Vineeth Chandran Suja

The subcutaneous (SC) absorption rate constant (ka) dictates critical pharmacokinetic and dosing parameters of injectable peptide therapeutics, yet currently, it cannot be predicted prior to clinical testing, forcing empirical decisions at the discovery and formulation stages. We address this important gap by constructing the first end-to-end machine learning framework that predicts SC ka, both point predictions and prediction intervals, purely from the amino acid sequence and conjugate chemistry. For developing the model, we first curated a comprehensive database of 41 human clinical ka values (0.0077−7.61 h−1), covering unmodified, fatty-acid-acylated, and protein-conjugated peptides. These data were subsequently encoded into a combination of protein language model (ESM-2) embeddings, chemical language model (ChemBERTa) embeddings, and 30 physics-informed molecular descriptors designed to capture the physical variables governing SC transport. Seven machine learning (ML) architectures and ensembles thereof were trained, with the best model (NGBoost) achieving R2 = 0.850 under leave-one-out cross-validation, a markedly high accuracy given the large variance in the clinically reported ka values. Notably, models trained on the physics-informed molecular descriptors or combinations thereof substantially outperformed models trained purely on learned embeddings (ESM-2, ChemBERTa)a direct consequence of the small scale of our training dataset. SHAP interpretability analysis indicates that predictions are consistent with established SC absorption physics, with properties including molecular weight, net charge, hydrophobicity, and acyl chain molecular characteristics dictating model predictions. Leveraging Jackknife+, the developed framework also reports ka prediction uncertainties (prediction intervals). Overall, this framework enables high-throughput sequence-level candidate ranking before in vivo data become available, supporting the rational early-stage development of peptide therapeutics.

Subcutaneous (SC) delivery of ultra‐high concentration antibody formulations (uHCAFs, > 150 mg/mL) is limited by excessive viscosity and poor bioavailability. Here, we present an ionic liquid made with choline and tryptophan (CHAT) as a multifunctional excipient that enables SC injection of antibody formulations at a concentration > 200 mg/mL by simultaneously reducing viscosity, enhancing tissue permeation, and stabilizing antibodies. Notably, CHAT‐formulated IgG exhibited viscosities below the injectability threshold (∼20 cP). In murine studies, SC delivery of CHAT‐formulated IgG achieved significantly greater systemic exposure than saline control, with up to a 2‐fold increase in area under the curve (AUC). Formulation of clinically relevant anti‐TNFα monoclonal antibody infliximab at >200 mg/mL with CHAT achieved near‐complete systemic exposure after SC administration, yielding an absolute bioavailability of ∼99% compared to ∼62% with saline. Mechanistically, CHAT disrupted collagen in the extracellular matrix, improving SC tissue penetration and accelerating antibody uptake (∼4× faster clearance from the injection site), and preserved antigen‐binding capacity after serum exposure (100% retention vs. ∼50% with saline). CHAT exhibited excellent biocompatibility with no histopathological or biochemical indications of toxicity in treated animals. Together, these results position CHAT as a single‐component platform for high‐dose, low‐volume SC delivery of monoclonal antibodies.

The clinical impact of gene therapies is constrained by poor delivery to target tissues beyond the liver after intravenous administration. Current molecular targeting strategies, such as capsid engineering or gene-carrier surface modification, have achieved only limited success due to their inability to overcome the hierarchical barriers from injection to deep tissue transduction. Here, we introduce a Multiscale Approach using RBC-mediated hitchhiking and Vascular Endothelium Leakage (MARVEL), which integrates red blood cell hitchhiking with VEGF-induced vascular permeabilization to enhance accumulation and penetration of cargoes. Using adeno-associated viruses (AAVs) as a model, MARVEL markedly increases AAV localization in the lungs, improves endothelial transcytosis, and enables gene expression in deeper tissue layers while maintaining a favorable safety profile. We further demonstrate that MARVEL can be adopted into an in situ hitchhiking approach, bypassing the need for ex vivo formulation. MARVEL provides a scalable strategy to address long-standing delivery challenges in gene therapy.

Thin film interferometry is a powerful technique for non-invasively measuring liquid film thickness with applications in ophthalmology, but its clinical translation is hindered by the challenges in reconstructing thickness profiles from interference patterns - an ill-posed inverse problem complicated by phase periodicity, imaging noise and ambient artifacts. Traditional reconstruction methods are either computationally intensive, sensitive to noise, or require manual expert analysis, which is impractical for real-time diagnostics. To address this challenge, here we present a vision transformer-based approach for real-time inference of thin liquid film thickness profiles directly from isolated interferograms. Trained on a hybrid dataset combining physiologically-relevant synthetic and experimental tear film data, our model leverages long-range spatial correlations to resolve phase ambiguities and reconstruct temporally coherent thickness profiles in a single forward pass from dynamic interferograms acquired in vivo and ex vivo. The network demonstrates state-of-the-art performance on noisy, rapidly-evolving films with motion artifacts, overcoming limitations of conventional phase-unwrapping and iterative fitting methods. Our data-driven approach enables automated, consistent thickness reconstruction at real-time speeds on consumer hardware, opening new possibilities for continuous monitoring of pre-lens ocular tear films and non-invasive diagnosis of conditions such as the dry eye disease.

Molecular rotors are molecules that form twisted conformations upon photoexcitation, with their fluorescence relaxation time serving as a measure of viscosity. They have been used to estimate the viscosity of biological and other membranes, but yield higher values than more common methods. We show that the rotor's relaxation time is influenced by a combination of membrane viscosity and interleaflet friction, and rationalize the existing discrepancy among methods.

