Oportunidades Públicas

Assembly and measurement of synthetic gene circuits

Construct DNAs using techniques from molecular biology and then measure their output in growing cell cultures.

Reconstruction of incomplete images

The images submuestreadas are a way to increase the speed of acquisition for the magnetic resonance imaging. In this project we will study different spaces in which they can represent the data in a manner to facilitate its reconstruction by employing algorithms of Compressed Sensing.

Quantification of remodeling in patients with tetralogy of Fallot

1 in 2000 kids are born with tetralogy of Fallot, a combination of 4 serious congenital heart defects. To overcome these problems, the patient undergoes a series of surgeries and the heart responds by remodeling, adapting its form and function. However, the way this adaptation occurs is not fully characterized. The goal of this study is to locally quantify the remodeling of the heart in response to these surgeries. We will magnetic resonance images and the finite element method. This research will enable the development of predictive models to help the planning and optimization of the current surgeries.

Magnetic Resonance Imaging Acquisition and Reconstruction

Deep learning based super resolution reconstruction for high resolution coronary magnetic resonance angiography

Coronary artery disease is currently diagnosed with X-ray or computed tomography coronary angiography (CTCA). However, both modalities expose patients to ionising radiation and iodinated contrast agents (CA). We have developed an alternative approach, coronary magnetic resonance angiography (CMRA), which is non-invasive, does not require the injection of CA and is free of radiation. Our 3D CMRA technique is approaching the resolution of CTCA but still requires a 10-minute scan. To further shorten the scan time to <1 minute and match the resolution of CTCA (0.6mm3), we propose to investigate novel deep learning based super resolution (SR) image reconstruction networks. The work will include a systematic literature review and the implementation of the most promising SR networks. We have a large clinical dataset of CMRA/CTCA data that can be used for training, testing and validation. It would be useful to know about the fundamentals of artificial intelligence.

Acquisition, reconstruction and motion correction for 3D whole-heart Magnetic Resonance Imaging

Magnetic Resonance Imaging (MRI) is an important non-invasive tool for risk assessment and treatment monitoring of cardiovascular disease. In comparison to other imaging modalities (ultrasound, x-ray and computed tomography) MRI has the advantage of combining excellent soft tissue contrast with high spatial resolution. However, a major limitation of current MRI protocols is that all imaging sequences are acquired sequentially, with different resolution, geometric orientations and breath-hold positions, resulting in long planning and scan times. Moreover, image quality degradation due to respiratory and cardiac motion are major challenges that greatly affect the accuracy and reproducibility of cardiac MRI. This research includes the development of novel whole-heart 3D MRI sequences, motion compensation techniques and deep learning methods to enable 3D, easy-to-plan, fast and efficient quantitative multi-parametric MRI of heart and vessels. The research is done together with King’s College London. Basic knowledge of MRI, signal processing and artificial intelligence would be useful.

Software development for Open Source Hardware documentation formats

This is a paid position for an open software development project to further develop the DocuBricks (https://docubricks.com/software.jsp) documentation editor and and standard format, specialised for Open Hardware instrumentation in science laboratories. The development includes developing a JS editor to work in the Eletron framework; to create a conversion tool between GitBuilding (https://gitbuilding.io/) and DocuBricks; as well as a GitHub resource development. https://forum.openhardware.science/t/software-for-making-assembly-manuals/2970/20?u=tobey

Chrono-Nutrition: A Study on Biological Rhythms and Eating Patterns

Recent research highlights the importance of chrono-nutrition, which studies how the timing of food intake affects health and performance. However, understanding these effects can be challenging due to the complexity of interactions between the internal biological clock and eating habits. With this in mind, we are looking for students interested in learning and applying mathematical modeling tools to develop a predictive system for chrono-nutrition. Participants will collect chronobiology and nutrition data to build mathematical models capable of predicting the effects of chrono-nutrition on health and performance.

Biomechanical Analysis of Figure Skating

To analyze and improve skaters' performance, biomechanics is used to study the complex movements and forces involved in jumps, spins, and steps. However, interpreting these movements can be challenging due to interferences and artifacts that appear in the collected data. To address this, we are seeking talented students interested in learning and applying biomechanical and mathematical modeling tools to develop a multifactorial analysis system. Participants will work with advanced motion capture technology, analyze EMG data, and measure differential pressure using insoles inserted into the skates.

Computational Modeling of Alveolar Micromechanics

Alveolar tissue supports gas exchange, the primary function of the respiratory system. To accomplish this, it cyclically undergoes stress and strain. This mechanical behavior is characterized by a non-linear relationship between stress and strain, as well as hysteresis caused by alveolar surfactant. This project seeks to develop a computational model that incorporates alveolar morphology and the non-linear behavior of the alveolar septum to understand its response under both normal and pathological conditions.

Building lung phantoms for mechanical ventilation

Phantoms are devices that replicate the anatomy and potentially the function of an organ. This project involves the design, fabrication, and validation of a lung phantom for the study of respiratory mechanics. The project combines medical image processing, 3D printing of biomodels, experimentation, and respiratory mechanics analysis to characterize lung phantoms.

