Improved motif-scaffolding with SE(3) flow matching.

Protein design often begins with knowledge of a desired function from a motif which motif-scaffolding aims to construct a functional protein around. Recently, generative models have achieved breakthrough success in designing scaffolds for a diverse range of motifs. However, the generated scaffolds tend to lack structural diversity, which can hinder success in wet-lab validation. In this work, we extend FrameFlow, an SE(3) flow matching model for protein backbone generation, to perform motif-scaffolding with two complementary approaches. The first is motif amortization, in which FrameFlow is trained with the motif as input using a data augmentation strategy. The second is motif guidance, which performs scaffolding using an estimate of the conditional score from FrameFlow, and requires no additional training. Both approaches achieve an equivalent or higher success rate than previous state-of-the-art methods, with 2.5 times more structurally diverse scaffolds. Code: https://github.com/microsoft/frame-flow.

Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back.

A closed-loop, autonomous molecular discovery platform driven by integrated machine learning tools was developed to accelerate the design of molecules with desired properties. We demonstrated two case studies on dye-like molecules, targeting absorption wavelength, lipophilicity, and photooxidative stability. In the first study, the platform experimentally realized 294 unreported molecules across three automatic iterations of molecular design-make-test-analyze cycles while exploring the structure-function space of four rarely reported scaffolds. In each iteration, the property prediction models that guided exploration learned the structure-property space of diverse scaffold derivatives, which were realized with multistep syntheses and a variety of reactions. The second study exploited property models trained on the explored chemical space and previously reported molecules to discover nine top-performing molecules within a lightly explored structure-property space.

De novo design of protein structure and function with RFdiffusion.

There has been considerable recent progress in designing new proteins using deep-learning methods1-9. Despite this progress, a general deep-learning framework for protein design that enables solution of a wide range of design challenges, including de novo binder design and design of higher-order symmetric architectures, has yet to be described. Diffusion models10,11 have had considerable success in image and language generative modelling but limited success when applied to protein modelling, probably due to the complexity of protein backbone geometry and sequence-structure relationships. Here we show that by fine-tuning the RoseTTAFold structure prediction network on protein structure denoising tasks, we obtain a generative model of protein backbones that achieves outstanding performance on unconditional and topology-constrained protein monomer design, protein binder design, symmetric oligomer design, enzyme active site scaffolding and symmetric motif scaffolding for therapeutic and metal-binding protein design. We demonstrate the power and generality of the method, called RoseTTAFold diffusion (RFdiffusion), by experimentally characterizing the structures and functions of hundreds of designed symmetric assemblies, metal-binding proteins and protein binders. The accuracy of RFdiffusion is confirmed by the cryogenic electron microscopy structure of a designed binder in complex with influenza haemagglutinin that is nearly identical to the design model. In a manner analogous to networks that produce images from user-specified inputs, RFdiffusion enables the design of diverse functional proteins from simple molecular specifications.

Deep learning identifies synergistic drug combinations for treating COVID-19.

Effective treatments for COVID-19 are urgently needed. However, discovering single-agent therapies with activity against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been challenging. Combination therapies play an important role in antiviral therapies, due to their improved efficacy and reduced toxicity. Recent approaches have applied deep learning to identify synergistic drug combinations for diseases with vast preexisting datasets, but these are not applicable to new diseases with limited combination data, such as COVID-19. Given that drug synergy often occurs through inhibition of discrete biological targets, here we propose a neural network architecture that jointly learns drug-target interaction and drug-drug synergy. The model consists of two parts: a drug-target interaction module and a target-disease association module. This design enables the model to utilize drug-target interaction data and single-agent antiviral activity data, in addition to available drug-drug combination datasets, which may be small in nature. By incorporating additional biological information, our model performs significantly better in synergy prediction accuracy than previous methods with limited drug combination training data. We empirically validated our model predictions and discovered two drug combinations, remdesivir and reserpine as well as remdesivir and IQ-1S, which display strong antiviral SARS-CoV-2 synergy in vitro. Our approach, which was applied here to address the urgent threat of COVID-19, can be readily extended to other diseases for which a dearth of chemical-chemical combination data exists.

A Deep Learning Approach to Antibiotic Discovery.

