：

23 个审阅

创建者 Hamzeh Mesrian Tanha

•Nov 08, 2018

Great place to start learning genomics in R

创建者 Ian Poole

•Aug 30, 2018

I did my best to work through module 1, but encountered one problem after another with installing the various required R packages, due to version issues. From the absence of recent discussion posts it seems that this is not really a current, viable course. From what I have seen of the course, I get the impression that even if package installation went smoothly, the course is more about R than statistics or genomics - which is not what I joined for.

创建者 ELISA WAXMAN

•Jul 23, 2018

I think this is one of the best courses in this specialization. I found it the most helpful in building together what should be learned in genomic data science. I wish 1) this course was earlier in the specialization, 2) there was additional building from this course to build together the workflow from beginning to end, and 3) reduction or removal of some of the other courses (or other courses taught together with this one).

创建者 李仕廷

•Jul 01, 2018

really a good course for people who want to learn use R to dispose genomic data

创建者 Zhen Miao

•Jun 28, 2018

The professor is really enthusiasm, so I was really impreesed by him. And his teaching is brief, and I can learn key points through the lectures. Great course!

创建者 Thodoris Savvidis

•May 23, 2018

too much overlap with Jeff's course in introduction to genomic data science

创建者 Saaket Varma

•Feb 19, 2018

Enjoyed it. One of better courses I have taken in Coursera. A good introduction to using statistics in Bioconductor with genomics data.

创建者 Roman Sankowski

•Jan 04, 2018

Really great and in-depth class! thank you

创建者 Paul Saunders

•Jan 03, 2018

The worst executed course I have taken in 36 years of post-graduate education.

1 The instructor speaks so fast it is difficult even for a native English speaker like myself to understand.

2. This course is only suitable as a review for people who are experts in the field already. Even if you know how to use Bioconductor and are familiar with programming in R, if you don't know the tools being used already the instruction in the course will not give enough information to be able to do the quizzes without a great deal of difficulty.

3. The examples presented are thrown out in a cursory fashion without enough detail about how the data is being set up or manipulated. Matrices are transformed and recombined with little explanation about why things are being done.

4. Although generalizing from material presented to new applications is a valid instructional approach, the instruction does not give the student enough information to do this and the instructor expects students to be able to figure out new algorithms from vague public domain documentation.

5. Although the instructor makes an impassioned plea for carefully thought out statistical test design, proper documentation of work flow, and appropriate use of p-values, he does not describe the interpretation of statistical tools presented. For example, tools for calculating thousands of principle components in seconds is given, but beyond showing clusters of dots on a graph may indicate a genetic cluster does not explain what the individual points in the PCA mean.

In summary, the tools presented are very powerful but are not well described. Extensive revision to the course is needed.

创建者 Andrew Milton

•Oct 29, 2017

This course is the shotgun approach to this topic. There's way too much material covered so shallowly that the instructor may as well not have bothered. While it is true that the course is heavily annotated with web links and references, IMNSHO, this is a cop-out. This course could improve dramatically by extending it a couple of weeks and covering some of the material in greater depth. I think the instructor also also buried his lede by deferring the discussion of predictive statistics and an overview various experimental processes/software until week 4. Both of these topics deserve better treatment front and center in week 1.