Category Archives: Machine Learning

Better Models Through Molecular Standardization

“Cheminformatics is hard.”

— Paul Finn

I would add: “Chemistry is nuanced”… Just as there are many different ways of drawing the same molecule, SMILES is flexible enough to allow us to write the same molecule in different ways. While canonical SMILES can resolve this problem, we sometimes have different problem. In some situations, e.g., in machine learning, we need to map all these variants back to the same molecule. We also need to make sure we clean up our input molecules and eliminate invalid or incomplete structures.

Different Versions of the Same Molecule: Salt, Neutral or Charged?

Sometimes, a chemical supplier or compound vendor provides a salt of the compound, e.g., sodium acetate, but all we care about is the organic anion, i.e., the acetate. Very often, our models are built on the assumption we have only one molecule as input—but a salt will appear as two molecules (the sodium ion and the acetate ion). We might also have been given just the negatively-charged acetate instead of the neutral acetic acid.

Tautomers

Another important chemical phenomenon exists where apparently different molecules with identical heavy atoms and a nearby hydrogen can be easily interconverted: tautomers. By moving just one hydrogen atom and exchanging adjacent bond orders, the molecule can convert from one form to another. Usually, one tautomeric form is most stable. Warfarin, a blood-thinning drug, can exist in solution in 40 distinct tautomeric forms. A famous example is keto-enol tautomerism: for example, ethenol (not ethanol) can interconvert with the ketone form. When one form is more stable than the other form(s), we need to make sure we convert the less stable form(s) into the most stable form. Ethenol, a.k.a. vinyl alcohol, (SMILES: ‘C=CO[H]’), will be more stable when it is in the ketone form (SMILES: ‘CC(=O)([H])’):

from IPython.display import SVG # to use Scalar Vector Graphics (SVG) not bitmaps, for cleaner lines

import rdkit
from rdkit import Chem
from rdkit.Chem import AllChem
from rdkit.Chem import Draw # to draw molecules
from rdkit.Chem.Draw import IPythonConsole # to draw inline in iPython
from rdkit.Chem import rdDepictor  # to generate 2D depictions of molecules
from rdkit.Chem.Draw import rdMolDraw2D # to draw 2D molecules using vectors

AllChem.ReactionFromSmarts('[C:1]-[C:2](-[O:3]-[H:4])>>[C:1]-[C:2](=[O:3])(-[H:4])')
Continue reading →

Einops: Powerful library for tensor operations in deep learning

Tobias and I recently gave a talk at the OPIG retreat on tips for using PyTorch. For this we created a tutorial on Google Colab notebook (link can be found here). I remember rambling about the advantages of implementing your own models against using other peoples code. Well If I convinced you, einops is for you!!

Basically, einops lets you perform operations on tensors using the Einstein Notation. This package comes with a number of advantages a few of which I will try and summarise here:

Continue reading →

3 Key Questions to Think About When Designing Proteins Computationally

We have reached the era of design, not just ‘hunting’. Particularly exciting to me is the de novo design of proteins, which have a wide and ever increasing range of applications from therapeutics to consumer products, biomanufacturing to biomaterials. Protein design has been a) enabled by decades of research that contributed to our understanding of protein sequence, structure & function and b) accelerated by computational advances – capturing the information we have learned from proteins and representing it for computers and machine learning algorithms.

In this blog post, I will discuss three key methodological considerations for computational protein design:

  1. Sequence- vs structure-based design
  2. ML- vs physics-based design
  3. Target-agnostic vs target-aware design
Continue reading →

How to turn a SMILES string into a molecular graph for Pytorch Geometric

Despite some of their technical issues, graph neural networks (GNNs) are quickly being adopted as one of the state-of-the-art methods for molecular property prediction. The differentiable extraction of molecular features from low-level molecular graphs has become a viable (although not always superior) alternative to classical molecular representation techniques such as Morgan fingerprints and molecular descriptor vectors.

But molecular data usually comes in the sequential form of labeled SMILES strings. It is not obvious for beginners how to optimally transform a SMILES string into a structured molecular graph object that can be used as an input for a GNN. In this post, we show how to convert a SMILES string into a molecular graph object which can subsequently be used for graph-based machine learning. We do so within the framework of Pytorch Geometric which currently is one of the best and most commonly used Python-based GNN-libraries.

We divide our task into three high-level steps:

  1. We define a function that maps an RDKit atom object to a suitable atom feature vector.
  2. We define a function that maps an RDKit bond object to a suitable bond feature vector.
  3. We define a function that takes as its input a list of SMILES strings and associated labels and then uses the functions from 1.) and 2.) to create a list of labeled Pytorch Geometric graph objects as its output.
Continue reading →

Antibody Engineering and Therapeutics Conference

I was invited to speak at the Antibody Engineering and Therapeutics Conference (presenting mine and Matt’s recently published epitope profiling paper), in San Diego (December 12th – 16th). Unfortunately, the pandemic had other ideas so I decided not to travel but luckily the conference was hybrid. 

