Category Archives: Machine Learning

Learning from Biased Datasets

Both the beauty and the downfall of learning-based methods is that the data used for training will largely determine the quality of any model or system.

While there have been numerous algorithmic advances in recent years, the most successful applications of machine learning have been in areas where either (i) you can generate your own data in a fully understood environment (e.g. AlphaGo/AlphaZero), or (ii) data is so abundant that you’re essentially training on “everything” (e.g. GPT2/3, CNNs trained on ImageNet).

This covers only a narrow range of applications, with most data not falling into one of these two categories. Unfortunately, when this is true (and even sometimes when you are in one of those rare cases) your data is almost certainly biased – you just may or may not know it.

Continue reading →

No labels, no problem! A quick introduction to Gaussian Mixture Models

Statistical Modelling Big Data AnalyticsTM is in vogue at the moment, and there’s nothing quite so fashionable as the neural network. Capable of capturing complex non-linear relationships and scalable for high-dimensional datasets, they’re here to stay.

For your garden-variety neural network, you need two things: a set of features, X, and a label, Y. But what do you do if labelling is prohibitively expensive or your expert labeller goes on holiday for 2 months and all you have in the meantime is a set of features? Happily, we can still learn something about the labels, even if we might not know what they are!

Continue reading →

K-Means clustering made simple

The 21st century is often referred to as the age of “Big Data” due to the unprecedented increase in the volumes of data being generated. As most of this data comes without labels, making sense of it is a non-trivial task. To gain insight from unlabelled data, unsupervised machine learning algorithms have been developed and continue to be refined. These algorithms determine underlying relationships within the data by grouping data points into cluster families. The resulting clusters not only highlight associations within the data, but they are also critical for creating predictive models for new data.

Continue reading →

ICML 2020: Chemistry / Biology papers

ICML is one of the largest machine learning conferences and, like many other conferences this year, is running virtually from 12th – 18th July.

The list of accepted papers can be found here, with 1,088 papers accepted out of 4,990 submissions (22% acceptance rate). Similar to my post on NeurIPS 2019 papers, I will highlight several of potential interest to the chem-/bio-informatics communities. As before, given the large number of papers, these were selected either by “accident” (i.e. I stumbled across them in one way or another) or through a basic search (e.g. Ctrl+f “molecule”).

Continue reading →

Understanding the synthesizability of molecules proposed by generative models

De novo molecular design is a computational technique to generate molecules with desired properties from scratch. Classical generative algorithms are based on Genetic Algorithms (GA) and the iterative construction of molecules from molecular fragments. Recently, Variational Auto-Encoders (VAEs), Generative Adversarial Networks (GANs) have been developed for this task, however, the synthesizability of the proposed molecular structures remains an issue. Gao and Coley[1] provided an analysis of the synthesizability of the molecules proposed by these de novo generative algorithms, and discuss their strengths and weaknesses.

Continue reading →

Identifying shared antibodies using deep learning

Antibody convergence is the presence of similar antibodies in different individuals – suggesting that the individuals have had exposure to a common antigen, which has stimulated the production of similar, antigen-specific antibodies. We want to be able to identify these shared antibodies, sometimes referred to as ‘public clones’, as it could lead to development of immunodiagnostic tests against the shared antibodies, and potentially assist in the design of vaccines and therapeutic antibodies. A recent paper on bioRxiv by Sai Reddy’s group[i] has applied deep learning techniques – variational autoencoders (VAE) and support vector machines (SVM) – to the problem of how to identify shared antibodies.

Continue reading →

CCK-18 is Going Virtual

We are going virtual! Our next Comp Chem Kitchen, CCK-18, will be via a Zoom Webinar, on Friday, March 27, 2020, at 5-6 pm. We are delighted to announce that Prof. Andreas Bender from the University of Cambridgewill be speaking, as well as Dr Vicky Hellon from F1000 Research. To attend the CCK-18 webinar, you must sign up for a free Eventbrite ticket (limit 100).

Visualisation of very large high-dimensional data sets as minimum spanning trees

Large high-dimensional data sets are frequently used in chemical and biological sciences. For example the ChEMBL database contain millions of bioactive molecules from the scientific literature and their associated biological assay data are usually used for drug discovery. Visualising such databases helps understand the structure of data.

Continue reading →

State of the art in AI for drug discovery: more wet-lab please

The reception of ML approaches for the drug discovery pipeline, especially when focused on the hit to lead optimization process, has been rather skeptical by the medchem community. One of the main drivers for that is the way many ML publications benchmark their models: Historic datasets are split into two parts, with the larger part used to train and the smaller to test ML models. In order to standardize that validation process, computational chemists have constructed widely used benchmark datasets such as the DUD-E set, which is commonly used as a standard for protein-ligand binding classification tasks. Common criticism from medicinal chemists centers on the main problem associated with benchmark datasets: the absence of direct lab validation.

Continue reading →