Mechanical and electrical characterization of bone tissue

Bone tissue is a porous structure with a high mineral content that provides structural support for the musculoskeletal system. Its mechanical properties are difficult to determine non-invasively. An opportunity to do so is through electrical impedance measurements, a field that has been underexplored. This project seeks to study the relationship between the electrical and mechanical properties of bone tissue.

Analysis of respiratory behavior in athletes using wearable devices

Breathing plays a fundamental role in the development of exercise and physical activity. This project seeks to validate respiratory sensors for the study of athletes, and to understand which aspects of breathing are most associated with athletic performance.

Digital Health – Software Quality

The advancement of digital health has led to a proliferation of technological solutions—such as telemedicine platforms, mobile applications, electronic health record systems, and applied artificial intelligence—that do not always comply with the required standards to ensure safety, interoperability, usability, and clinical effectiveness. This situation poses risks to patients, creates challenges in integrating with existing systems, and limits the ability of healthcare providers to assess the true quality of the tools they use or acquire. At the national level, this project proposes to explore and develop a comprehensive software quality assurance model specifically focused on the field of digital health, adapted to the regulatory, technical, and clinical conditions of the Chilean and Latin American context.

The model will include evaluation criteria based on international best practices (such as ISO/IEC 25010), automated testing tools, developer guidelines, and a quality seal to identify safe and reliable solutions.
This project will not only promote the continuous improvement of the digital health innovation ecosystem but also support informed decision-making by providers, patients, and public institutions.

Using generative AI for the de novo design of the metamorphic domain of RfaH in its autoinhibited state

The metamorphic protein RfaH is a bacterial virulence factor, which has two domains: NTD and CTD. The CTD reversible interconverts from an alpha-helical into a beta-barrel state through a metamorphic process. Although the possible folding routes between both states have been studied, it is unknown if there are other alternatives of folding topologies for the CTD in the autoinhibited state. In this regard, the use of generative AI tools for de novo protein structure design, such as RFDiffusion, allow to explore novel structures never seen in nature. The purpose of this research is, therefore, to ascertain if RFDiffusion allows to generate novel structures for the CTD of RfaH in the autoinhibited state, as well as analyzing the diversity of generated structures via clustering methods based on structural superposition metrics.

Experimental Analysis and Modeling of Collective Cancer Cell Migration

This project offers the opportunity to analyze experimental data from a cancer cell migration assay and translate the findings into a computational model, extending an existing Julia-based framework for simulating collective cell migration (see: https://doi.org/10.1039/c5ib00092k; https://doi.org/10.1101/2025.08.28.672905). The student will learn to process and analyze migration data, then implement it within a simulation platform using Julia or Python—modifying and expanding the model, performing parameter sweeps, and exploring how mechanical interactions influence emergent collective behaviors.
We seek motivated and independent students committed to applying computational tools to improve our understanding of cancer progression.
Let me know if you'd like it more specific about the type of migration assay or the analysis steps involved.

Translating a Single-Cell Migration Model from MATLAB to Python

This internship focuses on converting an existing single-cell migration computational model into Python to eliminate dependency on MATLAB licenses. The model follows the framework described in https://doi.org/10.1101/2025.08.28.672905.
The student will translate the model from MATLAB to Python, validate output equivalence between the two platforms, and restructure the code to ensure modularity and extensibility.
Ideal for students with basic programming experience interested in computational modeling for biological questions. Independence, dedication, and motivation to use computation in cancer research are essential.

Building a Multi-Cell Migration Model with Intercellular Interactions

This project aims to develop a new multi-cell computational model from scratch, incorporating intercellular interactions, geometric constraints, and emergent collective dynamics. The conceptual basis draws from https://doi.org/10.1073/pnas.1521151113 and https://doi.org/10.1101/2025.08.28.672905.
The student will design agent-based rules and implement efficient, object-oriented code capable of handling cell–cell forces, boundary constraints, interaction radii, and events such as extrusion or collision avoidance.
Best suited for students with a computational engineering or software background. Biological knowledge is not required; computational rigor, independence, and motivation to contribute to cancer research are essential.

Evaluation of Multifrequency Deep Image Prior for Real-Time 0.55 T Radial Cardiac Cine MRI

Cardiac cine Magnetic Resonance Imaging (MRI) is the gold standard for assessing heart function, but conventional techniques rely on electrocardiogram(ECG)-based acquisitions over multiple heartbeats, which limits temporal resolution and excludes patients with irregular heart rhythms. Recent advances in artificial intelligence have introduced Time-Dependent Deep Image Prior (TD-DIP), a powerful method that enables high–temporal-resolution cardiac imaging from very short MRI acquisitions. However, standard TD-DIP still depends on ECG signals, restricting its applicability in patients with arrhythmias. The Multifrequency TD-DIP framework overcomes this limitation by learning cardiac motion directly from the data—without requiring ECG input. This method has shown promising results at 1.5 T using spiral acquisitions. The objective of this project is to implement and evaluate Multifrequency TD-DIP for radial cardiac cine MRI at 0.55 T. Low-field MRI systems offer improved patient comfort, lower costs, and greater accessibility, but they also present exciting challenges due to reduced signal-to-noise ratio (SNR). This project offers hands-on experience at the intersection of MRI physics, signal processing, and deep learning, contributing to more accessible and patient-friendly cardiac MR imaging technologies.

