Biology subjects

Cowen, L.

Publications and source records attributed to Cowen, L..

16 recordsLinked to original sources

bioRxiv2026

A Novel ILP Framework to Identify Compensatory Pathways in Genetic Interaction Networks with GIDEON

In Bakers yeast, there exists a comprehensive collection of pairwise epistasis experiments that, for nearly every pair of non-essential genes, measures the growth of the double-knockout strain as compared to its component single knockouts. This data can be represented as a weighted signed graph termed the genetic interaction network, and we introduce a new ILP-based method named GIDEON to search for a diverse collection of Between-Pathway Models (BPMs) in this network, where BPMs are a graph motif signature that indicates potential compensatory pathways in the genetic interaction network. With both an improved distribution-informed edge weighting scheme and an improved ILP method, GIDEON produces BPM collections that are substantially larger and with better functional enrichment compared to previous methods. We find some interesting new BPM gene sets including one with potential insights into antifungal drug targets through ties between ergosterol and aromatic amino acid biosynthesis.

bioinformatics↗

bioRxiv2026

Learning a PRECISE language for small-molecule binding

Virtual screening of billion-scale compound libraries has become feasible through machine learning approaches. In particular, CoNCISE (RECOMB 2025) introduced drug quantization via code-books, achieving highly scalable and accurate binary predictions. However, drug discovery requires understanding not just whether molecules bind, but where they bind and how to target specific sites. Here, we present PRECISE which leverages CoNCISEs quantized small-molecule representations while operating on the targets 3D structure as its input. The key innovation of PRECISE is reimagining drug-target interaction as compatibility between quantized drug embeddings and a latent representation of the targets surface mesh, enriched with electrostatic and geometric features. PRECISE designs a novel surface representation, interpreted through a geometric deep learning architecture, enabling it to identify binding sites more accurately than state-of-the-art methods (DiffDock-L, Chai, and Boltz-2) while the codebook ensures billion-scale screening capability. Our formulation unlocks zero-shot generalization to complex targets such as metalloproteins and multi-chain complexes. To enable efficient integration with downstream docking workflows, we introduce PO_SCPLOWRECISEC_SCPLOW-MCTS, which combines fast PO_SCPLOWRECISEC_SCPLOW-based screening with selective Vina docking through an iterative Monte Carlo Tree Search approach. By providing both mechanistic understanding and massive scalability, PRECISE delivers capabilities that were previously mutually exclusive in virtual screening.

bioinformatics↗

bioRxiv2025

Learning a CoNCISE language for small-molecule binding

Rapid advances in deep learning have improved in silico methods for drug-target interaction (DTI) prediction. However, current methods do not scale to the massive catalogs that list millions or billions of commercially-available small molecules. Here, we introduce CoNCISE, a method that accelerates drug-target interaction (DTI) prediction by 2-3 orders of magnitude while maintaining high accuracy. CoNCISE uses a novel vector-quantized codebook approach and a residual-learning based training of hierarchical codes. Strikingly, we find that much of binding-specificity information in the small molecule space can be compressed into just 15 bits of information per compound, characterizing all small molecules into 32,768 hierarchically-organized binding categories. Our DTI architecture, which combines these compact ligand representations with fixed-length protein embeddings in a cross-attention framework, achieves state-of-the-art prediction accuracy at unprecedented speed. We demonstrate CoNCISEs practical utility by indexing 6.4 billion ligands in the Enamine dataset, enabling researchers to query vast chemical libraries against a protein target in seconds. A "CoNCISE + docking" pipeline screened Enamine to propose strong binders (predicted KD {approx} 10-20 {micro}M) of three difficult-to-drug targets, each within two hours. CoNCISEs advance could democratize access to largescale computational drug discovery, potentially enabling rapid identification of promising molecules for therapeutic targets and cellular perturbations.

