Category Archives: Machine Learning

Generating Haikus with Llama 3.2

At the recent OPIG retreat, I was tasked with writing the pub quiz. The quiz included five rounds, and it’s always fun to do a couple “how well do you know your group?” style rounds. Since I work with Transformers, I thought it would be fun to get AI to create Haiku summaries of OPIGlet research descriptions from the website.

AI isn’t as funny as it used to be, but it’s a lot easier to get it to write something coherent. There are also lots of knobs you can turn like temperature, top_p, and the details of the prompt. I decided to use Meta’s new Llama 3.2-3B-Instruct model which is publicly available on Hugging Face. I ran it locally using vllm, and instructed it to write a haiku for each member’s description using a short script which parses the html from the website.

Continue reading →

Visualising and validating differences between machine learning models on small benchmark datasets

Introduction
Author

Sam Money-Kyrle

Introduction

An epidemic is sweeping through cheminformatics (and machine learning) research: ugly results tables. These tables are typically bloated with metrics (such as regression and classification metrics next to each other), vastly differing tasks, erratic bold text, and many models. As a consequence, results become difficult to analyse and interpret. Additionally, it is rare to see convincing evidence, such as statistical tests, for whether one model is ‘better’ than another (something Pat Walters has previously discussed). Tables are a practical way to present results and are appropriate in many cases; however, this practicality should not come at the cost of clarity.

The terror of ugly tables extends to benchmark leaderboards, such as Therapeutic Data Commons (TDC). These leaderboard tables do not show:

  1. whether differences in metrics between methods are statistically significant,
  2. whether methods use ensembles or single models,
  3. whether methods use classical (such as Morgan fingerprints) or learned (such as Graph Neural Networks) representations,
  4. whether methods are pre-trained or not,
  5. whether pre-trained models are supervised, self-supervised, or both,
  6. the data and tasks that pre-trained models are pre-trained on.

This lack of context makes meaningful comparisons between approaches challenging, obscuring whether performance discrepancies are due to variance, ensembling, overfitting, exposure to more data, or novelties in model architecture and molecular featurisation. Confirming the statistical significance of performance differences (under consistent experimental conditions!) is crucial in constructing a more lucid picture of machine learning in drug discovery. Using figures to share results in a clear, non-tabular format would also help.

Statistical validation is particularly relevant in domains with small datasets, such as drug discovery, as the small number of test samples leads to high variance in performance between different splits. Recent work by Ash et al. (2024) sought to alleviate the lack of statistical validation in cheminformatics by sharing a helpful set of guidelines for researchers. Here, we explore implementing some of the methods they suggest (plus some others) in Python.

Continue reading →

The “AI-ntibody” Competition: benchmarking in silico antibody screening/design

We recently contributed to a communication in Nature Biotechnology detailing an upcoming competition coordinated by Specifica to evaluate the relative performance of in vitro display and in silico methods at identifying target-specific antibody binders and performing downstream antibody candidate optimisation.

Following in the footsteps of tournaments such as the Critical Assessment of Structure Prediction (CASP), which have led to substantial breakthroughs in computational methods for biomolecular structure prediction, the AI-ntibody initiative seeks to establish a periodic benchmarking exercise for in silico antibody discovery/design methods. It should help to identify the most significant breakthroughs in the space and orient future methods’ development.

Continue reading →

My CCDC Science Day Experience

In June, I had the opportunity to visit the Cambridge Crystallographic Data Centre (CCDC) for Science Day to give a lightning talk on my rotation project with OPIG. The day was packed with presentations from researchers and PhD students collaborating with the CCDC, offering a great opportunity to hear about some of the fascinating work happening there in the fields of Structural and Computational Chemistry.

We kicked off with a dinner at the University Arms in Cambridge. This was a great opportunity to meet people who were attending Science Day in a relaxed environment, complemented by the lovely food and drink.

The next day was all about the talks. The first part of the day was filled with longer talks by more senior PhD students and CCDC researchers, followed by lightning talks from first-year PhD or master’s students. These shorter presentations provided a fast-paced overview of each project.

