2021-22 Takeda Fellows: Leaning on AI to advance medicine for humans | MIT News

In slide 2020, MIT’s University of Engineering and Takeda Pharmaceuticals Business Limited launched the MIT-Takeda Application, a collaboration to support associates of the MIT community performing at the intersection of artificial intelligence and human wellness. Housed at the Abdul Latif Jameel Clinic for Machine Finding out in Wellbeing, the collaboration aims to use artificial intelligence to equally benefit human overall health and help in drug advancement. Combining technological know-how with reducing-edge well being study, the program’s participants hope to improve wellness results across the environment.

As a result much, the partnership has supported joint investigation efforts concentrated on matters such as automated inspection in sterile pharmaceutical manufacturing and machine studying for liver phenotyping.

Every single 12 months, the plan also cash graduate fellowships to assist college students pursuing analysis on a wide array of difficulties tied to health and AI. This year’s Takeda fellows, described under, are functioning on analysis involving digital wellbeing document algorithms, remote sensing information as it relates to environmental well being chance, and neural networks for the improvement of antibiotics.

Monica Agrawal

Agrawal is a PhD college student in the Division of Electrical Engineering and Laptop or computer Science (EECS). Her analysis focuses on the enhancement of equipment learning algorithms that could unlock the possible of electronic overall health data to electrical power customized, genuine-globe scientific studies of comparative efficiency. She is tackling the issue from 3 interconnected angles: knowing the standard constructing blocks of scientific text, enabling the structuring of medical timelines with only negligible labeled details, and redesigning scientific documentation to incentivize significant-quality structured info at the time of development. Agrawal attained equally a BS and an MS in laptop or computer science from Stanford University.

Peng Cao

A PhD college student in EECS, Peng Cao’s analysis is concentrated on producing a new technique to monitoring oxygen saturation by analyzing the radio frequency signals that bounce off a person’s body. To this finish, she is extracting respiration indicators from the radio indicators and then coaching a neural community to infer oxygen stages from it. Peng gained a BS in pc science from Peking University in China.

Bianca Lepe

A PhD student in biological engineering, Bianca Lepe is doing the job to benchmark current and defining following-era vaccine candidates for tuberculosis. She is using publicly obtainable data blended with equipment understanding algorithms to identify the Mtb proteins that are perfectly-suited as subunit vaccine antigens throughout the range of the human leukocyte antigen alleles. Lepe attained a BS in biological engineering and business from Caltech an MS in systems and synthetic biology from the College of Edinburgh in Scotland and an MPhil in engineering policy from the College of Cambridge in England.

Caroline McCue

Caroline McCue is a PhD scholar in mechanical engineering who is developing a technique that could simplify and pace up the system of cell passaging. Additional particularly, she is designing and testing a platform that triggers cell detachment in response to simple external stimuli, this sort of as a change in voltage or in mechanical homes. She designs to test the efficacy of this system by applying device mastering to quantify the adhesion of Chinese hamster ovary cells to these surfaces. McCue gained a BS in mechanical engineering from the College of Maryland.

Somesh Mohapatra

A PhD student in the Office of Products Science and Engineering, Somesh Mohapatra is also pursuing an MBA at the MIT Sloan Faculty of Management as element of the Leaders for International Functions Method. His doctoral investigation, in close collaboration with experimentalists at MIT, focuses on planning biomacromolecules applying interpretable device mastering and simulations. Exclusively, Mohapatra leverages macromolecule graph representations to produce equipment understanding products for quantitative prediction, optimization, and attribution solutions. He then applies these resources to elucidate layout principles and to enhance general performance and artificial accessibility of features macromolecules, ranging from peptides and glycans to electrolytes and thermosets. Mohapatra attained his BTech in metallurgical and resources engineering from the Indian Institute of Technology Roorkee in India.

Luke Murray

Luke Murray is a PhD student in EECS. He is establishing MedKnowts, a system that brings together machine discovering and human laptop interaction strategies to reduce the exertion needed to synthesize awareness for clinical decision-creating, and writer substantial-high-quality, structured, scientific documentation. MedKnowts unifies these two currently splintered workflows by providing a seamless interface that re-imagines documentation as a natural byproduct of scientific reasoning, instead than as a compliance need. Murray earned his BS in laptop or computer science from Brown University.

Ufuoma Ovienmhada

Ufuoma Ovienmhada SM ’20 is a PhD pupil in aeronautics and astronautics. Her investigate employs a mixed-approaches technique (group-centered structure, systems engineering, and machine finding out) to satellite remote sensing information to develop applications that consider how human health and fitness risk relates to environmental dangers. Ovienmhada gained her BS in mechanical engineering from Stanford University and her SM in media arts and sciences from MIT.​

Lagnajit Pattanaik

Lagnajit “Lucky” Pattanaik is a PhD pupil in chemical engineering. He seeks to change the paradigm of predictive natural chemistry from qualitative to quantitative. Additional exclusively, his exploration is concentrated on the enhancement of machine understanding tactics for predicting 3D structures of molecules and reactions, which includes changeover point out geometries and the geometrical conformations that molecules acquire in remedy. He acquired a BS in chemical engineering from Ohio State University.

Na Sun 

A PhD student in EECS, Na Sun is performing in the emerging field of neuro-immuno-genomics. More precisely, she is developing equipment mastering procedures to far better understand the interactions between two particularly intricate devices: the human mind and its dozens of mobile styles, and the human immune method and the dozens of biological procedures that it integrates throughout cognition, pathogen response, diet program-physical exercise-obesity, and synaptic pruning. Sunlight gained her BS in life sciences from Linyi University in China and an MS in developmental biology from the College of Chinese Academy of Sciences in China.

Jacqueline Valeri

Jacqueline Valeri is a PhD scholar in biological engineering who utilizes neural networks for antibiotics discovery. Her endeavours contain the recycling of compounds from present compound libraries and the computationally assisted structure of novel therapeutics. She is also excited by broader programs of device learning and synthetic intelligence in the fields of wellbeing treatment and biomedicine. Valeri acquired her BSE and MSE in bioengineering from the College of Pennsylvania.

Clinton Wang

A PhD college student in EECS, Clinton Wang SM ’20 has created a new form of conditional generative adversarial network primarily based on spatial-depth transforms. It achieves significant impression fidelity, is robust to artifacts in teaching details, and generalizes to held-out clinical websites. Wang now aims to extend his design to even much more demanding apps, together with visualizing transformations of focal pathologies, these as lesions, the place it could serve as a strong device for characterizing biomarkers of malignancy and remedy response. Wang attained a BS in biomedical engineering from Yale College and an SM in electrical engineering and laptop or computer science from MIT.