bioinformatics↗

bioRxiv2024

Decoding the Functional Interactome of Non-Model Organisms with PHILHARMONIC

Despite the widespread availability of genome sequencing pipelines, many genes remain part of the genome's "dark matter," where existing inference tools cannot even begin to guess the biological function of their proteins from sequence alone. This challenge is especially pronounced in organisms that are highly evolutionarily distant from well-studied models, where homology-based methods break down. Here, we describe PHILHARMONIC, a computational method that combines deep learning-based de novo protein interaction network inference with robust unsupervised spectral clustering and remote homology to illuminate functional organization in any non-model organism. From only a sequenced proteome, we show PHILHARMONIC generates meaningful functional hypothesis for protein functions, functional communities, and higher-order network structure. We validate its performance using experimental gene expression and pathway data in D. melanogaster, and we demonstrate its broad utility by analyzing temperature sensing and stress response pathways in the reef-building coral P. damicornis and its algal symbiont C. goreaui. PHILHARMONIC provides a general-purpose engine for functional discovery and biological hypothesis generation in non-model organisms, enabling systems-level insights across the full diversity of life.

bioinformatics↗

bioRxiv2023

Diverse Plant-Parasitic Nematodes are Selectively Killed by Oxadiazole Thioether Pro-Nematicides

Left unchecked, plant-parasitic nematodes have the potential to devastate crops globally. Highly effective but non-selective nematicides are justifiably being phased-out, leaving farmers with limited options for managing nematode infestation. Here, we report our discovery of a 1,3,4-oxadiazole thioether scaffold called Cyprocide that selectively kills diverse plant-parasitic nematodes. Cyprocide is bioactivated into a lethal reactive electrophilic metabolite by specific nematode cytochrome P450 enzymes. Because Cyprocide fails to kill non-target organisms, we infer that the targeted lethality of this pro-nematicide derives from P450 substrate selectivity. Our findings demonstrate that Cyprocide is a selective nematicidal scaffold with broad-spectrum activity that holds the potential to help safeguard our global food supply.

genetics↗

bioRxiv2023

MELISSA: Semi-Supervised Embedding for Protein Function Prediction Across Multiple Networks

MotivationSeveral popular methods exist to predict function from multiple protein-protein association networks. For example, both the Mashup algorithm, introduced by Cho, Peng and Berger, and deepNF, introduced by Gligorijevi[c], Barotand, and Bonneau, analyze the diffusion in each network first, to characterize the topological context of each node. In Mashup, the high-dimensional topological patterns in individual networks are canonically represented using low-dimensional vectors, one per gene or protein, to yield the multi-network embedding. In deepNF, a multimodal autoencoder is trained to extract common network features across networks that yield a low-dimensional embedding. Neither embedding takes into account known functional labels; rather, these are then used by the machine learning methods applied after embedding. ResultsWe introduce MELISSA (MultiNetwork Embedding with Label Integrated Semi-Supervised Augmentation) which incorporates functional labels in the embedding stage. The function labels induce sets of "must link" and "cannot link" constraints which guide a further semi-supervised dimension reduction to yield an embedding that captures both the network topology and the information contained in the annotations. We find that the MELISSA embedding improves on both the Mashup and deepNF embeddings in creating more functionally enriched neighborhoods for predicting GO labels for multiplex association networks in both yeast and humans. AvailabilityMELISSA is available at https://github.com/XiaozheHu/melissa

bioinformatics↗

bioRxiv2023

Characterizing transcriptomic responses to sediment stress across location and morphology in reef-building corals

Anthropogenic activities increase sediment suspended in the water column and deposition on reefs can be largely dependent on colony morphology. Massive and plating corals have a high capacity to trap sediments, and active removal mechanisms can be energetically costly. Branching corals trap less sediment, but are more susceptible to light limitation caused by suspended sediment. Despite deleterious effects of sediments on corals, few studies have examined the molecular response of corals with different morphological characteristics to sediment stress. To address this knowledge gap, this study assessed the transcriptomic responses of branching and massive corals in Florida and Hawai{square}i to varying levels of sediment exposure. Gene expression analysis revealed a molecular responsiveness to sediments across species and sites. Differentially Gene Expression (DEG) followed by Gene Ontology (GO) enrichment analysis identified that branching corals had the largest transcriptomic response to sediments, in developmental processes and metabolism, while significantly enriched GO terms were highly variable between massive corals, despite similar morphologies. Comparison of DEGs within orthogroups revealed that while all corals had DEGs in response to sediment, there was not a concerted gene set response by morphology or location. These findings illuminate the species specificity and genetic basis underlying coral susceptibility to sediments.

