IQ Machine Intelligence for Quantitative Modeling in Drug Discovery & Development Applications Workshop

In September 2022, the IQ Clinical Pharmacology Leadership Group's Artificial Intelligence and Machine Learning (AI/ML) Working Group held a 2-day workshop on Machine Intelligence for Quantitative Modeling in Drug Discovery & Development Applications. 

While there is significant interest from both industry & regulatory agencies in applying Artificial Intelligence (AI) and Machine Learning (ML) to quantitative modeling for drug development applications, several challenges remain: these include the generalizability, interpretability, and data requirement of such models. To help address these issues, within the IQ Consortium the AI/ML Working Group was formed with the aim to foster scientific dialogue on AI/ML applications and identify a set of good practices, so as to enable broader impacts in drug development. With this IQ Workshop, we aim to bring together experts from industry, academia, and the FDA to initiate a scientific dialogue and collaboration across disciplines to elevate the impact of ML.

Meet the speakers via their biographies, listen to the speakers' talks, and view their presentations below. 

---

Speaker Biographies

Recordings with time stamps

• Listen to 9/15 Day 1 

• Listen to 9/16 Day 2

Speaker Slides 

• Keynote: Application of Artificial Intelligence/Machine Learning (AI/ML) in Drug Development

• Session 1: AI/ML-ENABLED ANALYTICS & PHARMACOMETRICS WORKFLOWS

  • Leveraging AI and ML to Support Generic Drug Development and Regulatory Efficiency -- Meng Hu, FDA

  • AI_ML-enabled  Pharmacometrics Workflows -- Nadia Terranova, Merck KGaA

  • Neural-PK_PD as Pharmacology-Informed Deep Learning Architecture -- James Lu, Genentech

  • A Machine Learning Based Approach for Toxicity Predictions in Immuno-Oncology -- Kamrine Poels, Pfizer

• Session 2: EXPLAINABLE ML FOR DISEASE PROGRESSION/DIGITAL TWINS

  • Towards Inverse QSP Modeling for Virtual Patient Population Sampling

  • Machine Learning-based Prediction of disease activity in MS

  • Explainable Deep Learning for Tumor Dynamic Modeling and Overall Survival Prediction

• Session 3:  NLP IN QUANTITATIVE PHARMACOLOGY MODELING

  • Using Natural Language Processing (NLP) to Streamline Literature Selection for Meta-Analysis (MA)

  • An automated approach to extract pharmacokinetic parameters from scientific publications

  • Constructing a Large-scale Biomedical Knowledge Graph and its Applications

• Session 4: AI/ML UTILIZATION IN DRUG DISCOVERY

  • Applications of Machine Learning in Discovery and Development at Merck

  • Lab in the loop Machine learning for LMDD

  • Use of AI & ML in Discovery Toxicology