As a data-driven science, genomics largely utilizes machine learning to capture dependencies in data and derive novel biological hypotheses. However, the ability to extract new insights from the exponentially increasing volume of genomics data requires more expressive machine learning models. By effectively leveraging large data sets, deep learning has transformed fields such as computer vision and natural language processing. Now, it is becoming the method of choice for many genomics modelling tasks, including predicting the impact of genetic variation on gene regulatory mechanisms such as DNA accessibility and splicing. This Review describes different deep learning techniques and how they can be applied to extract biologically relevant information from large, complex genomic data sets.

Deep learning: new computational modelling techniques for genomics

The therapeutic properties of plants have been recognised since time immemorial. Many pathological conditions have been treated using plant-derived medicines. These medicines are used as concoctions or concentrated plant extracts without isolation of active compounds. Modern medicine however, requires the isolation and purification of one or two active compounds. There are however a lot of global health challenges with diseases such as cancer, degenerative diseases, HIV/AIDS and diabetes, of which modern medicine is struggling to provide cures. Many times the isolation of “active compound” has made the compound ineffective. Drug discovery is a multidimensional problem requiring several parameters of both natural and synthetic compounds such as safety, pharmacokinetics and efficacy to be evaluated during drug candidate selection. The advent of latest technologies that enhance drug design hypotheses such as Artificial Intelligence, the use of ‘organ-on chip’ and microfluidics technologies, means that automation has become part of drug discovery. This has resulted in increased speed in drug discovery and evaluation of the safety, pharmacokinetics and efficacy of candidate compounds whilst allowing novel ways of drug design and synthesis based on natural compounds. Recent advances in analytical and computational techniques have opened new avenues to process complex natural products and to use their structures to derive new and innovative drugs. Indeed, we are in the era of computational molecular design, as applied to natural products. Predictive computational softwares have contributed to the discovery of molecular targets of natural products and their derivatives. In future the use of quantum computing, computational softwares and databases in modelling molecular interactions and predicting features and parameters needed for drug development, such as pharmacokinetic and pharmacodynamics, will result in few false positive leads in drug development. This review discusses plant-based natural product drug discovery and how innovative technologies play a role in next-generation drug discovery.

https://www.mdpi.com/1422-0067/19/6/1578/pdf/1

Natural Products for Drug Discovery in the 21st Century: Innovations for Novel Drug Discovery.

Protein engineering through machine-learning-guided directed evolution enables the optimization of protein functions. Machine-learning approaches predict how sequence maps to function in a data-driven manner without requiring a detailed model of the underlying physics or biological pathways. Such methods accelerate directed evolution by learning from the properties of characterized variants and using that information to select sequences that are likely to exhibit improved properties. Here we introduce the steps required to build machine-learning sequence-function models and to use those models to guide engineering, making recommendations at each stage. This review covers basic concepts relevant to the use of machine learning for protein engineering, as well as the current literature and applications of this engineering paradigm. We illustrate the process with two case studies. Finally, we look to future opportunities for machine learning to enable the discovery of unknown protein functions and uncover the relationship between protein sequence and function.

/pdf/machine-learning-guided-directed-evolution-for-protein-2kyvo4u8ck.pdf

Machine-learning-guided directed evolution for protein engineering.

Deep learning methods are a class of machine learning techniques capable of identifying highly complex patterns in large datasets. Here, we provide a perspective and primer on deep learning applications for genome analysis. We discuss successful applications in the fields of regulatory genomics, variant calling and pathogenicity scores. We include general guidance for how to effectively use deep learning methods as well as a practical guide to tools and resources. This primer is accompanied by an interactive online tutorial.

A primer on deep learning in genomics.

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Generative artificial intelligence models present a fresh approach to chemogenomics and de novo drug design, as they provide researchers with the ability to narrow down their search of the chemical space and focus on regions of interest. We present a method for molecular de novo design that utilizes generative recurrent neural networks (RNN) containing long short-term memory (LSTM) cells. This computational model captured the syntax of molecular representation in terms of SMILES strings with close to perfect accuracy. The learned pattern probabilities can be used for de novo SMILES generation. This molecular design concept eliminates the need for virtual compound library enumeration. By employing transfer learning, we fine-tuned the RNN′s predictions for specific molecular targets. This approach enables virtual compound design without requiring secondary or external activity prediction, which could introduce error or unwanted bias. The results obtained advocate this generative RNN-LSTM system for high-impact use cases, such as low-data drug discovery, fragment based molecular design, and hit-to-lead optimization for diverse drug targets.

https://onlinelibrary.wiley.com/doi/pdf/10.1002/minf.201700111

Generative Recurrent Networks for De Novo Drug Design.