bioinformatics↗

bioRxiv2022

Learning the Drug-Target Interaction Lexicon

Sequence-based prediction of drug-target interactions has the potential to accelerate drug discovery by complementing experimental screens. Such computational prediction needs to be generalizable and scalable while remaining sensitive to subtle variations in the inputs. However, current computational techniques fail to simultaneously meet these goals, often sacrificing performance on one to achieve the others. We develop a deep learning model, ConPLex, successfully leveraging the advances in pre-trained protein language models ("PLex") and employing a novel protein-anchored contrastive co-embedding ("Con") to outperform state-of-the-art approaches. ConPLex achieves high accuracy, broad adaptivity to unseen data, and specificity against decoy compounds. It makes predictions of binding based on the distance between learned representations, enabling predictions at the scale of massive compound libraries and the human proteome. Furthermore, ConPLex is interpretable, which enables us to visualize the drug-target lexicon and use embeddings to characterize the function of human cell-surface proteins. We anticipate ConPLex will facilitate novel drug discovery by making highly sensitive and interpretable in-silico drug screening feasible at genome scale. Con-PLex is available open-source at https://github.com/samsledje/ConPLex. Significance StatementIn time and money, one of the most expensive steps of the drug discovery pipeline is the experimental screening of small molecules to see which will bind to a protein target of interest. Therefore, accurate high-throughput computational prediction of drug-target interactions would unlock significant value, guiding and prioritizing promising candidates for experimental screening. We introduce ConPLex, a machine learning method for predicting drug-target binding which achieves state-of-the-art accuracy on many types of targets by using a pre-trained protein language model. The approach co-locates the proteins and the potential drug molecules in a shared feature space while learning to contrast true drugs from similar non-binding "decoy" molecules. ConPLex is extremely fast, which allows it to rapidly shortlist candidates for deeper investigation.

bioinformatics↗

bioRxiv2022

Adapting protein language models for rapid DTI prediction

We consider the problem of sequence-based drug-target interaction (DTI) prediction, showing that a straightforward deep learning architecture that leverages pre-trained protein language models (PLMs) for protein embedding outperforms state of the art approaches, achieving higher accuracy, expanded generalizability, and an order of magnitude faster training. PLM embeddings are found to contain general information that is especially useful in few-shot (small training data set) and zero-shot instances (unseen proteins or drugs). Additionally, the PLM embeddings can be augmented with features tuned by task-specific pre-training, and we find that these task-specific features are more informative than baseline PLM features. We anticipate such transfer learning approaches will facilitate rapid prototyping of DTI models, especially in low-N scenarios.

bioinformatics↗

bioRxiv2022

Contrasting drugs from decoys

Protein language models (PLMs) have recently been proposed to advance drugtarget interaction (DTI) prediction, and have shown state-of-the-art performance on several standard benchmarks. However, a remaining challenge for all DTI prediction models (including PLM-based ones) is distinguishing true drugs from highly-similar decoys. Leveraging techniques from self-supervised contrastive learning, we introduce a second-generation PLM-based DTI model trained on triplets of proteins, drugs, and decoys (small drug-like molecules that do not bind to the protein). We show that our approach, CON-Plex, improves specificity while maintaining high prediction accuracy and generalizability to new drug classes. CON-Plex maps proteins and drugs to a shared latent space which can be interpreted to identify mutually-compatible classes of proteins and drugs. Data and code are available at https://zenodo.org/record/7127229.

bioinformatics↗

bioRxiv2022

Selective Control of Parasitic Nematodes Using Bioactivated Nematicides

Parasitic nematodes are a major threat to global food security, particularly as the world amasses 10 billion people amidst limited arable land. Most traditional nematicides have been banned due to poor nematode-selectivity, leaving farmers with inadequate controls. Here, we use the model nematode Caenorhabditis elegans to identify a family of selective imidazothiazole nematicides, called selectivins, that undergo cytochrome p450-dependent bioactivation exclusively in nematodes. At low parts-per-million concentrations, selectivins perform comparably well with commercial nematicides to control root infection by Meloidogyne incognita - the worlds most destructive plant-parasitic nematode. Tests against a wide range of phylogenetically diverse non-target systems demonstrate that selectivins are more nematode-selective than nearly all marketed nematicides. Thus, selectivins are first-in-class bioactivated nematode controls that provide efficacy as well as much-needed nematode selectivity.

