- Noteworthy blogs to follow:
- Online resources
- Industry-focused drug discovery reviews
- Special Journal Issues
- Meeting notes
- Specific areas of interest
- Code / Packages:
- Datasets & Chemical libraries
- Helpful utilities:
Last update: 11th May 2022
Noteworthy blogs to follow:
- Patrick Walters Blog on Cheminformatics
- DrugHunter - Dennis Hu
- F. Strieth-Kalthoff, F. Sandfort, M. H. S. Segler, and F. Glorius, Machine learning the ropes: principles, applications and directions in synthetic chemistry, Chem. Soc. Rev
Pedagogical account of various machine learning techniques, models, representation schemes from perspective of synthetic chemistry. Covers different applications of machine learning in synthesis planning, property prediction, molecular design, and reactivity prediction
- Mariia Matveieva & Pavel Polishchuk. Benchmarks for interpretation of QSAR models. Github. Patrick Walter’s blog on the paper.
Paper outlining good practices for interpretating QSAR (Quantative Structure-Property Prediction) models. Good set of heuristics and comparison in the paper in terms of model interpretability. Create 6 synthetic datasets with varying complexity for QSAR tasks. The authors compare interpretability of graph-based methods to conventional QSAR methods. In regards to performance graph-based models show low interpretation compared to conventional QSAR method.
- W. Patrick Walters & Regina Barzilay. Applications of Deep Learning in Molecule Generation and Molecular Property Prediction
Recent review summarising the state of the molecular property prediction and structure generation research. In spite of exciting recent advances in the modeling efforts, there is a need to generate better (realistic) training data, assess model prediction confidence, and metrics to quantify molecular generation performance.
Review from Aspuru-Guzik and Allen’s group discussing how ML can be leveraged for various tasks in drug formulation tasks.
Industry-focused drug discovery reviews
- Abramov, Yuriy A., Guangxu Sun, and Qun Zeng. “Emerging Landscape of Computational Modeling in Pharmaceutical Development.” Journal of Chemical Information and Modeling (2022).
Overview of methods and scope of computational methods used in the drug development process.
A. Bender and I. Cortés-Ciriano, “Artificial intelligence in drug discovery: what is realistic, what are illusions? Part 1: Ways to make an impact, and why we are not there yet,” Drug Discov. Today, vol. 26, no. 2, pp. 511–524, 2021
Special Journal Issues
Specific areas of interest
Catalog of recent reviews and manuscripts I have found useful when learning more about the state-of-the-art in Cheminformatics. I’ve tried to categorize them roughly based on their area of application:
M. Krenn, F. Hase, A. Nigam, P. Friederich, and A. Aspuru-Guzik, “Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation,” Mach. Learn. Sci. Technol., pp. 1–9, 2020
Comparative study of descriptor-based and graph-based models using public data set. Used descriptor-based models (XGBoost, RF, SVM, using ECFP) and compared them to graph-based models (GCN, GAT, AttentiveFP, MPNN). They show descriptor-based models outperform the graph-based models in terms of prediction accuracy and computational efficiency with SVM having best predictions. Graph-based methods are good for multi-task learning.
- Fang, Xiaomin, et al. “Geometry-enhanced molecular representation learning for property prediction.” Nature Machine Intelligence (2022): 1-8.
Self-supervised learning using special type of GNN architecture (GeoGNN) that includes molecule geometric / spatial information. Geometry-enhanced molecular representation learning method (GEM). The model achieves SOTA performance on 14 of 15 public classification and regression datasets.
- Yang, K., Swanson, K., Jin, W., Coley, C., Eiden, P., Gao, H., Guzman-Perez, A., Hopper, T., Kelley, B., Mathea, M. and Palmer, A., 2019. Analyzing learned molecular representations for property prediction. Journal of chemical information and modeling, 59(8), pp.3370-3388
Benchmark property prediction models on 19 public and 16 proprietary industrial data sets spanning a wide variety of chemical end points. Introduce a modeling framework (Chemprop) that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary data sets.
- Stuyver, T. and Coley, C.W., 2021. Quantum chemistry-augmented neural networks for reactivity prediction: Performance, generalizability and interpretability. arXiv preprint arXiv:2107.10402
Combine structure (Graph-networks) and descriptor based features (QM-derived) to predict activation energies (E2/SN2 barrier height prediction) and regioselectivity. Incorporating QM and structure leads to better overall accuracy and generalizability even in low data regions. Atom and bond level features derived using QM and used in the model generation with a smaller dataset.
