DNA Barcoding - Science topic

I would do both. One is mitochondrial, the other nuclear, which is nice. Both work well on Cone Snails and Mammals. CO1 is great for most anything.

Hebert et al. (2003) established a 2% threshold for intraspecific variations. However, they used many different taxa in their study. Based on my opinion, the threshold should be group-specific since 2% does not work in other taxa.

Similarly, do not just rely on molecular sequences for species delimitation and better to integrate it with morphological and ecological data.

Hi Olivier,

I agree that it's not exactly the OE PCR. I prefer 25 because it's room temperature. The reagents remain stable for that amount of it and since there's no additional denaturation condition like "initial denaturation" I prefer to keep it at that.

You might also try heating your primer mix to 80C and immediately put them in ice just before adding them to the reaction. This is because sometimes the primers might have higher probability of forming dimers. You will end up in separating them at higher temperatures and maintain them as such by immediately transferring them to ice. This can be done for long primers. But I am not sure how long your barcode primer is, so you can take a call accordingly.

Quite possibly, that is called species with 'deep split' barcode divergence. We presented many examples in our North American Noctuoidea barcode library a single species with 18 BINs! First, you need to make sure there's no misID involved, very common mistake. Could be an overlooked species despite having the same morphology and genitalic structures in adults, but different ecology and behaviour, pheromones, spatial distributions, etc.

I don't have specific information on the Palawan Forest Turtle's DNA barcoding requirements. However, the number of fresh-hatched eggs needed for DNA analysis can vary based on the species and the specific research methods used. It's best to consult scientific literature or a geneticist specializing in this area for accurate and up-to-date information on this topic.

I forgot to mention that if your primers include a sequence that does not exist in the template dna then you must not include that extra sequence when calculating the annealing temperature...only use that part of the primer that can aneal exactly to the template sequence

With some sequencing technologies up to the first 50 bases read tend to be unreliable so do not pass quality control. This means that often your primers are already cropped from the 5' end. I find it best to just align the forward and reverse sequences and see how much overlap you are getting.

Using SPIEC-EASI for microbiome study, an input dataset in the form of an abundance table or a count matrix is needed. This matrix represents the abundance levels of different microbial taxa across multiple samples. Each row corresponds to a specific microbial taxon, and each column represents a sample.

Here's an example of how the input data format may look like:

```

Taxon Sample1 Sample2 Sample3 Sample4

Taxon1 10 5 0 3

Taxon2 2 8 7 1

Taxon3 0 4 6 2

```

In this example, there are three microbial taxa (Taxon1, Taxon2, and Taxon3) and four samples (Sample1, Sample2, Sample3, and Sample4). The abundance values represent the number of reads or the relative abundance of each taxon in the respective samples.

=========

Certainly! Here's an example R script that demonstrates network analysis using SPIEC-EASI for a microbiome study:

```R

# Install necessary packages

install.packages("SPIEC-EASI")

install.packages("igraph")

# Load libraries

library(SPIEC-EASI)

library(igraph)

# Read the abundance table or count matrix

abundance_table <- read.csv("path/to/abundance_table.csv", header = TRUE, row.names = 1)

# Preprocess the abundance table

# You may need to perform data normalization, filtering, or transformation based on your specific requirements

# Run SPIEC-EASI to infer the network

network <- spiec.easi(abundance_table)

# Get the adjacency matrix from the network

adjacency_matrix <- network$network

# Convert the adjacency matrix to an igraph object

graph <- graph.adjacency(adjacency_matrix, mode = "undirected", weighted = TRUE)

# Visualize the network

plot(graph, edge.width = E(graph)$weight, edge.color = "gray", vertex.size = 10, vertex.label = NA)

# Perform additional network analysis or visualization as needed

# You can calculate network properties, identify clusters, or customize the network visualization

# Save the network as a graphml file

write.graph(graph, file = "path/to/network.graphml", format = "graphml")

```

Make sure to replace `"path/to/abundance_table.csv"` with the actual path to your abundance table or count matrix file. Additionally, you may need to customize the script based on your specific preprocessing steps and network analysis requirements.

Good luck

credit AI tools

DESS is the most commonlhy used preservative for molecular studies.

The choice of DNA extraction method for dried herbal powders and aromatic herbs depends on several factors, including the type and quantity of plant material, the desired downstream application of the extracted DNA, and the available laboratory resources.

