metadata
language:
- en
license: apache-2.0
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:36470
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: What are the targets of avapritinib?
sentences:
- >-
Origins of DNA replication on eukaryotic genomes have been observed to
fire
during S phase in a coordinated manner. Studies in yeast indicate that
origin
firing is affected by several factors, including checkpoint regulators
and
chromatin modifiers. However, it is unclear what the mechanisms
orchestrating
this coordinated process are. Recent studies have identified factors
that
regulate the timing of origin activation, including Rif1 which plays
crucial
roles in the regulation of the replication timing program in yeast as
well as in
higher eukaryotes. In mammalian cells, Rif1 appears to regulate the
structures
of replication timing domains through its ability to organize chromatin
loop
structures. Regulation of chromatin architecture by Rif1 may be linked
to other
chromosome transactions including recombination, repair, or
transcription. This
review summarizes recent progress in the effort to elucidate the
regulatory
mechanisms of replication timing of eukaryotic replicons.
- >-
Avapritinib (AYVAKIT™) is a potent and selective tyrosine kinase
inhibitor of
platelet-derived growth factor receptor alpha (PDGFRA) and KIT
activation loop
mutants. It is being developed by Blueprint Medicines for the treatment
of
gastrointestinal stromal tumours (GIST), solid tumours and systemic
mastocytosis. Avapritinib is approved in the USA for PDGFRA exon 18
(including
D842V) mutant GIST and is undergoing regulatory assessment in the USA as
a
4th-line treatment for GIST. Avapritinib is also undergoing regulatory
assessment in the EU for PDGFRA D842V mutant GIST. This article
summarizes the
milestones in the development of avapritinib leading to this first
approval for
the treatment of adults with unresectable or metastatic GIST harbouring
a PDGFRA
exon 18 mutation, including PDGFRA D842V mutations. Clinical development
of
avapritinib is also underway for the treatment of systemic mastocytosis
and
late-stage solid tumours in several countries.
- >-
PURPOSE: Primary chemotherapy provides an ideal opportunity to correlate
gene
expression with response to treatment. We used paraffin-embedded core
biopsies
from a completed phase II trial to identify genes that correlate with
response
to primary chemotherapy.
PATIENTS AND METHODS: Patients with newly diagnosed stage II or III
breast
cancer were treated with sequential doxorubicin 75 mg/M2 q2 wks x 3 and
docetaxel 40 mg/M2 weekly x 6; treatment order was randomly assigned.
Pretreatment core biopsy samples were interrogated for genes that might
correlate with pathologic complete response (pCR). In addition to the
individual
genes, the correlation of the Oncotype DX Recurrence Score with pCR was
examined.
RESULTS: Of 70 patients enrolled in the parent trial, core biopsies
samples with
sufficient RNA for gene analyses were available from 45 patients; 9
(20%) had
inflammatory breast cancer (IBC). Six (14%) patients achieved a pCR.
Twenty-two
of the 274 candidate genes assessed correlated with pCR (p < 0.05).
Genes
correlating with pCR could be grouped into three large clusters:
angiogenesis-related genes, proliferation related genes, and
invasion-related
genes. Expression of estrogen receptor (ER)-related genes and Recurrence
Score
did not correlate with pCR. In an exploratory analysis we compared gene
expression in IBC to non-inflammatory breast cancer; twenty-four (9%) of
the
genes were differentially expressed (p < 0.05), 5 were upregulated and
19 were
downregulated in IBC.
CONCLUSION: Gene expression analysis on core biopsy samples is feasible
and
identifies candidate genes that correlate with pCR to primary
chemotherapy. Gene
expression in IBC differs significantly from noninflammatory breast
cancer.
- source_sentence: List markers for autophagy.
sentences:
- >-
C/EBPbeta is an intrinsically repressed transcription factor that
regulates
genes involved in differentiation, proliferation, tumorigenesis, and
apoptosis.
C/EBPbeta acts as a repressor that is turned into an activator by the
Ras
oncoprotein through phosphorylation of a MAPK site. C/EBPbeta activation
is
accompanied by a conformational change. Active and repressive C/EBPbeta
interacts with multisubunit Mediator complexes through the CRSP130/Sur2
subunit.
