1 of 10

IMAG/MSM Working Group on Multiscale Modeling and Viral Pandemics Mini Seminars

April 7, 2022

Welcome - The meeting will start at 3PM ET

 

NOTE: THE MEETING WILL BE RECORDED, STREAMED AND PUBLICLY AVAILABLE�FOR THOSE MEMBERS UNABLE TO ATTEND

Agenda

  1. Welcome
  2. Links, people, other info
  3. Social media links
  4. Quick Announcements
  5. Upcoming Mini-Seminars and Request for Future Speakers
  6. Jonas Hue, King’s College, �Machine learning powered high content image analysis of routine H&E slides provide novel indicators to predict unfavourable outcome in HPV+ oropharyngeal squamous cell carcinoma patients
  7. Yuefan Deng, Stonybrook, �Multi-scale and Machine Learning Algorithms for Modeling Large Blood Clots
  8. Request for Further Business

 

2 of 10

People

Co-Lead: Reinhard Laubenbacher, PhD

Department of Medicine

Laboratory for Systems Medicine

University of Florida

reinhard.laubenbacher@medicine.ufl.edu

Co-Lead: James A. Glazier, PhD

Dept. of Intelligent Systems Engineering and Biocomplexity Institute

Indiana University, Bloomington

jaglazier@gmail.com

Web Administration, Slack: James P. Sluka, PhD

Dept. of Intelligent Systems Engineering and Biocomplexity Institute

Indiana University, Bloomington

jsluka@indiana.edu

Activities Coordination: Lorenzo Veschini, PhD

King’s College London

lorenzo.veschini@gmail.com

 

3 of 10

4 of 10

Please follow the�group on Twitter!

https://twitter.com/MsmViral

If you could re-tweet the weekly announcements �(there are usually two, one for each speaker) �that would help boost attendance and community awareness.

 

5 of 10

Announcements

Any short (~1 minute) items such as;

  • announcements
  • meetings
  • funding
  • publications
  • requests for help

Two new publications from Gary An et al.

  1. Dale Larie, Gary An, Robert Chase Cockrell, Preparing for the next COVID: Deep Reinforcement Learning trained Artificial Intelligence discovery of multi-modal immunomodulatory control of systemic inflammation in the absence of effective anti-microbials http://dx.doi.org/10.1101/2022.02.17.480940
  2. Gary An, Specialty Grand Challenge: What it will take to cross the Valley of Death: Translational Systems Biology, “True” Precision Medicine, Medical Digital Twins, Artificial Intelligence and In Silico Clinical trials (accepted pending final quality checks) https://www.frontiersin.org/articles/10.3389/fsysb.2022.901159/ful

6 of 10

Schedule for Upcoming Meetings and mini-Seminars

April 14:

  1. Natasha Diba Sheybani, University of Virginia.
  2. TBD

April 21:

  1. TBD
  2. TBD

April 28:

  1. Lucas Bottcher, Frankfurt School for finance & Management, UCLA �Title: AI Pontryagin or: How Neural Networks Learn to Control Dynamical Systems
  2. David Gibbs, Institute for Systems Biology, Seattle, WA. �Title: Patient specific cell-cell networks suggest important links in disease progression

Request for future speakers (April 14, …)

7 of 10

Mini-Seminar Machine learning powered high content image analysis of routine H&E slides provide novel indicators to predict unfavourable outcome in HPV+ oropharyngeal squamous cell carcinoma patients

Jonas Hue�King's College London

Aim: Patients with Human Papillomavirus positive oropharyngeal Squamous Cell Carcinoma (HPV+opSCC) have better prognosis than HPV- counterparts, raising the possibility of treatment de-escalation in the former. About 20% of HPV+opSCC patients demonstrate unfavourable outcomes, contraindicating de-escalation regimes in this subgroup; however, diagnostic procedures to identify such patients are currently unavailable. To address this issue, we developed an automated workflow for quantitative high content image analysis (HCA) of H&E stained sections of HPV+opSCCs. We quantified various known prognostic features such as number and spatial distribution of tumour-infiltrating lymphocytes (TILs) in the stromal and intra-tumour regions. In addition, we measured and attempted to identify other less established features such as stromal plasma cells, tumour nuclei features and morphological heterogeneity within tumour cells. Finally, we trained and validated a model to retrospectively prognosticate outcomes in a cohort of 58 HPV+opSCC patients. Results: Univariate and multivariate statistical analyses revealed that plasma cells, stromal and intra-tumour TILs were more numerous in favourable outcome (FO) patients. Tumour cell nuclei were rounder, less eccentric in morphology and packed closer to one another in patients with FO. Tumour nuclei in FO had more nucleoli and higher texture and granularity features than patients with unfavourable outcomes (UO). UO patients had greater tumour heterogeneity in morphological, spatial and textural measurements. To attempt separating the groups according to these variables we performed statistical discriminant analyses (either LDA or QDA). QDA had an accuracy of 81.7% and 88.1% in predicting UO and FO on our cohort. We validated our analysis by k-fold cross-validation, revealing an estimated overall accuracy of 76.2% and a Kappa statistic of 0.523, indicating a good model considering the complexity of the problem at hand. Conclusions: Single-cell quantitative image analysis of HPV+opSCC allows us to identify prognostic factors and quantify their heterogeneity within the tumour. We have shown that some of these measures are predictive in their own right, and that their variance within a tumour can itself be prognostic and improve the accuracy of statistical discriminant models. Our open-source HCA workflow on routine H&E slides and statistical modelling can aid prognostication of HPV+opSCCs �outcome with promising accuracy. Our work supports the use of ML-powered HCA �followed by statistical modelling in digital pathology to exploit clinically relevant�features in routine diagnostic pathology without additional biomarkers.

8 of 10

Mini-SeminarMulti-scale and Machine Learning Algorithms �for Modeling Large Blood Clots

Moderated byYuefan Deng�Stony Brook University

Multiscale modeling in biomedical engineering is gaining momentum because of progress in supercomputing, applied mathematics, and quantitative biomedical engineering. For example, scientists in various disciplines have been advancing, slowly but steadily, the simulation of blood including its flowing and the physiological properties of such components as red blood cells, white blood cells, and platelets. Aggregated platelets stimulate blood clotting that causes heart attacks and strokes, resulting in more than 20 million deaths annually (for a comparison, the lethal Covid-19 causes 5.7 million deaths as of Jan. 2022). To reduce such deaths, we must discover new drugs. To discover new drugs, we must understand the mechanism of platelet activation and aggregation. To model platelets’ dynamics involves setting up the basic space and time discretization in huge ranges of 5-6 orders of magnitudes, resulting from the relevant fundamental interactions at atomic, to molecular, to cell, to fluid scales. To achieve the desired accuracy at the minimal computational costs, we must select the correct physiological parameters in the force fields such as the Morse potential and Hooke’s law as well as the spatial and temporal discretization, by machine learning. We demonstrate our results of a multiscale 250-platelet (125 million particles) aggregation simulation and their �corroborations with in vitro experiments.

9 of 10

Requests for Input/Suggestions

  

 

We would like the subgroup leads to prepare brief presentations for the Thursday meetings, please let us know when you would like to present

Ideas/help for publicising our Thursday mini-seminars more effectively and for speakers to invite

Suggestions for agenda items and approaches to organizing the Steering Committee Meetings more effectively

There have also been a number of requests for more explicit statements of goals and tasks from the WG leadership, we would appreciate your suggestions

Please contact Reinhard Laubenbacher, James Glazier, James Sluka or Bruce Shapiro with your ideas on all of these issues

10 of 10

fini