Goal: To develop a compact, real-time microfluidic spectroscopy system capable of simultaneously measuring the concentrations of multiple solutes flowing together through a single fluid pathway with high temporal resolution. Methods: The measurement system integrates a Z-flow cell and dual-wavelength LED light sources with a compact spectrophotometer. The experimental setup consisted of two clinical infusion pumps delivering distinct marker dyes through a common fluid pathway composed of a clinical manifold and a single lumen of a clinical intravascular catheter, while a third pump delivered an inert carrier fluid. Concentration measurements of the mixed dyes were performed at high-frequency sampling intervals, with dynamic pump rate adjustments to evaluate the system's ability to detect real-time changes in solute concentration. A MATLAB-based control application enabled automated data acquisition, processing, and system control to enhance experimental efficiency. Results: The system accurately measured solute concentrations, capturing temporal variations with high precision. It demonstrated high reproducibility with a standard error of the mean no larger than $0.19 \,\mu \mathrm{g}\mathrm{/}\mathrm{m}\mathrm{L}$ for Erioglaucine and $1.32 \,\mu \mathrm{g}\mathrm{/}\mathrm{m}\mathrm{L}$ for Tartrazine at steady state, and high accuracy with a maximum deviation of $0.21 \,\mu \mathrm{g}\mathrm{/}\mathrm{m}\mathrm{L}$ for Erioglaucine and $0.5 \,\mu \mathrm{g}\mathrm{/}\mathrm{m}\mathrm{L}$ for Tartrazine from the expected steady-state concentrations. Conclusions: This system enables continuous, real-time monitoring of multiple solutes in dynamic flow conditions, offering a portable solution with high sensitivity to temporal concentration changes—advancing beyond traditional static fluid measurement methods.

Managing delivery of complex multidrug infusions in anesthesia and critical care presents a significant clinical challenge. Current practices relying on manual control of infusion pumps often result in unpredictable drug delivery profiles and dosing errors—key issues highlighted by the United States Food and Drug Administration (FDA). To address these issues, we introduce the SMART (synchronized‐pump management algorithms for reliable therapies) framework, a novel approach that leverages low Reynolds number drug transport physics and machine learning to accurately manage multidrug infusions in real‐time. SMART is activated based on the Shafer number (), a novel non‐dimensional number that quantifies the relative magnitude of a drug's therapeutic action timescale to its transport timescale within infusion manifolds. SMART is useful when , where drug transport becomes the rate limiting step in achieving the desired therapeutic effects. When activated, SMART monitors multidrug concentrations within infusion manifolds and leverages this information to perform end‐to‐end management of drug delivery using an ensemble of deterministic and deep reinforcement learning (RL) decision networks. Notably, SMART RL networks employ differentially sampled split buffer architecture that accelerates learning and improves performance by seamlessly combining deterministic predictions with RL experience during training. SMART deployed in standalone infusion pumps under simulated clinical conditions outperformed state‐of‐the‐art manual control protocols. This framework has the potential to revolutionize critical care by enhancing accuracy of medication delivery and reducing cognitive workloads. Beyond critical care, the ability to accurately manage multi‐liquid delivery via complex manifolds will have important bearings for manufacturing and process control.

Critically ill or anesthetized patients commonly receive pump-driven intravenous infusions of potent, fast-acting, short half-life medications for managing hemodynamics. Stepwise dosing, e.g. over 3–5 min, adjusts physiologic responses. Flow rates range from < 0.1 to > 30 ml/h, depending on pump type (large volume, syringe) and drug concentration. Most drugs are formulated in aqueous solutions. Hydrophobic drugs are formulated as lipid emulsions. Do the physical and chemical properties of emulsions impact delivery compared to aqueous solutions? Does stepwise dose titration by the pump correlate with predicted plasma concentrations? Precise, gravimetric, flow rate measurement compared delivery of a 20% lipid emulsion (LE) and 0.9% saline (NS) using different pump types and flow rates. We measured stepwise delivery and then computed predicted plasma concentrations following stepwise dose titration. We measured the pharmacokinetic coefficient of short-term variation, (PK-CV), to assess pump performance. LE and NS had similar mean flow rates in stepwise rate increments and decrements between 0.5 and 32 ml/h and continuous flows 0.5 and 5 ml/h. Pharmacokinetic computation predictions suggest delayed achievement of intended plasma levels following dose titrations. Syringe pumps exhibited smaller variations in PK-CV than large volume pumps. Pump-driven deliveries of lipid emulsion and aqueous solution behave similarly. At low flow rates we observed large flow rate variability differences between pump types showing they may not be interchangeable. PK-CV analysis provides a quantitative tool to assess infusion pump performance. Drug plasma concentrations may lag behind intent of pump dose titration.

Tumour-associated neutrophils can exert antitumour effects but can also assume a pro-tumoural phenotype in the immunosuppressive tumour microenvironment. Here we show that neutrophils can be polarized towards the antitumour phenotype by discoidal polymer micrometric ‘patches’ that adhere to the neutrophils’ surfaces without being internalized. Intravenously administered micropatch-loaded neutrophils accumulated in the spleen and in tumour-draining lymph nodes, and activated splenic natural killer cells and T cells, increasing the accumulation of dendritic cells and natural killer cells. In mice bearing subcutaneous B16F10 tumours or orthotopic 4T1 tumours, intravenous injection of the micropatch-loaded neutrophils led to robust systemic immune responses, a reduction in tumour burden and improvements in survival rates. Micropatch-activated neutrophils combined with the checkpoint inhibitor anti-cytotoxic T-lymphocyte-associated protein 4 resulted in strong inhibition of the growth of B16F10 tumours, and in complete tumour regression in one-third of the treated mice. Micropatch-loaded neutrophils could provide a potent, scalable and drug-free approach for neutrophil-based cancer immunotherapy.