Machine learning (ML) for biological/biomedical applications is very challenging – in large part due to limitations in publicly available data (something we recently published about [1]). Substantial amounts of time and resources may be required to generate the types of data (eg protein structures, protein-protein binding affinity, microscopy images, gene expression values) required to train ML models, however.
In cases where there is sufficient data available to provide signal, but not enough for the desired performance, ML strategies can be employed:
In this post I will cover how to calculate sequence identity and Tanimoto similarity between any pairs of complexes in PDBbind 2020. I used RDKit in python for Tanimoto similarity and the MMseqs2 software for sequence identity calculations.
A few weeks back I wanted to cluster the protein-ligand complexes in PDBbind 2020, but to achieve this I first needed to precompute the sequence identity between all pairs sequences in PDBbind, and Tanimoto similarity between all pairs of ligands. PDBbind 2020 includes 19.443 complexes but there are much fewer distinct ligands and proteins than that. However, I kept things simple and calculated the similarities for all 19.443*19.443 pairs. Calculating the Tanimoto similarity is relatively easy thanks to the BulkTanimotoSimilarity function in RDKit. The following code should do the trick:
from rdkit.Chem import AllChem, MolFromMol2File
from rdkit.DataStructs import BulkTanimotoSimilarity
import numpy as np
import os
fps = []
for pdb in pdbs:
mol = MolFromMol2File(os.path.join('data', pdb, f'{pdb}_ligand.mol2'))
fps.append(AllChem.GetMorganFingerprint(mol, 3))
sims = []
for i in range(len(fps)):
sims.append(BulkTanimotoSimilarity(fps[i],fps))
arr = np.array(sims)
np.savez_compressed('data/tanimoto_similarity.npz', arr)
Sequence identity calculations in python with Biopandas turned out to be too slow for this amount of data so I used the ultra fast MMseqs2. The first step to running MMseqs2 is to create a .fasta file of all the sequences, which I call QUERY.fasta. This is what the first few lines look like:
During the first 6 months of my DPhil, I worked on clustering antibodies and I thought I would share what I learned about these algorithms. Clustering is an unsupervised data analysis technique that groups a data set into subsets of similar data points. The main uses of clustering are in exploratory data analysis to find hidden patterns or data compression, e.g. when data points in a cluster can be treated as a group. Clustering algorithms have many applications in computational biology, such as clustering antibodies by structural similarity. Actually, this is objectively the most important application and I don’t see why anyone would use it for anything else.
There are several types of clustering algorithms that offer different advantages.
Today’s blog post is about using PLIP to extract information about interactions between a protein and ligand in a bound complex, using data from PDBbind. The blog post will cover how to combine the protein pdb file and the ligand mol2 file into a pdb file, and how to use PLIP in a high-throughput manner with python.
In order for PLIP to consider the ligand as one molecule interacting with the protein, we need to modify the mol2 file of the ligand. The 8th column of the atom portion of a mol2 file (the portion starts with @<TRIPOS>ATOM) includes the ID of the ligand that the atom belongs to. Most often all the atoms have the same ligand ID, but for peptides for instance, the atoms have the ID of the residue they’re part of. The following code snippet will make the required changes:
ligand_file = 'data/5oxm/5oxm_ligand.mol2'
with open(ligand_file, 'r') as f:
ligand_lines = f.readlines()
mod = False
for i in range(len(ligand_lines)):
line = ligand_lines[i]
if line == '@<TRIPOS>BOND\n':
mod = False
if mod:
ligand_lines[i] = line[:59] + 'ISK ' + line[67:]
if line == '@<TRIPOS>ATOM\n':
mod = True
with open('data/5oxm/5oxm_ligand_mod.mol2', 'w') as g:
for j in ligand_lines:
g.write(j)
Today’s post builds on my earlier blogpost on how to turn a SMILES string into an extended-connectivity fingerprint using RDKit and describes an interesting and easily implementable modification of the extended-connectivity fingerprint (ECFP) featurisation. This modification is based on representing the atoms in the input compound at a different (and potentially more useful) level of abstraction.
We remember that each binary component of an ECFP indicates the presence or absence of a particular circular subgraph in the input compound. Circular subgraphs that are structurally isomorphic are further distinguished according to their inherited atom- and bond features, i.e. two structurally isomorphic circular subgraphs with distinct atom- or bond features correspond to different components of the ECFP. For chemical bonds, this distinction is made on the basis of simple bond types (single, double, triple, or aromatic). To distinguish atoms, standard ECFPs use seven features based on the Daylight atomic invariants [1]; but there is also another less commonly used and often overlooked version of the ECFP that uses pharmacophoric atom features instead [2]. Pharmacophoric atom features attempt to describe atomic properties that are critical for biological activity or binding to a target protein. These features try to capture the potential for important chemical interactions such as hydrogen bonding or ionic bonding. ECFPs that use pharmacophoric atom features instead of standard atom features are called functional-connectivity fingerprints (FCFPs). The exact sets of standard- vs. pharmacophoric atom features for ECFPs vs. FCFPs are listed in the table below.
In RDKit, ECFPs can be changed to FCFPs extremely easily by changing a single input argument. Below you can find a Python/RDKit implementation of a function that turns a SMILES string into an FCFP if use_features = True and into an ECFP if use_features = False.
