• A simple intro to statistical distributions
• hypothesis testing
• linear models.

reading: http://compgenomr.github.io/book/stats.html

slides: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week1/compgen2021_stats.pdf

exercises+code: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week1/

Module 2: Unsupervised learning for genomics (9-15 August 2021)

• Understanding basic intuition behind machine learning approaches.
• Using unsupervised learning to cluster and visualise data points
• Dimension reduction techniques for visualisation and as input to clustering methods

reading: http://compgenomr.github.io/book/unsupervisedLearning.html

slides: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week2/compgen2021_unsupervisedLearning.pdf

exercises+code: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week2/

Module 3: Supervised learning for genomics (16-22 August 2021)

• Understanding and using supervised learning methods for predictive purposes
• How to measure prediction performance
• Understand and use cross-validation and related concepts

reading: http://compgenomr.github.io/book/supervisedLearning.html

slides: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week3/compgen2021_supervisedLearning.pdf

exercises+code: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week3/

https://github.com/BIMSBbioinfo/compgen2021

Address of the bookmark: https://github.com/BIMSBbioinfo/compgen2021

Modern sequencing technologies have turned biology into a data-heavy science. The human genome has about three billion DNA base pairs, and sequencing can produce massive datasets quickly. Bioinformatics helps organize and interpret this information, allowing scientists to compare genomes, find genes, spot genetic differences, study gene expression, and understand diseases at the molecular level. Now, AI is changing how these datasets are analyzed. Machine learning and deep learning can find complex patterns in biological data and make predictions using large datasets. Rather than following only set rules, AI systems can learn from data and help researchers solve tough biological problems.

A key example of AI in bioinformatics is predicting protein structures. Proteins are vital for many functions in living things, and their three-dimensional shapes are closely tied to what they do. For a long time, figuring out these structures in the lab was slow and difficult. AI-based tools like AlphaFold have shown that deep learning can predict protein structures with impressive accuracy. These advances help speed up biological research and give scientists useful predictions to support their experiments. This shift means bioinformatics is moving from just analyzing biological data to predicting how biology works and designing new solutions.

AI is also expected to greatly influence drug discovery. Traditionally, developing a new drug is a long and costly process that involves finding biological targets, searching for possible drug molecules, testing how well they work, studying their properties, and running many experiments. AI can help researchers analyze large chemical and biological datasets, predict how molecules might interact with targets, find promising compounds, and estimate properties of drug candidates. Generative AI can even help design new molecules to test in the lab. This does not mean lab experiments will go away, but AI can help researchers focus on the best options and possibly speed up some parts of drug development.

Personalized medicine is another area where AI-driven bioinformatics could make a big difference. Each person has a unique mix of genetic, molecular, environmental, and lifestyle factors, so people with the same disease might respond differently to the same treatment. Bioinformatics lets researchers study individual biological data, and AI can combine many types of information, like genetic data, gene expression, protein levels, medical images, clinical records, and drug responses. In the future, this could help doctors look beyond just the disease and focus on the specific biology of each patient. This would support more personalized ways to diagnose, assess risk, and choose treatments.

As AI becomes more common, the job of bioinformaticians will likely change. Instead of spending most of their time on repetitive computer tasks, they may focus more on creating research questions, understanding AI results, checking predictions, and linking computer findings to lab experiments. Future professionals will need to know about molecular biology, genetics, statistics, programming, machine learning, data science, databases, and computational biology. But technical skills alone will not be enough. Being able to ask good scientific questions and carefully judge computer results will be even more important, since AI can make predictions, but scientists must decide if those predictions make sense and can be proven in the lab.

Even with its great potential, using AI in bioinformatics comes with big challenges. AI systems rely on the quality and variety of the data they are trained on. Biological and clinical datasets can have missing information, technical errors, inconsistent measurements, and may not represent all groups equally. A model that works well on one dataset might not work as well on another group or in a different setting. That is why data quality, proper validation, transparency, reproducibility, and careful model development are crucial for the future of AI in bioinformatics. Researchers also need to think about genetic privacy, data ownership, security, and using personal biological information responsibly. These concerns are especially important when AI predictions are used in healthcare.

