Category Archives: Cheminformatics

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

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

Bayesian Optimization and Correlated Torsion Angles—in Small Molecules

Our collaborator, Prof. Geoff Hutchison from the University of Pittsburg recently took part in the Royal Society of Chemistry’s 2020 Twitter Poster Conference, to highlight the great work carried out by one of my DPhil students, Lucian Leung Chan, on the application of Bayesian optimization to conformer generation:

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

Effect of Debiasing Protein-Ligand binding data on Generalization

Virtual screening is a computational technique used in drug discovery to search libraries of small molecules in order to identify those structures that bind tightly and specifically to a given protein target. Many machine learning (ML) models have been proposed for virtual screening, however, it is not clear whether these models can truly predict the molecular properties accurately across chemical space or simply overfit the training data. As chemical space contains clusters of molecules around scaffolds, memorising the properties of a few scaffolds can be sufficient to perform well, masking the fact that the model may not generalise beyond close analogue. Different debiasing algorithms have been introduced to address this problem. These algorithms systematically partition the data to reduce bias and provide a more accurate metric of the model performance.

Continue reading

AutoDock 4 and AutoDock Vina

A recently just-released publication from Ngyuen et al. ing JCIM pointed out that while AutoDock Vina is faster, AutoDock 4 tends to have better correlation with experimental binding affinity.1

[This post has been edited to provide more information about the cited paper, as well as providing additional citations.]

Ngyuyen et al. selected 800 protein-ligand complexes for 47 protein targets that had both experimental PDB structures complexed with a ligand, as well as their associated binding affinity values.

Continue reading

Journal Club: Is our data biased, and should it be?

Jia, X., Lynch, A., Huang, Y. et al. Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis. Nature 573, 251–255 (2019) doi:10.1038/s41586-019-1540-5 https://www.nature.com/articles/s41586-019-1540-5

Last week I presented the above paper at group meeting. While a little different from a typical OPIG journal club paper, the data we have access to almost certainly suffers from the same range of (possible) biases explored in this paper.

Continue reading