Biology subjects

Avchaciov, K.

Publications and source records attributed to Avchaciov, K..

7 recordsLinked to original sources

bioRxiv2026

HARVEST: Unlocking the Dark Bioactivity Data of Pharmaceutical Patents via Agentic AI

Pharmaceutical patents contain vast Structure-Activity Relationship tables documenting protein- ligand binding data. While technically public, this information remains computationally inaccessible and effectively dark, trapped in bulky documents that no existing database has systematically captured. We present HARVEST, a multi-agent large language model pipeline that autonomously extracts structured bioactivity records from USPTO patent archives at $0.11 per document. Applied to 164,877 patents, HARVEST produced 3.15 million activity records, recovering 326,342 unique scaffolds and 967 protein targets absent from BindingDB. This pipeline completed in under a week a task that would otherwise require over 55 years of continuous expert labor. Automated extraction achieves 80% agreement with human curated corpus of US patents from BindingDB, a conservative lower bound given identified errors within the reference data. We further introduce H-Bench, a structurally guaranteed held-out benchmark built from this recovered data. Evaluation of the leading open-source model Boltz-2 on H-Bench reveals a two-dimensional generalization gap: performance degrades both on novel scaffolds and on uncharacterized protein targets, exposing fundamental limitations of models trained on existing public repositories.

bioinformatics↗

bioRxiv2026

Thermodynamic scaling of canine aging and reversible clock deceleration by a reverse transcriptase inhibitor

Aging was tracked in a cohort of 99 "retired" sled dogs over four years to characterize the latent dynamics of physiological decline. Animals were randomized to receive either placebo or the reverse transcriptase inhibitor lamivudine for [~]30 months. We employed a variational autoregressive model to integrate longitudinal blood parameters and DNA methylation (DNAm) profiles. The model defines Biological Age (BA) as a signature of irreversible damage with Poissonian statistics, a feature conserved across mammalian scales. Lamivudine modulated age-independent latent variables and temporarily decelerated the DNAm clock in females, but these effects were reversible upon treatment discontinuation and did not alter the long-term BA trajectory. Critically, we show that physiological fluctuations are governed by a single systemic factor - an effective or phenotypic temperature representing an emergent (macroscopic) property. We show that while the rate of damage accumulation (the BA slope) is independent of this temperature, actuarial aging parameters (initial mortality and the Gompertz exponent) are strongly temperature dependent. This supports a model where mortality arises from effective activation across a protective free energy barrier that erodes with age. These findings identify phenotypic temperature as an important control variable governing the kinetics of organism-level failure, offering a compelling target for interventions aimed at extending healthspan by "squaring" the survival curve.

systems biology↗

bioRxiv2025

ProtoBind-Diff: A Structure-Free Diffusion Language Model for Protein Sequence-Conditioned Ligand Design

Designing small molecules that selectively bind to protein targets remains a central challenge in drug discovery. While recent generative models leverage 3D structural data to guide ligand generation, their applicability is limited by the sparsity and bias of structural resources. Here, we introduce ProtoBind-Diff, a structure-free masked diffusion model that conditions molecular generation directly on protein sequences via pre-trained language model embeddings. Trained on over one million active protein-ligand pairs from BindingDB, ProtoBind-Diff generates chemically valid, novel, and target-specific ligands without requiring structural supervision. In extensive benchmarking against structure-based models, ProtoBind-Diff performs competitively in docking and Boltz-1 evaluations and generalizes well to challenging targets, including those with limited training data. Despite never observing 3D information during training, its attention maps align with predicted binding residues, suggesting the model learns spatially meaningful interaction priors from sequence alone. This sequence-conditioned generation framework may unlock ligand discovery across the full proteome, including orphan, flexible, or rapidly emerging targets for which structural data are unavailable or unreliable.

biophysics↗

bioRxiv2024

Multiple Targets, One Goal: Compounding life-extending effects through Polypharmacology