The CRSP130/Sur2 subunit is common to two distinct types of Mediator
complexes,
characterized by CRSP70 and CDK8 proteins as transcriptionally active
and
inactive Mediator, respectively. Knockdown of CRSP130/Sur2 prevents
Mediator
binding and transactivation through C/EBPbeta. Oncogenic Ras signaling
or
activating mutations in C/EBPbeta selects the transcriptionally active
Mediator
complex that also associates with RNA polymerase II. These results show
that a
Ras-induced structural alteration of C/EBPbeta determines differential
gene
activation through selective interaction with distinct Mediator
complexes.
- >-
Sporadic inclusion body myositis (sIBM) and polymyositis (PM) are
characterized
by muscle inflammation, with sIBM showing additional degenerative
alterations.
In this study we investigated human beta defensins and associated TLRs
to
elucidate the role of the innate immune system in idiopathic
inflammatory
myopathies (IIM), and its association with inflammatory and
degenerative
alterations. Expression levels of human beta-defensin (HBD)-1, HBD-2,
HBD-3 and
TLR2, 3, 4, 7 and 9 were analysed by quantitative real-time PCR in
skeletal
muscle tissue. Localization of HBD-3, collagen 6, dystrophin,
CD8-positive
T-cells, CD-68-positive macrophages, β-amyloid, the autophagy marker
LC3, and
TLR3 were detected by immunofluorescence and co-localization was
quantified.
HBD-3 and all TLRs except for TLR9 were overexpressed in both IIM with
significant overexpression of TLR3 in sIBM. HBD-3 showed characteristic
intracellular accumulations near deposits of β-amyloid, LC3 and TLR3 in
sIBM,
and was detected in inflammatory infiltrations and macrophages invading
necrotic
muscle fibres in both IIM. The characteristic intracellular localization
of
HBD-3 near markers of degeneration and autophagy, and overexpression of
endosomal TLR3 in sIBM hint at different pathogenetic mechanisms in
sIBM
compared with PM. This descriptive study serves as a first approach to
the role
of the innate immune system in sIBM and PM.
- >-
Circular RNAs (circRNAs) are a large type of noncoding RNAs
characterized by
their circular shape resulting from covalently closed continuous loops.
They are
known to regulate gene expression in mammals. These tissue-specific
transcripts
are largely generated from exonic or intronic sequences of their host
genes.
Although several models of circRNA biogenesis have been proposed, the
understanding of their origin is far from complete. Unlike other
noncoding RNAs,
circRNAs are widely expressed, highly conserved and stable in cytoplasm,
which
confer special functionalities to them. They are known to serve as
microRNA
(miRNA) sponges, regulators of alternative splicing, transcription
factors and
encode for proteins. The expression of circRNAs is associated with
several
pathological states and may potentially serve as novel diagnostic or
predictive
biomarkers. CircRNAs are known to regulate the expression of numerous
cancer-related miRNAs. The circRNA-miRNA-mRNA axis is a known regulatory
pattern
of several cancer-associated pathways, with both agonist and antagonist
effects
on carcinogenesis. In consideration of their potential clinical
relevance,
circRNAs are at the center of ongoing research initiatives on cancer
prevention
and treatment. In this review, we discuss the current understanding of
circRNAs
and the prospects for their potential clinical application in the
management of
cancer patients.
- source_sentence: Where is X-ray free electron laser used?