Enumeration of chemical space
- Subbaiah, Murugaiah AM, and Nicholas A. Meanwell. “Bioisosteres of the phenyl ring: Recent strategic applications in lead optimization and drug design.” Journal of Medicinal Chemistry 64.19 (2021): 14046-14128.
Looks at biosteric replacements for the phenyl rings in the lead optimization phase. Phenyl rings results in improve potency but have poor solubility and lipophilicitty. Find biosteres can be used to improve them.
- Ertl, Peter. “Magic Rings: Navigation in the Ring Chemical Space Guided by the Bioactive Rings.” Journal of Chemical Information and Modeling (2021).
Analyze the nature of rings which appear in bioactive compounds. Ring systems are systematically extracted from one billion molecules and are analyzed to discover a structure or correlation in the bioactivity and type of rings. No simple set of structural descriptors separating active and inactive rings could be identified, the separation is best described by a neural network model taking into account a complex combination of many substructure features.
- Bellmann, Louis, et al. “Comparison of Combinatorial Fragment Spaces and Its Application to Ultralarge Make-on-Demand Compound Catalogs.” Journal of Chemical Information and Modeling (2022).
Authors propose an algorithmic approach called as SpaceCompare to calculate overlap and diversity of the ultra-large combinatorial chemical libraries. The tool uses topological fragment spaces to capture the subtlties of the reaction having same product but different reactant substructures.
- Zabolotna, Yuliana, et al. “NP navigator: a new look at the natural product chemical space.” Molecular informatics 40.9 (2021): 2100068..
Organizing the chemical space of ChEMBL, and ZINC to compare its overlap with natural products through COCONUT. Generative Topological Mapping is used for the clustering and analysis. Helpful overview of the method with its application to drug discovery can be found here
- Nicolaou, Christos A., et al. “The proximal lilly collection: Mapping, exploring and exploiting feasible chemical space.” Journal of chemical information and modeling 56.7 (2016): 1253-1266.
Explainable/Interpretable Machine Learning
- Rodríguez-Pérez, Raquel, and Jürgen Bajorath. “Explainable Machine Learning for Property Predictions in Compound Optimization.” Journal of medicinal chemistry 64.24 (2021): 17744-17752
Benchmark different models and uncertainty metrics for molecular property prediction.
- Evidential Deep learning for guided molecular property prediction and disocovery Ava Soleimany, Conor Coley, et. al.. Slides
Train network to output the parameters of an evidential distribution. One forward-pass to find the uncertainty as opposed to dropout or ensemble - principled incorporation of uncertainties
Conduct a global multi-objective optimization with expected improvement criterion. Find transition metal complex redox couples for Redox flow batteries that address stability, solubility, and redox potential metric. Use distance of a point from a training data in latent space as a metric to quantify uncertainty.
Distance from available data in NN latent space is used as a variable for low-cost, quantitative uncertainty metric that works for both inorganic and organic chemistry. Introduce a technique to calibrate latent distances enabling conversion of distance-based metric to error estimates in units of predicted property
Active learning provides strategies for efficient screening of subsets of the library. In many cases, we can identify a large portion of the most promising molecules with a fraction of the compute cost.
Janet, J. P., Ramesh, S., Duan, C., & Kulik, H. J. (2020). Accurate multiobjective design in a space of millions of transition metal complexes with neural-network-driven efficient global optimization. ACS central science, 6(4), 513-524.
Experimental design using Bayesian Optimization.
- A. P. Soleimany, A. Amini, S. Goldman, D. Rus, S. N. Bhatia, and C. W. Coley, “Evidential Deep Learning for Guided Molecular Property Prediction and Discovery,” ACS Cent. Sci., Jul. 2021.. Slideshare
Train property prediction model to output a distribution statistics in single pass that describes the uncertainty. This is in contrast to using ensemble models like MC dropout. Interesting way to estimate the epistemic (due to / from model) uncertainty in the prediction. Use this approach on antibiotic search problem of Stokes et. al. Compare Chemprop and SchNet models on different tasks.
- Cai, Chenjing, et al. “Transfer learning for drug discovery.” Journal of Medicinal Chemistry 63.16 (2020): 8683-8694.
- Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning
Transfer learning by training a network to DFT data and then retrain on a dataset of gold standard QM calculations (CCSD(T)/CBS) that optimally spans chemical space. The resulting potential is broadly applicable to materials science, biology, and chemistry, and billions of times faster than CCSD(T)/CBS calculations.
Use CheMBL dataset to train a gated graph neural network (GGNN) for prediction and classification tasks using meta learning protocols. Show appreciable model performance even with just approx. 256 datapoints.