The lab of the future may look very different from today’s. Researchers might use AI to review scientific papers, find research questions, analyze large datasets, come up with ideas, and predict which experiments will be most helpful. Automated lab systems could then run these experiments, create new data, and send the results back to computer models. This would create a cycle of making guesses, predicting, experimenting, collecting data, and learning. This approach could speed up scientific discovery by helping researchers explore questions more efficiently. Bioinformatics could become a key link between computer predictions and real lab experiments.

In the end, the future of bioinformatics with AI will not be about replacing people with machines. It will be about humans and AI working together. Computers can handle huge amounts of biological data and spot patterns that a single person could not. But humans bring scientific understanding, creativity, critical thinking, ethical judgment, and the ability to see the bigger picture. AI might find a pattern in millions of genomes, but scientists need to figure out why it matters. An AI model could suggest a new drug, but researchers must check if it is safe and works well. A computer might find a genetic change, but doctors have to decide what it means for a real patient.

The future of bioinformatics is closely tied to the future of AI. As biological data grows and AI models get better, bioinformatics may shift from mainly analyzing data to predicting biological processes, designing new molecules, speeding up experiments, and supporting personalized healthcare. For students and researchers, this is an exciting chance to work where biology and technology meet. The most successful people will not just be those who use the latest AI tools, but those who understand biology well enough to ask good questions and judge the answers carefully. The future will not be about AI versus humans, but about people and AI working together to understand life in ways we never could before. The next big discovery may come from this partnership between a biological question, a computer model, a lab experiment, and human curiosity.

Address of the bookmark: https://www.stats.ox.ac.uk/__data/assets/pdf_file/0018/5373/LintonFinalReport.pdf

In comparative genome analysis work, we usually compare more than two genomes and looks for syntenic regions amongst them. In my research I used Evolution Highway (RH) http://eh-demo.ncsa.uiuc.edu/, which is a collaborative project designed to provide a visual means for simultaneously comparing genomes of multiple amniote species. The tool removes the burden of manually aligning these maps and allows cognitive skills to be used toward something more valuable than preparation and transformation of data. In addition to EH, attractive Circos (http://circos.ca/) is also very popular for this kind of analysis.

The EH is available online, and can be easily access and use, whereas Circos installation is not entirely straightforward. One of the most difficult parts of the installation involves installing the GD library. Since there weren't good instructions for installing this library on the internet I decided to post instructions here in case they are useful to anyone else.

Following are the steps to install GD modules in Mac OS

1. Setup

Create a folder for the files:

$ mkdir -p /SourceCache
$ cd /SourceCache

Get and unpack the required Jpeg-6b and GD libraries:
Download Jpeg-6b (http://code.google.com/p/google-desktop-for-linux-mirror/downloads/detail?name=jpeg-6b.tar.gz&can=2&q)
Download GD (http://search.cpan.org/~lds/GD-2.46/)

Place the "tar.gz" files in "/SourceCache" and double click to unpack.

2. Install libjpeg

Copy the "config.sub" and "config.guess" files to "/SourceCache". Note that your "config.sub" and ""config.guess" files may be in a slightly different location. The commands below show where they were on my machine:

$ cd /SourceCache/jpeg-6b/src
$ cp /usr/share/libtool/config/config.sub .
$ cp /usr/share/libtool/config/config.guess .

Configure libjpeg as follows. Note that this was installed on a 64 bit machine. However, this method may configure it in a 32 bit format. This may not be the best way to configure the installation but it works.

$ .configure --enable-shared
$ make

Check to see if the following directories exist on your machine. Create the missing directories in the following manner:

$ mkdir -p /usr/local/include
$ mkdir -p /usr/local/bin
$ mkdir -p /usr/local/lib
$ mkdir -p /usr/local/man/man1

Finish making and installing libjpeg:

$ make install

3. Install GD

$ cd /SourceCache/GD-2.46/GD/
$ perl Makefile.PL
$ make
$ make test (optional)
$ make html (optional)
$ make install

Other way for Mac OS
The easiest way to get a lot of these is with a program called Fink, which is similar in nature to the CPAN installer, but installs common GNU utilities. Fink is available from <http://sourceforge.net/projects/fink/>.

Follow the instructions for setting up Fink. Once it's installed, you'll want to run the following as root: fink install gd

It will prompt you for a number of dependencies, type 'y' and hit enter to install all of the dependencies. Then watch it work.

