What Isaiah and Sawyer Learned This Summer

Computers and a mountain

AI-generated art by Andy Masley, 2025

Over the last weeks, our last interns—Isaiah and Sawyer—concluded their internships with Rowan. Isaiah did a lot of useful work for our company, including building a series of labs illustrating how computational chemistry can be used to improve chemical education: check out his Diels–Alder lab and his stereochemistry lab.

Sawyer worked on assessing how well NNPs could predict reduction potentials and electron affinities (see his paper here) alongside a few other internal research projects. He ran over 14,000 workflows during his seven-week internship; that’s a workflow every 5 minutes, even counting nights and weekends. (In unrelated news, our API is getting pretty good.)

Here’s how they responded to our intern-exit-interview questions. (As in our previous intern reflections, it seems question 5 is becoming “the GeoGuessr question.”)

Isaiah’s Answers

What are five things you learned during your internship at Rowan?

  1. Textbooks and traditional lab experiments can only teach so much. Even if there’s a lot of great learning that can be done in those mediums, computational tools offer a flexibility of exploration that isn’t really viable in any other form.
  2. Making lessons and labs is hard. It turns out to be frustratingly difficult to give students the breadcrumbs they can follow to a conclusion without just practically giving them the conclusion you need them to reach.
  3. Sometimes, LLMs just lie. I learned this the hard way, when after several hours of attempted debugging it turned out the feature I needed was included on v0.20, when v0.19 was the latest version that actually existed.
  4. There’s often a sharp divide between educational science tools and specialized “real” science tools, and this doesn’t need to be the case. If the tools are well made, it shouldn’t need to matter who’s using it.
  5. With enough practice, one can figure out when an Australian city is Brisbane based on nothing but vibes.

A street with palm trees, shadows pointing south, cars driving on LHS.

Archetypal StreetView footage of Brisbane.

What's one thing you're hoping to learn more about following your time at Rowan?

I hope to learn more about how chemistry education can still be improved, especially in introductory levels of chemistry where the building of chemical intuition is so vital. 

Isaiah returns to Cambridge Rindge & Latin School this fall, where he will be a senior.

Sawyer’s Answers

What are five things you learned during your internship at Rowan?

  1. Multitasking is a great skill in computational chemistry. While you’re waiting for calculations to finish running, you can always be doing something else that’s productive.

  2. Things involving APIs/Git/programming are often hard to set up, but you get a lot of utility out of them once you’re used to them.

  3. When you’re writing something (e.g., a research paper), you have to carefully anticipate questions or critiques readers might have about what you’re writing, and address them in your paper ahead of time. (Unless you take your role as “corresponding author” really seriously and want to answer a bunch of emails.)

  4. Though they have their shortcomings, ML-based models show a lot of promise in computational chemistry. They’re not only fast, but accurate, even when you might not expect them to be.

  5. The distinguishing feature about Bogotá is the yellow license plates, although the UK and parts of Southeast Asia also have yellow license plates. But Bogotá can easily be distinguished by the distinctive grid of calle/carrera streets.

A meme explaining that Bogota has yellow license plates.

Rowan internal meme, 2025 (colorized)

What’s one thing you’re hoping to learn more about following your time at Rowan?

The ways that different computational chemistry methods fundamentally work. I’ve used a ton of different methods throughout my time at Rowan, but it would be nice to develop a good understanding of what’s going on behind the scenes.

Sawyer starts his undergraduate studies at Caltech this fall. Good luck Sawyer! If you’re a professor at Caltech, consider reaching out to him.

Banner background image

What to Read Next

ML Models for Aqueous Solubility, NNP-Predicted Redox Potentials, and More

ML Models for Aqueous Solubility, NNP-Predicted Redox Potentials, and More

the promise & peril of solubility prediction; our approach and models; pH-dependent solubility; testing NNPs for redox potentials; benchmarking opt. methods + NNPs; an FSM case study; intern farewell
Sep 5, 2025 · Eli Mann, Corin Wagen, and Ari Wagen
Machine-Learning Methods for pH-Dependent Aqueous-Solubility Prediction

Machine-Learning Methods for pH-Dependent Aqueous-Solubility Prediction

Prediction of aqueous solubility for unseen organic molecules remains an outstanding and important challenge in computational drug design.
Sep 5, 2025 · Elias L. Mann, Corin C. Wagen
What Isaiah and Sawyer Learned This Summer

What Isaiah and Sawyer Learned This Summer

Reflections from our other two interns on their time at Rowan and what they learned.
Sep 5, 2025 · Isaiah Sippel and Sawyer VanZanten
Benchmarking OMol25-Trained Models on Experimental Reduction-Potential and Electron-Affinity Data

Benchmarking OMol25-Trained Models on Experimental Reduction-Potential and Electron-Affinity Data

We evaluate the ability of neural network potentials (NNPs) trained on OMol25 to predict experimental reduction-potential and electron-affinity values for a variety of main-group and organometallic species.
Sep 4, 2025 · Sawyer VanZanten, Corin C. Wagen
Which Optimizer Should You Use With NNPs?

Which Optimizer Should You Use With NNPs?

The results of optimizing 25 drug-like molecules with each combination of four optimizers (Sella, geomeTRIC, and ASE's implementations of FIRE and L-BFGS) and four NNPs (OrbMol, OMol25's eSEN Conserving Small, AIMNet2, and Egret-1) & GFN2-xTB.
Sep 4, 2025 · Ari Wagen and Corin Wagen
Double-Ended TS Search and the Invisible Work of Computer-Assisted Drug Design

Double-Ended TS Search and the Invisible Work of Computer-Assisted Drug Design

finding transition states; the freezing-string method; using Rowan to find cool transition states; discussing drug design
Sep 3, 2025 · Jonathon Vandezande, Ari Wagen, Spencer Schneider, and Corin Wagen
The Invisible Work of Computer-Assisted Drug Design

The Invisible Work of Computer-Assisted Drug Design

Everything that happens before the actual designing of drugs, and how Rowan tries to help.
Aug 28, 2025 · Corin Wagen
MSA, Protein–Ligand Binding Affinity Exploration, and Stereochemistry

MSA, Protein–Ligand Binding Affinity Exploration, and Stereochemistry

MSA-related occurrences and our incident postmortem; MSA server coming soon; exploring new approaches to binding-affinity prediction; a farewell to interns; a new stereochemistry lab
Aug 22, 2025 · Ari Wagen, Corin Wagen, and Spencer Schneider
Co-Folding Failures, Our Response, and Rowan-Hosted MSA

Co-Folding Failures, Our Response, and Rowan-Hosted MSA

A narrative account of our response to a sudden rise in protein–ligand co-folding failures.
Aug 22, 2025 · Ari Wagen
Exploring Protein–Ligand Binding-Affinity Prediction

Exploring Protein–Ligand Binding-Affinity Prediction

Trying a few modern ML-based approaches for predicting protein–ligand binding affinity.
Aug 20, 2025 · Ishaan Ganti