Due to the rapid emergence of antibiotic-resistant bacteria, there is a growing need to discover new antibiotics. To address this challenge, we trained a deep neural network capable of predicting molecules with antibacterial activity. We performed predictions on multiple chemical libraries and discovered a molecule from the Drug Repurposing Hub-halicin-that is structurally divergent from conventional antibiotics and displays bactericidal activity against a wide phylogenetic spectrum of pathogens including Mycobacterium tuberculosis and carbapenem-resistant Enterobacteriaceae. Halicin also effectively treated Clostridioides difficile and pan-resistant Acinetobacter baumannii infections in murine models. Additionally, from a discrete set of 23 empirically tested predictions from >107 million molecules curated from the ZINC15 database, our model identified eight antibacterial compounds that are structurally distant from known antibiotics. This work highlights the utility of deep learning approaches to expand our antibiotic arsenal through the discovery of structurally distinct antibacterial molecules.

A graph-convolutional neural network model for the prediction of chemical reactivity.

We present a supervised learning approach to predict the products of organic reactions given their reactants, reagents, and solvent(s). The prediction task is factored into two stages comparable to manual expert approaches: considering possible sites of reactivity and evaluating their relative likelihoods. By training on hundreds of thousands of reaction precedents covering a broad range of reaction types from the patent literature, the neural model makes informed predictions of chemical reactivity. The model predicts the major product correctly over 85% of the time requiring around 100 ms per example, a significantly higher accuracy than achieved by previous machine learning approaches, and performs on par with expert chemists with years of formal training. We gain additional insight into predictions via the design of the neural model, revealing an understanding of chemistry qualitatively consistent with manual approaches.

Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction.

The task of learning an expressive molecular representation is central to developing quantitative structure-activity and property relationships. Traditional approaches rely on group additivity rules, empirical measurements or parameters, or generation of thousands of descriptors. In this paper, we employ a convolutional neural network for this embedding task by treating molecules as undirected graphs with attributed nodes and edges. Simple atom and bond attributes are used to construct atom-specific feature vectors that take into account the local chemical environment using different neighborhood radii. By working directly with the full molecular graph, there is a greater opportunity for models to identify important features relevant to a prediction task. Unlike other graph-based approaches, our atom featurization preserves molecule-level spatial information that significantly enhances model performance. Our models learn to identify important features of atom clusters for the prediction of aqueous solubility, octanol solubility, melting point, and toxicity. Extensions and limitations of this strategy are discussed.

Prediction of Organic Reaction Outcomes Using Machine Learning.

Computer assistance in synthesis design has existed for over 40 years, yet retrosynthesis planning software has struggled to achieve widespread adoption. One critical challenge in developing high-quality pathway suggestions is that proposed reaction steps often fail when attempted in the laboratory, despite initially seeming viable. The true measure of success for any synthesis program is whether the predicted outcome matches what is observed experimentally. We report a model framework for anticipating reaction outcomes that combines the traditional use of reaction templates with the flexibility in pattern recognition afforded by neural networks. Using 15 000 experimental reaction records from granted United States patents, a model is trained to select the major (recorded) product by ranking a self-generated list of candidates where one candidate is known to be the major product. Candidate reactions are represented using a unique edit-based representation that emphasizes the fundamental transformation from reactants to products, rather than the constituent molecules' overall structures. In a 5-fold cross-validation, the trained model assigns the major product rank 1 in 71.8% of cases, rank ≤3 in 86.7% of cases, and rank ≤5 in 90.8% of cases.

Discovering homotypic binding events at high spatial resolution.

MOTIVATION: Clusters of protein-DNA interaction events involving the same transcription factor are known to act as key components of invertebrate and mammalian promoters and enhancers. However, detecting closely spaced homotypic events from ChIP-Seq data is challenging because random variation in the ChIP fragmentation process obscures event locations. RESULTS: The Genome Positioning System (GPS) can predict protein-DNA interaction events at high spatial resolution from ChIP-Seq data, while retaining the ability to resolve closely spaced events that appear as a single cluster of reads. GPS models observed reads using a complexity penalized mixture model and efficiently predicts event locations with a segmented EM algorithm. An optional mode permits GPS to align common events across distinct experiments. GPS detects more joint events in synthetic and actual ChIP-Seq data and has superior spatial resolution when compared with other methods. In addition, the specificity and sensitivity of GPS are superior to or comparable with other methods. AVAILABILITY: http://cgs.csail.mit.edu/gps.

Automated discovery of functional generality of human gene expression programs.

