Biology subjects

Sanchez-Lengeling, B.

Publications and source records attributed to Sanchez-Lengeling, B..

10 recordsLinked to original sources

bioRxiv2026

Do protein representations encode variant function? Diagnosing residue-level protein attributions via embedding-space gradients

A common workflow in protein engineering involves building fitness predictors on protein language models (pLMs) to estimate a variant's fitness and interpret which residues drive it. Attribution methods such as integrated gradients address this second goal by assigning residues contributions to the variant's predicted fitness. However, without ground truth for residue importance, it is unclear whether these attributions reflect what the predictor learned about function. Here, we introduce IGLOO, a framework that scores residue-level attributions against synthetic fitness landscapes with known per-residue importance. Across experimental axes, high predictive accuracy did not guarantee faithful attributions. We identify model interventions that more than double attribution skill scores and raise TOPSIS by 29%, with similar patterns holding in real -amylase and {beta}-lactamase datasets. IGLOO provides a protocol for probing what pLMs learn and a guide for choosing defaults when using residue attributions to pick sequence edits and build more trustworthy protein models.

bioengineering↗

bioRxiv2026

kinGEMs: A Robust and Scalable Framework forResource-Constraint Models through StochasticTuning of Deep Learning-Predicted KineticParameters

The construction of accurate enzyme-constrained genome-scale models (ecGEMs) remains a critical challenge in systems biology, limited by sparse kinetic data and the need for biologically meaningful representations. This work presents an integrated framework combining CPI-Pred, a deep learning model to predict kinetic parameters (kcat) from sequence and compound embeddings, with kinGEMs, a pipeline to incorporate these uncertainty-aware parameters into ecGEMs for metabolic optimization. By leveraging representations at multiple scales, the approach captures sequence, structure, and kinetic data to enhance model generalizability and accuracy. Rigorous benchmarking demonstrates the frameworks capability to predict growth rates and fluxes that are consistent with experimental observations and measured proteome fractions, reduce median flux variability by several folds, and yield better-constrained metabolic models by explicitly accounting for the uncertainty inherent in ML-predicted kinetic parameters. kinGEMs successfully generated ecGEMs for 93 models spanning a phylogenetically diverse set of organisms including Gram-negative and Grampositive bacteria, mycobacteria, parasitic protists, fungi, and mammalian cell lines. These innovations breakdown the barrier to application of ecGEMs to non-model organisms and open new avenues for metabolic engineering and synthetic biology in more industrially relevant hosts.

bioengineering↗

bioRxiv2026

TubercuProbe: A Cross-Attention Graph-Sequence Model for Cross-Species Chemoproteomic Discovery in Mycobacterium tuberculosis

Activity-based protein profiling (ABPP) and residue-specific chemoproteomics have transformed human chemical biology, yet applying these approaches to pathogens remains limited by biosafety constraints, low throughput, and the absence of reusable atlases. We present TubercuProbe, a cross-species machine learning framework that leverages large-scale human chemoproteomic knowledge to prioritize compound-protein interactions in Mycobacterium tuberculosis (Mtb) and other pathogens. Our model integrates a graph isomorphism network (GINE) for ligand encoding with frozen ESM-C (600M) protein embeddings via bidirectional cross-attention. Trained on >2M ChEMBL compound-protein pairs (predominantly human targets), TubercuProbe achieves R2=0.77 (MSE=0.45) for continuous affinity prediction and transfers effectively to binary cysteine reactivity prediction (CysDB AUPRC=0.63). Ablation studies reveal that pretrained features are highly transferable across freezing strategies ({Delta}AUPRC<0.03), suggesting the model captures fundamental protein-molecule interaction patterns. As a case study, we prioritize cysteine-reactive electrophiles and molecular glues for three Mtb virulence proteins (PtpB, SapM, Rv3671c), providing candidate probes for prospective ABPP validation. Orthogonal comparison with Boltz-2 structure predictions shows moderate correlation (Pearson r{approx}0.69). TubercuProbe provides a lightweight, sequence-driven first-pass ranker that enables pre-experimental prioritization--reducing the time, cost, and experimental burden of chemoproteomic discovery in biosafety-restricted systems. We discuss extensions toward multitask learning that jointly predicts non-covalent binding and covalent reactivity, recognizing that effective covalent probes must both reach their target and react once there.

