Andrea Termine

Rome, Italy

+393280265942

PhD | Machine Learning Engineer

5 years of experience

andreatermine1@hotmail.it

Portfolio: andreater.github.io/portfolio-create-react-app

Blog: orcid.org/0000-0003-4374-7430

As a data scientist with three years of experience in big data and biomedical research, I have focused on developing clinical decision support software using artificial intelligence for neurodegenerative diseases. Throughout my career as a machine learning researcher, I have made significant contributions to the field through the publication of over 20 scientific papers in peer-reviewed journals. My expertise includes natural language processing, deep learning, predictive modeling, feature engineering, data visualization, and statistical analysis.

Skills:

Machine learning 6 years ⋅ AdvancedDeep Learning 5 years ⋅ AdvancedR 6 years ⋅ ExpertPython 5 years ⋅ AdvancedSQL 4 years ⋅ AdvancedGoogle Cloud Platform (GCP) 3 years ⋅ IntermediateAWS 3 years ⋅ Advanced

Experience

International Journal of Molecular Sciences  mdpi.com

Mar 2022 to Present

Artificial Intelligence Guest Editor Remote

IJMS is an international, peer-reviewed, open access journal providing an advanced forum for biochemistry, molecular biophysic and molecular medicine. I supervise the peer-review process and take decisions on new submissions in the Artificial Intelligence in molecular medicine topic.

  • Promoted the Artificial intelligence in molecular medicine topic at conferences, on social media and other relevant platforms.
  • Helped IJMS reach 6.2 Impact Factor.
  • Curated the Special Issue collection titled:"Biomedical Applications of Molecular Simulation and Machine Learning in Disease Modeling and Drug Repurposing".

Mondo Convenienza  mondoconv.it

May 2023 to Present

Machine Learning Engineer

Mondo Convenienza is an Italian company that focuses on organized large-scale retail of furniture and home furnishings, providing the best quality-price ratio in the market and making home projects accessible to everyone. In my role, I am responsible for Supply Chain Machine Learning and MLOps. I develop and deploy machine learning models to optimize supply chain operations

International Telematic University UNINETTUNO  uninettunouniversity.net

Sep 2021 to Present

Data Science Course Instructor Rome, Italy

UNINT is one of the world's leading distance learning universities and has won several international awards for the excellence of the E-Learning Platform from The European Association of Distance Teaching Universities (EADTU). I teach data science in the master's degree program in cognitive processes and technologies in neuroscience.

  • Introduced version control and product deployment methods in the course.
  • Supervised more than 40 students during the course.
  • Established a repository of R exercises from data wrangling to supervised machine learning.

National Virtual Dementia Institute, IRCCS Network of Neurosciences and Neurorehabilitation (RIN)  reteneuroscienze.it

Jan 2021 to May 2023

Genomic Data Scientist Rome, Italy

The National Virtual Dementia Institute is a core component of the Italian IRCCS Network of Neurosciences and Neurorehabilitation. The institute combines the most advanced IRCCS in the study and treatment of neurodegenerative diseases. In the bioinformatic unit, I manage omics big data and develop standardized diagnostic pipelines for whole exome sequencing, genome wide analysis, and RNA sequencing.

  • Contributed to the standardization of the diagnostic pipeline for Parkinson's Disease.
  • Contributed to define the schema of the database for omics data.
  • Updated the diagnostic pipeline of a Institute Member to the GATK - Broad Institute standards.

IRCCS Santa Lucia Foundation  hsantalucia.it

Sep 2020 to May 2023

Data Scientist Rome, Italy

The Santa Lucia Foundation of Rome is a Scientific Institute for Research, Hospitalization and Healthcare (IRCCS) specialized in the fields of neuro-rehabilitation and neurosciences. Among the leading IRCCS in Italy, the foundation is ranked first in the neuroscience sector for total scientific productivity. In my job, I developed clinical decision support and computer-aided diagnosis software based on artificial intelligence.

  • Published 30+ scientific articles on Artificial Intelligence in Neuroscience.
  • Generated more than 10 H-index points with 290+ citations in two years.
  • Built 2 Deep Learning computer-aided diagnosis softwares for neurological conditions based on 3D brain scan.
  • Built 2 clinical decision support system for the diagnosis and treatment of neurological conditions based on genomic data.
  • 2.63 scopus Topic Field-Weighted Citation Impact score in the Object Detection; Deep Learning; IOU section.

Italian Union Against Muscular Dystrophy  fondazioneuildmlazio.org

Jan 2020 to Sep 2020

Genomic Data Scientist Rome, Italy

UILDM was founded in 1961 to promote scientific research and health information on dystrophies and other neuromuscular diseases. I worked as a genomic data scientist in the genetic medicine lab. My job was to develop an automated Next Generation Sequencing pipeline for genetic variant discovery. The variants are used in the diagnostic workflow for many neuromuscular diseases.