Deep Learning–Based T1 and T2 3D Whole-Heart Mapping for Joint T1/T2 MRI

T1 and T2 mapping are cardiac Magnetic Resonance Imaging (MRI) techniques that have been shown to provide objective information about the myocardium, enabling the assessment of cardiac diseases that cannot be diagnosed using conventional cardiac imaging. Joint T1/T2 sequence enables the acquisition of simultaneous 3D T1 and T2 mapping from 3 water volumes. Since T1 and T2 maps are now estimated in 3D, this process can be time-consuming. The goal of this project is to train a neural network to directly estimate T1 and T2 maps from a novel joint T1/T2 sequence at 0.55T, reducing processing time and improving its accuracy.

PRISMA AI Program: Data for Better Health

This program aims to improve initial access to the healthcare system through artificial intelligence tools that support early clinical guidance and patient decision-making, helping optimize referrals and reduce pressure on emergency services. To achieve this, a set of interoperable solutions will be developed, integrated with clinical systems and trained using local data under robust data governance and security standards.

The portfolio includes projects such as P02 Clinical orientation chatbot (intelligent triage), P03 Ambient Listening for automated consultation capture, P04 Automatic clinical summaries using NLP, P05 Online DRG coding assistant, and P06 Digital clinical prescription, which aim to improve clinical workflow efficiency, strengthen medical record quality, and support clinical decision-making.
All developments are carried out jointly with the implementing partner Red UC CHRISTUS.

Multimodal integration in Alzheimer's Disease through Patient Similarity Networks

Patient Similarity Networks (PSNs) integrate heterogeneous data by turning each modality into a patient-by-patient similarity graph and fusing those graphs into one shared structure. The approach extends beyond omics to neuroimaging, clinical, and demographic data, yet multi-omics PSN work in Alzheimer's disease is still uncommon. In this project the student builds a PSN integration pipeline on real Alzheimer's data from ADNI, combining molecular and precomputed imaging features, and tests how the choice of distance metric, network fusion algorithm, and graph embedding shapes the patient subtypes it recovers. The goal is to find strata that single modalities miss, and to characterize them by diagnosis, APOE genotype, and cognition.

Semi-supervised automatic segmentation in cardiac magnetic resonance imaging

Medical image segmentation is a labor-intensive and time-consuming task, which presents a significant challenge in clinical practice. This is exacerbated by the scarcity of data manually annotated by experts, as the labeling of 3D volumes requires specialized personnel and extensive hours of work. In this context, artificial intelligence, and particularly semi-supervised learning, emerges as a promising solution: it allows for leveraging both a small set of labeled images and a larger volume of unlabeled images, reducing the reliance on manual annotations without sacrificing accuracy.
This work aims to utilize state-of-the-art neural network architectures, adapted for semi-supervised frameworks, to automatically segment various contrasts and 3D cardiac MRI maps, optimizing the annotation process and improving the model's accuracy even with limited labeled data.

Mechanical analysis of alveolar tissue during pulmonary emphysema

This research project aims to understand the behavior of stresses in alveolar tissue walls and how they are affected as pulmonary emphysema progresses. The project includes processing and analyzing murine lung micro-CT images, performing mechanical analysis using the finite element method, and conducting statistical analysis.

Mechanical characterization of the rat lung tissue

The mechanical behavior of the lung tissue determines respiratory function. This project aims to characterize the mechanical properties of lung tissue. The study involves conducting mechanical tests on soft tissues under different loading conditions and treatments, followed by their statistical analysis.

test

ttest test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test

Markerless Computer Vision-Based Gait Analysis for Objective Human Movement Assessment

Quantitative gait analysis is a key tool for functional assessment, clinical follow-up, and decision support in rehabilitation and sports medicine. However, traditional marker-based motion capture systems are costly, require specialized infrastructure, and are generally limited to laboratory settings. This project aims to develop and validate a markerless gait analysis platform based on conventional cameras and computer vision algorithms capable of estimating human kinematics without the need for body-mounted markers. The proposed platform will extract spatiotemporal and biomechanical gait parameters by integrating state-of-the-art pose estimation models and artificial intelligence techniques to improve the accuracy and robustness of the measurements. The system will be evaluated across different application scenarios, with the goal of providing a low-cost, scalable, and easily deployable solution for clinical, sports, and home-based environments. This initiative seeks to increase access to objective movement assessment tools and contribute to the advancement of digital health technologies for functional monitoring and personalized care.