Last year I dedicated three blogposts to mass spectrometry-based proteomics (MS-proteomics) data analysis: PEPTIDE SEARCH ENGINES THE PEPTIDE-SPECTRUM MATCH DATA LOSS AND WAYS TO CONTROL IT To continue with this subject, I now discuss how using deep learning algorithms to predict fragment (MS2) ion mass intensities increases the number of peptide sequences identified by a peptide search engine. From the handful of deep learning-based MS2 ion intensity predictors reported so f

In this blogpost I explain the architecture of DeepVariant (Google Brain team). Published in 2018, DeepVariant is a neural network-based variant caller that discovers genomic variants with 99.9% accuracy. A universal SNP and small-indel variant caller using deep neural networks   —2018 Unlike Bayesian-based variant callers (e.g., HaplotypeCaller), DeepVariant discovers SNPs and INDELs regardless of the sequencing technology used: Illumina short reads PacBio long reads Oxford

The deep learning architecture named Transformer first appeared in the literature 2017. You can check out the publication by clicking on this hyperlink: Attention Is All You Need — 2017 Conceived to overcome the limitations of the natural language processing models of the day, the Transformer architecture went from making text translation and next-word prediction more accurate, to inspiring the development of chatGPT (OpenAI). (GPT stands for Generative Pre-trained Transfo

In my previous blogpost, I explained what recurrent neural networks (RNNs) are. To read more about this topic, click on the following hyperlink: RECURRENT NEURAL NETWORKS RNNs are a specialized form of the classic feed forward network, which I explained in WHAT IS AN ARTIFICIAL NEURAL NETWORK? . Used to translate words or summarize text, RNNs ingest sequential inputs, such as the words in a sentence or paragraph ( Figure 1 ). Figure 1.  RNNs are feedforward networks with a hi

In this blogpost I talk to you about convolutional neural networks ( CNNs ), a specialized deep learning architecture used in computer vision. When processing images, CNNs outperform feedforward networks (FNNs) because they overcome the curse of dimensionality . FNNs assign an artificial neuron to each pixel in an image, and, because FNNs are densely interconnected, the number of neurons required to process a large image increases disproportionally (multidimensionally). This

Humanity was for centuries under the spell of smallpox, a deadly disease caused by a virus named variola . Smallpox was eradicated in 1977, but for this to happen, vaccine technology had to be invented. And it was a worldwide vaccination campaign that drove smallpox to extinction . Nothing else would have eliminated smallpox. A human-specific Orthopoxvirus, variola was encoded by a DNA genome. To propagate continuously, variola established endemicity in highly populated hum

THE GREAT SICKNESS Centuries ago, a deadly epidemic swept through Mesoamerica. Those who lived through it, called this malady cocoliztli , which means sickness or pestilence in the Nahuatl language. It was a hemorrhagic fever . One which in the spring of 1545, appeared out of nowhere in central Mexico's highlands. Cocoliztli spread with the wind, stopping only because the roads ended. Sonora to the north. Guatemala in the far south. Estimates from population censuses put th

ARTIFICIAL NEURAL NETWORKS Artificial neural networks , also known as deep learning networks, are a type of machine learning algorithm, which can extract exceedingly complex features from input data. Examples of input data features are the words in a sentence or the patterns in an image. In analogy to the huma n brain’s cognitive processes, deep learning networks acquire the ability to identify feature patterns ( learn )  by modulating the activation state of the artificial n

I provide in this post a high-level introduction to artificial neural networks in the context of MS-proteomics.

The grammar and sentence construction rules in scientific writing are well-defined and accept little or no variation. It is therefore...

This blogpost is about the first two components in a scientific research article ( paper ) — the title and abstract . Below I define...

This blogpost is a postscript  to the previous one — “THE PEPTIDE-SPECTRUM MATCH” — ,  in which I wrote about the peptide-spectrum match...

In my previous blogpost “PROTEOMICS SEARCH ENGINES”   I wrote about peptide search engines in the context of the data-dependent acquisition (DDA) approach used in shotgun proteomics. In this blogpost I discuss the strategies used by peptide search engines to mitigate the false discovery rate when analyzing DDA data. For those not familiar with proteomics jargon, the abbreviations used throughout the text are: Data-dependent acquisition ( DDA ) False discovery rate ( FDR ) Fra

In this blogpost I talk about peptide search engines—the algorithms used in MS-proteomics to assign peptide sequences to raw mass spectra. For those not familiar with proteomics jargon, the abbreviations used throughout the text are: Data-dependent acquisition ( DDA ) Data-independent acquisition ( DIA ) Mass spectrometry-based proteomics ( MS-proteomics ), AKA shotgun proteomics Peptide fragmentation spectra (MS2) Precursor ion spectra (MS1) Peptide-spectrum match ( PSM )

But mass spectrometry-based proteomics (MS-proteomics), as we know it, was not born in 1995, which is when the term proteome first...