if AI is so great why cant it unravel mysteries of genes, phylogenic placement, protein fold, all that?no AI tools are being used in these departments of biological researchresearchers use computer derived math invented back in early 2000s
>>17080178AI is working on those problems already. Reality is just slower to work with than math and has no easy ways to train like math or coding. AI models are in full use in major biomedical research for instance.
>>17080179>AI models are in full use in major biomedical research for instance.maybe but there is no proof they are being used in:>phylogenetic research>protein foldingis AI being taught billions of cancer pictures so it can predict if any picture given to it is cancer or not?yes, it is. but this is nothing more than visual learning a human can do as well, just not with such a huge number of pictures and not quicklyand this particular thing doesnt help with the problem of questions in phylogeny
>>17080183If you wanna consider phylogeny specifically you might initially have a minor training problem. Who says that the data is properly ordered to begin with? That would soon have us examine mutation rates however, ofc considering that mutation rates are not entirely a fixed parameter ... which however could leave us with an interesting point: Are there learnable rules to mutation rates?
Nigga ever heard of Alphafold?
>>17080204is it AI
>>17080208It is a transformer neural network - the same architecture LLMs are based on
>>17080183>there is no proof they are being usedhave you even looked for it, lmao?
>>17080183AI is used on both of those
>>17080234like I literally just open biorxiv, click evolutionary biology, click the very first result blindly, "An integrative cardio-informatics approach identifies positionally conserved ancestors of human lncRNA genes transcribed across vertebrate hearts"I scroll down the pdf>A neural network model was developed based on diverse groups of human lncRNAs and applied across vertebrate species>The classification model was implemented using TensorFlow and the Keras Functional API.>Then, the model`s classification performance was compared against LncFinder [45]and PreLnc [46], two tools with well-demonstrated accuracy, robustness, and cross-speciesapplicability. VertLncRNAchecker consistently recognized a higher percentage of lncRNAgenes as ‘true’ in diverse vertebrate genomes [...] Moreover, as VertLlncRNAchecker is organismagnostic, it successfully classified annotated lncRNA genes as ‘true’ in species not included in the LncFinder [...]These metrics demonstrated the superior performance and suitability ofVertLncRNAchecker. (the summary doesn't even do it justice, see pic. ~100% detection vs "usually better than a coin flip" for classic tools)>For PCR primer design, the mature lncRNA sequences of all the microsyntenically conserved DNA regions were predicted with SpliceBERT [36] and the computationally predicted sequences were used as input in Primer3Plus [39]. [...] Sequence identity between the obtained amplicons and the computationally predicted sequences was estimated using CLUSTALW [40], and coding potential was evaluated using CPC [35](SpliceBERT is a specialized LLM, CPC is a ML classifier tool)oh and you can bet AIs wrote all the integration scripts code and the web visualizer and API mentioned elsewhere in the paper, probably also to train their custom model.
>>17080234machine learning in phylogenyhttps://www.tutorsindia.com/blog/phylogenetic-analysis-using-machine-learning/Application of machine learning:Machine learning has found various applications in the field of technology-driven research. One such usage of machine learning is in the inference of the phylogenetic tree. In a recent study, researchers utilized the machine learning method to predict the best model for the most common prediction task: phylogenetic tree reconstruction for a given collection of sequences (Abadi 2020).A research study gave a detailed analysis of plant diversity trends to date, demonstrating that using machine learning to forecast future diversity could be tremendously beneficial. They applied machine learning approaches to phylogenetic diversity in vascular plants (Park 2020). Bhattacharjee et al., for the very first time, demonstrated the potential and feasibility of using deep learning techniques to compute distance matrices. The study evaluated both matrix factorization (ME) and autoencoder (AE) and aimed to develop improvised models for better results. They showed that both these methods are reliable and can be applied for handling large-scale datasets. They also highlighted the ability of these techniques over the heuristic-based techniques to automatically learn complicated inter-variable associations. Their research can also be used as a model for applying machine learning methods to the phylogenetic analysis (Bhattacharjee 2020).In another research, a machine learning framework was developed to rank the neighbouring trees in accordance with their prosperity to increase the likelihood. They applied multiple features and utilized machine learning to improve an optimal tool. The study suggested specific ways to practice machine learning algorithms in phylogenetic analysis.
>>17080269Furthermore, they presented a methodology that can significantly speed up tree-search algorithms without sacrificing accuracy(Azouri 2021).A recent review focused on the application of machine learning-based techniques in the data analysis of the human microbiome. It provided an insight into the plethora of advantages that machine learning has to offer over classical methods. The most common techniques covered in this review involved Support Vector Machines, Random Forest, k-NN and Logistic Regression. This review suggested how machine learning can contribute to the development of new models that can be useful in predicting classifications in the field of microbiology, inferring host phenotypes to predict diseases and characterization of state-specific microbial signatures using microbial communities(Macros 2021).Future scope:All the recently conducted research emphasizes the potential of artificial intelligence and machine learning in the inference of phylogenetic trees. These studies highlight the ability of machine learning in elevating the scale of analyzed datasets and the degree of sophistication in evolutionary models(Azouri 2021). Machine learning can thus be of high interest in the near future and contribute to efficient phylogenetic analysis in biological research.
>>17080269>>17080271Note the dates also, 2020 and 2021 lol
>>17080262>released yesterday>This article is a preprint and has not been certified by peer review
>>17080278Yes, that's what you'd expect to see when you click the first result on biorxiv or arxiv. I'm not really worried that this paper which is a collaboration of a dozen researchers from half a dozen institutes will fail review though.
I use AI in all my phrenology and eugenics work.In fact, all I use is AI.Proof.
>>17080178>no AI tools are being used in these departments of biological researchare you sure about that?
>>17080344cant find any AI tools on that departmentmaybe they are secret
NEURAL NETWORKS ARE USED IN BIOTECH, BIOCHEM, BIOINFORMATICS AND MOLBIOL ALL THE TIME DUMBASS NIGGER
>>17080178>no AI tools are being used in these departments of biological researchColossal Biosciences has developed Genomorph to simulate phenotopic variation as part of their efforts to revive a viable population of the Dodo through cloning, while only having access to one complete genome.