There are several commonly used DNA extraction methods for plant samples, including the CTAB method, commercial kits such as Qiagen DNeasy Plant Mini Kit, and modified versions of these protocols.

For dried herbal powders and aromatic herbs, a modified CTAB method may be a suitable choice for DNA extraction. This method involves grinding the plant material into a fine powder, adding a CTAB-based extraction buffer, and then proceeding with DNA purification using phenol-chloroform extraction and ethanol precipitation. This method can effectively remove polysaccharides, phenolic compounds, and other secondary metabolites that may interfere with downstream PCR-based applications.

Another commonly used method for DNA extraction from plant samples is commercial kits, such as the Qiagen DNeasy Plant Mini Kit. These kits are relatively easy to use and can provide high-quality DNA with consistent yields. However, they can be relatively expensive and may not be suitable for large-scale extractions.

Overall, the choice of DNA extraction method for dried herbal powders and aromatic herbs should be based on the specific requirements of the downstream application and the available laboratory resources.

Dear Mohammad,

An easier and faster way to do this is with ASAP (https://bioinfo.mnhn.fr/abi/public/asap/).

It will automatically delimit species in your dataset and provide you with a histogram on which the barcode gap is highlighted.

Best,

Denis

When it comes to marker genes, the bottle neck is not "how long (length) to sequence" but the problem is "how to sequence that long (length)".

If you have basic understanding of sequencing technologies and their benefits and shortfalls, you will understand this better.

So, I recommend to get that information, develop understanding and after that rethink over this question.

Hi Emmanuele,

The reason there is no one recommended enzyme is that there are LOTS that work really well. I'd advise a "hot start" enzyme since that will reduce primer artifacts. I'm also a fan of the ready-to-use PCR mixes (enzyme, buffer, MgCl2, etc. all in one tube). Makes it much easier to have consistent results.

You should have a really robust positive control, test out your primers and cycle conditions on non-precious samples first, and always include a full set of controls.

Good luck!

The fewer data you can use, the better; then your paper will be more elegant and enlightened :)

Did you check https://www.wikigenes.org/ ? It also provides specific references for each gene

HI My dear

http://biorad-ads.com/DNABarcodeWeb/ this URL can you generate BarCode for your sequence , may be simple and more helpful for you .

Well, I think the second method is more appropriate.You can prepare a list of plants fed according to the desired organism and then proceed to extract their DNA and then check the feces and match the extracted DNA. Then you will find out the amount of DNA of the desired plant by using quantification extraction methods. Of course, it is a time-consuming process.

It depends on the level and what you mean by genetic diversity. Within a single organism? No. Within a population? No. Within a species? Normally not. Between species - yes, but that would be genetic diversity in the sense of species diversity.

Cheers

Konrad

I don't see an issue using this type of over for your incubation step.

Just make sure the quality of the plastic tube doesn't deteriorate inside the oven. If the plastic tube warps and loosens the seal around the cap, your sample may start to evaporate due to the low to no humidity in the chamber. I would test with a blank tube and water to see if there are any changes before and after incubation

Thank you so much for your valuable comments.

Yes DNA barcoding is a roadmap

You can use ITS.2 primers :

Roberta Piredda Thanks for your answer. It's a useful tool for calculating barcoding gap actually. I'll try it more.

It depends on the question you are asking. If you are interested in systematics, than sample size is not really that important (certainly not in terms of statistical significance, or whatever). What you need is a sample of each taxon large enough to ensure that the character states you are observing are representative of the taxon and not of individual organisms.

If you are going to do barcoding at all, historically most methods have used a very nice cytochrome oxidase I gene because the primers have readily available for decades (see early Chris Simon lit).

However, I reason that barcoding is foolish because it depends on so little sequence. These days you should be doing a phylogeny with whatever multiple gene set you can obtain or generate sequences from - some nuclear and plenty of mtDNA. The clades in a molecular tree will be best if you use maximum likelihood techniques and generate a full tree. Then the branch lengths (corrected distances) will give you a good sense for whether the taxa look like different species (always a subjective judgment about just how distant taxa should be to be considered separate species). Better yet compare the molecular tree to a morphologically based one to see if your results make biological sense.

Dear Ayan,

You can simply concatenate your markers using software such as SequenceMatrix (http://www.ggvaidya.com/taxondna/), and then use this concatenated alignment for distance calculation with software such as MEGA X (https://www.megasoftware.net/).