Continue reading →

Incorporating conformer ensembles for better molecular representation learning

Conformer ensemble of tryptophan from Seibert et. al.

The spatial or 3D structure of a molecule is particularly relevant to modeling its activity in QSAR. The 3D structural information affects molecular properties and chemical reactivities and thus it is important to incorporate them in deep learning models built for molecules. A key aspect of the spatial structure of molecules is the flexible distribution of their constituent atoms known as conformation. Given the temperature of a molecular system, the probability of each of its possible conformation is defined by its formation energy and this follows a Boltzmann distribution [McQuarrie and Simon, 1997]. The Boltzmann distribution tells us the probability of a certain confirmation given its potential energy. The different conformations of a molecule could result in different properties and activity. Therefore, it is imperative to consider multiple conformers in molecular deep learning to ensure that the notion of conformational flexibility is embedded in the model developed. The model should also be able to capture the Boltzmann distribution of the potential energy related to the conformers.

Continue reading →

Architectural highlights of AlphaFold3

DeepMind and Isomophic Labs recently published the methods behind AlphaFold3, the sequel to the famous AlphaFold2. The involvement of Isomorphic Labs signifies a shift that Alphabet is getting serious about drug design. To this end, AlphaFold3 provides a substantial improvement in the field of complex prediction, a major piece in the computational drug design pipeline.

Continue reading →

The Tale of the Undead Logger

A picture of a scary-looking zombie in a lumberjack outfit holding an axe, in the middle of a forest at night, staring menacingly at the viewer.
Fear the Undead Logger all ye who enter here.
For he may strike, and drain the life out nodes that you hold dear.
Among the smouldering embers of jobs you thought long dead,
he lingers on, to terrorise, and cause you frightful dread.
But hark ye all my tale to save you from much pain,
and fight ye not anew the battles I have fought in vain.

Or simply…

… Tips and Tricks to Use When wandb Logger Just. Won’t. DIE.

The Weights and Biases Logger (illustrated above by DALL-E; admittedly with some artistic license) hardly requires introduction. It’s something of an industry standard at this point, well-regarded for the extensive (and extensible) functionality of its interactive dashboard; for advanced features like checkpointing model weights in the cloud and automating hyperparameter sweeps; and for integrating painlessly with frameworks like PyTorch and PyTorch Lightning. It simplifies your life as an ML researcher enormously by making it easy to track and compare experiments, monitor system resource usage, all while giving you very fun interactive graphs to play with.
Plot arbitrary quantities you may be logging against each other, interactively, on the fly, however you like. In Dark Mode, of course (you’re a professional, after all). Here’s a less artistic impression to give you an idea, should you have been living under a rock:

Continue reading →

My take on the Collaborations Workshop (CW) 2024

At the end of April, I attended the CW 2024. This yearly hybrid event organised by the Software Sustainability Institute (SSI) has been running since 2011! The event brings people together to discuss best practices and the future of software in research. This year’s event themes were (1) AI/ML tools for Science, (2) Citizen Science and (3) Environmental sustainability.

As a Research Software Engineer (RSE) working with OPIG, I felt a great curiosity to attend and find out what I could bring of use to the group, as most people work on AI/ML applications. In this blog post, I share a few bits of the event which resonated with me and I found most interesting and relevant to share with my group.

Continue reading →

Organise Your ML Projects With Hydra

One of the most annoying parts of ML research is keeping track of all the various different experiments you’re running – quickly changing and keeping track of changes to your model, data or hyper-parameters can turn into an organisational nightmare. I’m normally a fan of avoiding too many different libraries/frameworks as they often break down if you to do anything even a little bit custom and days are often wasted trying to adapt yourself to a new framework or adapt the framework to you. However, my last codebase ended up straying pretty far into the chaotic side of things so I thought it might be worth trying something else out for my next project. In my quest to instil a bit more order, I’ve started using Hydra, which strikes a nice balance between giving you more structure to organise a project, while not rigidly insisting on it, and I’d highly recommend checking it out yourself.

Continue reading →