BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:America/New_York X-WR-TIMEZONE:America/New_York BEGIN:VEVENT UID:536@fds.yale.edu DTSTART;TZID=America/New_York:20231130T160000 DTEND;TZID=America/New_York:20231130T170000 DTSTAMP:20250916T142128Z URL:https://fds.yale.edu/events/data-science-project-match/ SUMMARY:Data Science Project Match DESCRIPTION:Remote access available to Yale-only.\n\n\nProject Presenters:\ n\n\n\nJonathan Reuning-SchererSenior Lecturer in StatisticsYale Dept of S tatistics / School of the EnvironmentJonathan.reuning-scherer@yale.edu |  https://environment.yale.edu/profile/ruening-schererDramatists Guild Mem bership Survey AnalysisDuring spring of 2023\, the largest ever survey was conducted of the membership of the Dramatists Guild of America.  The re sulting database contains demographic\, compensation\, attitudinal\, and c areer history for 2000 respondents.  In addition\, data was collected on the details surrounding the creation of 1000 creative works including maj or Broadway shows.  There is the opportunity for 2-3 students to complet e senior projects/graduate practical work during the spring of 2024 workin g with DG leadership and Jonathan Reuning-Scherer.  Results will likely be published in DG materials around the 2024 Tony Awards.\n\n\n\nMark Gers tein Albert L Williams Professor of Biomedical Informatics Professor of Molecular Biophysics & Biochemistry\, of Computer Science\, and of Statist ics & Data Science Project presented by Joel RozowskyResearch Scientist i n Molecular Biophysics and Biochemistry\, Gerstein Labmark@gersteinlab.org \, joel.rozowsky@yale.edu | http://gersteinlab.orgGenomics & Bioinforma tics Research in the Gerstein Lab\n\n\n\nThe Gerstein lab conducts bioinfo rmatics research in the biomedical and genomic fields. We use various data computational data analytics methods including machine learning technique s to analyze large biomedical datasets. The lab is particularly focused on the following areas of research: genomic privacy\, personal genomes\, gen ome annotation and neurogenomics.\n\n\n\nKim R. M. Blenman\, Ph.D.\, M.S.A ssistant ProfessorDepartment of Internal Medicine\, Section of Medical Onc ology\, School of MedicineDepartment of Computer Science\, School of Engin eering and Applied ScienceYale Cancer Centerkim.blenman@yale.edu | Profile : https://medicine.yale.edu/profile/kim_blenman/Research: https://blenma ninnovationgroup.org/Statistical Analysis and Data Visualization for Predi ctive and Prognostic Tools for ProteomicsStatistical analysis and data vis ualization for predictive and prognostic tools are the cornerstones of omi cs analysis in medicine. Although we have progressed through the age of ge nomics\, as a field we are also now moving into the age of proteomics. The biology assays that generate the data for genomics and proteomics are not the same. Therefore\, new statistical analysis tools are required for thi s new proteomics revolution. Students who are interested in being part of this revolution are welcome to join my research group. There are many proj ects available.\n\n\n\nLeandros TassiulasJohn C. Malone Professor of Elect rical Engineering & Computer ScienceProject Presented by Georgios Palaiokr assasPostdoctoral Associate\, Electrical Engineering\, Tassiulas Lableandr os.tassiulas@yale.edu\, georgios.palaiokrassas@yale.edu | https://seas. yale.edu/faculty-research/faculty-directory/leandros-tassiulas\n\n\n\nBloc kchain Analytics: A Machine Learning Approach\n\n\n\nThe inception of perm issionless blockchains with Bitcoin in 2008\, was followed by the developm ent of Ethereum and other blockchain platforms\, offering new solutions by enabling smart contracts’ implementation and execution. This project em phasizes into applying machine learning techniques including statistical m ethods\, GNNs and LLMs to an extensive transaction dataset spanning multip le blockchain platforms. The project aims to uncover patterns\, trends\, a nd anomalies within the blockchain transactions for use cases such as iden tifying fraudulent activities\, predicting cryptocurrency price fluctuatio ns\, and understanding the network's growth dynamics. Another direction is the combination of data processing\, feature engineering and application of Machine Learning to estimate the risk of transactions\, assess the cred it scoring of users and recommend strategies to mitigate risk.