biochemistry↗

bioRxiv2025

High-Fidelity Tuning of Olfactory Mixture Distances in the Perceptual Space of Smell Through a Community Effort

A central goal in sensory science is to establish quantitative mappings between physical stimuli and perceptual responses. While such mappings are well characterized in vision and audition, they remain poorly defined in olfaction, limiting progress toward understanding the representations of smell. Predicting perceptual similarity between odor mixtures offers a promising route to formalize these relationships. To advance this effort, the DREAM (Dialogue for Reverse Engineering Assessment and Methods) Olfactory Mixtures Prediction Challenge assembled a curated, cross-study dataset describing the similarity of 507 mixture pairs and an unpublished test set of 46 mixture pairs. Teams competed to predict the perceptual similarity of mixture pairs, and then collaborated post-challenge to create an ensemble combining top-performing models that notably improves predictions over the existing state-of-the-art models. Moreover, ensemble model maintains high predictive accuracy in novel validation set. Our model provides a reproducible framework for neuroscientists, chemists, and engineers to compare odor mixtures and provides a foundation for future efforts towards better understanding the olfactory properties of mixtures.

neuroscience↗

bioRxiv2022

A deep learning and digital archaeology approach for mosquito repellent discovery

Insect-borne diseases kill >0.5 million people annually. Currently available repellents for personal or household protection are limited in their efficacy, applicability, and safety profile. Here, we describe a machine-learning-driven high-throughput method for the discovery of novel repellent molecules. To achieve this, we digitized a large, historic dataset containing [~]19,000 mosquito repellency measurements. We then trained a graph neural network (GNN) to map molecular structure and repellency. We applied this model to select 317 candidate molecules to test in parallelizable behavioral assays, quantifying repellency in multiple pest species and in follow-up trials with human volunteers. The GNN approach outperformed a chemoinformatic model and produced a hit rate that increased with training data size, suggesting that both model innovation and novel data collection were integral to predictive accuracy. We identified >10 molecules with repellency similar to or greater than the most widely used repellents. We analyzed the neural responses from the mosquito antennal (olfactory) lobe to selected repellents and found a limited correlation between these responses and our GNN representation. This approach enables computational screening of billions of possible molecules to identify empirically tractable numbers of candidate repellents, leading to accelerated progress towards solving a global health challenge.

bioengineering↗

bioRxiv2022

A Principal Odor Map Unifies Diverse Tasks in Human Olfactory Perception

Mapping molecular structure to odor perception is a key challenge in olfaction. Here, we use graph neural networks (GNN) to generate a Principal Odor Map (POM) that preserves perceptual relationships and enables odor quality prediction for novel odorants. The model is as reliable as a human in describing odor quality: on a prospective validation set of 400 novel odorants, the model-generated odor profile more closely matched the trained panel mean (n=15) than did the median panelist. Applying simple, interpretable, theoretically-rooted transformations, the POM outperformed chemoinformatic models on several other odor prediction tasks, indicating that the POM successfully encoded a generalized map of structure-odor relationships. This approach broadly enables odor prediction and paves the way toward digitizing odors. One-Sentence SummaryAn odor map achieves human-level odor description performance and generalizes to diverse odor-prediction tasks.

neuroscience↗

bioRxiv2022

Metabolic activity organizes olfactory representations

Hearing and vision sensory systems are tuned to the natural statistics of acoustic and electromagnetic energy on earth, and are evolved to be sensitive in ethologically relevant ranges. But what are the natural statistics of odors, and how do olfactory systems exploit them? Dissecting an accurate machine learning model1 for human odor perception, we find a computable representation for odor at the molecular level that can predict the odor-evoked receptor, neural, and behavioral responses of nearly all terrestrial organisms studied in olfactory neuroscience. Using this olfactory representation (Principal Odor Map, POM), we find that odorous compounds with similar POM representations are more likely to co-occur within a substance and be metabolically closely related; metabolic reaction sequences2 also follow smooth paths in POM despite large jumps in molecular structure. Just as the brains visual representations have evolved around the natural statistics of light and shapes, the natural statistics of metabolism appear to shape the brains representation of the olfactory world.