Consortia comprising of leading resarch labs and companies working on decentralized datasets and predictive modeling of biochemical and cellular activity.
Mouchlis VD, Afantitis A, Serra A, et al. Advances in de Novo Drug Design: From Conventional to Machine Learning Methods. Int J Mol Sci. 2021;22(4):1676. Published 2021 Feb 7. doi:10.3390/ijms22041676
- Flam-Shepherd, Daniel, Kevin Zhu, and Alán Aspuru-Guzik. “Keeping it Simple: Language Models can learn Complex Molecular Distributions.” arXiv preprint arXiv:2112.03041 (2021).
Test SOTA language models and representation performance against graph-based methods (CGVAE, JTVAE) for ‘challenging’ generative modeling tasks - generate a molecule - property distribution as a function of synthetic feasiblity. Graph models faced chanllenge in generating large molcules (> 100 HAs). Selfies provided advantage here. All of the models seem to generate novel molecules - how practical each of these novel molecules are is yet an open question.
Propose a platform to deploy and compare state-of-the-art generative models for exploring molecular space on same dataset. In addition the authors also propose list of metrics to evaluate the quality and diversity of the generated structures.
Evaluation framework from BenevolentAI to compare different de-novo design models.
- J. Zhang, R. Mercado, O. Engkvist, and H. Chen, “Comparative Study of Deep Generative Models on Chemical Space Coverage,” J. Chem. Inf. Model., vol. 61, no. 6, pp. 2572–2581, Jun. 2021.
Interesting analysis from team at AstraZeneca R&D. They look at the chemical space coverage accounted by the SOTA generative models. Proposes a metric for evaluating space coverage, and thereby comparing different SOTA models, using a reference data (GDB-13 in this case). The new metric computes how much of the GDB-13 dataset can be recovered by a model that is trained on small GDB subset. Generative models were trained on same 1M data points and 1B molecules were then sampled from each model. It was seen that at most 39% of the molecules in the parent dataset were sampled / generated by the model. Most models sampled the same compounds atleast twice. It was observed that graph-based model sampled much diverse molecules than string-based methods. Besides, the coverage of GAN-based models was worse compared to Language and Graph models.
- Gao, W.; Coley, C. W. The Synthesizability of Molecules Proposed by Generative Models. J. Chem. Inf. Model. 2020
This paper looks at different ways of integrating synthesizability criteria into generative models.
Bechmark work from AstraZeneca/MIT AI team to document different graph architecture schemes and algorithms for generative models.
- R. Gómez-Bombarelli et al., “Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules,” ACS Cent. Sci., vol. 4, no. 2, pp. 268–276, 2018
One of the first implementation of a variation auto-encoder for molecule generation
Representation using SELFIES proposed to make it much more powerful
SMILES-based language model that generates molecules from scaffolds and can be trained from any arbitrary molecular set. Uses randomized SMILES to improve final prediction validity.
- Flam-Shepherd, Daniel, Alexander Zhigalin, and Alán Aspuru-Guzik. “Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning.” arXiv preprint arXiv:2202.00658 (2022)
Reinforcement learning-based generative model whici is an update on point cloud approach by the same group to now incorporate ‘grammar’ for building molecules in form of functional groups in 3D space.
- W. Jin, R. Barzilay, and T. Jaakkola, “Junction tree variational autoencoder for molecular graph generation,” 35th Int. Conf. Mach. Learn. ICML 2018, vol. 5, pp. 3632–3648, 2018
Junction tree based decoding. Define a grammar for the small molecule and find sub-units based on that grammar to construct a molecule. The molecule is generated in two-steps: first being generating the scaffold or backbone of the molelcule, then the nodes are added with molecular substructure as identified from the ‘molecular grammar’.
- MPGVAE: Message passing graph networks for molecular generation, Daniel Flam-Shepherd et al 2021 Mach. Learn.: Sci. Technol.
Introduce a graph generation model by building a Message Passing Neural Network (MPNNs) into the encoder and decoder of a VAE (MPGVAE).
Algorithm to predict 3D conforms from molecular graphs.
- GraphINVENT: R. Mercado, T. Rastemo, E. Lindelöf, G. Klambauer and O. Engkvist, “Graph networks for molecular design,” Mach. Learn. Sci. Technol., vol. 2, no. 2, p. 25023, 2021. Github. Blogpost
GraphINVENT uses a tiered deep neural network architecture to probabilistically generate new molecules a single bond at a time.