The conference included 1 day of pre-conference workshops and 4 days of presentations from academic and industry, with livestreaming of the initial keynotes (including one from Charlotte). Remaining talks were recorded and made available after the conference. I’ve highlighted a few of my favourite talks and conference themes, with links to papers where available.

Naturally, a lot of the presented research related to covid-19. I was speaking in the ‘Antibody Repertoires and Covid-19’ session, where there were interesting presentations from Professor Eline Luning Prak from the University of Pennsylvania and Elaine Chen from Vanderbilt University analysing antibody responses in covid-recovered individuals, and comparing vaccine responses in covid-recovered vs covid-naiive individuals. Other talks around SARS-CoV-2 vaccines included Dr Laura Walker from Adimab/Adagio Therapeutics comparing BCR repertoire responses to different types of vaccinations, and the effect of using different booster types.

Continue reading →

Highlights from the European Antibody Congress 2021

Last month, I was fortunate enough to be able to attend (in person!) and present at the Festival of Biologics European Antibody Congress (9-11 November, 2021) in Basel, Switzerland. The Festival of Biologics is an annual conference, which brings together researchers from industry and academia. It was an excellent opportunity to learn about exciting research and meet people working in the antibody development field.

Here are some of my highlights from the European Antibody Congress, with a focus on antibody design and engineering:

Continue reading →

New review on BCR/antibody repertoire analysis out in MAbs!

In our latest immunoinformatics review, OPIG has teamed up with experienced antibody consultant Dr. Anthony Rees to outline the evidence for BCR/antibody repertoire convergence on common epitopes post-pathogen exposure, and all the ways we can go about detecting it from repertoire gene sequencing data. We highlight the new advances in the repertoire functional analysis field, including the role for OPIG’s latest tools for structure-aware antibody analytics: Structural Annotation of AntiBody repertoires+ (SAAB+), Paratyping, Ab-Ligity, Repertoire Structural Profiling & Structural Profiling of Antibodies to Cluster by Epitope (‘SPACE’).

Continue reading →

A logical brain teaser to derail your afternoon

Brain teasers have a strange power. For many they evoke nothing more than a mild and transient sense of curiosity. But for a certain subset of people they create an irresistible intellectual temptation which even needs to actively be avoided at times as not to completely derail conversations and take over whole afternoons.

For better or worse, I am in the camp of people who are highly susceptible to brain teasers. I just love them too much. More than once in my lifetime I had to ask a friend not to tell me about a particular brain teaser they had heard about because I knew it would inevitably take over my mind and send me down an almost hypnotic spiral of thoughts whose only escape would be finding the solution.

While brain teasers can admittedly turn into ridiculously powerful distractions for some of us, they are not necessarily a waste of time. They have high recreational value and help the mind to enter a playful and creative state. They serve as mental gymnastics to directly train logical thinking skills, and logical thinking is arguably one of the most powerful transferable skills that exists. And last but not least, brain teasers are canonically used nowadays in job interviews at some of the worlds top employers (Google, Facebook, Microsoft, prestigious hedge funds, …).

In this post, I will present one of my favourite brain teasers to see if I can get you hooked. It is a slightly modified and self-contained version of the so-called pirate game. You can find the solution at the end of the page. Enjoy responsibly! Continue reading →

Issues with graph neural networks: the cracks are where the light shines through

Deep convolutional neural networks have lead to astonishing breakthroughs in the area of computer vision in recent years. The reason for the extraordinary performance of convolutional architectures in the image domain is their strong ability to extract informative high-level features from visual data. For prediction tasks on images, this has lead to superhuman performance in a variety of applications and to an almost universal shift from classical feature engineering to differentiable feature learning.

Unfortunately, the picture is not quite as rosy yet in the area of molecular machine learning. Feature learning techniques which operate directly on raw molecular graphs without intermediate feature-engineering steps have only emerged in the last few years in the form of graph neural networks (GNNs). GNNs, however, still have not managed to definitively outcompete and replace more classical non-differentiable molecular representation methods such as extended-connectivity fingerprints (ECFPs). There is an increasing awareness in the computational chemistry community that GNNs have not quite lived up to the initial hype and still suffer from a number of technical limitations.

Continue reading →

How to interact with small molecules in Jupyter Notebooks

The combination of Python and the cheminformatics toolkit RDKit has opened up so many ways to explore chemistry on a computer. Jupyter — named for the three languages, Julia, Python, and R — ties interactivity and visualization together, creating wonderful environments (Notebooks and JupyterLab) to carry out, share and reproduce research, including:

“data cleaning and transformation, numerical simulation, statistical modeling, data visualization, machine learning, and much more.”

—https://jupyter.org

At this year’s annual RDKit UGM (User Group Meeting), Cédric Bouysset shared a tutorial explaining how to create a grid of molecules that you can interact with, using his “mols2grid“:

Continue reading →