Analysis of lifespan-extending compounds suggested the most effective geroprotectors target multiple biogenic amine receptors. To test this hypothesis, we used graph neural networks to predict such polypharmacological compounds and evaluated them in C. elegans. Over 70% of the selected compounds extended lifespan, with effect sizes in the top 5% compared to the DrugAge database. This reveals that rationally designing polypharmacological compounds enables the design of geroprotectors with exceptional efficacy. Key takeawaysO_LIThe most effective known geroprotectors act by polypharmacological mechanisms. C_LIO_LIGraph neural networks predicted polypharmacological geroprotectors with a hit rate of 70%. C_LIO_LIThe predicted polypharmacological geroprotectors are exceptionally effective. C_LIO_LIThe predicted polypharmacological mechanism was experimentally confirmed. C_LIO_LIRationally designing polypharmacological compounds results in geroprotectors with exceptional efficacy. C_LI

pharmacology and toxicology↗

bioRxiv2020

Identification of a blood test-based biomarker of aging through deep learning of aging trajectories in large phenotypic datasets of mice

We proposed and characterized a novel biomarker of aging and frailty in mice trained from the large set of the most conventional, easily measured blood parameters such as Complete Blood Counts (CBC) from the open-access Mouse Phenome Database (MPD). Instead of postulating the existence of an aging clock associated with any particular subsystem of an aging organism, we assumed that aging arises cooperatively from positive feedback loops spanning across physiological compartments and leading to an organism-level instability of the underlying regulatory network. To analyze the data, we employed a deep artificial neural network including auto-encoder (AE) and auto-regression (AR) components. The AE was used for dimensionality reduction and denoising the data. The AR was used to describe the dynamics of an individual mouses health state by means of stochastic evolution of a single organism state variable, the "dynamic frailty index" (dFI), that is the linear combination of the latent AE features and has the meaning of the total number of regulatory abnormalities developed up to the point of the measurement or, more formally, the order parameter associated with the instability. We used neither the chronological age nor the remaining lifespan of the animals while training the model. Nevertheless, dFI fully described aging on the organism level, that is it increased exponentially with age and predicted remaining lifespan. Notably, dFI correlated strongly with multiple hallmarks of aging such as physiological frailty index, indications of physical decline, molecular markers of inflammation and accumulation of senescent cells. The dynamic nature of dFI was demonstrated in mice subjected to aging acceleration by placement on a high-fat diet and aging deceleration by treatment with rapamycin.

bioinformatics↗

bioRxiv2019

Longitudinal analysis of blood markers reveals progressive loss of resilience and predicts ultimate limit of human lifespan

We investigated the dynamic properties of the organism state fluctuations along individual aging trajectories in a large longitudinal database of CBC measurements from a consumer diagnostics laboratory. To simplify the analysis, we used a log-linear mortality estimate from the CBC variables as a single quantitative measure of aging process, henceforth referred to as dynamic organism state index (DOSI). We observed, that the age-dependent population DOSI distribution broadening could be explained by a progressive loss of physiological resilience measured by the DOSI auto-correlation time. Extrapolation of this trend suggested that DOSI recovery time and variance would simultaneously diverge at a critical point of 120 - 150 years of age corresponding to a complete loss of resilience. The observation was immediately confirmed by the independent analysis of correlation properties of intraday physical activity levels fluctuations collected by wearable devices. We conclude that the criticality resulting in the end of life is an intrinsic biological property of an organism that is independent of stress factors and signifies a fundamental or absolute limit of human lifespan.

systems biology↗

bioRxiv2017

Quantitative Characterization of Biological Age and Frailty Based on Locomotor Activity Records

We performed a systematic evaluation of the relationships between locomotor activity and signatures of frailty, morbidity, and mortality risks using physical activity records from the 2003 - 2006 National Health and Nutrition Examination Survey (NHANES) and UK BioBank (UKB). We proposed a statistical description of the locomotor activity tracks and transformed the provided time series into vectors representing physiological states for each participant. The Principal Components Analysis of the transformed data revealed a winding trajectory with distinct segments corresponding to subsequent human development stages. The extended linear phase starts from 35 40 years old and is associated with the exponential increase of mortality risks according to the Gompertz mortality law. We characterized the distance traveled along the aging trajectory as a natural measure of biological age and demonstrated its significant association with frailty and hazardous lifestyles, along with the remaining lifespan and healthspan of an individual. The biological age explained most of the variance of the log-hazard ratio that was obtained by fitting directly to mortality and the incidence of chronic diseases. Our findings highlight the intimate relationship between the supervised and unsupervised signatures of the biological age and frailty, a consequence of the low intrinsic dimensionality of the aging dynamics.

systems biology↗