\n\n\n\nWe a re looking for students who have background in applied machine learning. A ny experience in the areas of Blockchain and Decentralized Finance are a p lus!\n\n\n\nJun Deng\, PhD\, DABR\, FAAPM\, FASTROProfessor of Therapeutic Radiology\; Director of Physics Research\, Therapeutic Radiology\; Associ ate Director of Medical Physics Residency Program\, Therapeutic Radiologyj un.deng@yale.edu | Profile: https://medicine.yale.edu/profile/jun-deng/  Research: https://medicine.yale.edu/lab/deng/Enabling Digital Twins for Predictive OncologyThe human body is a complex\, multiscale\, dynamical s ystem with constant interactions within itself and with the environment. M any new technologies have been used for health profiling\, such as functio nal and molecular imaging\, liquid biopsies\, digital pathology\, genomic profiling\, fitness trackers and wearables\, and implantable sensors. Whil e each of these technologies sheds light on one's health state\, these mul timodal datasets are scattered and disconnected\, not amenable to AI/ML an alysis at scale.Predictive oncology is to anticipate likely patient outcom es and health status based on multimodal data by modeling the dynamics and trajectory for individual cancer patient. One of the promising technologi es to explore predictive oncology is by creating digital twins of cancer p atients. A person's digital twin may aid in monitoring health status\, sim ulating patient outcome trajectories\, developing tailored therapeutic str ategies\, preventing adverse effects\, and improving lifestyle. In this pr oject\, we aim to develop novel AI/ML algorithms by modeling existing clin ical\, imaging\, and radiotherapy datasets to enable cancer patient digita l twins in radiation oncology.We are looking for students to join our lab and help enable digital twins for predictive oncology via statistical\, co mputational\, mathematical\, and mechanistic modeling of spatiotemporal pa tient data.\n\n\n\nVictor S. Batista\, FRSCJohn Gamble Kirkwood Professor of ChemistryYale Quantum Institute & Yale Energy Sciences InstituteACS Ass ociate Editor\, JCTCvictor.batista@yale.edu | http://ursula.chem.yale.ed u/~batista/\n\n\n\nQuantum and Classical Machine Learning Models for Molec ular Design\n\n\n\nThe incredible capabilities of generative machine learn ing models and recent advances in quantum computing have the potential to revolutionize the field of molecular design and drug discovery. My group i s working on the development and implementation of generative algorithms f or design of drugs and retrosynthetic pathways. We are currently working o n state-of-the-art transformers\, quantum convolutional neural networks\, and quantum variational autoencoders for de novo molecular design\, and development of a cloud server interface to make our methods available to e xternal users from pharmaceutical companies. \n\n\n\nDavid van Dijk\, Ph. D.Assistant Professor of Medicine\, Yale School of MedicineAssistant Profe ssor of Computer Science Project presented by Daniel LevinePostdoctoral A ssociatedavid.vandijk@yale.edu | vandijklab.org“Using Machine Learning to understand the language of biology”Recent advances in large language models provide new opportunities for decoding biology. Single-cell omics data encodes complex cellular behaviors and processes into high-dimensiona l molecular profiles. By treating these data as textual representations\, we can apply and fine-tune neural language models to uncover the underlyin g grammatical rules governing biological systems. We have demonstrated tha t these models can learn to translate between species\, matching cell type s and gene expression programs between mice and humans in a completely uns upervised fashion. This cross-species translation highlights how fundament al aspects of biology form a universal language translatable across organi sms. More broadly\, interpreting single cell data as “biological text” enables leveraging powerful natural language processing approaches to fin d patterns\, generate hypotheses\, and gain conceptual understanding of bi ology.