Dear Lauren,

In this case it is better to say that identifications are ambiguous. Having multiple hits with the same (low?) similarity means that your sequences are not very similar to anything that is so far available in the database.

One way around this would be to download the most similar sequences (or what you think is taxonomically closer to your focal taxa) and build a phylogenetic tree. Such a tree would give you a more precise insight into the taxonomic affinity of your taxa than just a simple percentage threshold.

Agreed with Nouh Saad

Hi Trina:

I did not know if you were writing about different contigs of a same gene or fragments of different genes. Looking at your profile I saw that you are working with DNA barcodes of plants using multiple loci, so I assume your question is about using more than one gene to generate a single phylogeny.

If this is the case, yes, concatenation ("make one long stretch of sequence") of your gene sequences is one option. However, the most important step is to align each gene independently, and later concatenate the aligned sequences. The result of this concatenation of multiple genes will be a matrix that can be analyzed using your preferred phylogenetic method(s).

You can easily concatenate your sequences using the program Sequence Matrix, available here: http://www.ggvaidya.com/taxondna/

I hope it helps!

Thanks Miguel for the linking message. Hi Lawrence, in my opinion, @miniPCR is a versatile, precise and low cost equipment, useful for any process related to PCR and thermo block functions.

We have used in remote field work and in lab. Highly recomendable for education and portable research.

We currently have the https://www.minipcr.com/product/minipcr-lab-in-a-box-2/ with a Gyro mini centrifuge

Hi! Keya Modak

It is generally advisable to use the primer pair as it is and not interchange (like forward of ITS 1 and reverse of ITS 2).

However, if you really require so, I can suggest you to do an In-silico analysis of the forward primer from ITS 1 together with reverse primer from ITS 2.

Dear Brenden Holland thnak you so much for this collaboration proposition.

Good luck ... I am sorry to tell you that this species is not present in Med sea and this region the shark is very accesory Sp.

Hello Malitha,

you can check this article. They used SSRs for genetic diversity analysis. After that they selected 5 polymorphic SSRs for barcoding and for QR-code generation of the sertain cultivars of tea plant (go to page 11 to se the figure there).

Good luck!

If you mean bioinformatics resources /databases

NCBI

EMBL-EBI

DDBJ

BOLD (FOR, COI barcodes)

Try mitochondrial markers for barcoding

Hi Samitha,

Some thoughts on your sequences.

DA1TRNHPSBAfp

Starts with strong (>1000) well spaced base peaks dropping slowly from base 105 to about 330 bases with a signal/noise of 200. Quite good sequencing but this kit is capable of 900 bases of strong intensity signal. This is usually cause by insufficient primer or template. If this sample has primer dimer ( PD) then this will measure as DSdna so less template will go into the sequencing mix and the signal will die early and the remaining template will give a weak but readable signal

DA2TRNHPSBAFP

The signal strength is only 28 and s/n ratio is 4 so no readable sequence at all.The reaction has failed completely so possibly primer and template do not match

DI5MATKKIMM13FP

Clean strong base peaks up to base 53 ( strength 1600)then signal drops to zero.

This can happen with some secondary structure problems in the template dna but can also happen if you run out of primer. In this case I suggest that the sequencing primer has been used up sequencing PD

DI7MATKKIMM13FP

Good clean strong ( 3700) sequence up to 46 bases then dropping to baseline intensity. There is no huge unincorporated dye peak so the sequencing reaction is working but clearly no on the template dna so I think that we are sequencing a strong PD

De1TRNHPSBAFP

Very large dye peak ( mixed bases) at start of sequence (>4500) then no peaks. The sequencing reaction failed completely. Either no primer, no template or the wrong primer used in sequencing.

D13MATKKIMM13FP2

160 strong bases all Ns. We have 2 primers annealing in different places and producing 2 sequences. As it is unlikely that you supplied 2 templates so something is acting as a second primer or one primer is annealing in 2 places on the template dna ( unlikely), The sequence stops much too early. I do not know the cause for this one but if you had not told me that there was no PD I would say the pd has dissociated and caused F and R primers to anneal to the template and has used up the sequencing mix too early.

RecA C92f

Huge unincorporated dye peaks (17000 and 4500) at ends of sequence with low intensity clean sequence in between. I think that you have light PD which has sequences and used much of the sequencing primer and the rest has produced a weak but accurate sequence that has not been basecalled. The reason for not calling the bases is that the unincorporated base peaks are so high that the base calls are below the set cut off value of 5% of the highest peaks so they are ignored.

