Nicola Romanò @nicolaromano@qoto.org
Senior lecturer at the Zhejiang-Edinburgh Joint Institute (ZJE) and Edinburgh University.
Undergraduate Programme Director, Biomedical Informatics at ZJE.
I teach #imageanalysis & #dataanalysis with #RStats & #python. I study #heterogeneity in #pituitary (and other) cells.
I'm also very interested in #reproducibility and #openscience.
Joined Oct 2022
Nicola Romanò
boosted
We have an opening for a technician on a KWF (Dutch cancer charity) funded project. Interested? More info in the link below.
Nicola Romanò
boosted
Revisiting the thorny issue of missing values in single-cell proteomics | https://arxiv.org/abs/2304.06654v1 #proteomics
Following up from last week's post, here is the continuation of our journey onto neural networks! In this post I discuss the basics of neural network training. 🤖
https://www.nicolaromano.net/data-thoughts/training-neural-networks/
Keep watching this space as more posts are in the pipeline! Next up: make your first neural network in Python!
Are you interested in the topic? Let me know what you would like to hear next
#neuralnetworks #ai #artificialintelligence #machinelearning #training #statistics #python
Nicola Romanò
boosted
Inuit children invented their own system for writing numbers which makes arithmetic easier. Now its in Unicode.
Nicola Romanò
boosted
Nicola Romanò
boosted
@nicolaromano This is refreshing to hear. I agree that we need to get real about peer review and its limitations. Our papers could all do with some deflation too. Right now any flaws are removed/minimised for fear that this will jeopardise the chance of publication (or negative data is simply left in the drawer). None of that is good for science.
I have been considering publishing my next article in #elife
I was not very convinced by their new #publishing method, but the more I think about it, the more I like it.
What convinced me is that I think of the way I review papers myself. I won't ever reject a paper unless there is something majorly wrong e.g. from an ethical point of view. Instead, I would rather spend time and give constructive and realistic feedback to improve the study.
This is because of two reasons:
1. If the study idea/methodology etc, is good but maybe is missing some key experiment, I think that the authors must have put a lot of effort, time and money into producing this. I have been through the "your work is not fancy enough for our prestigious journal" crap enough times that I will not engage in that. Ever. There is no reason your paper should not publish negative results if the study is well done.
Also, people's jobs and mental health depend on that, which is way more important.
Also, there are plenty of papers in "fancy journals" that are just piles of bs, so I really won't buy into shiny names (I have just spent an entire day trying to run code from several papers published in high-IF journals to no avail...).
2. If the study is poor, it is easy to say: "This is cr*p, straight reject". This just means the authors will submit elsewhere, hoping the next reviewer won't be bothered reading the paper in depth and will let it through. Even worse, this plays into the hands of #predatory journals. I would rather say this can be accepted after all of these major revisions.
The authors get useful feedback on how to improve their study; they might choose not to act on it, but at least I have made my part.
I would be interested in hearing other views on this.
Nicola Romanò
boosted
In the tidyverse, we work with a lot of people - each other and #rstats community members.
We wanted to document how we handle code review, so we've drafted a guide detailing our review principles!
We hope you find it useful, and we welcome your feedback!
Nicola Romanò
boosted
Nicola Romanò
boosted
Does anyone know of a piece of software to split multiple voices from a single audio file?
I know of things like lalal.ai to split vocals from music, and I can find a bunch of research papers about voice separation from Google and Facebook, but I'm struggling to find actual software I can run myself on my own audio files.
Nicola Romanò
boosted
Learn to segment your images with the Segment Anything Model (SAM) by Meta AI in just a few lines of #Python code! Check out my YouTube tutorial: https://youtu.be/fVeW9a6wItM
#imageSegmentation #MetaAI #segmentanything #microscopy
Nicola Romanò
boosted
Extending the sensitivity, consistency and depth of single-cell proteomics | https://www.nature.com/articles/s41592-023-01786-2 #proteomics
After a long hiatus (because, life...) I have updated my blog!
I have been meaning to write about neural networks for a while, so here it is! Part 1 of ... a certain number😜
In this first episode, I will guide you through what is a neural network, with a bit of history on the topic!
https://www.nicolaromano.net/data-thoughts/intro-neural-networks-pt1/
Stay tuned because other posts will be showing up in the upcoming weeks... we'll see a bit more of the theory of how these networks are trained, and then we'll code our own network in #python!
#ai #machinelearning #neuralnetworks #statistics #artificialintelligence
Nicola Romanò
boosted
“‘It’s always done like this, whether getting women to champion other women’s oppression or Jews who supported Hitler, it’s absolutely essential to get a token member of the targeted group to promote the extremist agenda’” #MAGAFascism https://buckscountybeacon.com/2023/04/the-truth-about-maga-activist-scott-presler/
Nicola Romanò
boosted
At one in six, it is more likely than not that you know someone who has had issues with fertility. However, given the taboo nature of the topic, it is much less likely that you know about it. Normalising talking about issues is a big step towards improving the lives and mental health of those you meet in this world. #infertility #MentalHealth
Nicola Romanò
boosted
🇫🇷 French newspapers published a large investigation on delivery workers in mid-sized towns.
Lots of interesting tidbits there, like the fact that they earn roughly 1500€/month for 10 hours of work, with no days off. That's half the minimum wage.
See here e.g. in Lorraine: https://www.republicain-lorrain.fr/societe/societe/livreurs-les-forcats-de-l-uberisation
Nicola Romanò
boosted
@nicolaromano two of my favourite topics!
(see e.g. https://tomstafford.github.io/psy-checklist/ and https://tomstafford.github.io/psy6422/)
We have a research assistant position to work on a study surveying how experimental study design and analysis are taught at the undergraduate level in the UK (position based at the University of Edinburgh, Scotland). The post is for four months full-time or equivalent part-time (e.g. eight. months 50%).
If you are interested or know someone who is, you can find more details here:
https://elxw.fa.em3.oraclecloud.com/hcmUI/CandidateExperience/en/sites/CX_1001/job/7014
#job #research #experimentalDesign #dataAnalysis #survey #statistics
Nicola Romanò
boosted
“Help,” cries the journalist, “I’m being held captive by Elon Musk!”
He calls out from the unlocked cage, door wide open, to which he holds the key in his own hands.
“Quickly,” he begs now, “I can’t bear the thought that someone might think I’m paying for this.”
He gestures to the searing blue legacy checkmark, a brand affixed not to his skin, but the cage.
Concerned passerby leave treats at the door, in the hopes he might free himself. But alas, he shall surely starve.
Nicola Romanò
boosted
I was under the impression (will look later for corroboration) that poor grammar in phishing serves as a filter: phishers don't want to waste their time on people who won't get duped, so in an attempt to filter those people out early they send initial e-mails that will look suspicious to those people. If that's true, then the most obvious way to interpret the reason from that article doesn't apply. However, there might be some more involved reasons: e.g. if text generators make interaction with the potential victim cheaper, the reason for the filter's existence might disappear.
Senior lecturer at the Zhejiang-Edinburgh Joint Institute (ZJE) and Edinburgh University.
Undergraduate Programme Director, Biomedical Informatics at ZJE.
I teach #imageanalysis & #dataanalysis with #RStats & #python. I study #heterogeneity in #pituitary (and other) cells.
I'm also very interested in #reproducibility and #openscience.
Joined Oct 2022
