Category Archives: Data Science

Non-linear Dependence? Mutual Information to the Rescue!

We are all familiar with the idea of a correlation. In the broadest sense of the word, a correlation can refer to any kind of dependence between two variables. There are three widely used tests for correlation:

  • Spearman’s r: Used to measure a linear relationship between two variables. Requires linear dependence and each marginal distribution to be normal.
  • Pearson’s ρ: Used to measure rank correlations. Requires the dependence structure to be described by a monotonic relationship
  • Kendall’s 𝛕: Used to measure ordinal association between variables.

While these three measures give us plenty of options to work with, they do not work in all cases. Take for example the following variables, Y1 and Y2. These might be two variables that vary in a concerted manner.

Perhaps we suspect that a state change in Y1 leads to a state change in Y2 or vice versa and we want to measure the association between these variables. Using the three measures of correlation, we get the following results:

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 →

snakeMAKE better workflows with your code

When developing your pipeline for processing, annotating and/or analyzing data, you will probably find yourself needing to continuously re-run it, as you play around with your code. This can become a problem when working with long pipelines, large datasets and cpu’s begging you not to run some pieces of code again.

Luckily, you are not the first one to have been annoyed by this and other related struggles. Some people were actually so annoyed that they created Snakemake. Snakemake can be used to create workflows and help solve problems, such as the one mentioned above. This is done using a Snakefile, which helps you split your pipeline into “rules”. To illustrate how this helps you create a better workflow, we will be looking at the example below.

Continue reading →

Getting the PDB structures of compounds in ChEMBL

Recently I was dealing with a set of compounds with known target activities from the ChEMBL database, and I wanted to find out which of them also had PDB  crystal structures in complex with that target.

Referencing this manually is very easy for cases where we are interested in 2-3 compounds, but for any larger number, using the ChEMBL and PDB web services greatly reduces the number of clicks.

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 →

Former OPIGlets – where are they now?

Since OPIG began in 2003, 53 students* have managed to escape. But where are these glorious people now? I decided to find out, using my best detective skills (aka LinkedIn, Google and Twitter).

* I’m only including full members who have left the group, as per the former members list on the OPIG website

Where are they?

Firstly, the countries. OPIGlets are mostly still residing in the UK, primarily in the ‘golden triangle’ of London, Oxford and Cambridge. The US comes in second, followed closely by Germany (Note: one former OPIGlet is in Malta, which is too small to be recognised in Geopandas so just imagine it is shown on the world map below)

Continue reading →

2021 likely to be a bumper year for therapeutic antibodies entering clinical trials; massive increase in new targets

Earlier this month the World Health Organisation (WHO) released Proposed International Nonproprietary Name List 125 (PL125), comprising the therapeutics entering clinical trials during the first half of 2021. We have just added this data to our Therapeutic Structural Antibody Database (Thera-SAbDab), bringing the total number of therapeutic antibodies recognised by the WHO to 711.

This is up from 651 at the end of 2020, a year which saw 89 new therapeutic antibodies introduced to the clinic. This rise of 60 in just the first half of 2021 bodes well for a record-breaking year of therapeutics entering trials.

Continue reading →

How do I do regression when my predictors have multicollinearity?

A quick summary of the key idea of principal components regression (PCR), its advantages and extensions.

Sometimes we find ourselves in a dire situation. We have measured some response y and a set of predictors W. Unfortunately, W is a wide but short matrix, say 10×100 or worse 10×100000. We’ve made only 10 observations. Standard regression is simply not going to work, because W is singular. Some would say p is bigger than n.

So what can we do? Many of us would jump to LASSO or ridge regression. However, there is another way that is often overlooked.

Continue reading →

Can few-shot language models perform bioinformatics tasks?

In 2019, I tried my hand at using large language models, specifically GPT-2, for text generation. In that blogpost, I used Hansard files to fine-tune the public release of GPT-2 to generate speeches by several speakers in the House of Commons (link).

In 2020, OpenAI released GPT-3, their new and improved text generation model (paper), which uses a whopping 175 billion parameters (as opposed to its predecessor’s 1.5 billion) and not only proved to be capable of state of the art performance on common text prediction benchmarks, but also generated a considerable amount of interest in the news media:

Continue reading →