neuroscience↗

bioRxiv2018

The thermodynamic landscape of carbon redox biochemistry

Redox biochemistry plays a key role in the transduction of chemical energy in living systems. However, the compounds observed in metabolic redox reactions are a minuscule fraction of chemical space. It is not clear whether compounds that ended up being selected as metabolites display specific properties that distinguish them from non-biological compounds. Here we introduce a systematic approach for comparing the chemical space of all possible redox states of linear-chain carbon molecules to the corresponding metabolites that appear in biology. Using cheminformatics and quantum chemistry, we analyze the physicochemical and thermodynamic properties of the biological and non-biological compounds. We find that, among all compounds, aldose sugars have the highest possible number of redox connections to other molecules. Metabolites are enriched in carboxylic acid functional groups and depleted of carbonyls, and have higher solubility than non-biological compounds. Upon constructing the energy landscape for the full chemical space as a function of pH and electron donor potential, we find that over a large range of conditions metabolites tend to have lower Gibbs energies than non-biological molecules. Finally, we generate Pourbaix phase diagrams that serve as a thermodynamic atlas to indicate which compounds are local and global energy minima in redox chemical space across a set of pH values and electron donor potentials. Our work yields insight into the physicochemical principles governing redox metabolism, and suggests that thermodynamic stability in aqueous environments may have played an important role in early metabolic processes.

systems biology↗

bioRxiv2018

A mixed quantum chemistry/machine learning approach for the fast and accurate prediction of biochemical redox potentials and its large-scale application to 315,000 redox reactions

A quantitative understanding of the thermodynamics of biochemical reactions is essential for accurately modeling metabolism. The group contribution method (GCM) is one of the most widely used approaches to estimating standard Gibbs energies and redox potentials of reactions for which no experimental measurements exist. Previous work has shown that quantum chemical predictions of biochemical thermodynamics are a promising approach to overcome the limitations of GCM. However, the quantum chemistry approach is significantly more expensive. Here we use a combination of quantum chemistry and machine learning to obtain a fast and accurate method for predicting the thermodynamics of biochemical redox reactions. We focus on predicting the redox potentials of carbonyl functional group reductions to alcohols and amines, two of the most ubiquitous carbon redox transformations in biology. Our method relies on semi-empirical quantum chemistry calculations calibrated with Gaussian Process (GP) regression against available experimental data. Our approach results in higher predictive power than the GCM at a low computational cost. We design and implement a network expansion algorithm that iteratively reduces and oxidizes a set of natural seed metabolites, and demonstrate the high-throughput applicability of our method by predicting the standard potentials of more than 315,000 redox reactions involving approximately 70,000 compounds. Additionally, we developed a novel fingerprint-based framework for detecting molecular environment motifs that are enriched or depleted across different regions of the redox potential landscape. We provide open access to all source code and data generated.

biophysics↗

bioRxiv2018

Quantum chemistry reveals the thermodynamic principles of redoxbiochemistry

Thermodynamics dictates the structure and function of metabolism. Redox reactions drive cellular energy and material flow. Hence, accurately quantifying the thermodynamics of redox reactions should reveal key design principles that shape cellular metabolism. However, only a limited number of redox potentials have been measured experimentally, and mostly with inconsistent, poorly-reported experimental setups. Here, we develop a quantum chemistry approach for the calculation of redox potentials of biochemical reactions. We demonstrate that our method predicts experimentally measured potentials with unparalleled accuracy. We calculate the reduction potentials of all redox pairs that can be generated from biochemically relevant compounds and highlight fundamental thermodynamic trends that define cellular redox biochemistry. We further use the calculated potentials to address the question of why NAD/NADP are used as the primary cellular electron carriers, demonstrating how their physiological redox range specifically fits the reactions of central metabolism and minimizes the concentration of reactive carbonyls. The use of quantum chemistry tools, as demonstrated in this study, can revolutionize our understanding of key biochemical phenomena by enabling fast and accurate calculation of large datasets of thermodynamic values.

biochemistry↗