RECAC92F

Huge (>12000) unincorporated dye peak at start dropping very rapidly after 35 bases. Dye peaks at 85 and 120 bases indicate that the sequencing has failed. I think the primer was all used on the PD sequence and the unincorporate dbases are from the unused sequencing mix

Overall I feel that your problems are caused by PD using up all the sequencing primer not leaving enough to get a good signal from the template dna. Additionally pd is double stranded so will measure as DS dna when calculating the amount of dna to sequence so you are actually sequencing too little dna.

You may need to clean up your pcr ( use less primer for a start) or gel separate the template and clean it up before sequencing.

Re amplification must be treated with care. In early stage pcr every 10 cycles is 1000 times more product so if you use too much template or too many cycles the amplimer will self anneal and form smears of lonmers. I would use 1ul of first round product...dilute it into 100ul and use 1ul of this dilution. Set up 6 tubes of pcr and set for 24 cycles and remove a tube at 12,14,16.....24 cycles and see which cycle number gives good clean amplification.

A cleaner way is to design an internal primer set just inside the first pcr primers. They can be quite poor as primers because the template is almost all the correct amplimer.. Run 20 cycles of a 1% dilution of the first round product ( 1ul of 1/100 dilution) and it should give a clean product. There is no need to clean up the first round product between amplifications

I think, it is possible. So, you can try to do it as early as possible Dr @Mélodie Ollivier

Generally speaking, the scientific community's standards for species descriptions, at least for macroscopic organisms, include morphological or other non-molecular characters by which the species may be distinguished from its close relatives based on observation. One can describe species based only on fixed nucleotide differences, but doing so means that all future specimens may only be identified by sequencing them, as well. So in my opinion, you need to think about why you want to describe species based on barcodes before you start doing it. It is a slippery slope.

thank you for your answer Siva sankar Anisetti

Dear Mélodie,

I strongly recommend you take a look at the polymorphism in your group of taxa.

People have used, besides rbcl and ITS, the matK and trnH-psbA (Galimbert et al. 2014) genes as potential species-specific makers, and often more than one together. The trnH-psbA seems to be promising. However, that is a little bit different from animals where the COI has some clock-like passe of mutation across many taxa (it still challenging in cnidarians, though).

You might find out more about plant barcodes in Hollingswort et al. (2011) and Li et al. (2015). Especially for pollen identification, I've found some interesting reports and opinions in Bell et al. (2016), Galimbert et al. (2014) and Bruni et al. (2015).

My advice is to think about what criteria you are going to use for identification. Some of them are base on genetic distances (like K2P thresholds; ABGD), other on trees like the coalescent models (GMYC) and Poisson tree process (PTP) models, and some other on diagnostic characters (see review in Dellicour and Flot, 2018). The point is that all methods bring some bias and a consense of methods from different natures would lead to a more accurate delimitation.

If you are going to use a multi-locus approach, I would recommend the PHRAPL framework (See Jackson et al. 2017).

I hope you find this helpful.

Cheers

Bell et al. 2016:

Dellicour and Float 2018:

Galimbert et al. (2014)

Well, that "depends". There are several alternatives, depending on how your dataset looks like. Perhaps, it would be more effective if we ask ourselves what does the bootstrap means and how it's "calculated".

Considering that it is the number of times that a certain topology or node is recovered (or sort of...) we would conclude that you probably have too many equally likely topologies.

Then you can choose either tuning your analysis to "prefer" a solution to the detriment of any other or step back and think why you are getting this.

If you pick the first path, I would recommend this topic (https://www.researchgate.net/post/How_to_improve_low_bootstrap_values_in_phylogenetic_tree) where people are discussing something similar for amino-acids data, but it is not that different for nucleotide sequences. Strategies usually include increase the replication numbers; replicate terminal taxa (both new samples and artificially created ones); tuning up parameters; reconsidering your alignment and their algorithm; trim out the sequences edges; picking up a different tree estimation methodology, maybe maximum likelihood or Bayesian frameworks...

However, I would recommend you to think a little bit about it. Why are you getting such results? If you are not screwing things (I believe not), the phylogenetic signal may be too low (i.e. very conserved gene/low informative sequence), then any technical improvement or tuning would result in a methodological artifact, not the real meaning of the thing. If you realize that your data is too poor then the obvious thing is to get more info on that. If it is not possible then just report it. Keep one eye on that uncertainty and you should be fine.