sentences:
- >-
The phase problem is inherent to crystallographic, astronomical and
optical
imaging where only the intensity of the scattered signal is detected and
the
phase information is lost and must somehow be recovered to reconstruct
the
object's structure. Modern imaging techniques at the molecular scale
rely on
utilizing novel coherent light sources like X-ray free electron lasers
for the
ultimate goal of visualizing such objects as individual biomolecules
rather than
crystals. Here, unlike in the case of crystals where structures can be
solved by
model building and phase refinement, the phase distribution of the wave
scattered by an individual molecule must directly be recovered. There
are two
well-known solutions to the phase problem: holography and coherent
diffraction
imaging (CDI). Both techniques have their pros and cons. In holography,
the
reconstruction of the scattered complex-valued object wave is directly
provided
by a well-defined reference wave that must cover the entire detector
area which
often is an experimental challenge. CDI provides the highest possible,
only
wavelength limited, resolution, but the phase recovery is an iterative
process
which requires some pre-defined information about the object and whose
outcome
is not always uniquely-defined. Moreover, the diffraction patterns must
be
recorded under oversampling conditions, a pre-requisite to be able to
solve the
phase problem. Here, we report how holography and CDI can be merged into
one
superior technique: holographic coherent diffraction imaging (HCDI). An
inline
hologram can be recorded by employing a modified CDI experimental
scheme. We
demonstrate that the amplitude of the Fourier transform of an inline
hologram is
related to the complex-valued visibility, thus providing information on
both,
the amplitude and the phase of the scattered wave in the plane of the
diffraction pattern. With the phase information available, the condition
of
oversampling the diffraction patterns can be relaxed, and the phase
problem can
be solved in a fast and unambiguous manner. We demonstrate the
reconstruction of
various diffraction patterns of objects recorded with visible light as
well as
with low-energy electrons. Although we have demonstrated our HCDI method
using
laser light and low-energy electrons, it can also be applied to any
other
coherent radiation such as X-rays or high-energy electrons.
- >-
We study, using simulated experiments inspired by thin-film magnetic
domain
patterns, the feasibility of phase retrieval in x-ray diffractive
imaging in the
presence of intrinsic charge scattering given only photon-shot-noise
limited
diffraction data. We detail a reconstruction algorithm to recover the
sample's
magnetization distribution under such conditions and compare its
performance
with that of Fourier transform holography. Concerning the design of
future
experiments, we also chart out the reconstruction limits of diffractive
imaging
when photon-shot-noise and the intensity of charge scattering noise are
independently varied. This work is directly relevant to the
time-resolved
imaging of magnetic dynamics using coherent and ultrafast radiation from
x-ray
free-electron lasers and also to broader classes of diffractive imaging
experiments which suffer noisy data, missing data, or both.
- >-
INTRODUCTION: Most cases of Charcot-Marie-Tooth (CMT) disease are caused
by
mutations in the peripheral myelin protein 22 gene (PMP22), including
heterozygous duplications (CMT1A), deletions (HNPP), and point
mutations
(CMT1E).
METHODS: Single-nucleotide polymorphism (SNP) arrays were used to study
PMP22
mutations based on the results of multiplex ligation-dependent probe
amplification (MLPA) and polymerase chain reaction-restriction fragment
length
polymorphism methods in 77 Chinese Han families with CMT1. PMP22
sequencing was
performed in MLPA-negative probands. Clinical characteristics were
collected for
all CMT1A/HNPP probands and their family members.
RESULTS: Twenty-one of 77 CMT1 probands (27.3%) carried
duplication/deletion
(dup/del) copynumber variants. No point mutations were detected. SNP
array and
MLPA seem to have similar sensitivity. Fifty-seven patients from 19
CMT1A
families had the classical CMT phenotype, except for 1 with concomitant
CIDP.
Two HNPP probands presented with acute ulnar nerve palsy or recurrent
sural
nerve palsy, respectively.
CONCLUSIONS: The SNP array has wide coverage, high sensitivity, and
high
resolution and can be used as a screening tool to detect PMP22 dup/del
as shown
in this Chinese Han population.
- source_sentence: Which syndromes are associated with heterochromia iridum?
sentences:
- >-
BACKGROUND: The three-dimensional (3D) structure of the genome plays a
crucial
role in gene expression regulation. Chromatin conformation capture
technologies
(Hi-C) have revealed that the genome is organized in a hierarchy of
topologically associated domains (TADs), sub-TADs, and chromatin loops.
Identifying such hierarchical structures is a critical step in
understanding
genome regulation. Existing tools for TAD calling are frequently
sensitive to
biases in Hi-C data, depend on tunable parameters, and are
computationally
inefficient.