An important research problem in computational biology is the identification of expression programs, sets of co-expressed genes orchestrating normal or pathological processes, and the characterization of the functional breadth of these programs. The use of human expression data compendia for discovery of such programs presents several challenges including cellular inhomogeneity within samples, genetic and environmental variation across samples, uncertainty in the numbers of programs and sample populations, and temporal behavior. We developed GeneProgram, a new unsupervised computational framework based on Hierarchical Dirichlet Processes that addresses each of the above challenges. GeneProgram uses expression data to simultaneously organize tissues into groups and genes into overlapping programs with consistent temporal behavior, to produce maps of expression programs, which are sorted by generality scores that exploit the automatically learned groupings. Using synthetic and real gene expression data, we showed that GeneProgram outperformed several popular expression analysis methods. We applied GeneProgram to a compendium of 62 short time-series gene expression datasets exploring the responses of human cells to infectious agents and immune-modulating molecules. GeneProgram produced a map of 104 expression programs, a substantial number of which were significantly enriched for genes involved in key signaling pathways and/or bound by NF-kappaB transcription factors in genome-wide experiments. Further, GeneProgram discovered expression programs that appear to implicate surprising signaling pathways or receptor types in the response to infection, including Wnt signaling and neurotransmitter receptors. We believe the discovered map of expression programs involved in the response to infection will be useful for guiding future biological experiments; genes from programs with low generality scores might serve as new drug targets that exhibit minimal "cross-talk," and genes from high generality programs may maintain common physiological responses that go awry in disease states. Further, our method is multipurpose, and can be applied readily to novel compendia of biological data.

High-resolution computational models of genome binding events.

Direct physical information that describes where transcription factors, nucleosomes, modified histones, RNA polymerase II and other key proteins interact with the genome provides an invaluable mechanistic foundation for understanding complex programs of gene regulation. We present a method, joint binding deconvolution (JBD), which uses additional easily obtainable experimental data about chromatin immunoprecipitation (ChIP) to improve the spatial resolution of the transcription factor binding locations inferred from ChIP followed by DNA microarray hybridization (ChIP-Chip) data. Based on this probabilistic model of binding data, we further pursue improved spatial resolution by using sequence information. We produce positional priors that link ChIP-Chip data to sequence data by guiding motif discovery to inferred protein-DNA binding sites. We present results on the yeast transcription factors Gcn4 and Mig2 to demonstrate JBD's spatial resolution capabilities and show that positional priors allow computational discovery of the Mig2 motif when a standard approach fails.

Semi-supervised analysis of gene expression profiles for lineage-specific development in the Caenorhabditis elegans embryo.

MOTIVATION: Gene expression profiling is a powerful approach to identify genes that may be involved in a specific biological process on a global scale. For example, gene expression profiling of mutant animals that lack or contain an excess of certain cell types is a common way to identify genes that are important for the development and maintenance of given cell types. However, it is difficult for traditional computational methods, including unsupervised and supervised learning methods, to detect relevant genes from a large collection of expression profiles with high sensitivity and specificity. Unsupervised methods group similar gene expressions together while ignoring important prior biological knowledge. Supervised methods utilize training data from prior biological knowledge to classify gene expression. However, for many biological problems, little prior knowledge is available, which limits the prediction performance of most supervised methods. RESULTS: We present a Bayesian semi-supervised learning method, called BGEN, that improves upon supervised and unsupervised methods by both capturing relevant expression profiles and using prior biological knowledge from literature and experimental validation. Unlike currently available semi-supervised learning methods, this new method trains a kernel classifier based on labeled and unlabeled gene expression examples. The semi-supervised trained classifier can then be used to efficiently classify the remaining genes in the dataset. Moreover, we model the confidence of microarray probes and probabilistically combine multiple probe predictions into gene predictions. We apply BGEN to identify genes involved in the development of a specific cell lineage in the C. elegans embryo, and to further identify the tissues in which these genes are enriched. Compared to K-means clustering and SVM classification, BGEN achieves higher sensitivity and specificity. We confirm certain predictions by biological experiments. AVAILABILITY: The results are available at http://www.csail.mit.edu/~alanqi/projects/BGEN.html.

Computational discovery of gene modules and regulatory networks.

We describe an algorithm for discovering regulatory networks of gene modules, GRAM (Genetic Regulatory Modules), that combines information from genome-wide location and expression data sets. A gene module is defined as a set of coexpressed genes to which the same set of transcription factors binds. Unlike previous approaches that relied primarily on functional information from expression data, the GRAM algorithm explicitly links genes to the factors that regulate them by incorporating DNA binding data, which provide direct physical evidence of regulatory interactions. We use the GRAM algorithm to describe a genome-wide regulatory network in Saccharomyces cerevisiae using binding information for 106 transcription factors profiled in rich medium conditions data from over 500 expression experiments. We also present a genome-wide location analysis data set for regulators in yeast cells treated with rapamycin, and use the GRAM algorithm to provide biological insights into this regulatory network

Continuous representations of time-series gene expression data.