pharmacology and toxicology↗

bioRxiv2021

Transfer of Knowledge from Model Organisms to Evolutionarily Distant Non-Model Organisms: The Coral Pocillopora damicornis Membrane Signaling Receptome

With the ease of gene sequencing and the technology available to study and manipulate non-model organisms, the need to translate our understanding of model organisms to non-model organisms has become an urgent problem. For example, mining of large coral and their symbiont sequence data is a challenge, but also provides an opportunity for understanding functionality and evolution of these and other non-model organisms. Much more information than for any other eukaryotic species is available for humans, especially related to signal transduction and diseases. However, the coral cnidarian host and human have diverged over 700 million years ago and homologies between proteins are therefore often in the gray zone or undetectable with traditional BLAST searches. We introduce a two-stage approach to identifying putative coral homologues of human proteins. First, through remote homology detection using Hidden Markov Models, we identify candidate human homologues in the cnidarian genome. However, for many proteins, the human genome alone contains multiple family members with similar or even more divergence in sequence. In the second stage, therefore, we filter the remote homology results based on the functional and structural plausibility of each coral candidate, shortlisting the coral proteins likely to be true human homologues. We demonstrate our approach with a pipeline for mapping membrane receptors in humans to membrane receptors in corals, with specific focus on the stony coral, P. damicornis. More than 1000 human membrane receptors mapped to 335 coral receptors, including 151 G protein coupled receptors (GPCRs). To validate specific sub-families, we chose opsin proteins, representative GPCRs that confer light sensitivity, and Toll-like receptors, representative non-GPCRs, which function in the immune response, and their ability to communicate with microorganisms. Through detailed structure-function analysis of their ligand-binding pockets and downstream signaling cascades, we selected those candidate remote homologues likely to carry out related functions in the corals. This pipeline may prove generally useful for other non-model organisms, such as to support the growing field of synthetic biology.

bioinformatics↗

bioRxiv2021

A functionally divergent intrinsically disordered region underlying the conservation of stochastic signaling

Stochastic signaling dynamics expand living cells information processing capabilities. An increasing number of studies report that regulators encode information in their pulsatile dynamics. The evolutionary mechanisms that lead to complex signaling dynamics remain uncharacterized, perhaps because key interactions of signaling proteins are encoded in intrinsically disordered regions (IDRs), whose evolution is difficult to analyze. Here we focused on the stochastic pulsing dynamics of Crz1, a transcription factor in fungi downstream of the widely conserved calcium signaling pathway. We find that Crz1 IDRs from anciently diverged fungi can all respond transiently to calcium stress; however, only Crz1 IDRs from the Saccharomyces clade support pulsatility, encode extra information, and rescue fitness, while the Crz1 IDRs from distantly related fungi do none of the three. On the other hand, we find that Crz1 pulsing is conserved in the distantly related fungi, consistent with the evolutionary model of stabilizing selection. Further, we show that a calcineurin docking site in a specific part of the IDRs appears to be sufficient for pulsing and show evidence for a beneficial increase in the relative calcineurin affinity of this docking site. We propose that evolutionary flexibility of functionally divergent IDRs underlies the conservation of stochastic signaling by stabilizing selection.

evolutionary biology↗

bioRxiv2021

Rieske head domain dynamics and indazole-derivative inhibition of Candida albicans complex III

During cellular respiration, electron transfer between the integral membrane protein complexes of the electron transport chain is coupled to proton translocation across the inner mitochondrial membrane, which in turn powers synthesis of ATP and transmembrane transport processes. The homodimeric electron transport chain Complex III (CIII2) oxidizes ubiquinol (UQH2) to ubiquinone (UQ), transferring electrons to cytochrome c, and translocating protons through a mechanism known as the Q cycle. The Q cycle involves UQH2 oxidation and UQ reduction at two different sites within each CIII monomer, as well as movement of the head domain of the Rieske subunit. We used cryoEM to determine the structure of CIII2 from Candida albicans, revealing density for endogenous UQ in the structure and allowing us to directly visualize the continuum of conformations of the Rieske head domain. Analysis of these conformations does not indicate cooperativity in the position of the Rieske head domains or binding of ligands in the two CIIIs of the CIII2 dimer. CryoEM with the indazole derivative Inz-5, which inhibits fungal CIII2 and is fungicidal when administered with fungistatic azole drugs, showed that inhibition by Inz-5 alters the equilibrium of the Rieske head domain positions.