\n\n\n\nRohan Khera\, MD\, MSDirector\, Cardiovascular Data Science (CarDS) LabAssistant Professor\, Cardiovascular Medicine\, Yale School of MedicinePresented by Lovedeep Dhingra and Arya AminorroayaPostdoctoral Ass ociatesrohan.khera@yale.edu | CarDS-Lab.org\n\n\n\n"Innovating Cardiovas cular Care with Multimodality Data Science"The Cardiovascular Data Science (CarDS) Lab at Yale leverages advances in deep learning and AI to enhance and automate care. The work uses numerous data streams in the electronic health record and focuses on natural language processing\, federated learn ing\, signal processing\, and computer vision for enhanced inference\, and develops and deploys novel convolutional neural networks and transformer models to address care challenges. The experience is ideal for students in terested in health tech and/or medicine and looking to gain from a longitu dinal research experience.\n\n\n\nEduardo Fernandez-DuqueProfessor of Anth ropology. School of the Environmenteduardo.fernandez-duque@yale.edu | ht tps://www.eduardofernandez-duque.comQuerying a Social Evolution Research V ideo Database for Research and TeachingEduardo Fernandez-Duque (Anthropolo gy and School of the Environment) has been co-organizing the international remote Frontiers in Social Evolution Seminar Series (FINE website).  Res earchers from > 20 countries and all continents have given 125 one-hour ta lks on their "social evolution" research followed by a 1-hour Q&A session.   All weekly seminars were recorded live and made publicly available in t he FINE YouTube channel (FINE YouTube Channel).Data set: 2\,500 hours of v ideos on social evolution research and follow-up discussions.Specific poss ible objectives:1- to develop searching tools to query the video collectio n and to extract "material" (e.g. graphs\, tables\, images) from the video s2- to produce series of short video clips illustrating topics that cut ac ross many of the talks.\n\n\nReza YaesoubiAssociate Professor of Public He althAssociate Professor\, Institution for Social and Policy Studiesreza.ya esoubi@yale.edu | https://ysph.yale.edu/profile/reza-yaesoubi/ Generatin g and evaluating simple classification rules to predict local surges in CO VID-19 hospitalizationsLow rates of vaccination\, emergence of novel varia nts of SARS-CoV-2\, and increasing transmission relating to seasonal chang es and relaxation of mitigation measures leave many US communities at risk for surges of COVID-19 that might strain hospital capacity. The trajector ies of COVID-19 hospitalizations differ across communities\, but existing predictive models of COVID-19 hospitalizations are almost exclusively focu sed on state-level predictions. We are interested to develop and evaluate methods to generate simple\, interpretable classification rules to predict whether COVID-19 hospitalization will exceed the local hospitalization ca pacity in the short term.\n\n\nElena GrewalLecturer\, Yale School of the E nvironmentelena.grewal@yale.edu | Informing policy decisions to increase affordable housingNew Haven has an affordable housing crisis. The number of homeless students has doubled in the past year. Residents cannot affo rd to stay in their homes because of rent increases and a general shortage of affordable housing. While there are new apartments being built\, many are high-end and not something that people who are being pushed out of the ir homes can afford. A policy to allow homeowners to make attics/basements and attached buildings to their own homes into rental units (ADUs) result ed in no additional housing being built.  It would be helpful to have d ata on the current housing stock and rental market to inform policy makers decisions.  The Fair Rent Commission is tasked with reviewing rent incr eases and also reducing rents when tenants live in poor conditions (exampl e here). Recently the commission has seen cases of parents with children and elderly on fixed income who do not have other options. There is a staf f member who is tasked with knocking on doors to raise awareness of the co mmission and also to inspect housing conditions. It would be helpful to us e data to target their efforts. In addition the commission is supposed to use the availability of other housing as a factor in decisions and there i s no database available for this. The Fair Rent Commission can also make h ousing policy recommendations. \n CATEGORIES:FDS Events,Project Match END:VEVENT BEGIN:VTIMEZONE TZID:America/New_York X-LIC-LOCATION:America/New_York BEGIN:STANDARD DTSTART:20231105T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 TZNAME:EST END:STANDARD END:VTIMEZONE END:VCALENDAR