Praedicare: The Best Drug Developer in The Game

The Silicon Review

Praedicare's revolutionary SoS approach accelerates drug development. With first-of-its kind integrated multiple wet lab systems, system of mathematical models, suite of AI tools, and clinical trial databases to give outcomes that are emergent properties that reduce timelines 2-3 times, >90% of costs, and maximize phase-by-phase success rates from preclinical phases to NDA/BLA. The team is dedicated to transforming healthcare through the innovative solutions. By reducing drug development costs by up to 20 times, accelerating the development cycle by 2-3x, and significantly improving patient safety, Praedicare is revolutionizing the healthcare landscape. Explore the cutting-edge technologies and discover how the team is reshaping the future of healthcare, one advancement at a time. The commitment to continuous, groundbreaking innovation keeps driving the team to develop precise quantitative and physical tools and platforms.

These advancements push the frontiers of drug development science, enhancing patient outcomes. Embracing a System of Systems approach, the team integrates data, non-animal wet lab tools, virtual lab twins, mathematics, and artificial intelligence to achieve superior predictions in drug development outcomes, and shorten time from discovery to the bedside three fold. This dedication benefits biopharma companies and the global population of patients. The team prioritizes preserving human life and well-being by reducing the need for human volunteers at risk of injury or harm during clinical trials. Striving for a better future, the team is committed to significantly lowering the cost of drug development by up to 90% and reducing drug prices. The goal is to make essential treatments more affordable and accessible, positively impacting mankind.

Best services Praedicare provides its clients

Math Modeling and AI systems: Praedicare uses advanced mechanistic translational disease mathematical models, Quantitative systems pharmacology, distance-based dynamical systems, category theory, quantitative outputs from multiple customized wet lab systems, AI/ML, and pharmacometrics for an integrated output to make quantitative clinical predictions using data generated early during preclinical stages.

Morphism mapping and category theory from preclinical models to patients to identify response trajectories & therapy duration
Development of biomarkers for clinical response outcomes from preclinical models using Morphism mapping
Pediatric maturation pharmacology using integrated approaches with sui generis multi-scale systems modeling from the level of cellular chemical reactions such as Michaelis-Menten reaction kinetics constructed de novo based on serum/plasma PKs, the child’s genome, to whole body physiological and age/sex parameters to model drug PKs
Mathematical mapping of drug concentrations across organs, lesions and 3D space using dynamical sink models
Modeling to map hundreds of physiological pathways and complex adaptive systems using multiple ‘omics across organs, 3D disease lesions and histopathological space using dynamical sink models and simulations for design of vaccines and therapeutics
Use of machine learning algorithms to identify PK covariates & use of fractals obese patients
Use of machine learning algorithms and clinical trial data to identify clinical MIC/resistance breakpoints
Use of AI to deconvolute the effect & concentration thresholds associated with optimal efficacy of component drugs in combinations
Use of AI and clinical trial data to identify optimal doses for efficacy & concentration thresholds associated with toxicity

In Silico and Real Clinical Trials: Clinical trials design based on quantitative translation methods, rate of response biomarkers/endpoints design, monitoring response parameters based on quantitative translation methods. Adaptive clinical trials designs driven by quantitative forecasting approach based on rate of response. Pharmacometrics combined with machine learning for phase I and II clinical data to identify optimal exposures, drivers of efficacy, and optimal doses for drugs as monotherapy and in combination. Machine learning for phase I and II clinical data to identify biomarkers and subgroups of patients likely to respond to therapy in phase III studies, identify early biomarkers of response using preclinical and clinical data, to reduce sample size, and increase confidence intervals, and innovative stopping and proceeding rules in clinical trials. Function as lab on record, with appropriate SOPs, for drug concentration assays during clinical trials. Function as lab on record for phase I-III clinical trials for microbiology assays, whole genome and next generation sequencing, and the development and implementation of biomarkers. Praedicare physician medical monitor teams with expertise in clinical trials and subject/disease content for clinical trials and research monitoring.

Meet the leader behind the success of Praedicare

Tawanda Gumbo, Chief Executive Officer

Tawanda Gumbo, MD, is a physician scientist, rising to the rank of Professor of Medicine. Medical School was at the University of Zimbabwe, Residency in Internal Medicine at Case Western Reserve University, and Fellowship in Infectious Diseases at the Cleveland Clinic, in Cleveland, Ohio. Dr. Gumbo developed several preclinical and clinical laboratory systems for fungal, parasitic, bacterial and viral infections, the human immune system, and cancer. He started using AI algorithms with publications as far back as 2006, with intensification of such work in subsequent decades. He has also developed several mathematical models for translation from the laboratory to patients in the area of therapeutics and quantitative translational pharmacology, and for characterizing disease progression and the immune system in patients based on next generation sequencing and other ‘omics. He has received research funding for decades from the US NIH, and other private-public funders. Dr. Gumbo is the recipient of numerous awards. His research work has been used to identify optimal doses of the three currently licensed antifungal drugs called echinocandins, anti-TB compounds by the WHO Global TB Program and by national TB programs in numerous countries, the design of new anti-TB drug regimens for children and adults, treatment of non-tuberculous mycobacteria, and together with his team recently identified and characterized safe inhibitors of the fundamental physiologic pathway, sonic hedgehog signaling, and the role of inhibitory immune checkpoints in TB.