biochemistry↗

bioRxiv2021

Sequence-based prediction of protein-protein interactions: a structure-aware interpretable deep learning model

Protein-protein interaction (PPI) networks have proven to be a valuable tool in systems biology to facilitate the discovery and understanding of protein function. Unfortunately, experimental PPI data remains sparse in most model organisms and even more so in other species. Existing methods for computational prediction of PPIs seek to address this limitation, and while they perform well when sufficient within-species training data is available, they generalize poorly to new species or often require specific types and sizes of training data that may not be available in the species of interest. We therefore present D-SCRIPT, a deep learning method for predicting a physical interaction between two proteins given just their sequences. Compared to existing methods, D-SCRIPT generalizes better to new species and is robust to limitations in training data size. Our approach encodes the intuition that for two proteins to physically interact, a subset of amino acids from each protein should be in contact with the other. The intermediate stages of D-SCRIPT directly implement this intuition; the penultimate stage in D-SCRIPT is a rough estimate of the inter-protein contact map of the protein dimer. This structurally-motivated design enables interpretability of our model and, since structure is more conserved evolutionarily than sequence, improves generalizability across species. We show that a D-SCRIPT model trained on 38,345 human PPIs enables significantly improved functional characterization of fly proteins compared to the state-of-the-art approach. Evaluating the same D-SCRIPT model on protein complexes with known 3-D structure, we find that the inter-protein contact map output by D-SCRIPT has significant overlap with the ground truth. Our work suggests that recent advances in deep learning language modeling of protein structure can be leveraged for protein interaction prediction from sequence. D-SCRIPT is available at http://dscript.csail.mit.edu.

bioinformatics↗

bioRxiv2020

Cell shape, and not 2D migration, predicts ECM-driven 3D cell invasion in breast cancer

Metastasis, the leading cause of death in cancer patients, requires the invasion of tumor cells through the stroma in response to migratory cues, such as those provided by the extracellular matrix (ECM). Recent advances in proteomics have led to the identification of hundreds of ECM proteins which are more abundant in tumors relative to healthy tissue. Our goal was to develop a pipeline to easily predict which of these ECM proteins is more likely to have an effect on cancer invasion and metastasis. We evaluated the effect of 4 ECM proteins upregulated in breast tumor tissue in multiple human breast cancer cell lines in 3 assays. We found there was no linear relationship between the 11 cell shape parameters we quantified when cells adhere to ECM proteins and 2D cell migration speed, persistence or 3D invasion. We then used classifiers and partial-least squares regression analysis to identify which metrics best predicted ECM-driven 2D migration and 3D invasion responses. ECM-driven 2D cell migration speed or persistence did not correlate with or predict 3D invasion in response to that same cue. However, cell adhesion, and in particular cell elongation and irregularity accurately predicted the magnitude of ECM-driven 2D migration and 3D invasion in all cell lines. Testing predictions revealed that our models are good at predicting the effect of novel ECM proteins within a given cell line, but that ECM responses are cell-line specific. Overall, our studies identify the cell morphological features that determine 3D invasion responses to individual ECM proteins. This platform will help provide insight into the functional role of ECM proteins abundant tumor tissue and help prioritize strategies for targeting tumor-ECM interactions to treat metastasis. FundingThis work was supported by the National Institutes of Health [R00-CA207866-04 to M.J.O.]; Tufts University [Start-up funds from the School of Engineering to M.J.O.] and funds from NSF REU to A.W. Conflict-of-interest: None. Insight BoxMetastasis, the dissemination of tumor cells, is driven by the interaction of invading tumor cells with their local environment, in particular with the ECM, which provides structure and support to our tissues. This study presents an integrated approach to predict the effect of individual ECM proteins on 3D invasion and metastasis based on simple adhesion assays which quantify cell shape. Machine learning classification and partial-least squares regression models reveal that ECM-driven 2D cell migration metrics are not predictive of 3D invasion, and that cell shape of cells adhered to ECM can predict that proteins effect on 3D invasion. These data provide a pipeline for predicting the effect of ECM proteins on breast cancer cell invasion and metastasis.

bioengineering↗