Good luck

If you go through the previous plant barcoding papers, you would realize that barcoding, per se, did not work as well in plants as in animals. If you want to work on specific cpDNA regions of your desired family, I would suggest you to go through previous gene specific marker works on the specific family. Also, you can check the Barcode of Life websites for further information.

The short answer would be no. COI is a single maternally inherited marker, so it may provide relevant information on the directionality of introgression, or give you an idea about the geographic origin or the number of independent hybridisation events (in relation to the parental species' diversity). But identying hybrids themselves critically depends on nuclear genetic markers (and then COI can provide the additionally useful information stated above). Morphology may or may not be a good advisor in any case. Hope this helps.

Dear Derradj,

Thank you very much for your collaboration offer.

Since the last records of C paludivagus that I know date from several decades ago, I had even thought that this species was extinct.

From your address I suposse that the material will be from the mountains near Constantine.

Best

Luismi

support values would be low for deep branches and/or they would be unresolved (as Artur already mentioned). And COI is NOT suited to resolve deep branches. For closely related species it is fine, but also for closely related species you always have the problem that if you analyze a single gene, you will only receive a gene tree. Not the underlying species tree and that might be quite different

shamelessly promoting my own tool for this here: https://github.com/cdoorenweerd/PyCOIStats

It is better to focus on Dmin_NN (minimum distance to nearest neighbor) and Dmax (maximum intraspecific distance) values, which PyCOIStats also provides. Hope you find it useful

It is a very important step, if implemented in India. There are more duplicacy in the variety exist in the country.

Sergey Viktorovich Pushkin right statements. It really depends on the age of the samples. During my PhD thesis, I was dealing with old alcohol arthropods with an age of 15 to 30 years and it was impossible to extract DNA from them as I was really eager to do that. Instead I used a DNA extraction method to clear these specimens to inspect them under microscope for accurate identification for further biodiversity calculations. Just check the link below:

Maybe it is interesting for you colleagues in soil zoology.

Principal Component Analysis (PCA) is normally able to gather similar data and discriminate between different sets. We successfully did it with coffee aroma analysis using GC-MS.

We exactly CANNOT identity new species based on barcoding! Barcoding data could have a signal for existing of a new species, it's true. Barcodind identifies some BINs, nobody known what is it, and they change all the times after adding new sequences. Regading these strange products as something species-like is clearly contradicting to the main approach declared in the Preambule to the International Code of Zoological Nomenclature created for STABILITY.

ITS works!

Hello Shuaichen Liu Matthew Dunn ,

I am studying a similar technique and had same question.

A paper i read talks about adding about 5 different 10nt long barcode in 5' end of the primer. This is called compressed barcoding space. According to this concept, one can create few number of barcodes and use its permutations to barcode many primers. I was wondering if it will cause any issues during PCR.

Can you please tell me from your experience how feasible is such experiment.

Incase, you are wondering what i'm reading https://www.biorxiv.org/content/10.1101/2020.04.06.025635v1

it is wide scale pooled sequencing for covid testing.

Thanks a lot Dear Dr. Shahnawaz Gul , I really appreciate your contribution. Regards

I agree. Look for example in GenBank which marker is most commonly used. Chloroplasts, Internal transcribed spacer 1 or 2 (ITS1, ITS2) and 18s ribosomal RNA gene are commonly used, but look up genes relevant to the genera you're interested in. For classification the same thing is relevant, but look for papers and see which markers the best ones used to estimate phylogenies.

Use one script "filter_otus_from_otu_table.py" in QIIME pipeline. You can find the detailed description at http://qiime.org/scripts/filter_otus_from_otu_table.html.

If data are not normally distributed, Wilcoxon Signed-Rank Test is used in place of Dependent t-test. See this link to perform Wilcoxon Signed-Rank Test with SPSS.

https://statistics.laerd.com/spss-tutorials/wilcoxon-signed-rank-test-using-spss-statistics.php

How does fingerprints work with remote sensing and DNA Barcodes?

Muhammad Sufian sir

i think this paper will be workable for you.

Hello Abdullah,

You may assess the potential success or failure of the universal primers described by Folmer et al. (1994) based on the results of the enclosed article.

Exactly, since endemic species are not universal but variable based on the geography, there can not be a standard database to have the information in one place.

In you original question you did not mention about which species you are interested in, animals; plants etc. thus referring you to any database is not logical. Also, most of the databases contains genomic data and metadata about environmental parameters, genome content etc. But I have not seen any database which contains the barcodes/primer information, and secondary metabolites.

