30th Meetup

Note: Please use your full real names where signing up, otherwise we have problems with building security.

This will be our special post Christmas / New Year meetup, with the usual free beer and pizza and maybe some extra goodies, generously provided by AHL.

---

Main speakers:

Riley Doyle (https://twitter.com/doyle_riley) on Personalising Genome Surgery (with Python)

Today surgeons consult radiologists before operating on their patient. In the future, surgeons will consult a gene editing AI which will help them design a personalised approach to literally edit out the mutated DNA that causes a patient’s disease. Riley Doyle’s team at Desktop Genetics is designing and testing an AI to perform surgery on the DNA of human patients. His team is currently working with laboratory users of CRISPR and DNA sequencing technologies to pilot the approach, which involves handling massive amounts of genomic data and all of its variants. In this talk Riley Doyle, CEO and technical lead at Desktop Genetics, will discuss the datasets that make every patient unique, outline unique outlooks on vectorising the drug-resistance behaviours of cancerous cells in ovarian tumours, and how his company looks to overcome the challenges involved in predicting molecular surgery at the genomic scale.

Gusztav (https://ventilator-python.github.io/) Belteki (MD, PhD) (http://www.belteki.co.uk/) on Analysing neonatal ventilator data with Python

Mechanical ventilators are widely used in intensive care. Even two decades ago they were be primarily mechanical devices whose “only” task was to inflate the patient’s lung. Recently, however, they have become equipped with powerful computers that provide sophisticated ventilator modes and display many parameters about ventilation and patient-ventilator interaction. Some of these ventilator modes are not routinely used in clinical practice and many of the parameters and reports are disregarded due to time constraints and lack of expertise. Data provided by the ventilator are almost never downloaded, stored or analysed.

I am interested in the analysis of the data that modern ventilators generate. My ultimate aim is to provide the clinician with simple and easy-to-interpret parameters that inform him or her about the quality of patient’s mechanical ventilation and the patient’s interaction with the ventilator over the previous hours or days of care. To get enough details, a high sampling frequency of the ventilator parameters over longer periods (hours or days) is required. This means that one needs to handle very large datasets requiring computing for analysis and interpretation.

I have been downloading raw data from the ventilators with 100/second sampling frequency over a total of 160 ventilator days so far. I have been using the Python computer language to analyse these data. Python has got several additional data analysis tools available that are also free to use. I am using some of these tools (pandas, numpy, matplotlib, scipy, sckit-learn ) to interpret my data. I am using these data for teaching nurses and junior doctors and also for feedback to the clinical care team. I am also using this method for research projects.

---

Lightning Talks:

Tariq Rashid (https://twitter.com/postenterprise) on Lessons in performance with pandas, numpy and JIT

Tariq has been trying to make his own text mining toolkit from scratch .. just for fun (and education). On his journey, he's hit several performance bumps and resolved a few. He'll give a short talk on his experience with Python, pandas, numpy, JIT compilation with numba and share some of his findings, some of which were pleasantly surprising.

---

Logistics:

Doors open at 6.30, talks start at 7pm (get there early as you have to sign-in via AHL's security), decamp to a pub at around 9pm.

We normally have > 200 folk in the room so there's plenty of people to discuss data science questions with!

Please unRSVP in good time if you realise you can't make it. We're limited by building security on number of attendees, so please free up your place for your fellow community members!

Follow @pydatalondon (https://twitter.com/pydatalondon) for updates and early announcements.