Open Molecular Science Cloud Workshop at EUCO-CTC 2019

Throughout the years, I’ve given many posters and had many engaging conversations at chemistry conferences. Today marks another landmark for me as I gave my first conference talk as a part of the Open Molecular Science Cloud workshop at the 12th European Conference on Computational and Theoretical Chemistry (EUCO-CTC 2019)!

My journey to EUCO-CTC 2019 actually began when I attended the ACS Spring 2019 conference in Orlando, FL and was drawn to the Sustainable Software session being hosted by the Molecular Sciences Software Institute (MolSSI). I am sympathetic with MolSSI’s attempts to cultivate proper software development practices in the computational chemistry community and saw an opportunity to potentially connect my work with some of their efforts (i.e. my TeraChem Cloud with the QCEngine component of the QCArchive project).

With MolSSI more prominently on my radar, I was pleasantly surprised to see an announcement for a travel grant to attend an Open Molecular Science Cloud (OMSC) workshop at EUCO-CTC 2019. I applied in June and was awarded the travel grant in July, and so come September, I was off to Perugia to give a talk on TeraChem Cloud!

Badge and certification of presentation to my first conference talk!
Conference hall was pretty large, with a projector and screen to match. (Photo credit: Grier Jones)
Always more things to improve on: looking at the audience during the start of the talk! (Photo credit: Grier Jones)

After the MolSSI contribution section, we learned how the University of Perugia was using OpenStack to test HPC on cloud resources and their efforts in creating a distributed repository of lessons for chemistry education. The second half of the week was spent back in Rome, discussing potential paths forward for computational molecular sciences with cloud computing.

Second part of OMSC workshop in the Biblioteca Accademia Nazionale delle Scienza in Rome.

I think the most valuable experience for me was getting to connect with my fellow young academics through MolSSI during this trip. It was awesome to hear about their efforts in using high-throughput calculations for automatic force field parameterization (@JessMaat), using machine learning to build correlation energy corrections (@vwcruzeiro), or recycling electronic structure intermediates to speed up expensive calculations (@JonesGrier). It was also a great opportunity to learn more about QCArchive from the project lead himself (@dga_smith).

Post-workshop discussions in Perugia with a beautiful view. (Photo credit: Sara Tortorella)
The full MolSSI crew in St. Peter’s Square during post-conference exploration.

I am extremely grateful to Professor Antonio Laganá of the University of Perugia for organizing the OMSC workshop at EUCO-CTC 2019 and to MolSSI for making it possible for me to attend. Interacting with all these amazing people working on the future of computational chemistry has been a fantastic experience, and I look forward to seeing what comes out of the friendships and ideas built this week!

Stairway to Heme

Nowadays, it’s even easier to get started with machine learning and art. The Martinez Group recently had an internal competition using the neural_style package and a pre-trained VGG net to transfer art styles onto pictures of molecules we are studying.

Myoglobin, with secondary structure (dark gray) and heme group (center) emphasized.

I chose this image of myoglobin I generated for a benchmark paper I am writing as it is one of the most composed molecular images I have generated so far. The actual structure is shown in the transparent ball-and-stick style, with the heme group (an iron atom in a porphyrin ring) displayed as thicker and more opaque. Due to the size of proteins, it is common to visualize a cartoon-y ribbon style that shows secondary structure, such as the various alpha helices shown in dark gray.

Relativity by M.C. Escher (1953)

I wouldn’t say I know a lot about art or art history, but you don’t need an encyclopedic knowledge of artists and art styles to try and make something cool. In this case, the ribbon representation of the alpha helices reminded me of the stairs looping around in Relativity by M.C. Escher. I thought it would be cool if the stair pattern could be imprinted into the alpha helices of the myoglobin, so I chose this piece for the style.

In the end, the net was fairly simple to run, assuming you have Anaconda installed on a machine with a GPU and are somewhat comfortable on the terminal:

git clone https://github.com/anishathalye/neural-style.git
conda create -n neural_style
conda activate neural_style
cd neural-style
pip install -r requirements.txt
curl http://www.vlfeat.org/matconvnet/models/imagenet-vgg-verydeep-19.mat -o imagenet-vgg-verydeep-19.mat

python neural_style.py --content myoglobin.png --styles escher.jpg --content-weight-blend 0.2 --pooling avg --style-scales 0.2 --preserve-colors --output stairway_to_heme.png

Only the content, styles, and output keywords are needed for the net to run. However, I played with a few other keywords to get something closer to what I was looking for:

  • I lowered content-weight-blend to transfer more of the style since I didn’t care about the fine detail structure of the myoglobin
  • I lowered style-scales to try and match the size of the stairs in Relativity with the alpha helices
  • I switched pooling from max to avg to go for a more abstract look
  • I used preserve-colors so that the nitrogen (blue), oxygen (red), and iron (orange) have a chance to pop out

I didn’t get exactly what I was imagining, but for half an hour of playing with some command line arguments, I’m pleasantly surprised by the results. I call it Stairway to Heme, and challenge you to try it for yourself!

Stairway to Heme

Website Migrated to WordPress

My previous site was a foray into DIY web-hosting using GitHub Pages in combination with Jekyll, originally inspired by this post. It was a great first step: got me playing with Ruby & HTML again and creating some easy DNS records to route my stefanseritan.com domain to GitHub Pages.

However, I’m happy with the decision to migrate my website hosting to WordPress. Moving forward, it should be easier to provide some more content on personal milestones and my thoughts on events in chemistry, tech, or anything else I find interesting!