To prevent creating conflicts with the software that Apple installs by default, Fink creates its own directory tree at /sw where it installs most of the software that it installs. This means your libraries and headers for libgd will be at /sw/lib and /sw/include instead of /usr/lib and /usr/local/include. Because of these changed locations for the libraries, the Perl GD module will not install directly via CPAN, because it looks for the specific paths instead of getting them from your environment. But there's a way around that :-)

Instead of typing "install GD" at the cpan> prompt, type look GD. This should go through the motions of downloading the latest version of the GD module, then it will open a shell and drop you into the build directory. Apply below patch to the Makefile.PL file (save the patch into a file and use the command patch < patchfile.)

Then, run these commands to finish the installation of the GD module:

perl Makefile.PL
make
make test
make install
And don't forget to run exit to get back to CPAN.

Install on MS Window, using PPM

C:\Documents and Settings\Owner>ppm
PPM interactive shell (2.2.0) - type 'help' for available commands.
PPM> install GD
Install package 'GD?' (y/N): y
Installing package 'GD'...
Downloading http://ppm.ActiveState.com/PPMPackages/5.6plus/MSW. ...
Installing C:\Perl\site\lib\auto\GD\GD.bs
Installing C:\Perl\site\lib\auto\GD\GD.dll
Installing C:\Perl\site\lib\auto\GD\GD.exp
Installing C:\Perl\site\lib\auto\GD\GD.lib
Installing C:\Perl\html\site\lib\GD.html
Installing C:\Perl\site\lib\GD.pm
Installing C:\Perl\site\lib\qd.pl
Installing C:\Perl\site\lib\auto\GD\autosplit.ix
PPM>


If you can't install it from ppm. You can download it:
http://ppm.ActiveState.com/PPMPackages/5.6plus/MSW.


BTW,All Perl 5.6.1 Modules are located at:

http://ppm.ActiveState.com/PPMPackages/5.6plus/MSW.

Install the Perl GD Module on Linux

$ sudo perl -MCPAN -e shell

Since it was the first time I had run this command on this particular machine I had to answer a lot of questions but simply selected the defaults for everything as this usually works for me. Once in the CPAN shell I entered

$ install Bundle::CPAN

and selected all of the defaults again. Once the CPAN bundle had finished installing I tried to install GD::Graph by typing

$ install GD::Graph

but it failed with hundreds of errors – the first of which was

GD.xs:7:16: error: gd.h: No such file or directory

This was fixed with the following apt-get command (in the bash shell)

$ sudo apt-get install libgd2-xpm-dev

back in the CPAN shell I still couldn’t get GD::Graph to build and I guessed this was because of some left over files from the failed build. I don’t know the command to clean things up inside the CPAN shell and am too lazy to read the docs so I simply went into the .cpan/build directory in my home directory and deleted anything that started with GD – eg

$ rm -rf GD-2.35-HC_vkB

$ rm -rf GDGraph-1.44-Evfibe

and so on. Those strings at the end (VkB and so on) look random so they might be different on your machine. Then I went back into the CPAN shell and ran

$ install GD::Graph

There were a few dependencies which the script fetched and installed for me but everything worked smoothly.

Manual and other Perl Module instalation are mentioned in my previous blog @ http://bioinformaticsonline.com/blog/view/710/how-to-install-perl-modules-manually-using-cpan-command-and-other-quick-ways

Address of the bookmark: http://www.citrusperl.com/

Address of the bookmark: http://cbb.sjtu.edu.cn/course/database/beginning.pdf

Originally design to map the location of objects in a 10 km map IrishGrid includes:

• native support of the Irish Grid System (see http://www.osi.ie/)
• optimize for speed (there's as less as possible data to conversion)
• customized color functions

https://code.google.com/p/irishgrid/downloads/detail?name=irishgrid.pl

Address of the bookmark: https://code.google.com/p/irishgrid/

Bioinformatics Textbook Track

Find more about Rosalind puzzle at http://rosalind.info/problems/list-view/?location=bioinformatics-textbook-track

I will provide solution of all the Rosalind problem with Perl for community.

Check out the right sidebar for more links ...

More at http://cpansearch.perl.org/src/TJPARNELL/

Address of the bookmark: http://cpansearch.perl.org/src/TJPARNELL/