Ofcourse you can use universal primers to target the species in question, and there are many out there on innternet or in published papers.

I dont think you can find all at one place, what you want to find, as of today. However, it would be a good database to make and have all such information in one place. May be you can make one and publish.

You can use

Check this one

http://userpages.fu-berlin.de/digga/p4b.pdf

Dear Chris De Ruyck

This response may be a little late. However there are faecal preservation buffers that can protect nucleic acids for 2 years at room temperature and prevent microbial growth.

Depending on your sample amount, there are smaller or larger tubes available. The smaller tubes will also come with glass beads and are compatible with any isolation workflows requiring homogenization.

Small tubes for preservation: https://norgenbiotek.com/product/fecal-dna-collection-preservation-mini-tubes

Larger tubes for preservation: https://norgenbiotek.com/product/stool-nucleic-acid-collection-and-preservation-tubes

Attached is more information on preservation of the gut microbiome diversity with fresh, frozen, TE-buffer, or Norgen preserved samples.

Hope that helps.

JP

Freeze for a period of time

Hey,

may I ask for what purpose you need this synthetic dataset and how shall it look like and what did you do with your "real" dataset (methodically)?

Regards,

André

I have read the question carefully and what you have wrote in brackets does not mean singleton species.

Sorry I don't know if it will help you, although i send u.

matK-QR classifier: a patterns based approach for plant species identification

Ravi Prabhakar More, Rupali Chandrashekhar Mane, and Hemant J. Purohit

Use of ITS2 Region as the Universal DNA Barcode for Plants and Animals

Hui Yao, Jingyuan Song, [...], and Shilin Chen

You can see

This method sort sequences into putative species based on pairwise distance, you can work with distance matrix or you can use. the alignment that the ABDG web serve make the distance matrix before analyzes. The ABDG web serve separates the species based on a range of maximum intraspecific distance. I mean, the ABDG consider different value of maximum intraspecific divergence to separete species (graph below) .You can click each point (yellow or red) to see which species were delimited for each maximum intraspecific divergence. If you know the intraspecific divergence of the gene in your taxonomic group, you can modify the parameter on web serve and maybe you get better results. Other important point is: the ABDG works better if you use the sequences closer phylogenetic each others(for e.g use sequences from the same class or genus). Because the substitutions rates (consequently intraspecific distance ) can vary among taxonomy groups. For this reason, I recommend exclude the outgroup from alignment before analyses. Since the greater pairwise distance between ingroup and outgroup can "confuse " ABDG.

Hi Ammar, there is a reason. Cox1 gene is pretty good barcode marker for most groups of animals. However, it does not work so well for other groups such as plants (where rbcL is preferred), fungi (ITS rDNA is preferred), not even speaking about various groups of protists! For many groups, it does not have sufficient resolution (i.e. it cannot distinguish closely related species), universality or/and practicality.

I don't consider it wise to use whatever barcode markers you wish. Your choice should be guided by research on potential barcode markers carried out in your taxonomic group. If you are working on animals, plants or fungi, you can begin with standard markers for these, which are cox1, rbcl, and ITS, respectively. However, specialists on many other groups (especially protists) still did not agree on standard markers for those particular groups.

For example, diatoms are extremely species-rich group (cca 100 000 spp.) so it is difficult or perhaps impossible to find single barcode marker which would be sufficient in terms of universality, practicality and resolution. Thus we are forced to switch to dual-locus barcode system (and we did not yet agreed on which two markers should be selected as standard barcode markers for diatoms).

Hi, DNA barcoding is a very cool method for species identification but also for detection of taxonomic inconsistencies at the species level. Hovever, if you want to work on higher taxonomic levels, you need to perform the phylogenetic analysis and for this the variability of the barcodes (COI) is definitely not sufficient (e.g. due to saturation of substitutions). Besides you need to use several independent (nuclear) markers that complement the mitochondrial markers (which are not independent as they are inherited as one locus). Hope I could help.

Best,

Michal

Most journals (and funding sources) require you to make sequence data publicly available when you publish in a peer-reviewed scientific journal. Part of the collaborative nature of science, adding to the known data collection, etc. It's unprofessional to not make your data available.

A thesis isn't technically a peer-reviewed publication so you don't have to publish your sequences. But you can't cite your unpublished thesis.

That's what's normal for my field of research. Other fields might have different conventions.