# import packages
import numpy as np
from rdkit.Chem import AllChem
# define function that transforms a SMILES string into an FCFP if use_features = True and into an ECFP if use_features = False
def FCFP_from_smiles(smiles,
R = 2,
L = 2**10,
use_features = True,
use_chirality = False):
"""
Inputs:
- smiles ... SMILES string of input compound
- R ... maximum radius of circular substructures
- L ... fingerprint-length
- use_features ... if true then use pharmacophoric atom features, if false then use standard DAYLIGHT atom features
- use_chirality ... if true then append tetrahedral chirality flags to atom features
Outputs:
- np.array(feature_list) ... FCFP/ECFP with length L and maximum radius R
"""
molecule = AllChem.MolFromSmiles(smiles)
feature_list = AllChem.GetMorganFingerprintAsBitVect(molecule,
radius = R,
nBits = L,
useFeatures = use_features,
useChirality = use_chirality)
return np.array(feature_list)
The use of pharmacophoric atom features makes FCFPs more specific to molecular interactions that drive biological activity. In certain molecular machine-learning applications, replacing ECFPs with FCFPs can therefore lead to increased performance and decreased learning time, as important high-level atomic properties are presented to the learning algorithm from the start and do not need to be inferred statistically. However, the standard atom features used in ECFPs contain more detailed low-level information that could potentially still be relevant for the prediction task at hand and thus be utilised by the learning algorithm. It is often unclear from the outset whether FCFPs will provide a substantial advantage over ECFPs in a given application; however, given how easy it is to switch between the two, it is almost always worth trying out both options.
[1] Weininger, David, Arthur Weininger, and Joseph L. Weininger. “SMILES. 2. Algorithm for generation of unique SMILES notation.” Journal of Chemical Information and Computer Sciences 29.2 (1989): 97-101.
[2] Rogers, David, and Mathew Hahn. “Extended-connectivity fingerprints.” Journal of Chemical Information and Modeling 50.5 (2010): 742-754.
I am not sure the University of Oxford logo works in the gold from the University of Otago…
A few months back I moved from the Oxford BRC to OPIG, both within the university of Oxford, but like many in academia I have moved across a few universities. As this is my first post here I wanted to do something neat: a JS tool that swapped colours in university logos! It was a rather laborious task requiring a lot of coding, but once I got it working, I ended up tripping up at the last metre. So for technical reasons, I have resorted to hosting it in my own blog (see post), but nevertheless the path towards it is worth discussing.
pMHCs are set to become a major target class in drug discovery; unusual peptide fragments presented by MHC can be used to distinguish infected/cancerous cells from healthy cells more precisely than over-expressed biomarkers. In this blog post, I will highlight a prototype resource: Dr. Chris Thorpe’s new database of pMHC structures, histo.fyi.
histo.fyi provides a one-stop shop for data on (currently) around 1400 pMHC complexes. Similar to our dedicated databases for antibody/nanobody structures (SAbDab) and T-cell receptor (TCR) structures (STCRDab), histo.fyi will scrape the PDB on a weekly basis for any new pMHC data and process these structures in a way that facilitates their analysis.
Have you ever had an annoying dataset that looks something like this?
or even worse, just several of them
In this blog post, I will introduce basic techniques you can use and implement with Python to identify and clean outliers. The objective will be to get something more eye-pleasing (and mostly less troublesome for further data analysis) like this
ECFPs were originally described in a 2010 article of Rogers and Hahn [1] and still belong to the most popular and efficient methods to turn a molecule into an informative vectorial representation for downstream machine learning tasks. The ECFP-algorithm is dependent on two predefined hyperparameters: the fingerprint-length L and the maximum radius R. An ECFP of length L takes the form of an L-dimensional bitvector containing only 0s and 1s. Each component of an ECFP indicates the presence or absence of a particular circular substructure in the input compound. Each circular substructure has a center atom and a radius that determines its size. The hyperparameter R defines the maximum radius of any circular substructure whose presence or absence is indicated in the ECFP. Circular substructures for a central nitrogen atom in an example compound are depicted in the image below.
Graph neural networks (GNNs) have quickly become one of the most important tools in computational chemistry and molecular machine learning. GNNs are a type of deep learning architecture designed for the adaptive extraction of vectorial features directly from graph-shaped input data, such as low-level molecular graphs. The feature-extraction mechanism of most modern GNNs can be decomposed into two phases:
Message-passing: In this phase the node feature vectors of the graph are iteratively updated following a trainable local neighbourhood-aggregation scheme often referred to as message-passing. Each iteration delivers a set of updated node feature vectors which is then imagined to form a new “layer” on top of all the previous sets of node feature vectors.
Global graph pooling: After a sufficient number of layers has been computed, the updated node feature vectors are used to generate a single vectorial representation of the entire graph. This step is known as global graph readout or global graph pooling. Usually only the top layer (i.e. the final set of updated node feature vectors) is used for global graph pooling, but variations of this are possible that involve all computed graph layers and even the set of initial node feature vectors. Commonly employed global graph pooling strategies include taking the sum or the average of the node features in the top graph layer.
While a lot of research attention has been focused on designing novel and more powerful message-passing schemes for GNNs, the global graph pooling step has often been treated with relative neglect. As mentioned in my previous post on the issues of GNNs, I believe this to be problematic. Naive global pooling methods (such as simply summing up all final node feature vectors) can potentially form dangerous information bottlenecks within the neural graph learning pipeline. In the worst case, such information bottlenecks pose the risk of largely cancelling out the information signal delivered by the message-passing step, no matter how sophisticated the message-passing scheme.