We present algorithms for time-series gene expression analysis that permit the principled estimation of unobserved time points, clustering, and dataset alignment. Each expression profile is modeled as a cubic spline (piecewise polynomial) that is estimated from the observed data and every time point influences the overall smooth expression curve. We constrain the spline coefficients of genes in the same class to have similar expression patterns, while also allowing for gene specific parameters. We show that unobserved time points can be reconstructed using our method with 10-15% less error when compared to previous best methods. Our clustering algorithm operates directly on the continuous representations of gene expression profiles, and we demonstrate that this is particularly effective when applied to nonuniformly sampled data. Our continuous alignment algorithm also avoids difficulties encountered by discrete approaches. In particular, our method allows for control of the number of degrees of freedom of the warp through the specification of parameterized functions, which helps to avoid overfitting. We demonstrate that our algorithm produces stable low-error alignments on real expression data and further show a specific application to yeast knock-out data that produces biologically meaningful results.

Comparing the continuous representation of time-series expression profiles to identify differentially expressed genes.

We present a general algorithm to detect genes differentially expressed between two nonhomogeneous time-series data sets. As increasing amounts of high-throughput biological data become available, a major challenge in genomic and computational biology is to develop methods for comparing data from different experimental sources. Time-series whole-genome expression data are a particularly valuable source of information because they can describe an unfolding biological process such as the cell cycle or immune response. However, comparisons of time-series expression data sets are hindered by biological and experimental inconsistencies such as differences in sampling rate, variations in the timing of biological processes, and the lack of repeats. Our algorithm overcomes these difficulties by using a continuous representation for time-series data and combining a noise model for individual samples with a global difference measure. We introduce a corresponding statistical method for computing the significance of this differential expression measure. We used our algorithm to compare cell-cycle-dependent gene expression in wild-type and knockout yeast strains. Our algorithm identified a set of 56 differentially expressed genes, and these results were validated by using independent protein-DNA-binding data. Unlike previous methods, our algorithm was also able to identify 22 non-cell-cycle-regulated genes as differentially expressed. This set of genes is significantly correlated in a set of independent expression experiments, suggesting additional roles for the transcription factors Fkh1 and Fkh2 in controlling cellular activity in yeast.

K-ary clustering with optimal leaf ordering for gene expression data.

MOTIVATION: A major challenge in gene expression analysis is effective data organization and visualization. One of the most popular tools for this task is hierarchical clustering. Hierarchical clustering allows a user to view relationships in scales ranging from single genes to large sets of genes, while at the same time providing a global view of the expression data. However, hierarchical clustering is very sensitive to noise, it usually lacks of a method to actually identify distinct clusters, and produces a large number of possible leaf orderings of the hierarchical clustering tree. In this paper we propose a new hierarchical clustering algorithm which reduces susceptibility to noise, permits up to k siblings to be directly related, and provides a single optimal order for the resulting tree. RESULTS: We present an algorithm that efficiently constructs a k-ary tree, where each node can have up to k children, and then optimally orders the leaves of that tree. By combining k clusters at each step our algorithm becomes more robust against noise and missing values. By optimally ordering the leaves of the resulting tree we maintain the pairwise relationships that appear in the original method, without sacrificing the robustness. Our k-ary construction algorithm runs in O(n(3)) regardless of k and our ordering algorithm runs in O(4(k)n(3)). We present several examples that show that our k-ary clustering algorithm achieves results that are superior to the binary tree results in both global presentation and cluster identification. AVAILABILITY: We have implemented the above algorithms in C++ on the Linux operating system.

Combining location and expression data for principled discovery of genetic regulatory network models.

We develop principled methods for the automatic induction (discovery) of genetic regulatory network models from multiple data sources and data modalities. Models of regulatory networks are represented as Bayesian networks, allowing the models to compactly and robustly capture probabilistic multivariate statistical dependencies between the various cellular factors in these networks. We build on previous Bayesian network validation results by extending the validation framework to the context of model induction, leveraging heuristic simulated annealing search algorithms and posterior model averaging. Using expression data in isolation yields results inconsistent with location data so we incorporate genomic location data to guide the model induction process. We combine these two data modalities by allowing location data to influence the model prior and expression data to influence the model likelihood. We demonstrate the utility of this approach by discovering genetic regulatory models of thirty-three variables involved in S. cerevisiae pheromone response. The models we automatically generate are consistent with the current understanding regarding this regulatory network, but also suggest new directions for future experimental investigation.