  • Developed an automated python NGS pipeline for somatic short variant discovery and annotation.
  • Aligned the diagnostic pipeline to the GATK - Broad Institute best practices.
  • The pipeline works both on Illumina or Thermofisher devices and on whole exome sequencing data.

Projects

NeuroPGx

A clinical decision-support system developed to foresee potential drug–drug interactions based on high-throughput real-time PCR genotyping data. NeuroPGx is an open-source web-based software for genotype/diplotype/phenotype interpretation for neuropharmacogenomic purposes. The software is described in the following scientific paper: Journal of Personalized Medicine (https://doi.org/10.3390/jpm11090851).

R, shiny, tidyverse

RED-CAD

RED-CAD (Reproducible Deep-Learning Computer-Aided Diagnosis for FTD) is a prototype of a computer-aided diagnosis tool for Frontotemporal Lobar Degeneration (FTD). We trained a DenseNet 121, which is a Densely Connected Convolutional Neural Network, on the largest dataset of 3D MRI brain scans of FTD patients. The image collection was provided by the Frontotemporal Lobar Degeneration Neuroimaging Initiative. Explainable AI methods were also applied to understand the AI's behavior and to identify critical regions of the brain. The prototype is described in the following scientific paper, published in Life (https://doi.org/10.3390/life12070947).

Python

WARE

WARE is a clinical decision support system that provides individual risk profiles for Age-Related Macular Degeneration (AMD) based on genetic risk measures. WARE is an open-source software, and we described it in a peer-reviewed paper published in the Journal of Personalized Medicine (https://doi.org/10.3390/jpm12071034).

R

Education

Tor Vergata University of Rome

Nov 2020 to Dec 2023

Doctor of Philosophy - PhD, Neuroscience

I worked on the development of clinical decision support software powered by Artificial Intelligence for diagnosis and treatment of neurological conditions.

Sapienza University of Rome

Sep 2016 to Dec 2018

Master of Science - MS, Cognitive Neuroscience

Certificates

AWS Certified Cloud Practitioner

Amazon Web Services (AWS)
May 2023

English Proficiency Certificate

Duolingo English Test
2022

IBM AI Engineering Professional Certificate

IBM
2021

Data Science Professional Certificate

IBM
2021

Statistics with R - Specialization

Duke University | Coursera
2018

Bayesian Statistics: From Concept to Data Analysis

University of California, Santa Cruz | Coursera
2018

Volunteer

DataKind  datakind.org

Aug 2022

Data Scientist

DataKind is a nonprofit organization that brings together data scientists, social sector organizations, and communities to use data science in the service of humanity. They work to address some of the world's most pressing social issues by applying data science techniques to large-scale data sets in order to identify patterns, trends, and insights that can inform decision-making and drive positive change. They also provide training and resources to help social sector organizations effectively use data science in their work.

Selected Publications

A Reproducible Deep-Learning-Based Computer-Aided Diagnosis Tool for Frontotemporal Dementia Using MONAI and Clinica Frameworks

Life
Jun 2022

A Hybrid Machine Learning and Network Analysis Approach Reveals Two Parkinson’s Disease Subtypes from 115 RNA-Seq Post-Mortem Brain Samples

International Journal of Molecular Sciences
Feb 2022

Precision Medicine into Clinical Practice: A Web-Based Tool Enables Real-Time Pharmacogenetic Assessment of Tailored Treatments in Psychiatric Disorders

Journal of Personalized Medicine
Aug 2021

Identification of Genetic Networks Reveals Complex Associations and Risk Trajectory Linking Mild Cognitive Impairment to Alzheimer’s Disease

Frontiers in Aging Neuroscience
Feb 2022

Artificial Intelligence for Alzheimer’s Disease: Promise or Challenge?

Diagnostics
Aug 2021

Multi-Layer Picture of Neurodegenerative Diseases: Lessons from the Use of Big Data through Artificial Intelligence

Journal of Personalized Medicine
Apr 2021

BNT162b2 vaccination induces durable SARS-CoV-2–specific T cells with a stem cell memory phenotype

Science Immunology
Dec 2021

Transcriptomic and Network Analyses Reveal Immune Modulation by Endocannabinoids in Approach/Avoidance Traits

International Journal of Molecular Sciences
Feb 2022

D4Z4 Methylation Levels Combined with a Machine Learning Pipeline Highlight Single CpG Sites as Discriminating Biomarkers for FSHD Patients

Dec 2022

Languages

Inglese Professional WorkingItalian Native Speaker