Generative adversarial network for finding small molecules using graph networks, quite interesting. Avoids issues arising from node ordering that are associated with likelihood based methods by using an adversarial loss instead (GAN)
- LatentGAN: A de novo molecular generation method using latent vector based generative adversarial network
Molecular generation strategy is described which combines an autoencoder and a GAN. Generator and discriminator network do not use SMILES strings as input, but instead n-dimensional vectors derived from the code-layer of an autoencoder trained as a SMILES heteroencoder that way syntax issues are expected to be addressed.
Team at Novartis and Microsoft propose MoLeR, graph based model to generate molecule using scaffold as a seed. Scaffold based SAR speed up shown.
- Bolcato, Giovanni, and Jonas Boström. “On the Value of Using 3D-shape and Electrostatic Similarities in Deep Generative Methods.” ChemRxiv (2021).
Extension to the fragment-based reinforcement learning methods for generating novel compounds. Comparison of 3D molecular fragments to aid in identifying bioactive conformations.
- Iovanac, Nicolae C., Robert MacKnight, and Brett Savoie. “Actively Searching: Inverse Design of Novel Molecules with Simultaneously Optimized Properties.” ChemRxiv (2021)
Using quantum chemistry attributes calculated on-the-fly as scoring functions for sampling the generative model chemical space. Active learning strategy is deployed to explore the area of space where the properties of the molecules are unknown.
Computer Aided Synthesis Planning (CASP)
Perspective article summarising their position on the current state of research and future considerations on developing better reaction network models. Break down the analysis of reaction networks as into 3 classes (1) Front Open End: exploration of products from reactants (2) Backward Open Start: Know the product and explore potential reactants (3) Start to End: Product and reactant known, explore the likely intermediates.
Nice summary of potential challenges in the field:
- Validating exploration algorithms on a consistent set of reaction system.
- Need to generate a comparative metric to benchmark different algorithms.
Considering effect of solvents and/or protein embeddings in the analysis
- Previous review article by same group: Exploration of Reaction Pathways and Chemical Transformation Networks
Technical details of various algorithms being implemented for reaction mechanism discovery at the time of writing the review.
- Gimadiev, T. R., Lin, A., Afonina, V. A., Batyrshin, D., Nugmanov, R. I., Akhmetshin, T., … & Varnek, A. (2021). Reaction Data Curation I: Chemical Structures and Transformations Standardization. Molecular Informatics, 2100119.
Article from Varnek group on best practices on processing data for reaction informatics.
- Genheden S, Bjerrum E. PaRoutes: a framework for benchmarking retrosynthesis route predictions. ChemRxiv. Cambridge: Cambridge Open Engage; 2022. Github
Benchmarking framework for comparing different multi-step retrosynthesis methods from researchers at AstraZeneca R&D. Provides 10k synthetic routes which can be used as a validation set for different methodologies, providing a platform for systematic comparison of different methods being proposed in the community.
Classifying chemical reactions:
- Schneider, N., et al. (2015). “Development of a Novel Fingerprint for Chemical Reactions and Its Application to Large-Scale Reaction Classification and Similarity.” Journal of Chemical Information and Modeling 55(1): 39-53.
Using scrapped US Patent data to classify chemical reactions and deploy various fingerprints and ML models for classification.
- Schwaller, Philippe, et al. “Mapping the space of chemical reactions using attention-based neural networks.” Nature Machine Intelligence 3.2 (2021): 144-152.. rxnfp - Github. Preprint. News Article.
Transformer-based model for reaction classification. Compared it with BERT. Besides classification, the work also formalizes the reaction fingerprint generation using the learned representations. The reaction fingerprints are visualized using TMAPS.
Reaction classifiction prediction using atom-mapped reaction that are used to generate condensed reaction graphs and passed through a GCN-variant as implemented in chemprop.
- Lin, A., et al. (2021). “Atom-to-atom Mapping: A Benchmarking Study of Popular Mapping Algorithms and Consensus Strategies.”
Comparative analysis of different atom-mapping schemes for generating atom-mapped reaction features. Comments on the state of the art methods and their performance on a curated reaction database.
Data-driven atom mapping schemes which uses transformers for learning the context of the chemical reaction. Researchers at IBM trained a flavor of language model based on Transformer architecture and used it to find reaction centers and maps atoms. Shown to be robust compared to other SOTA methods.
Predicting reaction outcomes:
- C. W. Coley et al., “A graph-convolutional neural network model for the prediction of chemical reactivity,” Chem. Sci., vol. 10, no. 2, pp. 370–377, 2019.
