Austin H. Patton retweeted
How to transform UMAP from a black box into a glass box: by using a special type of deep network, we can now compute exact linear equivalents that reveal which features drive each point's position in the embedding.
@ArcadiaScience [1/8]
Austin H. Patton retweeted
I worked on a small project this weekend that bridges learning with usefulness. As mentioned in my earlier tweet, bioRxiv hosts over 311,000 manuscripts. A rapid method for identifying relevant papers would be handy.
Austin H. Patton retweeted
Job opportunity for evolutionary biologists:
🚨New @ArcadiaScience job alert!
We’re looking to add an evolutionary biologist to our platform team to help us develop methods to more effectively mine the tree of life! Apply now!
jobs.lever.co/arcadiascience…
Austin H. Patton retweeted
⏩ “That is what we think will be the key for our startups — we want to find the shortcuts through evolution”
@seemaychou talks strategy and areas of opportunity with @BIOS_Community. Full podcast here: buff.ly/48UjfRY
Austin H. Patton retweeted
We updated this preprint based on a bunch of awesome comments we got from too many people to name, and think it's become a much better manuscript! If you haven't taken a look yet, make sure to check out the updated version! biorxiv.org/content/10.1101/…
I'm excited to share this new preperint with @mwpen and @DocEdge85 about the unifying mapping approaches within and between species biorxiv.org/content/10.1101/…
Austin H. Patton retweeted
🚨New @ArcadiaScience job alert!
We’re looking to add an evolutionary biologist to our platform team to help us develop methods to more effectively mine the tree of life! Apply now!
jobs.lever.co/arcadiascience…
Austin H. Patton retweeted
Are you attending #TAGC24 and interested in comparative phylogenomics methods?
Chat with @AustinHPatton on Sat 3/9 about NovelTree, a Nextflow pipeline that outputs gene families, gene family trees, species trees, and more! 👇
Austin H. Patton retweeted
It's time to stop making t-SNE & UMAP plots. In a new preprint w/ Tara Chari we show that while they display some correlation with the underlying high-dimension data, they don't preserve local or global structure & are misleading. They're also arbitrary.🧵biorxiv.org/content/10.1101/…
Austin H. Patton retweeted
Tree sequences as a general-purpose tool for population genetic inference biorxiv.org/cgi/content/shor… #biorxiv_evobio
Austin H. Patton retweeted
I'm excited to share this new preperint with @mwpen and @DocEdge85 about the unifying mapping approaches within and between species biorxiv.org/content/10.1101/…
Austin H. Patton retweeted
Good at thinking through high leverage research projects that you’re happy to iterate on or sunset if they don’t pan out so you can test new approaches/insights? You might be the ideal Discovery Project Scientist @ArcadiaScience! Our next round of review begins in about a month so this is the time to apply!
jobs.lever.co/arcadiascience…
Austin H. Patton retweeted
📢Calling all current or aspiring scientist founders: a scientist role open @ArcadiaScience to get the ball rolling for a future start-up. Come build💪📈 jobs.lever.co/arcadiascience…
Austin H. Patton retweeted
Homology detection using a protein secondary structure-based large language model biorxiv.org/cgi/content/shor… #biorxiv_bioinfo
Austin H. Patton retweeted
Tertiary-interaction characters enable fast, model-based structural phylogenetics beyond the twilight zone biorxiv.org/cgi/content/shor… #biorxiv_evobio
Austin H. Patton retweeted
ROC and AUC are important concepts for evaluating classification models in business (e.g. lead scoring). In 6 minutes, I'll share what took me 60 days to figure out. Let's dive in.
1. ROC Curve: The ROC curve, which stands for Receiver Operating Characteristic curve, is a graphical representation used to evaluate the performance of a binary classifier system as its discrimination threshold is varied.
2. True Positive Rate (TPR): On the y-axis, the ROC curve plots the True Positive Rate (also known as sensitivity, or recall) which measures the proportion of actual positives that are correctly identified as such. It's calculated as TPR = TP / (TP + FN), where TP is true positives and FN is false negatives.
3. False Positive Rate (FPR): On the x-axis, the curve plots the False Positive Rate, which measures the proportion of actual negatives that are incorrectly identified as positives. It's calculated as FPR = FP / (FP + TN), where FP is false positives and TN is true negatives.
4. Thresholds: The ROC curve is created by plotting TPR against FPR at various threshold settings. A threshold in a classification algorithm is a point at which the decision is made whether a given instance belongs to a certain class.
5. Area Under the Curve (AUC): The area under the ROC curve is a measure of the effectiveness of a binary classification algorithm. An AUC of 1 represents a perfect classifier, while an AUC of 0.5 represents a worthless classifier.
6. AUC Calculation: The most common method for calculating the AUC of an ROC curve is by using the trapezoidal rule. This approach involves approximating the area under the curve by summing up the areas of trapezoids formed beneath the curve.
7. Interpretation: A curve closer to the top-left corner indicates a better performance. As the area under the ROC curve increases, the model is better at distinguishing between the positive and negative classes.
===
Ready to learn Data Science for Business?
I put together a free on-demand workshop that covers the 10 skills that helped me make the transition to Data Scientist: learn.business-science.io/fr…
And if you'd like to speed it up, I have a live workshop next week where I'll share how to use ChatGPT for Data Science: learn.business-science.io/re…
If you like this post, please reshare ♻️ it so others can get value.
Austin H. Patton retweeted
A non-adaptive explanation for macroevolutionary patterns in the evolution of complex multicellularity biorxiv.org/cgi/content/shor… #biorxiv_evobio
Austin H. Patton retweeted
Are you a creative scientist or a creator who loves science? I am hiring a Creative Director for @ArcadiaScience in Berkeley, CA
jobs.lever.co/arcadiascience…
Austin H. Patton retweeted
The enzymes for polyphosphate formation are present in nearly all bacteria, but only some store large amounts of polyP. Why? @ArcadiaScience we tackled this problem by looking at structural similarity of the protein catalyzing polyP formation 🧵 [1/12]
research.arcadiascience.com/…
Austin H. Patton retweeted
NovelTree: Highly parallelized phylogenomic inference and the application of this pipeline to TSAR research.arcadiascience.com/…
Austin H. Patton retweeted
Prior to #ProteinCartography, @JaseGehring and I tried to see if we could use protein structure to compare gene expression across species.
We've paused this work, but our explorations are summarized in this @ArcadiaScience pub:
doi.org/10.57844/arcadia-vw5…
🧵1/n





















