3

Please take a look at An open access pilot freely sharing cancer genomic data from participants in Texas Although I have not worked on this paper but author claimed that both tumor and normal data is publicly available. In case if you still need something more, than you can work on virtual normal data. And there are several papers which provide machnine ...


3

If helpful for anyone else, I found that all and much more are available. See below 2 links. https://www.ncbi.nlm.nih.gov/projects/gap/cgi-bin/dataset.cgi?study_id=phs000424.v8.p2&phv=169091&phd=3910&pha=&pht=2742&phvf=&phdf=&phaf=&phtf=&dssp=1&consent=&temp=1 https://ftp.ncbi.nlm.nih.gov/dbgap/studies/phs000424/...


3

You may try Code Ocean. Currently, it is not that easy to use IMHO, but one of their tech leads promises to substantially improve it towards the year end.


3

In my experience, it is more common to use all clinical data as-is for clinical studies. And if data is missing, either omit the sample or omit the variable with missing data. If your classifier can't handle the wide variation commonly seen in clinical studies then you may want to use a classifier which is less impacted by outliers.


2

One such database/tool is “[PharmacoGx][1]: an R package for analysis of large pharmacogenomic datasets.” Bioinformatics (Oxford, England). They brought together a large compendium of experimental data (cell lines and the like if I remember correctly from a talk), standardized these and made available within a special object class. I think there is genomic ...


2

It seems like there are some files related to the databases at the ftp site: http://ftp.mcs.anl.gov/pub/WIT2/. The related files were last updated on 2002. I found it via searching at google: site:*.mcs.anl.gov/ WIT. Which reports also a page about the database. There seems to be a project to develop WIT3, because there is a mailing list for developers, ...


2

In addition I would like to add "Vectorbase", the curator "Dan" is a good guy (I forget his surname right now) and it's a good team. However, please read my rather somber assessment of arthropod genomics first. We appear to be talking about lower metazoans, e.g. not protists, or yeasts (the latter I suspect are really good for your question). I don't know ...


2

Kaggle has a cats v dogs dataset if you want to try your hand at biological image classification: https://www.kaggle.com/c/dogs-vs-cats The DREAM challenge competitions are usually specifically oriented to solving biological classification or learning problems with ML: http://dreamchallenges.org/


2

I have seen some (1 or more) articles with interactive data displays in the F1000Research journal I don't know recall now if they had interactive tables or plots but they used plotly for sure.


1

From this SO post. You can use seqkit to remove duplicate sequences with the command below: seqkit rmdup -s < sequences.txt > out.fa The rmdup option removes duplicates, and the -s option calls duplicates on the basis of sequence, ignoring differences in headers.


1

Gene read counts are the number of reads or fragments that are mapped to each gene. So it is an integer and the values are not directly comparable between samples due to differences in sequencing depth. TPM stands transcripts per million. It is the normalized gene expression level. Basically, you first normalize read counts by gene length and then normalize ...


1

Removing outliers is common practice in statistical modeling and perfectly acceptable. However, with regards 1.5 IQR I am far from certain about this approach. Normally, if you want to be conservative then 3 standard deviations (SD) denote an outlier, which is more stringent than IQR. Some use 2 SD. If the value is lower than 2 SD from the group mean it isn'...


1

The example looks a lot like a shiny application. Your best bet then is one of the following: Ask your IT department to setup a shiny server for you. They can use the free version. Post your shiny app on shinyapps.io. Depending on how popular the page becomes, you might have to pay for an account. The free version of shiny works for most cases (it's what ...


Only top voted, non community-wiki answers of a minimum length are eligible