METHODS: To address these challenges, we developed a novel sliding
window-based
spectral clustering framework that uses gaps between consecutive
eigenvectors
for TAD boundary identification.
RESULTS: Our method, implemented in an R package, SpectralTAD, detects
hierarchical, biologically relevant TADs, has automatic parameter
selection, is
robust to sequencing depth, resolution, and sparsity of Hi-C data.
SpectralTAD
outperforms four state-of-the-art TAD callers in simulated and
experimental
settings. We demonstrate that TAD boundaries shared among multiple
levels of the
TAD hierarchy were more enriched in classical boundary marks and more
conserved
across cell lines and tissues. In contrast, boundaries of TADs that
cannot be
split into sub-TADs showed less enrichment and conservation, suggesting
their
more dynamic role in genome regulation.
CONCLUSION: SpectralTAD is available on Bioconductor,
http://bioconductor.org/packages/SpectralTAD/ .
- >-
Holoprosencephaly (HPE) is a congenital defect of the brain, median
structures,
and face resulting from an incomplete cleavage of the primitive brain
during
early embryogenesis. The authors report a case of trisomy 13 syndrome
diagnosed
at prenatal follow up. The preterm newborn lived only 5 hours, and died
because
of severe respiratory failure. The autopsy findings disclosed facial,
skull,
limbs, cardiac, and cerebral malformations. Among the latter, the
presence of
alobar HPE, the central theme of this report, was evident. The most
common
nonrandom chromosomal abnormality in patients with HPE is trisomy 13.
The most
severe variant, namely alobar HPE, is shown in this case report.
Discussion on
this severe anomaly, along with the case report with details of Patau's
syndrome, is the goal of this report.
- >-
BACKGROUND: Heterochromia iridis, asymmetry of iris pigmentation, has
been well
described with congenital Horner syndrome. Acquired heterochromia
associated
with lesions in the ocular sympathetic pathways in adulthood, however,
is rare.
METHODS: Two cases are reported in which sympathectomy in adults
resulted in
ipsilateral Horner syndrome with heterochromia. In each case,
pharmacologic
testing with cocaine and hydroxyamphetamine was performed.
RESULTS: In both cases, sympathectomy occurred at the level of the
second order
neuron, but hydroxyamphetamine testing suggested at least partial third
order
neuron involvement.
CONCLUSION: Acquired heterochromia can occur in adults. The partial
response to
hydroxyamphetamine in the two cases presented may reflect
trans-synaptic
degeneration of the postganglionic neuron. A reduction in trophic
influences on
iris melanocytes may have contributed to the observed heterochromia.
- source_sentence: What is Pseudomelanosis duodeni?
sentences:
- >-
Pseudomelanosis duodeni is a rare condition in which dark pigment
accumulates in
macrophages located in the lamina propria of the duodenal mucosa. Three
cases
are reported here and the literature is reviewed. No clinical
association can be
found that points clearly to the underlying etiology. Electron probe
x-ray
microanalysis was used to study the pigment in macrophage granules in 2
of our
patients and demonstrated high iron and sulfur content. Iron
accumulation in
ferritinlike particles was detected in absorptive cell lysosomes. A
possible
mechanism for the accumulation of absorbed iron by macrophages is
considered.
- >-
Initiation of eukaryotic DNA replication requires phosphorylation of the
MCM
complex by Dbf4-dependent kinase (DDK), composed of Cdc7 kinase and its
activator, Dbf4. We report here that budding yeast Rif1
(Rap1-interacting factor
1) controls DNA replication genome-wide and describe how Rif1 opposes
DDK
function by directing Protein Phosphatase 1 (PP1)-mediated
dephosphorylation of
the MCM complex. Deleting RIF1 partially compensates for the limited
DDK
activity in a cdc7-1 mutant strain by allowing increased, premature
phosphorylation of Mcm4. PP1 interaction motifs within the Rif1
N-terminal
domain are critical for its repressive effect on replication. We confirm
that
Rif1 interacts with PP1 and that PP1 prevents premature Mcm4
phosphorylation.
Remarkably, our results suggest that replication repression by Rif1 is
itself
also DDK-regulated through phosphorylation near the PP1-interacting
motifs.