Template-free prediction of organic reaction outcomes using graph convolutional neural networks
- Zabolotna, Y., et al. (2021). “SynthI: A New Open-Source Tool for Synthon-Based Library Design.” Journal of Chemical Information and Modeling.
Interesting work on de-novo design of molecules wherein, the molecules being created are made up from the fragments that is known to exist and are available to the user. New molecules are generated based on the fragmented (synthons) made available in the dataset.
Generation reaction networks:
- M. Liu et al., “Reaction Mechanism Generator v3.0: Advances in Automatic Mechanism Generation,” J. Chem. Inf. Model., May 2021
Newest version of RMG (v3) is updated to Python v3. It has ability to generate heterogeneous catalyst models, uncertainty analysis to conduct first order sensitivity analysis. RMG dataset for the thermochemical and kinetic parameters have been expanded.
- More and Faster: Simultaneously Improving Reaction Coverage and Computational Cost in Automated Reaction Prediction Tasks
Presents an algorithmic improvement to the reaction network prediction task through their YARP (Yet Another Reaction Program) methodology. Shown to reduce computational cost of optimization while improving the diversity of identified products and reaction pathways.
- Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction
- Machine learning in chemical reaction space
Look at exploration of reaction space rather than compound space. SOAP kernel for representing the moelcules. Estimate atomization energy for the molecules using ML. Calculate the d(AE) for different ML-estimated AEs. Reaction energies (RE) are estimated and uncertainty propogation is used to estimate the errors. Uncorrelated constant error propogation. 30,000 bond breaking reaction steps Rad-6-RE network used. RE prediction is not as good as AE.
- Kearnes, S. M., et al. (2021). “The Open Reaction Database.” Journal of the American Chemical Society.
New form of storing huge amounts of molecule related data using DNA. Made partially possible by low cost of DNA sequencing. Each molecule in the storage is attached with a DNA strand which encode information about its recipe.
DNA encodings for discovery of novel small-molecule protein inhibitors. Outline a process for building a ML model using DEL. Compare graph convolutions to random forest for classification tasks with application to protein target binding. Graph models seemed to achieve high hit rate comapred to random forest. Apply diversity, logistical, structural filtering to search for novel candidates. First work to use GCN for hit searching.
Code / Packages:
Automates the selection of decision threshold for imbalanced classification task. The assumption for this method to work is the similar characteristics (like imbalance ratio) of training and test data.
Benchmarking platform to implement molecular generative models. It also provides a set of metrics to evaluate the quality and diversity of the generated molecules. A benchmark dataset (subset of ZINC) is provided for training the models.
Production-ready tool for de novo design from Astra Zeneca. It can be effectively applied on drug discovery projects that are striving to resolve either exploration or exploitation problems while navigating the chemical space. Language model with SMILE output and trained by “randomizing” the SMILES representation of the input data. Implement reinforcement-leraning for directing the model towards relevant area of interest.
DeepChem aims to provide a high quality open-source toolchain that democratizes the use of deep-learning in drug discovery, materials science, quantum chemistry, and biology - from Github
Github repository for implmenting message passing neural networks for molecular property prediction as described in the paper Analyzing Learned Molecular Representations for Property Prediction by Yang et. al.
“Chainer Chemistry is a deep learning framework (based on Chainer) with applications in Biology and Chemistry. It supports various state-of-the-art models (especially GCNN - Graph Convolutional Neural Network) for chemical property prediction” - from their Github repo introduction
Tool to generate chemical reaction networks. Includes Arkane, package for calculating thermodynamics from quantum mechanical calculations.
Active learning approach to efficiently and confidently identify the Pareto front with any regression model that can output a mean and a standard deviation.
Github repository to generate chemical reaction fingerprints from reaction SMILES.
Interactive chemical viewer for small molecules (RDKit wrapper)
Spotfire like capabilities to jupyter notebook.
Datasets & Chemical libraries
PubChem: public sourced molecules
ChEMBL: bioactive molecules (most synthetic)
ZINC: collection of synthetic molecules (not all are bioactive)
QM 7/8/9: small molecules having not more than 7/8/9 heavy atoms
COCONUT: NP 400k there are some which are not NP
Mcule: Used in DEL enumerations
Commericial (building block) vendors
eMolecules building blocks
Enamine REAL Space
WuXi GalaXi space
- Therapeutics Data Commons “Therapeutics Data Commons is an open-science platform with AI/ML-ready datasets and learning tasks for therapeutics, spanning the discovery and development of safe and effective medicines. TDC also provides an ecosystem of tools, libraries, leaderboards, and community resources, including data functions, strategies for systematic model evaluation, meaning”