Generative adversarial networks (GANs) represent an attractive and novel approach to generate realistic data, such as genes, proteins or drugs, in synthetic biology. Here, we apply GANs to generate synthetic DNA sequences encoding for proteins of variable length. We propose a novel feedback-loop architecture, feedback GAN (FBGAN), to optimize the synthetic gene sequences for desired properties using an external function analyser. The proposed architecture also has the advantage that the analyser does not need to be differentiable. We apply the feedback-loop mechanism to two examples: generating synthetic genes coding for antimicrobial peptides, and optimizing synthetic genes for the secondary structure of their resulting peptides. A suite of metrics, calculated in silico, demonstrates that the GAN-generated proteins have desirable biophysical properties. The FBGAN architecture can also be used to optimize GAN-generated data points for useful properties in domains beyond genomics. Generative machine learning models are used in synthetic biology to find new structures such as DNA sequences, proteins and other macromolecules with applications in drug discovery, environmental treatment and manufacturing. Gupta and Zou propose and demonstrate in silico a feedback-loop architecture to optimize the output of a generative adversarial network that generates synthetic genes to produce ones specifically coding for antimicrobial peptides.

Feedback GAN for DNA optimizes protein functions

Generative Adversarial Networks (GANs) represent an attractive and novel approach to generate realistic data, such as genes, proteins, or drugs, in synthetic biology. Here, we apply GANs to generate synthetic DNA sequences encoding for proteins of variable length. We propose a novel feedback-loop architecture, called Feedback GAN (FBGAN), to optimize the synthetic gene sequences for desired properties using an external function analyzer. The proposed architecture also has the advantage that the analyzer need not be differentiable. We apply the feedback-loop mechanism to two examples: 1) generating synthetic genes coding for antimicrobial peptides, and 2) optimizing synthetic genes for the secondary structure of their resulting peptides. A suite of metrics demonstrate that the GAN generated proteins have desirable biophysical properties. The FBGAN architecture can also be used to optimize GAN-generated datapoints for useful properties in domains beyond genomics.

Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions.

Erratum: Generative Recurrent Networks for De Novo Drug Design.

Targeted optimizing of existing DNA sequences for useful properties, has the potential to enable several synthetic biology applications from modifying DNA to treat genetic disorders to designing regulatory elements to fine tune context-specific gene expression. Current approaches for targeted genome editing are largely based on prior biological knowledge or ad-hoc rules. Few if any machine learning approaches exist for targeted optimization of regulatory DNA sequences. Here, we propose a novel generative neural network architecture for targeted DNA sequence editing - the EDA architecture - consisting of an encoder, decoder, and analyzer. We showcase the use of EDA to optimize regulatory DNA sequences to bind to the transcription factor SPI1. Compared to other state-of-the-art approaches such as a textual variational autoencoder and rule-based editing, EDA significantly improves predicted binding of SPI1 of genomic sequences with the minimal set of edits. We also use EDA to design regulatory elements with optimized grammars of CREB1 binding sites that can tune reporter expression levels as measured by massively parallel reporter assays (MPRA). We analyze the properties of the binding sites in the edited sequences and find patterns that are consistent with previously reported grammatical rules which tie gene expression to CRE binding site density, spacing and affinity.

/pdf/targeted-optimization-of-regulatory-dna-sequences-with-3ry64ev894.pdf

Anvita Gupta

Papers

Generative Recurrent Networks for De Novo Drug Design.

Feedback GAN for DNA optimizes protein functions

Feedback GAN (FBGAN) for DNA: a Novel Feedback-Loop Architecture for Optimizing Protein Functions.

Erratum: Generative Recurrent Networks for De Novo Drug Design.

Targeted optimization of regulatory DNA sequences with neural editing architectures