Based on our findings, we propose that Rif1 is a novel PP1 substrate
targeting
subunit that counteracts DDK-mediated phosphorylation during
replication.
Fission yeast and mammalian Rif1 proteins have also been implicated in
regulating DNA replication. Since PP1 interaction sites are
evolutionarily
conserved within the Rif1 sequence, it is likely that replication
control by
Rif1 through PP1 is a conserved mechanism.
- >-
This year marks the 100th anniversary of the deadliest event in human
history.
In 1918-1919, pandemic influenza appeared nearly simultaneously around
the globe
and caused extraordinary mortality (an estimated 50-100 million deaths)
associated with unexpected clinical and epidemiological features. The
descendants of the 1918 virus remain today; as endemic influenza
viruses, they
cause significant mortality each year. Although the ability to predict
influenza
pandemics remains no better than it was a century ago, numerous
scientific
advances provide an important head start in limiting severe disease and
death
from both current and future influenza viruses: identification and
substantial
characterization of the natural history and pathogenesis of the 1918
causative
virus itself, as well as hundreds of its viral descendants; development
of
moderately effective vaccines; improved diagnosis and treatment of
influenza-associated pneumonia; and effective prevention and control
measures.
Remaining challenges include development of vaccines eliciting
significantly
broader protection (against antigenically different influenza viruses)
that can
prevent or significantly downregulate viral replication; more complete
characterization of natural history and pathogenesis emphasizing the
protective
role of mucosal immunity; and biomarkers of impending
influenza-associated
pneumonia.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- cosine_accuracy@1
- cosine_accuracy@3
- cosine_accuracy@5
- cosine_accuracy@10
- cosine_precision@1
- cosine_precision@3
- cosine_precision@5
- cosine_precision@10
- cosine_recall@1
- cosine_recall@3
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@10
- cosine_mrr@10
- cosine_map@100
model-index:
- name: Biomedical MRL
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 768
type: dim_768
metrics:
- type: cosine_accuracy@1
value: 0.7454031117397454
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.8500707213578501
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8910891089108911
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9236209335219236
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.7454031117397454
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.6025459688826026
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.5270155586987271
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.4107496463932107
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.2250855612939271
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.39083578086577686
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.4920587987757972
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.626230051288883
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.7029780298857469
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.8069851372892393
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.6478394926216507
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 512
type: dim_512
metrics:
- type: cosine_accuracy@1
value: 0.7340876944837341
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.8415841584158416
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8826025459688827
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9193776520509194
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.7340876944837341
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.6001885902876002
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.5230551626591231
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.40947666195190946
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.22084064700657996
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.38663251424675177
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.48277567466168336
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.6228226830239426
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.6974451148765582
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.797282840528951
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.6413853118418739
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 256
type: dim_256
metrics:
- type: cosine_accuracy@1
value: 0.7213578500707214
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.8373408769448374
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8727015558698727
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9066478076379066
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.7213578500707214
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.5898161244695899
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.5106082036775106
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.40282885431400284
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.21851800409940159
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.38143229614225316
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.4684035311435285
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.605079189964237
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.6838557382875731
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.7865545227992186
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.6256997609817881
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 128
type: dim_128
metrics:
- type: cosine_accuracy@1
value: 0.6987270155586988
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.8161244695898161
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.842998585572843
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8925035360678925
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.6987270155586988
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.5605846298915605
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.4862800565770863
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.37850070721357854
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.2107728574016154
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.3586858510427449
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.437764794946033
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.5727124785732842
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.6485243360567318
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.7642615792191463
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.5843572398023539
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 64
type: dim_64
metrics:
- type: cosine_accuracy@1
value: 0.6393210749646393
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.7637906647807637
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.8132956152758133
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.8472418670438473
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.6393210749646393
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.5134370579915134
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.4517680339462518
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.3490806223479491
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.1844044968212152
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.3196269161523018
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.398801159559495
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.5072426828594248
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.5876796250069416
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.7114153252059898
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.5187521840685396
name: Cosine Map@100
Then you can load this model and run inference.
